66156 lines
1.8 MiB
66156 lines
1.8 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.7062391194474085,
|
|
"eval_steps": 3000,
|
|
"global_step": 33000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742159652709962,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7889,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10897.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742175674438476,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.8009,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 23084.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742210578918456,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 5.5625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7749,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 35810.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.74219331741333,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.6856,
|
|
"mean_token_accuracy": 7.733951788395644e-05,
|
|
"num_tokens": 46019.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742153644561768,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.589,
|
|
"mean_token_accuracy": 0.002765530865872279,
|
|
"num_tokens": 57272.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741812324523925,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4689,
|
|
"mean_token_accuracy": 0.020725749712437392,
|
|
"num_tokens": 68686.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.740827941894532,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3154,
|
|
"mean_token_accuracy": 0.03502877987921238,
|
|
"num_tokens": 79187.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.738996601104736,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.1929,
|
|
"mean_token_accuracy": 0.034967335499823095,
|
|
"num_tokens": 90293.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.736058044433594,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.049,
|
|
"mean_token_accuracy": 0.03895519729703665,
|
|
"num_tokens": 100420.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.732771301269532,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0083,
|
|
"mean_token_accuracy": 0.035632238164544104,
|
|
"num_tokens": 111198.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.73068790435791,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9428,
|
|
"mean_token_accuracy": 0.039259918965399265,
|
|
"num_tokens": 124723.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.7278546333313,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.8503,
|
|
"mean_token_accuracy": 0.035383212938904764,
|
|
"num_tokens": 136366.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.726744270324707,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.7831,
|
|
"mean_token_accuracy": 0.034513541124761106,
|
|
"num_tokens": 146536.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.725561046600342,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.7329,
|
|
"mean_token_accuracy": 0.04032005164772272,
|
|
"num_tokens": 157005.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.72284231185913,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.679,
|
|
"mean_token_accuracy": 0.03617443889379501,
|
|
"num_tokens": 167864.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.718811416625977,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6241,
|
|
"mean_token_accuracy": 0.03666241765022278,
|
|
"num_tokens": 179635.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.711934661865234,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.5509,
|
|
"mean_token_accuracy": 0.04279168993234635,
|
|
"num_tokens": 190614.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.70248441696167,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4575,
|
|
"mean_token_accuracy": 0.03979911990463734,
|
|
"num_tokens": 201496.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.693810176849365,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.3507,
|
|
"mean_token_accuracy": 0.04250855315476656,
|
|
"num_tokens": 211606.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.682610416412354,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.2629,
|
|
"mean_token_accuracy": 0.045587668940424916,
|
|
"num_tokens": 223503.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.668240451812744,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.1962,
|
|
"mean_token_accuracy": 0.04557593278586865,
|
|
"num_tokens": 234744.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.644842338562011,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.122,
|
|
"mean_token_accuracy": 0.0518043052405119,
|
|
"num_tokens": 247663.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.604430007934571,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9874,
|
|
"mean_token_accuracy": 0.05278271734714508,
|
|
"num_tokens": 260326.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.556639862060546,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8544,
|
|
"mean_token_accuracy": 0.04873238429427147,
|
|
"num_tokens": 271568.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.503229522705078,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.6905,
|
|
"mean_token_accuracy": 0.05787150226533413,
|
|
"num_tokens": 282651.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.44473876953125,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.5255,
|
|
"mean_token_accuracy": 0.06597345359623433,
|
|
"num_tokens": 292753.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.36376428604126,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.48,
|
|
"mean_token_accuracy": 0.05933795906603336,
|
|
"num_tokens": 302981.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.280290031433106,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3896,
|
|
"mean_token_accuracy": 0.061843172460794446,
|
|
"num_tokens": 314461.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.177413368225098,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2591,
|
|
"mean_token_accuracy": 0.07499396502971649,
|
|
"num_tokens": 326877.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.032635498046876,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.0657,
|
|
"mean_token_accuracy": 0.07227128334343433,
|
|
"num_tokens": 337831.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.885223960876464,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.9346,
|
|
"mean_token_accuracy": 0.07391955740749837,
|
|
"num_tokens": 348233.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.693181419372559,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.7979,
|
|
"mean_token_accuracy": 0.07743496969342231,
|
|
"num_tokens": 359113.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.46179666519165,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.7962,
|
|
"mean_token_accuracy": 0.07372267432510853,
|
|
"num_tokens": 370284.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.257444763183594,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7268,
|
|
"mean_token_accuracy": 0.07272499725222588,
|
|
"num_tokens": 381415.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.014177513122558,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6032,
|
|
"mean_token_accuracy": 0.08806980401277542,
|
|
"num_tokens": 392080.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.82464370727539,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5586,
|
|
"mean_token_accuracy": 0.07858657464385033,
|
|
"num_tokens": 402551.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.636843490600587,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5404,
|
|
"mean_token_accuracy": 0.07701119184494018,
|
|
"num_tokens": 414670.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.47730884552002,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.4795,
|
|
"mean_token_accuracy": 0.08224375993013382,
|
|
"num_tokens": 427162.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.355635261535644,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.3622,
|
|
"mean_token_accuracy": 0.08267558068037033,
|
|
"num_tokens": 438628.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.201725959777832,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.2728,
|
|
"mean_token_accuracy": 0.08908244222402573,
|
|
"num_tokens": 449248.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.132552146911621,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.2451,
|
|
"mean_token_accuracy": 0.08406969904899597,
|
|
"num_tokens": 460815.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.04080147743225,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.3843,
|
|
"mean_token_accuracy": 0.08254060074687004,
|
|
"num_tokens": 471972.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.043025588989257,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3464,
|
|
"mean_token_accuracy": 0.08762349262833595,
|
|
"num_tokens": 482775.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.987480306625367,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.2777,
|
|
"mean_token_accuracy": 0.08940344825387,
|
|
"num_tokens": 495151.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.8895745277404785,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.243,
|
|
"mean_token_accuracy": 0.09175463244318963,
|
|
"num_tokens": 506947.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.909286975860596,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.2692,
|
|
"mean_token_accuracy": 0.08727651685476304,
|
|
"num_tokens": 519153.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.8730621337890625,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2326,
|
|
"mean_token_accuracy": 0.09193299040198326,
|
|
"num_tokens": 531050.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.918293619155884,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1756,
|
|
"mean_token_accuracy": 0.09726689383387566,
|
|
"num_tokens": 542744.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.826691198348999,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.2491,
|
|
"mean_token_accuracy": 0.09064291417598724,
|
|
"num_tokens": 554748.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.765559387207031,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.1701,
|
|
"mean_token_accuracy": 0.09881943240761756,
|
|
"num_tokens": 564868.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.843354749679565,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1927,
|
|
"mean_token_accuracy": 0.09846951141953468,
|
|
"num_tokens": 575668.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.848422527313232,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.2952,
|
|
"mean_token_accuracy": 0.09341520965099334,
|
|
"num_tokens": 587956.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.872948122024536,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1371,
|
|
"mean_token_accuracy": 0.1014053001999855,
|
|
"num_tokens": 598246.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.68636121749878,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.2494,
|
|
"mean_token_accuracy": 0.09885063543915748,
|
|
"num_tokens": 610628.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.642057609558106,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0149,
|
|
"mean_token_accuracy": 0.10172908902168273,
|
|
"num_tokens": 621214.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.758373641967774,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1046,
|
|
"mean_token_accuracy": 0.1080682247877121,
|
|
"num_tokens": 631123.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.735682725906372,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.0981,
|
|
"mean_token_accuracy": 0.10117569863796234,
|
|
"num_tokens": 643434.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.62876443862915,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0811,
|
|
"mean_token_accuracy": 0.10320050120353699,
|
|
"num_tokens": 655336.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.703513860702515,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0693,
|
|
"mean_token_accuracy": 0.10180106833577156,
|
|
"num_tokens": 666591.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.638863277435303,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0786,
|
|
"mean_token_accuracy": 0.1021819569170475,
|
|
"num_tokens": 678288.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.589478445053101,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0006,
|
|
"mean_token_accuracy": 0.10565904229879379,
|
|
"num_tokens": 688526.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.551162624359131,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.928,
|
|
"mean_token_accuracy": 0.11400648429989815,
|
|
"num_tokens": 698727.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.529042816162109,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.9796,
|
|
"mean_token_accuracy": 0.10720190778374672,
|
|
"num_tokens": 710042.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.545799398422242,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.922,
|
|
"mean_token_accuracy": 0.1121792696416378,
|
|
"num_tokens": 721390.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.540653800964355,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0781,
|
|
"mean_token_accuracy": 0.10771138444542885,
|
|
"num_tokens": 732949.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.559352111816406,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.1071,
|
|
"mean_token_accuracy": 0.10489999055862427,
|
|
"num_tokens": 744943.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.444735479354859,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8866,
|
|
"mean_token_accuracy": 0.10991243943572045,
|
|
"num_tokens": 756579.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.3910911083221436,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8272,
|
|
"mean_token_accuracy": 0.11481509283185005,
|
|
"num_tokens": 767260.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.433158874511719,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9127,
|
|
"mean_token_accuracy": 0.11195246949791908,
|
|
"num_tokens": 778163.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.444675302505493,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9433,
|
|
"mean_token_accuracy": 0.1094307117164135,
|
|
"num_tokens": 788912.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.543854188919068,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.0517,
|
|
"mean_token_accuracy": 0.10905506610870361,
|
|
"num_tokens": 801405.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.323230171203614,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8506,
|
|
"mean_token_accuracy": 0.11496956795454025,
|
|
"num_tokens": 813023.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.459993314743042,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8647,
|
|
"mean_token_accuracy": 0.11342948451638221,
|
|
"num_tokens": 823993.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.434476852416992,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9265,
|
|
"mean_token_accuracy": 0.10957189053297042,
|
|
"num_tokens": 836642.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.298930406570435,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7553,
|
|
"mean_token_accuracy": 0.11839937195181846,
|
|
"num_tokens": 847475.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.317954063415527,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8152,
|
|
"mean_token_accuracy": 0.11555981338024139,
|
|
"num_tokens": 857949.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.365426969528198,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8614,
|
|
"mean_token_accuracy": 0.10808339864015579,
|
|
"num_tokens": 868661.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.30035982131958,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8987,
|
|
"mean_token_accuracy": 0.10754143446683884,
|
|
"num_tokens": 879651.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.385866975784301,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8691,
|
|
"mean_token_accuracy": 0.107125935703516,
|
|
"num_tokens": 891189.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.330320978164673,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7832,
|
|
"mean_token_accuracy": 0.11402576118707657,
|
|
"num_tokens": 902915.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.2686628818511965,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8793,
|
|
"mean_token_accuracy": 0.1092168889939785,
|
|
"num_tokens": 914108.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.39061598777771,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.881,
|
|
"mean_token_accuracy": 0.10963215455412864,
|
|
"num_tokens": 925729.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.315005111694336,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.89,
|
|
"mean_token_accuracy": 0.11587361320853233,
|
|
"num_tokens": 936912.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.332214736938477,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8452,
|
|
"mean_token_accuracy": 0.11978999823331833,
|
|
"num_tokens": 948576.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.238273620605469,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7107,
|
|
"mean_token_accuracy": 0.11704700067639351,
|
|
"num_tokens": 959346.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.15445294380188,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.727,
|
|
"mean_token_accuracy": 0.12021773234009743,
|
|
"num_tokens": 970124.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.241500425338745,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8059,
|
|
"mean_token_accuracy": 0.118399990350008,
|
|
"num_tokens": 981628.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.145569133758545,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7491,
|
|
"mean_token_accuracy": 0.12629036754369735,
|
|
"num_tokens": 992423.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.303143882751465,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7625,
|
|
"mean_token_accuracy": 0.11583313271403313,
|
|
"num_tokens": 1002954.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.111866235733032,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6469,
|
|
"mean_token_accuracy": 0.1229097992181778,
|
|
"num_tokens": 1013351.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.203304386138916,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.75,
|
|
"mean_token_accuracy": 0.11591361835598946,
|
|
"num_tokens": 1023781.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.240522956848144,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8126,
|
|
"mean_token_accuracy": 0.11724791452288627,
|
|
"num_tokens": 1034565.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.143156623840332,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6276,
|
|
"mean_token_accuracy": 0.12182217463850975,
|
|
"num_tokens": 1045595.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.085393238067627,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6279,
|
|
"mean_token_accuracy": 0.12069518566131592,
|
|
"num_tokens": 1056084.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.194664669036865,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6631,
|
|
"mean_token_accuracy": 0.12125146389007568,
|
|
"num_tokens": 1067014.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.012721920013428,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6366,
|
|
"mean_token_accuracy": 0.1270107574760914,
|
|
"num_tokens": 1078557.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.065823554992676,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.12492740824818611,
|
|
"num_tokens": 1090541.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.157057046890259,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7532,
|
|
"mean_token_accuracy": 0.12073619738221168,
|
|
"num_tokens": 1101851.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.091975212097168,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6682,
|
|
"mean_token_accuracy": 0.11754756048321724,
|
|
"num_tokens": 1112728.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.128147745132447,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7761,
|
|
"mean_token_accuracy": 0.11911589205265045,
|
|
"num_tokens": 1124537.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.011446475982666,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6831,
|
|
"mean_token_accuracy": 0.11788979321718215,
|
|
"num_tokens": 1135749.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.022298192977905,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5983,
|
|
"mean_token_accuracy": 0.11912425011396408,
|
|
"num_tokens": 1147597.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.0590613842010494,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.1268024981021881,
|
|
"num_tokens": 1158975.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.009570455551147,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6792,
|
|
"mean_token_accuracy": 0.1236396610736847,
|
|
"num_tokens": 1170556.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.001147222518921,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5523,
|
|
"mean_token_accuracy": 0.12127840742468834,
|
|
"num_tokens": 1180757.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.999064159393311,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5758,
|
|
"mean_token_accuracy": 0.12697923853993415,
|
|
"num_tokens": 1192428.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.076443672180176,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.631,
|
|
"mean_token_accuracy": 0.1223110742866993,
|
|
"num_tokens": 1203867.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.007501935958862,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6394,
|
|
"mean_token_accuracy": 0.12882392182946206,
|
|
"num_tokens": 1214059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.954019689559937,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6937,
|
|
"mean_token_accuracy": 0.12546431198716163,
|
|
"num_tokens": 1224750.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.1395269393920895,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7529,
|
|
"mean_token_accuracy": 0.12238883227109909,
|
|
"num_tokens": 1235936.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.959107255935669,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5809,
|
|
"mean_token_accuracy": 0.12458711341023446,
|
|
"num_tokens": 1247619.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.031533432006836,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6474,
|
|
"mean_token_accuracy": 0.12089557126164437,
|
|
"num_tokens": 1258089.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.041066884994507,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7217,
|
|
"mean_token_accuracy": 0.11978143155574798,
|
|
"num_tokens": 1270727.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.913246822357178,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5936,
|
|
"mean_token_accuracy": 0.12437130734324456,
|
|
"num_tokens": 1280886.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.04746732711792,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6106,
|
|
"mean_token_accuracy": 0.12972260043025016,
|
|
"num_tokens": 1292205.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.911301755905152,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6,
|
|
"mean_token_accuracy": 0.1212221659719944,
|
|
"num_tokens": 1304621.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.122457599639892,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6713,
|
|
"mean_token_accuracy": 0.1255178600549698,
|
|
"num_tokens": 1315481.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.905537509918213,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.12450234517455101,
|
|
"num_tokens": 1328726.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.024345827102661,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.7014,
|
|
"mean_token_accuracy": 0.12013381794095039,
|
|
"num_tokens": 1340151.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.872124052047729,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4814,
|
|
"mean_token_accuracy": 0.12421990558505058,
|
|
"num_tokens": 1350833.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.007877540588379,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6394,
|
|
"mean_token_accuracy": 0.12776005491614342,
|
|
"num_tokens": 1362332.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.8815089702606205,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5402,
|
|
"mean_token_accuracy": 0.13264288678765296,
|
|
"num_tokens": 1373696.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.756528091430664,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.464,
|
|
"mean_token_accuracy": 0.13654546514153482,
|
|
"num_tokens": 1383553.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.904419851303101,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5823,
|
|
"mean_token_accuracy": 0.12500577047467232,
|
|
"num_tokens": 1394487.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.089482641220092,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5904,
|
|
"mean_token_accuracy": 0.1287471428513527,
|
|
"num_tokens": 1404928.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.700677680969238,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4711,
|
|
"mean_token_accuracy": 0.13175692334771155,
|
|
"num_tokens": 1415854.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.857469606399536,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.13403325900435448,
|
|
"num_tokens": 1427153.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.866606903076172,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6234,
|
|
"mean_token_accuracy": 0.13062414675951003,
|
|
"num_tokens": 1438907.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.878033590316773,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5067,
|
|
"mean_token_accuracy": 0.1253124348819256,
|
|
"num_tokens": 1449975.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.877867889404297,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4895,
|
|
"mean_token_accuracy": 0.13475129678845404,
|
|
"num_tokens": 1460815.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.8674421310424805,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.1258758708834648,
|
|
"num_tokens": 1472403.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.812349843978882,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5533,
|
|
"mean_token_accuracy": 0.1228983834385872,
|
|
"num_tokens": 1484015.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.90525712966919,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5784,
|
|
"mean_token_accuracy": 0.12541323602199556,
|
|
"num_tokens": 1495383.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.874822282791138,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.12995083034038543,
|
|
"num_tokens": 1505893.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.941184377670288,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.12604367062449456,
|
|
"num_tokens": 1518933.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.911136102676392,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6501,
|
|
"mean_token_accuracy": 0.12984378784894943,
|
|
"num_tokens": 1530603.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.9132781505584715,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.1325322173535824,
|
|
"num_tokens": 1540977.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.804541158676147,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5812,
|
|
"mean_token_accuracy": 0.12221492826938629,
|
|
"num_tokens": 1553004.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.866607427597046,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.13336056619882583,
|
|
"num_tokens": 1563446.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.832825613021851,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5462,
|
|
"mean_token_accuracy": 0.12922437787055968,
|
|
"num_tokens": 1573884.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.808780765533447,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4227,
|
|
"mean_token_accuracy": 0.13714208453893661,
|
|
"num_tokens": 1585396.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.692774391174316,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.13936696648597718,
|
|
"num_tokens": 1596934.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.7500427722930905,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4633,
|
|
"mean_token_accuracy": 0.13480807468295097,
|
|
"num_tokens": 1608069.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.736125421524048,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3819,
|
|
"mean_token_accuracy": 0.13503086492419242,
|
|
"num_tokens": 1619532.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.771858787536621,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5233,
|
|
"mean_token_accuracy": 0.13306568711996078,
|
|
"num_tokens": 1630697.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.781781196594238,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5165,
|
|
"mean_token_accuracy": 0.13028716892004014,
|
|
"num_tokens": 1641854.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.8811887264251705,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.6306,
|
|
"mean_token_accuracy": 0.12956687957048416,
|
|
"num_tokens": 1653036.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.706860542297363,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3928,
|
|
"mean_token_accuracy": 0.13188852593302727,
|
|
"num_tokens": 1664096.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.775880146026611,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5639,
|
|
"mean_token_accuracy": 0.12743774950504302,
|
|
"num_tokens": 1677890.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.855115127563477,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4359,
|
|
"mean_token_accuracy": 0.1298883818089962,
|
|
"num_tokens": 1687627.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.8540863513946535,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.6391,
|
|
"mean_token_accuracy": 0.12884086221456528,
|
|
"num_tokens": 1700843.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.653585767745971,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4637,
|
|
"mean_token_accuracy": 0.12760308086872102,
|
|
"num_tokens": 1712356.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.830094861984253,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.13208287805318833,
|
|
"num_tokens": 1722041.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.732513952255249,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.557,
|
|
"mean_token_accuracy": 0.1303403578698635,
|
|
"num_tokens": 1733628.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.743438959121704,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.4222,
|
|
"mean_token_accuracy": 0.13407000303268432,
|
|
"num_tokens": 1745174.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.709445190429688,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.1347622461616993,
|
|
"num_tokens": 1757117.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.706043720245361,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3512,
|
|
"mean_token_accuracy": 0.14104517698287963,
|
|
"num_tokens": 1767343.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.705164098739624,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.1354410707950592,
|
|
"num_tokens": 1778500.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.704329490661621,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4623,
|
|
"mean_token_accuracy": 0.13586708009243012,
|
|
"num_tokens": 1788474.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.827891683578491,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6174,
|
|
"mean_token_accuracy": 0.12774253413081169,
|
|
"num_tokens": 1800756.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.589310979843139,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.13237445279955865,
|
|
"num_tokens": 1812172.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.696872234344482,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4571,
|
|
"mean_token_accuracy": 0.14194565117359162,
|
|
"num_tokens": 1822057.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.707974147796631,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.3982,
|
|
"mean_token_accuracy": 0.1391292504966259,
|
|
"num_tokens": 1833074.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.551404857635498,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3851,
|
|
"mean_token_accuracy": 0.13646574839949607,
|
|
"num_tokens": 1844932.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.779546499252319,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.13488720655441283,
|
|
"num_tokens": 1855591.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.598760938644409,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.13601110577583314,
|
|
"num_tokens": 1866726.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.665882396697998,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.399,
|
|
"mean_token_accuracy": 0.13704331815242768,
|
|
"num_tokens": 1877385.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.596274948120117,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.13590012937784196,
|
|
"num_tokens": 1887905.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.544144535064698,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.13350442200899124,
|
|
"num_tokens": 1898649.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.670406293869019,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3721,
|
|
"mean_token_accuracy": 0.1349139153957367,
|
|
"num_tokens": 1908808.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.681371879577637,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4775,
|
|
"mean_token_accuracy": 0.12984352186322212,
|
|
"num_tokens": 1920360.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.629400205612183,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3831,
|
|
"mean_token_accuracy": 0.1338461585342884,
|
|
"num_tokens": 1931082.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.672259140014648,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5216,
|
|
"mean_token_accuracy": 0.12983292788267137,
|
|
"num_tokens": 1942712.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.529405975341797,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2652,
|
|
"mean_token_accuracy": 0.13643566891551018,
|
|
"num_tokens": 1953316.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.653924989700317,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3296,
|
|
"mean_token_accuracy": 0.13486339151859283,
|
|
"num_tokens": 1963936.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.65830512046814,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.376,
|
|
"mean_token_accuracy": 0.1389057829976082,
|
|
"num_tokens": 1974502.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.551113176345825,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.13925166726112365,
|
|
"num_tokens": 1985746.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.622382593154907,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.409,
|
|
"mean_token_accuracy": 0.13811005428433418,
|
|
"num_tokens": 1997696.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.633377408981323,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3843,
|
|
"mean_token_accuracy": 0.1356112003326416,
|
|
"num_tokens": 2009462.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.530625629425049,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.13701687082648278,
|
|
"num_tokens": 2019547.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.470341348648072,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.13039888590574264,
|
|
"num_tokens": 2030990.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.555771684646606,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3831,
|
|
"mean_token_accuracy": 0.13693194836378098,
|
|
"num_tokens": 2042488.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.6713659286499025,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4142,
|
|
"mean_token_accuracy": 0.13591785058379174,
|
|
"num_tokens": 2052822.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.662473487854004,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3762,
|
|
"mean_token_accuracy": 0.13703339472413062,
|
|
"num_tokens": 2063274.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.709976673126221,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4291,
|
|
"mean_token_accuracy": 0.1309817112982273,
|
|
"num_tokens": 2074424.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.533333730697632,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4147,
|
|
"mean_token_accuracy": 0.13632471337914467,
|
|
"num_tokens": 2085776.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.739099597930908,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4813,
|
|
"mean_token_accuracy": 0.13343799486756325,
|
|
"num_tokens": 2096789.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.534065246582031,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.389,
|
|
"mean_token_accuracy": 0.13717718720436095,
|
|
"num_tokens": 2108335.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.631331920623779,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4657,
|
|
"mean_token_accuracy": 0.13420545905828477,
|
|
"num_tokens": 2121063.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.629163551330566,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.14141536504030228,
|
|
"num_tokens": 2132442.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.519858121871948,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.14491503611207007,
|
|
"num_tokens": 2142155.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.535245704650879,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.14321411550045013,
|
|
"num_tokens": 2152923.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.522160243988037,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.1394087068736553,
|
|
"num_tokens": 2164640.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.464917230606079,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2233,
|
|
"mean_token_accuracy": 0.1389392763376236,
|
|
"num_tokens": 2175403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.522283029556275,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.13505593836307525,
|
|
"num_tokens": 2186031.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.556379938125611,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.1329805336892605,
|
|
"num_tokens": 2198152.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.509692525863647,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3253,
|
|
"mean_token_accuracy": 0.13835065215826034,
|
|
"num_tokens": 2209435.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.4863756656646725,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3012,
|
|
"mean_token_accuracy": 0.14111311957240105,
|
|
"num_tokens": 2219476.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.572051095962524,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3796,
|
|
"mean_token_accuracy": 0.13706994503736497,
|
|
"num_tokens": 2231131.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.530418062210083,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.14110670536756514,
|
|
"num_tokens": 2242309.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.406200790405274,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.1407,
|
|
"mean_token_accuracy": 0.13889531120657922,
|
|
"num_tokens": 2252236.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.604990386962891,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.4418,
|
|
"mean_token_accuracy": 0.13547984585165979,
|
|
"num_tokens": 2263529.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.467497253417969,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.28,
|
|
"mean_token_accuracy": 0.14054934605956076,
|
|
"num_tokens": 2275318.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.547984170913696,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.3228,
|
|
"mean_token_accuracy": 0.14013427048921584,
|
|
"num_tokens": 2287434.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.423276138305664,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.2246,
|
|
"mean_token_accuracy": 0.14131729006767274,
|
|
"num_tokens": 2299145.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.478960466384888,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.14057428762316704,
|
|
"num_tokens": 2309841.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.519130516052246,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.14342720210552215,
|
|
"num_tokens": 2322143.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.387487173080444,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.2526,
|
|
"mean_token_accuracy": 0.13191457092761993,
|
|
"num_tokens": 2333207.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.460022974014282,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.1400797076523304,
|
|
"num_tokens": 2345542.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.52472333908081,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.295,
|
|
"mean_token_accuracy": 0.14530514925718307,
|
|
"num_tokens": 2356612.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.412943410873413,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.2282,
|
|
"mean_token_accuracy": 0.13911499530076982,
|
|
"num_tokens": 2368204.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.429121255874634,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.2581,
|
|
"mean_token_accuracy": 0.14445163011550904,
|
|
"num_tokens": 2379114.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.4838306427001955,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.13635856211185454,
|
|
"num_tokens": 2390562.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.4884007453918455,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.3504,
|
|
"mean_token_accuracy": 0.13818884044885635,
|
|
"num_tokens": 2402352.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.559914827346802,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.3831,
|
|
"mean_token_accuracy": 0.13666045516729355,
|
|
"num_tokens": 2415140.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.480178022384644,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.13918514922261238,
|
|
"num_tokens": 2426679.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.524165916442871,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.3315,
|
|
"mean_token_accuracy": 0.14310413375496864,
|
|
"num_tokens": 2437735.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.418136215209961,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.2481,
|
|
"mean_token_accuracy": 0.14297899305820466,
|
|
"num_tokens": 2448611.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.380622625350952,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.1691,
|
|
"mean_token_accuracy": 0.14379421919584273,
|
|
"num_tokens": 2461101.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.438853454589844,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.14165812805294992,
|
|
"num_tokens": 2473569.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.3875250816345215,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.14042257517576218,
|
|
"num_tokens": 2483970.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.487800598144531,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.14397675544023514,
|
|
"num_tokens": 2494184.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.424576663970948,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.1468231901526451,
|
|
"num_tokens": 2505715.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.577597522735596,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.14024857580661773,
|
|
"num_tokens": 2517168.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.49650354385376,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.371,
|
|
"mean_token_accuracy": 0.1400489442050457,
|
|
"num_tokens": 2528296.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.495221996307373,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.14460598528385163,
|
|
"num_tokens": 2540648.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.282399272918701,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.1797,
|
|
"mean_token_accuracy": 0.14570244327187537,
|
|
"num_tokens": 2551840.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.529202556610107,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.1393646366894245,
|
|
"num_tokens": 2561362.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.449448585510254,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.14824813604354858,
|
|
"num_tokens": 2573584.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.655548143386841,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.13177204579114915,
|
|
"num_tokens": 2585255.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.267699909210205,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.14294029027223587,
|
|
"num_tokens": 2596849.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.447602844238281,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.2532,
|
|
"mean_token_accuracy": 0.13973233699798585,
|
|
"num_tokens": 2606918.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.374657249450683,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.1423034094274044,
|
|
"num_tokens": 2617779.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.407828426361084,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.13924483358860015,
|
|
"num_tokens": 2630294.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.340870380401611,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.14684706702828407,
|
|
"num_tokens": 2641002.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.343483114242554,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.147942453622818,
|
|
"num_tokens": 2652188.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.338960742950439,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.1904,
|
|
"mean_token_accuracy": 0.14238052293658257,
|
|
"num_tokens": 2662542.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.44409818649292,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2037,
|
|
"mean_token_accuracy": 0.14257570207118989,
|
|
"num_tokens": 2673292.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.3447812557220455,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.1507535383105278,
|
|
"num_tokens": 2684042.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.4087217330932615,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.14439617618918418,
|
|
"num_tokens": 2694716.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.433208656311035,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.14215576499700547,
|
|
"num_tokens": 2706200.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.231206655502319,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.1457333743572235,
|
|
"num_tokens": 2716814.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.470926666259766,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.1392791375517845,
|
|
"num_tokens": 2728042.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.371030998229981,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.1419711485505104,
|
|
"num_tokens": 2739093.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.47151198387146,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.14010858312249183,
|
|
"num_tokens": 2750307.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.368812513351441,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1905,
|
|
"mean_token_accuracy": 0.1476987473666668,
|
|
"num_tokens": 2760534.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.282177257537842,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.13831715583801268,
|
|
"num_tokens": 2772459.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.307314777374268,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.1116,
|
|
"mean_token_accuracy": 0.14874064177274704,
|
|
"num_tokens": 2784038.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.414990377426148,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.14876076579093933,
|
|
"num_tokens": 2795756.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.324886178970337,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.1493593215942383,
|
|
"num_tokens": 2806242.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.431931829452514,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.14621126055717468,
|
|
"num_tokens": 2817017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.327989101409912,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.14934326112270355,
|
|
"num_tokens": 2827415.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.379254484176636,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.15096642822027206,
|
|
"num_tokens": 2837595.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.243520879745484,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.1508125752210617,
|
|
"num_tokens": 2847906.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.427999448776245,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.13904368355870247,
|
|
"num_tokens": 2859145.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.2583085060119625,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14405062198638915,
|
|
"num_tokens": 2870704.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.418164968490601,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.2484,
|
|
"mean_token_accuracy": 0.14485250860452653,
|
|
"num_tokens": 2881861.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.383849573135376,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.1769,
|
|
"mean_token_accuracy": 0.14679245054721832,
|
|
"num_tokens": 2893247.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.203914022445678,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.15197635889053346,
|
|
"num_tokens": 2905351.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.3811376094818115,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.1659,
|
|
"mean_token_accuracy": 0.15029374808073043,
|
|
"num_tokens": 2915153.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.259037733078003,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.1388898678123951,
|
|
"num_tokens": 2926234.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.276462173461914,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.14983634203672408,
|
|
"num_tokens": 2937033.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.2190779685974125,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.1483589932322502,
|
|
"num_tokens": 2945904.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.290797710418701,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.2419,
|
|
"mean_token_accuracy": 0.1454251542687416,
|
|
"num_tokens": 2956298.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.387047481536865,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.14700962603092194,
|
|
"num_tokens": 2967660.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.273607492446899,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.14173401966691018,
|
|
"num_tokens": 2978616.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.283357286453247,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.15247107595205306,
|
|
"num_tokens": 2989731.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.304700946807861,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.14539775550365447,
|
|
"num_tokens": 3002110.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.181425333023071,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.15465341359376908,
|
|
"num_tokens": 3012709.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.394105720520019,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.2965,
|
|
"mean_token_accuracy": 0.13710058107972145,
|
|
"num_tokens": 3025738.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.322883129119873,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.14873576164245605,
|
|
"num_tokens": 3037711.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.385323190689087,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.3268,
|
|
"mean_token_accuracy": 0.14197970777750016,
|
|
"num_tokens": 3048929.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.2612724781036375,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.15912340208888054,
|
|
"num_tokens": 3059717.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.348027324676513,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.15389773696660997,
|
|
"num_tokens": 3069530.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.321991920471191,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.14062497690320014,
|
|
"num_tokens": 3080705.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.341788578033447,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.14362404346466065,
|
|
"num_tokens": 3092553.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.345370769500732,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.14683938324451445,
|
|
"num_tokens": 3102947.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.237121629714966,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.15067995637655257,
|
|
"num_tokens": 3114157.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.184521913528442,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.14959800392389297,
|
|
"num_tokens": 3125739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.257222080230713,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.15115083754062653,
|
|
"num_tokens": 3136970.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.251573801040649,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.1482801616191864,
|
|
"num_tokens": 3148512.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.233679914474488,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.1032,
|
|
"mean_token_accuracy": 0.15640820562839508,
|
|
"num_tokens": 3159477.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.284524965286255,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.15160105079412461,
|
|
"num_tokens": 3171361.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.3336728572845455,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.2799,
|
|
"mean_token_accuracy": 0.14425793811678886,
|
|
"num_tokens": 3184652.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.371946477890015,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1549,
|
|
"mean_token_accuracy": 0.1490624487400055,
|
|
"num_tokens": 3195557.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.29681806564331,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.13826513439416885,
|
|
"num_tokens": 3207139.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.38665280342102,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.1390974797308445,
|
|
"num_tokens": 3218967.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.33486762046814,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.14666435718536378,
|
|
"num_tokens": 3230168.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.135511350631714,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.149,
|
|
"mean_token_accuracy": 0.1418899655342102,
|
|
"num_tokens": 3241829.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.392429447174072,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.14229773133993148,
|
|
"num_tokens": 3253195.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.247541046142578,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.14251446202397347,
|
|
"num_tokens": 3264951.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.2502806186676025,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.1511962153017521,
|
|
"num_tokens": 3276054.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.167913818359375,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 6.0024,
|
|
"mean_token_accuracy": 0.15492074191570282,
|
|
"num_tokens": 3285540.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.318518781661988,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.14897073954343795,
|
|
"num_tokens": 3296869.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.224885034561157,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.0735,
|
|
"mean_token_accuracy": 0.15889174938201905,
|
|
"num_tokens": 3307554.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.121176862716675,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.1480540670454502,
|
|
"num_tokens": 3319685.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.324452352523804,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.15056272149085997,
|
|
"num_tokens": 3330742.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.18217282295227,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.14542819410562516,
|
|
"num_tokens": 3343613.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.439804410934448,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.1974,
|
|
"mean_token_accuracy": 0.15067817121744156,
|
|
"num_tokens": 3355162.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.241834735870361,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.15669388324022293,
|
|
"num_tokens": 3366324.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.349331521987915,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.14172908142209054,
|
|
"num_tokens": 3378571.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.296334838867187,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.1698,
|
|
"mean_token_accuracy": 0.1408284679055214,
|
|
"num_tokens": 3390605.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.261933708190918,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.15232473611831665,
|
|
"num_tokens": 3402735.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.265532779693603,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.1022,
|
|
"mean_token_accuracy": 0.15048839300870895,
|
|
"num_tokens": 3413079.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.202383279800415,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.0373,
|
|
"mean_token_accuracy": 0.15026211589574814,
|
|
"num_tokens": 3423098.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.250395059585571,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.0698,
|
|
"mean_token_accuracy": 0.1483706794679165,
|
|
"num_tokens": 3435794.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.316862487792969,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.1399092845618725,
|
|
"num_tokens": 3448125.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.26985650062561,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.1499591626226902,
|
|
"num_tokens": 3458217.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.10562105178833,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 6.0887,
|
|
"mean_token_accuracy": 0.15155576467514037,
|
|
"num_tokens": 3469553.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.309259700775146,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 6.0386,
|
|
"mean_token_accuracy": 0.1534125417470932,
|
|
"num_tokens": 3480928.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.211579370498657,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.15074966102838516,
|
|
"num_tokens": 3492074.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.318174982070923,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.1394,
|
|
"mean_token_accuracy": 0.15032617449760438,
|
|
"num_tokens": 3503320.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.094528245925903,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.1539114683866501,
|
|
"num_tokens": 3515466.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.302529811859131,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.15576242208480834,
|
|
"num_tokens": 3525584.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.116282892227173,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.1511538565158844,
|
|
"num_tokens": 3536973.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.274351692199707,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.14852190166711807,
|
|
"num_tokens": 3547799.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.267402791976929,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.15419369488954543,
|
|
"num_tokens": 3558436.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.240382862091065,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.15452160835266113,
|
|
"num_tokens": 3569851.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.229211044311524,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.15327125638723374,
|
|
"num_tokens": 3580797.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.190174341201782,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.15331678166985513,
|
|
"num_tokens": 3592552.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.141517210006714,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.155684494972229,
|
|
"num_tokens": 3603932.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.239850759506226,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.15877142027020455,
|
|
"num_tokens": 3614865.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.0710132122039795,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.15842452943325042,
|
|
"num_tokens": 3626275.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.2320445537567135,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.1467394173145294,
|
|
"num_tokens": 3638416.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.100798749923706,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.9409,
|
|
"mean_token_accuracy": 0.15524060577154158,
|
|
"num_tokens": 3649651.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.265647649765015,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.15043193548917771,
|
|
"num_tokens": 3661172.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.17116060256958,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 6.0211,
|
|
"mean_token_accuracy": 0.1554769456386566,
|
|
"num_tokens": 3672086.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.211421918869019,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.15613652467727662,
|
|
"num_tokens": 3682579.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.14499340057373,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.1462409794330597,
|
|
"num_tokens": 3694616.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.109319877624512,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.9048,
|
|
"mean_token_accuracy": 0.156711246073246,
|
|
"num_tokens": 3706821.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.144946670532226,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9537,
|
|
"mean_token_accuracy": 0.15782452672719954,
|
|
"num_tokens": 3717552.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.13314003944397,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.15105085968971252,
|
|
"num_tokens": 3728300.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.166549253463745,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.16351160258054734,
|
|
"num_tokens": 3738545.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.192590284347534,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.1535608723759651,
|
|
"num_tokens": 3749190.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.16079683303833,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.154031240940094,
|
|
"num_tokens": 3760978.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.146186113357544,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.15957706719636916,
|
|
"num_tokens": 3771339.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.097730922698974,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.15911781340837478,
|
|
"num_tokens": 3781550.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.093053245544434,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.14508662447333337,
|
|
"num_tokens": 3793700.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.319051504135132,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.14944599717855453,
|
|
"num_tokens": 3806114.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.132070541381836,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.1544131487607956,
|
|
"num_tokens": 3817251.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.240864896774292,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.0334,
|
|
"mean_token_accuracy": 0.15655466467142104,
|
|
"num_tokens": 3828544.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.111740303039551,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.14879243224859237,
|
|
"num_tokens": 3840423.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.233397626876831,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.156166410446167,
|
|
"num_tokens": 3852751.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.10665807723999,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.1576487198472023,
|
|
"num_tokens": 3863382.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.092583036422729,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.153714869171381,
|
|
"num_tokens": 3874294.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.184678983688355,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.14937564805150033,
|
|
"num_tokens": 3886693.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.071629571914673,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.15917861759662627,
|
|
"num_tokens": 3897755.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.1856848239898685,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.1593487538397312,
|
|
"num_tokens": 3909418.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.118424940109253,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.15099436342716216,
|
|
"num_tokens": 3919992.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.222498369216919,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.16219737380743027,
|
|
"num_tokens": 3930648.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.983048439025879,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.1618564561009407,
|
|
"num_tokens": 3941883.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.136180400848389,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.15810384154319762,
|
|
"num_tokens": 3952005.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.073668003082275,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.15803829729557037,
|
|
"num_tokens": 3963720.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.086091995239258,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.15588136315345763,
|
|
"num_tokens": 3974998.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.1153318881988525,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.1507617637515068,
|
|
"num_tokens": 3986469.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.125176620483399,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.16210003495216369,
|
|
"num_tokens": 3997553.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.051495170593261,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.15678568929433823,
|
|
"num_tokens": 4008613.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.25986499786377,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.1511420801281929,
|
|
"num_tokens": 4019860.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.070135641098022,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.15927470326423646,
|
|
"num_tokens": 4030602.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.085792970657349,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.15847504436969756,
|
|
"num_tokens": 4041878.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.058462238311767,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.15737630277872086,
|
|
"num_tokens": 4052799.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.136221027374267,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.15604432299733162,
|
|
"num_tokens": 4064339.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.031656074523926,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.1572178602218628,
|
|
"num_tokens": 4076246.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.095151281356811,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.1537073940038681,
|
|
"num_tokens": 4088006.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.104758310317993,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1572451949119568,
|
|
"num_tokens": 4098122.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.2256176471710205,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 6.1921,
|
|
"mean_token_accuracy": 0.1437402881681919,
|
|
"num_tokens": 4109958.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.188172292709351,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.14831269308924674,
|
|
"num_tokens": 4121262.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.1079864501953125,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.16434507966041564,
|
|
"num_tokens": 4130958.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.098403882980347,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.1472492016851902,
|
|
"num_tokens": 4143779.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.181719636917114,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.1468734547495842,
|
|
"num_tokens": 4155367.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.058016586303711,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.16174145489931108,
|
|
"num_tokens": 4166657.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.105555009841919,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 6.0224,
|
|
"mean_token_accuracy": 0.14920274317264556,
|
|
"num_tokens": 4177517.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.036544847488403,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.15815571695566177,
|
|
"num_tokens": 4188182.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.182504177093506,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.15333779901266098,
|
|
"num_tokens": 4199415.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.979681015014648,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 5.9412,
|
|
"mean_token_accuracy": 0.15690148621797562,
|
|
"num_tokens": 4210025.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.1226019859313965,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 5.8744,
|
|
"mean_token_accuracy": 0.16220202147960663,
|
|
"num_tokens": 4219920.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.0972521781921385,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.15590526312589645,
|
|
"num_tokens": 4232647.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.165735292434692,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 5.9247,
|
|
"mean_token_accuracy": 0.1573575183749199,
|
|
"num_tokens": 4242637.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.995357322692871,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.1608116880059242,
|
|
"num_tokens": 4253633.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.009541988372803,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.16294526755809785,
|
|
"num_tokens": 4264472.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.103630399703979,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.16053721606731414,
|
|
"num_tokens": 4275233.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.138267850875854,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.1537788674235344,
|
|
"num_tokens": 4287063.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.093268156051636,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.1523205667734146,
|
|
"num_tokens": 4298761.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.902304172515869,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.17036231160163878,
|
|
"num_tokens": 4309650.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.102732372283936,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.1670605018734932,
|
|
"num_tokens": 4320403.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.949552011489868,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.16250850558280944,
|
|
"num_tokens": 4332049.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.0235730648040775,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 5.8167,
|
|
"mean_token_accuracy": 0.16921360194683074,
|
|
"num_tokens": 4342551.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.074724721908569,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.1658030316233635,
|
|
"num_tokens": 4355156.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.030336904525757,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.9847,
|
|
"mean_token_accuracy": 0.1548118010163307,
|
|
"num_tokens": 4367402.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.063125991821289,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.16011397689580917,
|
|
"num_tokens": 4378687.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.11883807182312,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 6.0076,
|
|
"mean_token_accuracy": 0.16261736303567886,
|
|
"num_tokens": 4388871.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.988837957382202,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.162466561794281,
|
|
"num_tokens": 4399440.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.941546154022217,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.1630281165242195,
|
|
"num_tokens": 4409989.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.065251159667969,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 5.9984,
|
|
"mean_token_accuracy": 0.1544574961066246,
|
|
"num_tokens": 4422149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.177413558959961,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 6.0168,
|
|
"mean_token_accuracy": 0.15239877253770828,
|
|
"num_tokens": 4433157.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.089473867416382,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.15246912017464637,
|
|
"num_tokens": 4444595.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.120593118667602,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.15409756153821946,
|
|
"num_tokens": 4456592.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.121118116378784,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.8493,
|
|
"mean_token_accuracy": 0.16634103059768676,
|
|
"num_tokens": 4467624.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.943814611434936,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.15561599880456925,
|
|
"num_tokens": 4479766.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.113874292373657,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.1569325476884842,
|
|
"num_tokens": 4490023.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.037247514724731,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.15561158508062362,
|
|
"num_tokens": 4500651.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.112947797775268,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.15552351623773575,
|
|
"num_tokens": 4512934.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.043955087661743,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.16139791309833526,
|
|
"num_tokens": 4524251.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.077435302734375,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.150946182012558,
|
|
"num_tokens": 4536025.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.093569087982178,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.1649656981229782,
|
|
"num_tokens": 4546717.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.023766326904297,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.1631228283047676,
|
|
"num_tokens": 4557206.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.963823461532593,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.16605208814144135,
|
|
"num_tokens": 4568123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.033819532394409,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.16001455634832382,
|
|
"num_tokens": 4579385.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.062153911590576,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.1521618500351906,
|
|
"num_tokens": 4590514.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.082054615020752,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.153742416203022,
|
|
"num_tokens": 4601624.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.105756950378418,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.16200845390558244,
|
|
"num_tokens": 4612822.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.051490926742554,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.929,
|
|
"mean_token_accuracy": 0.16690855622291564,
|
|
"num_tokens": 4623443.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.051272869110107,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.1661006435751915,
|
|
"num_tokens": 4633600.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.0167961597442625,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.15368257761001586,
|
|
"num_tokens": 4644217.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.108413362503052,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.15525178462266923,
|
|
"num_tokens": 4654671.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.070890235900879,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.1527330458164215,
|
|
"num_tokens": 4665920.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.972177171707154,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.15897351056337355,
|
|
"num_tokens": 4675406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.0809448719024655,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 5.8903,
|
|
"mean_token_accuracy": 0.16125291138887404,
|
|
"num_tokens": 4686870.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.024101495742798,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.16157461553812028,
|
|
"num_tokens": 4698926.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.141122198104858,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.14744750112295152,
|
|
"num_tokens": 4709318.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.015442180633545,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.1723887175321579,
|
|
"num_tokens": 4718819.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.982702779769897,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.8017,
|
|
"mean_token_accuracy": 0.16581914126873015,
|
|
"num_tokens": 4729513.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.98707799911499,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 5.9057,
|
|
"mean_token_accuracy": 0.15758601874113082,
|
|
"num_tokens": 4739875.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.0923699855804445,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 6.0225,
|
|
"mean_token_accuracy": 0.1554579645395279,
|
|
"num_tokens": 4752933.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.974790573120117,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.16447033137083053,
|
|
"num_tokens": 4762969.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.082480096817017,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.1587963581085205,
|
|
"num_tokens": 4773495.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.049421215057373,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.16418441534042358,
|
|
"num_tokens": 4785335.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.163424825668335,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 6.0968,
|
|
"mean_token_accuracy": 0.14945545122027398,
|
|
"num_tokens": 4798068.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.0176959991455075,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.16261069476604462,
|
|
"num_tokens": 4809338.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.989019584655762,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.1641616255044937,
|
|
"num_tokens": 4819636.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.011251974105835,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.1603941172361374,
|
|
"num_tokens": 4830975.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.966836786270141,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.1578209728002548,
|
|
"num_tokens": 4841951.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.1164428234100345,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 5.8761,
|
|
"mean_token_accuracy": 0.1654752865433693,
|
|
"num_tokens": 4852919.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.980111455917358,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.9057,
|
|
"mean_token_accuracy": 0.15989038348197937,
|
|
"num_tokens": 4863433.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.0681713104248045,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.15361687242984773,
|
|
"num_tokens": 4875685.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.988730716705322,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.16120025664567947,
|
|
"num_tokens": 4886347.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.954083442687988,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.1674610421061516,
|
|
"num_tokens": 4896898.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.130784559249878,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.15649908781051636,
|
|
"num_tokens": 4908892.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.014833641052246,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.9208,
|
|
"mean_token_accuracy": 0.15536497831344603,
|
|
"num_tokens": 4920855.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.0808075904846195,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.15927496701478958,
|
|
"num_tokens": 4932857.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.966658067703247,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.15816042721271514,
|
|
"num_tokens": 4944063.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.944167375564575,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8061,
|
|
"mean_token_accuracy": 0.16439082026481627,
|
|
"num_tokens": 4955126.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.084042644500732,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.1617278426885605,
|
|
"num_tokens": 4965738.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.134811353683472,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.15683721601963044,
|
|
"num_tokens": 4976963.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.042261409759521,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.15658585280179976,
|
|
"num_tokens": 4987577.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.049076557159424,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.15402466356754302,
|
|
"num_tokens": 5000234.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.0481400966644285,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.15810587257146835,
|
|
"num_tokens": 5011652.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.035883140563965,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.9072,
|
|
"mean_token_accuracy": 0.1647823467850685,
|
|
"num_tokens": 5023603.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.978365039825439,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.8563,
|
|
"mean_token_accuracy": 0.1620233327150345,
|
|
"num_tokens": 5034427.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.99632716178894,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.1620258703827858,
|
|
"num_tokens": 5045738.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.919189691543579,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.7802,
|
|
"mean_token_accuracy": 0.16498485058546067,
|
|
"num_tokens": 5057021.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.9743774890899655,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.8854,
|
|
"mean_token_accuracy": 0.1610313430428505,
|
|
"num_tokens": 5067676.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.005889177322388,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.15866817831993102,
|
|
"num_tokens": 5079422.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.90629301071167,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.16426429897546768,
|
|
"num_tokens": 5091242.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.06869740486145,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.1580610081553459,
|
|
"num_tokens": 5102251.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.930915403366089,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.8698,
|
|
"mean_token_accuracy": 0.16566325724124908,
|
|
"num_tokens": 5113276.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.010626745223999,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.16318711042404174,
|
|
"num_tokens": 5124472.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.961625862121582,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.16604483723640442,
|
|
"num_tokens": 5134896.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.043686580657959,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.9178,
|
|
"mean_token_accuracy": 0.1696077510714531,
|
|
"num_tokens": 5145115.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.99830584526062,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.16266248524188995,
|
|
"num_tokens": 5155620.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.022756099700928,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.15687264502048492,
|
|
"num_tokens": 5166260.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.0588476181030275,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.1637933596968651,
|
|
"num_tokens": 5177143.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.015928792953491,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.1574145197868347,
|
|
"num_tokens": 5187795.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.936374187469482,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.16259244084358215,
|
|
"num_tokens": 5199365.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.100434160232544,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 6.042,
|
|
"mean_token_accuracy": 0.1578855521976948,
|
|
"num_tokens": 5212264.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.104435873031616,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.15828471332788469,
|
|
"num_tokens": 5223544.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.906753635406494,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.16902802437543868,
|
|
"num_tokens": 5234713.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.066522216796875,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.15844368189573288,
|
|
"num_tokens": 5246103.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.899614429473877,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.1704252302646637,
|
|
"num_tokens": 5257372.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.868502807617188,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.8083,
|
|
"mean_token_accuracy": 0.17290476560592652,
|
|
"num_tokens": 5268677.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.034987688064575,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.16481703519821167,
|
|
"num_tokens": 5279056.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.886941146850586,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.17248104959726335,
|
|
"num_tokens": 5289310.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.019134283065796,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.17079123556613923,
|
|
"num_tokens": 5300619.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.1063557147979735,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15677325427532196,
|
|
"num_tokens": 5311554.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.00995283126831,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.16173881739377977,
|
|
"num_tokens": 5323592.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.008228588104248,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.15665378868579866,
|
|
"num_tokens": 5334978.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.9265830516815186,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.16208231300115586,
|
|
"num_tokens": 5345724.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.07269515991211,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.15637324675917624,
|
|
"num_tokens": 5357141.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.932098627090454,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.1618094637989998,
|
|
"num_tokens": 5367889.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.812581205368042,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.6722,
|
|
"mean_token_accuracy": 0.170235738158226,
|
|
"num_tokens": 5379329.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.949158430099487,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.16787477880716323,
|
|
"num_tokens": 5389525.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.908147192001342,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.16844977140426637,
|
|
"num_tokens": 5401061.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.966408777236938,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.16398034989833832,
|
|
"num_tokens": 5411791.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.976400709152221,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.17024448215961457,
|
|
"num_tokens": 5422790.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.782303380966186,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.16513014137744902,
|
|
"num_tokens": 5434170.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.027258634567261,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.16099891066551208,
|
|
"num_tokens": 5445948.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.965994501113892,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.16192535758018495,
|
|
"num_tokens": 5457786.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.920778036117554,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.16586329638957978,
|
|
"num_tokens": 5469434.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.895144510269165,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.1602018490433693,
|
|
"num_tokens": 5480393.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.922933530807495,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.16891190260648728,
|
|
"num_tokens": 5490452.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.818361806869507,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.1680010199546814,
|
|
"num_tokens": 5501404.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.061710166931152,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.16127527356147767,
|
|
"num_tokens": 5512938.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.909400939941406,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.16050694435834884,
|
|
"num_tokens": 5524009.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.011155271530152,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.16401957720518112,
|
|
"num_tokens": 5535930.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.986298990249634,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.16194411218166352,
|
|
"num_tokens": 5547295.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.009273624420166,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.7989,
|
|
"mean_token_accuracy": 0.17319263219833375,
|
|
"num_tokens": 5558447.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.96380934715271,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.16416196078062056,
|
|
"num_tokens": 5569822.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.027960157394409,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.15599055737257003,
|
|
"num_tokens": 5582284.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.983034563064575,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.16630165725946428,
|
|
"num_tokens": 5593765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.863309574127197,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.16631342470645905,
|
|
"num_tokens": 5605080.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.068916463851929,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.1609751209616661,
|
|
"num_tokens": 5616739.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.9176679134368895,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.8352,
|
|
"mean_token_accuracy": 0.16028473302721977,
|
|
"num_tokens": 5628779.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.980112838745117,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.16063708662986756,
|
|
"num_tokens": 5639168.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.925217819213867,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.8408,
|
|
"mean_token_accuracy": 0.15582945495843886,
|
|
"num_tokens": 5650739.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.962657737731933,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.1636558547616005,
|
|
"num_tokens": 5662630.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.969783163070678,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.8546,
|
|
"mean_token_accuracy": 0.1752678006887436,
|
|
"num_tokens": 5673473.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.0135582447052,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.1577160730957985,
|
|
"num_tokens": 5686577.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.950829219818115,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.16806843429803847,
|
|
"num_tokens": 5697570.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.950319719314575,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.16019970327615737,
|
|
"num_tokens": 5708601.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.871870040893555,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.16131263971328735,
|
|
"num_tokens": 5719619.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.911778259277344,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.16822923272848128,
|
|
"num_tokens": 5730061.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.969560956954956,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.7994,
|
|
"mean_token_accuracy": 0.16950215995311738,
|
|
"num_tokens": 5741579.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.914897680282593,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8391,
|
|
"mean_token_accuracy": 0.16543644070625305,
|
|
"num_tokens": 5754001.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.0193511009216305,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.15843083187937737,
|
|
"num_tokens": 5766224.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.983878946304321,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.16135504990816116,
|
|
"num_tokens": 5777475.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.076950168609619,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.8778,
|
|
"mean_token_accuracy": 0.16028642505407334,
|
|
"num_tokens": 5788359.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.886411142349243,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.16728834807872772,
|
|
"num_tokens": 5799116.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.826918363571167,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.7676,
|
|
"mean_token_accuracy": 0.16748019605875014,
|
|
"num_tokens": 5811221.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.939854955673217,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.8372,
|
|
"mean_token_accuracy": 0.16192400455474854,
|
|
"num_tokens": 5822099.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.914843559265137,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.8035,
|
|
"mean_token_accuracy": 0.16361870169639586,
|
|
"num_tokens": 5832836.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.896129131317139,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.16292071640491484,
|
|
"num_tokens": 5842892.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.918717002868652,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.1763001188635826,
|
|
"num_tokens": 5852909.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.980309391021729,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.15793548226356507,
|
|
"num_tokens": 5864676.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.77226767539978,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.17642656713724136,
|
|
"num_tokens": 5875258.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.905883407592773,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.791,
|
|
"mean_token_accuracy": 0.16764549165964127,
|
|
"num_tokens": 5885611.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.887779760360718,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.16326538920402528,
|
|
"num_tokens": 5896726.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.924360132217407,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.16243307292461395,
|
|
"num_tokens": 5907860.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.907531642913819,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.17331860065460206,
|
|
"num_tokens": 5918676.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.913064241409302,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.17093740105628968,
|
|
"num_tokens": 5928646.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.853926038742065,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.16346052289009094,
|
|
"num_tokens": 5938990.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.917220211029052,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.17096300721168517,
|
|
"num_tokens": 5948811.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.823526763916016,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.17077333182096482,
|
|
"num_tokens": 5959227.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.881898880004883,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.1701909199357033,
|
|
"num_tokens": 5970546.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.973955917358398,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.15238012224435807,
|
|
"num_tokens": 5983936.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.863779735565186,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.161880199611187,
|
|
"num_tokens": 5994963.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.776348447799682,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.16576454639434815,
|
|
"num_tokens": 6005836.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.9588319778442385,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.1713724598288536,
|
|
"num_tokens": 6017408.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.842836093902588,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.1661224380135536,
|
|
"num_tokens": 6029281.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.883819055557251,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.759,
|
|
"mean_token_accuracy": 0.16810831427574158,
|
|
"num_tokens": 6039354.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.921117639541626,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.1678776279091835,
|
|
"num_tokens": 6050053.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.91437873840332,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.16302036195993425,
|
|
"num_tokens": 6060221.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.843975639343261,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.1659985974431038,
|
|
"num_tokens": 6070963.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.950300931930542,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.16181914508342743,
|
|
"num_tokens": 6082028.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.977104949951172,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.16607709527015685,
|
|
"num_tokens": 6092778.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.7921388149261475,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.5646,
|
|
"mean_token_accuracy": 0.1747915893793106,
|
|
"num_tokens": 6103093.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.797026968002319,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.178237247467041,
|
|
"num_tokens": 6113516.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.882149982452392,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.16529948264360428,
|
|
"num_tokens": 6125723.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.8273285865783695,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.16806278824806214,
|
|
"num_tokens": 6137091.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.784055280685425,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.1776074782013893,
|
|
"num_tokens": 6147941.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.786372470855713,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.17576141506433487,
|
|
"num_tokens": 6158493.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.836715936660767,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.16508943885564803,
|
|
"num_tokens": 6170759.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.878335046768188,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.6746,
|
|
"mean_token_accuracy": 0.17149458974599838,
|
|
"num_tokens": 6182488.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.919682121276855,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.847,
|
|
"mean_token_accuracy": 0.16313490122556687,
|
|
"num_tokens": 6193849.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.828121614456177,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.17412626296281813,
|
|
"num_tokens": 6204132.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.993827295303345,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.16273073852062225,
|
|
"num_tokens": 6215547.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.847994089126587,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.8449,
|
|
"mean_token_accuracy": 0.1607251435518265,
|
|
"num_tokens": 6227150.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.91080322265625,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.16594284176826476,
|
|
"num_tokens": 6237387.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.8898156642913815,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.1719898834824562,
|
|
"num_tokens": 6248623.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.753886318206787,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.18067649155855178,
|
|
"num_tokens": 6258596.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.859442329406738,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.9048,
|
|
"mean_token_accuracy": 0.15376001298427583,
|
|
"num_tokens": 6270529.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.051477670669556,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.16815871745347977,
|
|
"num_tokens": 6280891.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.761784839630127,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.16217630952596665,
|
|
"num_tokens": 6292247.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.809435749053955,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.17023676931858062,
|
|
"num_tokens": 6302403.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.740662288665772,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.172358837723732,
|
|
"num_tokens": 6313901.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.930067825317383,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.816,
|
|
"mean_token_accuracy": 0.16757736802101136,
|
|
"num_tokens": 6323711.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.868600368499756,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.16836982667446138,
|
|
"num_tokens": 6334937.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.916298198699951,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.16250242441892623,
|
|
"num_tokens": 6345723.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.8533323287963865,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.1683129131793976,
|
|
"num_tokens": 6357573.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.885237789154052,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.17246728241443635,
|
|
"num_tokens": 6367417.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.871446180343628,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.17002974152565004,
|
|
"num_tokens": 6377753.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.884670543670654,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.7774,
|
|
"mean_token_accuracy": 0.16697053462266923,
|
|
"num_tokens": 6388613.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.82194676399231,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.16596254110336303,
|
|
"num_tokens": 6399415.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.88742470741272,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.757,
|
|
"mean_token_accuracy": 0.16477338075637818,
|
|
"num_tokens": 6411435.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.980797052383423,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.1647609367966652,
|
|
"num_tokens": 6423030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.861991214752197,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.17240484952926635,
|
|
"num_tokens": 6434330.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.849894571304321,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.7912,
|
|
"mean_token_accuracy": 0.16527882367372512,
|
|
"num_tokens": 6446452.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.8581075191497805,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.17281781435012816,
|
|
"num_tokens": 6456723.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.8677558422088625,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.1585501030087471,
|
|
"num_tokens": 6468117.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.830036211013794,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.1726029947400093,
|
|
"num_tokens": 6479465.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.896154689788818,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.8609,
|
|
"mean_token_accuracy": 0.1708883285522461,
|
|
"num_tokens": 6490868.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.001963043212891,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.16834608167409898,
|
|
"num_tokens": 6502126.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.7357367992401125,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.16112906187772752,
|
|
"num_tokens": 6514382.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.8750903606414795,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.16924595683813096,
|
|
"num_tokens": 6526272.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.848873710632324,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.7359,
|
|
"mean_token_accuracy": 0.16710613369941713,
|
|
"num_tokens": 6537511.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.877924013137817,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.1693133145570755,
|
|
"num_tokens": 6549737.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.783770656585693,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.16940745562314988,
|
|
"num_tokens": 6560318.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.822894144058227,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.6838,
|
|
"mean_token_accuracy": 0.16761136800050735,
|
|
"num_tokens": 6570575.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.842888498306275,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.7403,
|
|
"mean_token_accuracy": 0.16567477136850356,
|
|
"num_tokens": 6582083.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.039827919006347,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.17067424952983856,
|
|
"num_tokens": 6592240.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.79384560585022,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.17623669505119324,
|
|
"num_tokens": 6602680.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.797509860992432,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.1686142474412918,
|
|
"num_tokens": 6613399.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.95811276435852,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.8369,
|
|
"mean_token_accuracy": 0.16310859918594361,
|
|
"num_tokens": 6624410.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.856153345108032,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.17337045669555665,
|
|
"num_tokens": 6635523.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.817016696929931,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.16047198623418807,
|
|
"num_tokens": 6648416.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.736549949645996,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.17165274024009705,
|
|
"num_tokens": 6658907.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.9185343265533445,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.7859,
|
|
"mean_token_accuracy": 0.16719561964273452,
|
|
"num_tokens": 6669682.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.90661244392395,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.8562,
|
|
"mean_token_accuracy": 0.16160167306661605,
|
|
"num_tokens": 6681919.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.866507720947266,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.16645660400390624,
|
|
"num_tokens": 6693988.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.801587915420532,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.7447,
|
|
"mean_token_accuracy": 0.16580444276332856,
|
|
"num_tokens": 6705413.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.891839265823364,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.1712946116924286,
|
|
"num_tokens": 6716217.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.614162020994456,
|
|
"eval_loss": 5.75322961807251,
|
|
"eval_mean_token_accuracy": 0.17627679489347348,
|
|
"eval_num_tokens": 6716217.0,
|
|
"eval_runtime": 18.5182,
|
|
"eval_samples_per_second": 1674.73,
|
|
"eval_steps_per_second": 209.362,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.78242506980896,
|
|
"epoch": 0.33750772168248444,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004994248234418611,
|
|
"loss": 5.759,
|
|
"mean_token_accuracy": 0.1712668463587761,
|
|
"num_tokens": 6728059.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.835500621795655,
|
|
"epoch": 0.33806929859044194,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499421950949953,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.16704993844032287,
|
|
"num_tokens": 6740650.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.737871837615967,
|
|
"epoch": 0.3386308754983995,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499419071312363,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.17291368097066878,
|
|
"num_tokens": 6751467.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.797616624832154,
|
|
"epoch": 0.33919245240635704,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994161845291828,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.17209089547395706,
|
|
"num_tokens": 6761377.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.772194671630859,
|
|
"epoch": 0.3397540293143146,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994132906005041,
|
|
"loss": 5.6591,
|
|
"mean_token_accuracy": 0.16932108253240585,
|
|
"num_tokens": 6773296.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.864219617843628,
|
|
"epoch": 0.34031560622227214,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994103895264193,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.16549092382192612,
|
|
"num_tokens": 6784122.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.71503791809082,
|
|
"epoch": 0.3408771831302297,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994074813070207,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.1766498789191246,
|
|
"num_tokens": 6795604.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.74120078086853,
|
|
"epoch": 0.34143876003818724,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994045659424007,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.16953518241643906,
|
|
"num_tokens": 6806671.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.899382257461548,
|
|
"epoch": 0.3420003369461448,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004994016434326524,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.17025199234485627,
|
|
"num_tokens": 6818271.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.772518682479858,
|
|
"epoch": 0.34256191385410234,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993987137778687,
|
|
"loss": 5.7462,
|
|
"mean_token_accuracy": 0.16914957016706467,
|
|
"num_tokens": 6830049.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.942037725448609,
|
|
"epoch": 0.3431234907620599,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499395776978143,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.159001362323761,
|
|
"num_tokens": 6842275.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.944367122650147,
|
|
"epoch": 0.3436850676700174,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993928330335686,
|
|
"loss": 5.7986,
|
|
"mean_token_accuracy": 0.17024847567081453,
|
|
"num_tokens": 6854910.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.859592390060425,
|
|
"epoch": 0.34424664457797494,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993898819442395,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.17515058517456056,
|
|
"num_tokens": 6866031.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.8712687492370605,
|
|
"epoch": 0.3448082214859325,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993869237102494,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.16718256026506423,
|
|
"num_tokens": 6877672.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.807470035552979,
|
|
"epoch": 0.34536979839389004,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993839583316927,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.17618233412504197,
|
|
"num_tokens": 6889089.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.683108758926392,
|
|
"epoch": 0.3459313753018476,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993809858086638,
|
|
"loss": 5.6224,
|
|
"mean_token_accuracy": 0.1751579910516739,
|
|
"num_tokens": 6899877.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.749358797073365,
|
|
"epoch": 0.34649295220980514,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993780061412571,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.17820996344089507,
|
|
"num_tokens": 6910686.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.782812070846558,
|
|
"epoch": 0.3470545291177627,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993750193295678,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.17682573795318604,
|
|
"num_tokens": 6920867.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.897553300857544,
|
|
"epoch": 0.34761610602572024,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993720253736909,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.17185292541980743,
|
|
"num_tokens": 6932779.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.880787181854248,
|
|
"epoch": 0.3481776829336778,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993690242737216,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.17311576753854752,
|
|
"num_tokens": 6943378.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.751677703857422,
|
|
"epoch": 0.3487392598416353,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993660160297555,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.17099200636148454,
|
|
"num_tokens": 6955469.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.951087760925293,
|
|
"epoch": 0.34930083674959284,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993630006418885,
|
|
"loss": 5.7979,
|
|
"mean_token_accuracy": 0.17271935790777207,
|
|
"num_tokens": 6966750.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.837881851196289,
|
|
"epoch": 0.3498624136575504,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993599781102166,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.1683436319231987,
|
|
"num_tokens": 6979010.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.824759435653687,
|
|
"epoch": 0.35042399056550794,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004993569484348359,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.17285715341567992,
|
|
"num_tokens": 6990566.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.81737904548645,
|
|
"epoch": 0.3509855674734655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993539116158429,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.1737413913011551,
|
|
"num_tokens": 7000288.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.670182228088379,
|
|
"epoch": 0.35154714438142304,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004993508676533346,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.17245251089334487,
|
|
"num_tokens": 7011143.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.991838359832764,
|
|
"epoch": 0.3521087212893806,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993478165474074,
|
|
"loss": 5.8035,
|
|
"mean_token_accuracy": 0.16104445606470108,
|
|
"num_tokens": 7022797.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.813840723037719,
|
|
"epoch": 0.35267029819733814,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993447582981588,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.16577449291944504,
|
|
"num_tokens": 7033477.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.8245768547058105,
|
|
"epoch": 0.3532318751052957,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499341692905686,
|
|
"loss": 5.7861,
|
|
"mean_token_accuracy": 0.17256249785423278,
|
|
"num_tokens": 7045249.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.871769857406616,
|
|
"epoch": 0.35379345201325324,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993386203700868,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.16594111919403076,
|
|
"num_tokens": 7056890.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.872320079803467,
|
|
"epoch": 0.35435502892121074,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993355406914589,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.1734893202781677,
|
|
"num_tokens": 7067181.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.805927848815918,
|
|
"epoch": 0.3549166058291683,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993324538699003,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.17190838903188704,
|
|
"num_tokens": 7078220.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.805079126358033,
|
|
"epoch": 0.35547818273712584,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993293599055094,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.17236423939466478,
|
|
"num_tokens": 7089536.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.841126775741577,
|
|
"epoch": 0.3560397596450834,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993262587983848,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.17327343225479125,
|
|
"num_tokens": 7101535.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.835830736160278,
|
|
"epoch": 0.35660133655304094,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499323150548625,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.1670640841126442,
|
|
"num_tokens": 7112468.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.800496578216553,
|
|
"epoch": 0.3571629134609985,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993200351563291,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.17924662828445434,
|
|
"num_tokens": 7123192.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.783369350433349,
|
|
"epoch": 0.35772449036895604,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993169126215962,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.1768344223499298,
|
|
"num_tokens": 7133063.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.814163255691528,
|
|
"epoch": 0.3582860672769136,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993137829445259,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.16557977348566055,
|
|
"num_tokens": 7144190.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.762482309341431,
|
|
"epoch": 0.35884764418487114,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993106461252177,
|
|
"loss": 5.6958,
|
|
"mean_token_accuracy": 0.17058299779891967,
|
|
"num_tokens": 7155433.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.922268724441528,
|
|
"epoch": 0.3594092210928287,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993075021637716,
|
|
"loss": 5.7664,
|
|
"mean_token_accuracy": 0.17212285101413727,
|
|
"num_tokens": 7166084.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.865365695953369,
|
|
"epoch": 0.3599707980007862,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993043510602875,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.17279787808656694,
|
|
"num_tokens": 7176948.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.783645582199097,
|
|
"epoch": 0.36053237490874374,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499301192814866,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.17580555528402328,
|
|
"num_tokens": 7188601.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.84276647567749,
|
|
"epoch": 0.3610939518167013,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992980274276074,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.1767750233411789,
|
|
"num_tokens": 7198495.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.817327785491943,
|
|
"epoch": 0.36165552872465884,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992948548986128,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.17252013683319092,
|
|
"num_tokens": 7209848.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.767550325393676,
|
|
"epoch": 0.3622171056326164,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992916752279829,
|
|
"loss": 5.7938,
|
|
"mean_token_accuracy": 0.16765172630548478,
|
|
"num_tokens": 7220366.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.839201498031616,
|
|
"epoch": 0.36277868254057394,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499288488415819,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.16565712094306945,
|
|
"num_tokens": 7231442.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.8749549865722654,
|
|
"epoch": 0.3633402594485315,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992852944622229,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.17133863121271134,
|
|
"num_tokens": 7242391.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.750967168807984,
|
|
"epoch": 0.36390183635648904,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992820933672958,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.16752980500459672,
|
|
"num_tokens": 7252061.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.824452924728393,
|
|
"epoch": 0.3644634132644466,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992788851311399,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.16855442821979522,
|
|
"num_tokens": 7264035.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.959766483306884,
|
|
"epoch": 0.3650249901724041,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992756697538574,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.16422308832406998,
|
|
"num_tokens": 7275988.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.777556467056274,
|
|
"epoch": 0.36558656708036164,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992724472355505,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.17620886117219925,
|
|
"num_tokens": 7286509.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.8404552936553955,
|
|
"epoch": 0.3661481439883192,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992692175763219,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.1743360698223114,
|
|
"num_tokens": 7296916.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.819206237792969,
|
|
"epoch": 0.36670972089627674,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992659807762745,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.16182578057050706,
|
|
"num_tokens": 7309563.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.877304553985596,
|
|
"epoch": 0.3672712978042343,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992627368355112,
|
|
"loss": 5.6625,
|
|
"mean_token_accuracy": 0.1648653566837311,
|
|
"num_tokens": 7320264.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.6788671016693115,
|
|
"epoch": 0.36783287471219184,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992594857541355,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.1724314123392105,
|
|
"num_tokens": 7330442.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.85842227935791,
|
|
"epoch": 0.3683944516201494,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992562275322506,
|
|
"loss": 5.8375,
|
|
"mean_token_accuracy": 0.16724578142166138,
|
|
"num_tokens": 7342292.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.919377565383911,
|
|
"epoch": 0.36895602852810694,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004992529621699606,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.17189548313617706,
|
|
"num_tokens": 7353857.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.832791090011597,
|
|
"epoch": 0.3695176054360645,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992496896673692,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.17282834500074387,
|
|
"num_tokens": 7365653.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.792215967178345,
|
|
"epoch": 0.37007918234402204,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992464100245809,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.16720979213714598,
|
|
"num_tokens": 7376522.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.810261487960815,
|
|
"epoch": 0.37064075925197953,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992431232416997,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.17675220519304274,
|
|
"num_tokens": 7388562.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.789384889602661,
|
|
"epoch": 0.3712023361599371,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004992398293188307,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1754407361149788,
|
|
"num_tokens": 7398597.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.7290369987487795,
|
|
"epoch": 0.37176391306789464,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992365282560784,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.1758016139268875,
|
|
"num_tokens": 7409656.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.781803274154663,
|
|
"epoch": 0.3723254899758522,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992332200535483,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.17091058045625687,
|
|
"num_tokens": 7420621.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.883068466186524,
|
|
"epoch": 0.37288706688380974,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004992299047113452,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.1757379040122032,
|
|
"num_tokens": 7432951.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.75234055519104,
|
|
"epoch": 0.3734486437917673,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992265822295752,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.17107966244220735,
|
|
"num_tokens": 7443630.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.827858543395996,
|
|
"epoch": 0.37401022069972484,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992232526083438,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.16994171291589738,
|
|
"num_tokens": 7454535.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.871645116806031,
|
|
"epoch": 0.3745717976076824,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499219915847757,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.16868658512830734,
|
|
"num_tokens": 7467751.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.738165473937988,
|
|
"epoch": 0.37513337451563994,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004992165719479211,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.18112843185663224,
|
|
"num_tokens": 7479347.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.821383810043335,
|
|
"epoch": 0.37569495142359743,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992132209089427,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.1710151970386505,
|
|
"num_tokens": 7490916.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.822624063491821,
|
|
"epoch": 0.376256528331555,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004992098627309283,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.175274857878685,
|
|
"num_tokens": 7500824.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.864793014526367,
|
|
"epoch": 0.37681810523951254,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499206497413985,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.16568053364753724,
|
|
"num_tokens": 7511778.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.869888639450073,
|
|
"epoch": 0.3773796821474701,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992031249582197,
|
|
"loss": 5.8351,
|
|
"mean_token_accuracy": 0.15724601224064827,
|
|
"num_tokens": 7522616.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.843500757217408,
|
|
"epoch": 0.37794125905542764,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991997453637401,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.17476143091917037,
|
|
"num_tokens": 7533019.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.76868200302124,
|
|
"epoch": 0.3785028359633852,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991963586306536,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.17255220115184783,
|
|
"num_tokens": 7544139.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.733314943313599,
|
|
"epoch": 0.37906441287134274,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991929647590682,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.16957715004682541,
|
|
"num_tokens": 7554638.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.880502223968506,
|
|
"epoch": 0.3796259897793003,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991895637490917,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.17726439684629441,
|
|
"num_tokens": 7565158.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.795942211151123,
|
|
"epoch": 0.38018756668725784,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004991861556008326,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.17030572146177292,
|
|
"num_tokens": 7576381.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.655525064468383,
|
|
"epoch": 0.3807491435952154,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991827403143992,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.17820151895284653,
|
|
"num_tokens": 7586631.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.807266664505005,
|
|
"epoch": 0.3813107205031729,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991793178899006,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.1734530508518219,
|
|
"num_tokens": 7598321.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.7635985851287845,
|
|
"epoch": 0.38187229741113043,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004991758883274455,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.17152283787727357,
|
|
"num_tokens": 7609336.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.731612586975098,
|
|
"epoch": 0.382433874319088,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991724516271432,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.17833686769008636,
|
|
"num_tokens": 7619116.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.763440132141113,
|
|
"epoch": 0.38299545122704554,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991690077891032,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.16949160993099213,
|
|
"num_tokens": 7630567.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.864394044876098,
|
|
"epoch": 0.3835570281350031,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991655568134348,
|
|
"loss": 5.7759,
|
|
"mean_token_accuracy": 0.16765906810760497,
|
|
"num_tokens": 7642564.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.855806350708008,
|
|
"epoch": 0.38411860504296064,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991620987002483,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.16712219268083572,
|
|
"num_tokens": 7654588.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.824643468856811,
|
|
"epoch": 0.3846801819509182,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991586334496536,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.1752467632293701,
|
|
"num_tokens": 7666120.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.768717050552368,
|
|
"epoch": 0.38524175885887574,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991551610617611,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.1685003787279129,
|
|
"num_tokens": 7677132.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.940306901931763,
|
|
"epoch": 0.3858033357668333,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991516815366812,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.16965620517730712,
|
|
"num_tokens": 7687515.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.787281799316406,
|
|
"epoch": 0.38636491267479084,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499148194874525,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.1683681681752205,
|
|
"num_tokens": 7698454.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.656362056732178,
|
|
"epoch": 0.38692648958274833,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004991447010754032,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.17882477939128877,
|
|
"num_tokens": 7708940.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.767519760131836,
|
|
"epoch": 0.3874880664907059,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991412001394273,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.17307667434215546,
|
|
"num_tokens": 7719705.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.8929778099060055,
|
|
"epoch": 0.38804964339866344,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991376920667086,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.16626095473766328,
|
|
"num_tokens": 7730649.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.797096109390258,
|
|
"epoch": 0.388611220306621,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991341768573589,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.16590397655963898,
|
|
"num_tokens": 7742014.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.828636598587036,
|
|
"epoch": 0.38917279721457854,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00049913065451149,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.16780297905206681,
|
|
"num_tokens": 7752892.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.845754241943359,
|
|
"epoch": 0.3897343741225361,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991271250292141,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.16321016550064088,
|
|
"num_tokens": 7762959.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.864690637588501,
|
|
"epoch": 0.39029595103049364,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991235884106437,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.1749914526939392,
|
|
"num_tokens": 7773566.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.749264574050903,
|
|
"epoch": 0.3908575279384512,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991200446558913,
|
|
"loss": 5.6429,
|
|
"mean_token_accuracy": 0.16560774743556977,
|
|
"num_tokens": 7785782.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.819610452651977,
|
|
"epoch": 0.39141910484640874,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991164937650698,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.16680697947740555,
|
|
"num_tokens": 7797551.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.756519174575805,
|
|
"epoch": 0.39198068175436623,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991129357382922,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.18425198793411254,
|
|
"num_tokens": 7808819.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.670140218734741,
|
|
"epoch": 0.3925422586623238,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991093705756718,
|
|
"loss": 5.5356,
|
|
"mean_token_accuracy": 0.17683782428503036,
|
|
"num_tokens": 7818940.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.773275756835938,
|
|
"epoch": 0.39310383557028133,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991057982773221,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.18041023463010789,
|
|
"num_tokens": 7829733.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.7527330875396725,
|
|
"epoch": 0.3936654124782389,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991022188433569,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.17617231905460357,
|
|
"num_tokens": 7840427.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.806566381454468,
|
|
"epoch": 0.39422698938619644,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049909863227389,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.1745058462023735,
|
|
"num_tokens": 7852834.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.78091082572937,
|
|
"epoch": 0.394788566294154,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990950385690358,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.17124974131584167,
|
|
"num_tokens": 7864993.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.769370985031128,
|
|
"epoch": 0.39535014320211154,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004990914377289088,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.17346420437097548,
|
|
"num_tokens": 7876578.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.692425966262817,
|
|
"epoch": 0.3959117201100691,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004990878297536233,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.1766596630215645,
|
|
"num_tokens": 7886770.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.720070791244507,
|
|
"epoch": 0.39647329701802664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990842146432946,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.1706479623913765,
|
|
"num_tokens": 7897106.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.804665803909302,
|
|
"epoch": 0.3970348739259842,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990805923980375,
|
|
"loss": 5.5465,
|
|
"mean_token_accuracy": 0.18475940972566604,
|
|
"num_tokens": 7907321.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.712037420272827,
|
|
"epoch": 0.3975964508339417,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990769630179673,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.18286396265029908,
|
|
"num_tokens": 7918628.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.77279314994812,
|
|
"epoch": 0.39815802774189923,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990733265032,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.16232608407735824,
|
|
"num_tokens": 7929387.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.9796497344970705,
|
|
"epoch": 0.3987196046498568,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004990696828538508,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.17559124529361725,
|
|
"num_tokens": 7940840.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.616290664672851,
|
|
"epoch": 0.39928118155781434,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499066032070036,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.17131029963493347,
|
|
"num_tokens": 7952243.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.804094076156616,
|
|
"epoch": 0.3998427584657719,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990623741518719,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.17473671734333038,
|
|
"num_tokens": 7963150.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.864617919921875,
|
|
"epoch": 0.40040433537372944,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499058709099475,
|
|
"loss": 5.7785,
|
|
"mean_token_accuracy": 0.16341475993394852,
|
|
"num_tokens": 7974862.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.837929630279541,
|
|
"epoch": 0.400965912281687,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990550369129618,
|
|
"loss": 5.7788,
|
|
"mean_token_accuracy": 0.17297388166189193,
|
|
"num_tokens": 7986438.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.796816873550415,
|
|
"epoch": 0.40152748918964454,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990513575924494,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.17586228251457214,
|
|
"num_tokens": 7996958.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.843265104293823,
|
|
"epoch": 0.4020890660976021,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990476711380548,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.16684656739234924,
|
|
"num_tokens": 8008862.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.7693767070770265,
|
|
"epoch": 0.40265064300555964,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004990439775498954,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.1781591311097145,
|
|
"num_tokens": 8018940.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.822980308532715,
|
|
"epoch": 0.40321221991351713,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499040276828089,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.1677076756954193,
|
|
"num_tokens": 8029148.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.7980344772338865,
|
|
"epoch": 0.4037737968214747,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990365689727533,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.1787825793027878,
|
|
"num_tokens": 8039618.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.689665508270264,
|
|
"epoch": 0.40433537372943223,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990328539840062,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.17121676951646805,
|
|
"num_tokens": 8051145.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.778972959518432,
|
|
"epoch": 0.4048969506373898,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990291318619663,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.16660722196102143,
|
|
"num_tokens": 8061520.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.729770660400391,
|
|
"epoch": 0.40545852754534734,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990254026067518,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.1721972182393074,
|
|
"num_tokens": 8072876.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.850456666946411,
|
|
"epoch": 0.4060201044533049,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990216662184817,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.18159251362085344,
|
|
"num_tokens": 8084240.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.754564523696899,
|
|
"epoch": 0.40658168136126244,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004990179226972749,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.17786346524953842,
|
|
"num_tokens": 8095773.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.634076023101807,
|
|
"epoch": 0.40714325826922,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990141720432504,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.17616600096225737,
|
|
"num_tokens": 8107003.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.742863512039184,
|
|
"epoch": 0.40770483517717754,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990104142565279,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.1816662520170212,
|
|
"num_tokens": 8117864.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.81513237953186,
|
|
"epoch": 0.40826641208513503,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499006649337227,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.16966941058635712,
|
|
"num_tokens": 8129363.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.785495042800903,
|
|
"epoch": 0.4088279889930926,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004990028772854674,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.17465245276689528,
|
|
"num_tokens": 8141319.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.798785448074341,
|
|
"epoch": 0.40938956590105013,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004989990981013693,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.17832515388727188,
|
|
"num_tokens": 8153344.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.720279788970947,
|
|
"epoch": 0.4099511428090077,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498995311785053,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.16710296124219895,
|
|
"num_tokens": 8164196.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.7291107177734375,
|
|
"epoch": 0.41051271971696524,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989915183366392,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.1734949141740799,
|
|
"num_tokens": 8174663.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.756137275695801,
|
|
"epoch": 0.4110742966249228,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989877177562485,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.17827233523130417,
|
|
"num_tokens": 8185215.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.725867748260498,
|
|
"epoch": 0.41163587353288034,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000498983910044002,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.17710465043783188,
|
|
"num_tokens": 8195694.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.726460266113281,
|
|
"epoch": 0.4121974504408379,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989800952000209,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.19022790789604188,
|
|
"num_tokens": 8206112.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.766532516479492,
|
|
"epoch": 0.41275902734879544,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004989762732244268,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.1736864060163498,
|
|
"num_tokens": 8216548.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.843055868148804,
|
|
"epoch": 0.413320604256753,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989724441173413,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.17897214889526367,
|
|
"num_tokens": 8226643.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.8469569206237795,
|
|
"epoch": 0.4138821811647105,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989686078788862,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.17345338314771652,
|
|
"num_tokens": 8236755.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.780122184753418,
|
|
"epoch": 0.41444375807266803,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004989647645091839,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.17510487288236617,
|
|
"num_tokens": 8247526.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.733848237991333,
|
|
"epoch": 0.4150053349806256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989609140083565,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.16700498163700103,
|
|
"num_tokens": 8258649.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.737814903259277,
|
|
"epoch": 0.41556691188858313,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004989570563765269,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.17942749559879304,
|
|
"num_tokens": 8268260.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.82305498123169,
|
|
"epoch": 0.4161284887965407,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989531916138176,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.173169869184494,
|
|
"num_tokens": 8280090.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.774903345108032,
|
|
"epoch": 0.41669006570449824,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004989493197203519,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.17832693904638292,
|
|
"num_tokens": 8291217.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.782907104492187,
|
|
"epoch": 0.4172516426124558,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498945440696253,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.17522466629743577,
|
|
"num_tokens": 8303541.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.736049461364746,
|
|
"epoch": 0.41781321952041334,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004989415545416444,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.1725260615348816,
|
|
"num_tokens": 8316104.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.676948499679566,
|
|
"epoch": 0.4183747964283709,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989376612566498,
|
|
"loss": 5.5834,
|
|
"mean_token_accuracy": 0.1761096328496933,
|
|
"num_tokens": 8327158.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.809417057037353,
|
|
"epoch": 0.4189363733363284,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989337608413933,
|
|
"loss": 5.7316,
|
|
"mean_token_accuracy": 0.17283382564783095,
|
|
"num_tokens": 8337685.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.8715009689331055,
|
|
"epoch": 0.41949795024428593,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989298532959989,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.16970106363296508,
|
|
"num_tokens": 8349778.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.819469594955445,
|
|
"epoch": 0.4200595271522435,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004989259386205912,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.18156449794769286,
|
|
"num_tokens": 8361041.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.78918981552124,
|
|
"epoch": 0.42062110406020103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989220168152948,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.16831362545490264,
|
|
"num_tokens": 8373227.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.710517692565918,
|
|
"epoch": 0.4211826809681586,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989180878802346,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.1777936562895775,
|
|
"num_tokens": 8384223.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.79281325340271,
|
|
"epoch": 0.42174425787611614,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004989141518155354,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.17828506231307983,
|
|
"num_tokens": 8395014.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.717869615554809,
|
|
"epoch": 0.4223058347840737,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004989102086213229,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.16793012470006943,
|
|
"num_tokens": 8406445.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.717303514480591,
|
|
"epoch": 0.42286741169203124,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989062582977225,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.18339111357927323,
|
|
"num_tokens": 8417488.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.804220819473267,
|
|
"epoch": 0.4234289885999888,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004989023008448599,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.16667583137750625,
|
|
"num_tokens": 8430582.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.744842958450318,
|
|
"epoch": 0.42399056550794634,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988983362628614,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.17447961419820784,
|
|
"num_tokens": 8442033.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.716476202011108,
|
|
"epoch": 0.42455214241590383,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988943645518528,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.17734331786632537,
|
|
"num_tokens": 8451722.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.672188568115234,
|
|
"epoch": 0.4251137193238614,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988903857119611,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.1754377618432045,
|
|
"num_tokens": 8462753.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.832608222961426,
|
|
"epoch": 0.42567529623181893,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988863997433125,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.17005208432674407,
|
|
"num_tokens": 8472755.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.690932178497315,
|
|
"epoch": 0.4262368731397765,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988824066460341,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.17494447529315948,
|
|
"num_tokens": 8483296.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.760097885131836,
|
|
"epoch": 0.42679845004773403,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498878406420253,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.1804656684398651,
|
|
"num_tokens": 8493739.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.770771741867065,
|
|
"epoch": 0.4273600269556916,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004988743990660967,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.17196254432201385,
|
|
"num_tokens": 8504788.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.740551280975342,
|
|
"epoch": 0.42792160386364914,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988703845836927,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.1754516087472439,
|
|
"num_tokens": 8514708.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.691767930984497,
|
|
"epoch": 0.4284831807716067,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004988663629731687,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.1853637471795082,
|
|
"num_tokens": 8525227.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.660324048995972,
|
|
"epoch": 0.42904475767956424,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498862334234653,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.17812691628932953,
|
|
"num_tokens": 8536502.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.717139530181885,
|
|
"epoch": 0.4296063345875218,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004988582983682737,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.17199601382017135,
|
|
"num_tokens": 8548087.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.804413986206055,
|
|
"epoch": 0.4301679114954793,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988542553741594,
|
|
"loss": 5.6891,
|
|
"mean_token_accuracy": 0.17578112035989762,
|
|
"num_tokens": 8560856.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.845123910903931,
|
|
"epoch": 0.43072948840343683,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988502052524388,
|
|
"loss": 5.8027,
|
|
"mean_token_accuracy": 0.17262884229421616,
|
|
"num_tokens": 8572521.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.82160587310791,
|
|
"epoch": 0.4312910653113944,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004988461480032408,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.1777540698647499,
|
|
"num_tokens": 8583977.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.661305332183838,
|
|
"epoch": 0.43185264221935193,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004988420836266946,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.17490361034870147,
|
|
"num_tokens": 8594441.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.774579763412476,
|
|
"epoch": 0.4324142191273095,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988380121229298,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.1769399091601372,
|
|
"num_tokens": 8604843.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.771303749084472,
|
|
"epoch": 0.43297579603526704,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004988339334920757,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.1730481505393982,
|
|
"num_tokens": 8616059.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.669122123718262,
|
|
"epoch": 0.4335373729432246,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988298477342625,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.18117850869894028,
|
|
"num_tokens": 8626203.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.748584270477295,
|
|
"epoch": 0.43409894985118214,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049882575484962,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.17327094674110413,
|
|
"num_tokens": 8636921.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.609547519683838,
|
|
"epoch": 0.4346605267591397,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004988216548382787,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.185021248459816,
|
|
"num_tokens": 8648526.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.749398231506348,
|
|
"epoch": 0.4352221036670972,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004988175477003691,
|
|
"loss": 5.6932,
|
|
"mean_token_accuracy": 0.166272434592247,
|
|
"num_tokens": 8660339.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.910698366165161,
|
|
"epoch": 0.43578368057505473,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000498813433436022,
|
|
"loss": 5.7547,
|
|
"mean_token_accuracy": 0.16805825829505922,
|
|
"num_tokens": 8671835.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.646166086196899,
|
|
"epoch": 0.4363452574830123,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988093120453684,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.18140540271997452,
|
|
"num_tokens": 8681146.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.6193399906158445,
|
|
"epoch": 0.43690683439096983,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988051835285394,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.17882596999406813,
|
|
"num_tokens": 8691623.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.7039693832397464,
|
|
"epoch": 0.4374684112989274,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004988010478856667,
|
|
"loss": 5.5865,
|
|
"mean_token_accuracy": 0.1710977166891098,
|
|
"num_tokens": 8703702.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.892058563232422,
|
|
"epoch": 0.43802998820688493,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987969051168816,
|
|
"loss": 5.7551,
|
|
"mean_token_accuracy": 0.17641495168209076,
|
|
"num_tokens": 8715434.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.669679069519043,
|
|
"epoch": 0.4385915651148425,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987927552223165,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.187179234623909,
|
|
"num_tokens": 8726135.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.618429136276245,
|
|
"epoch": 0.43915314202280004,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987885982021032,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.17829640805721284,
|
|
"num_tokens": 8736538.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.76555495262146,
|
|
"epoch": 0.4397147189307576,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987844340563741,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.18081898391246795,
|
|
"num_tokens": 8746456.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.767681503295899,
|
|
"epoch": 0.44027629583871514,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987802627852619,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.1785939320921898,
|
|
"num_tokens": 8757143.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.79232439994812,
|
|
"epoch": 0.44083787274667263,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004987760843888992,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.17781463116407395,
|
|
"num_tokens": 8769084.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.725571489334106,
|
|
"epoch": 0.4413994496546302,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004987718988674193,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.17253756821155547,
|
|
"num_tokens": 8780707.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.736790466308594,
|
|
"epoch": 0.44196102656258773,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987677062209552,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.17054901868104935,
|
|
"num_tokens": 8792157.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.84659514427185,
|
|
"epoch": 0.4425226034705453,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987635064496407,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.17696321457624437,
|
|
"num_tokens": 8802691.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.749785280227661,
|
|
"epoch": 0.44308418037850283,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004987592995536093,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.1767987549304962,
|
|
"num_tokens": 8814869.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.704902648925781,
|
|
"epoch": 0.4436457572864604,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004987550855329951,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.18619299978017806,
|
|
"num_tokens": 8825264.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.800254678726196,
|
|
"epoch": 0.44420733419441794,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004987508643879322,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.17100632488727568,
|
|
"num_tokens": 8837128.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.782445049285888,
|
|
"epoch": 0.4447689111023755,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987466361185549,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.17345671951770783,
|
|
"num_tokens": 8848587.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.822360897064209,
|
|
"epoch": 0.44533048801033304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987424007249979,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.1681307628750801,
|
|
"num_tokens": 8859219.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.759450244903564,
|
|
"epoch": 0.4458920649182906,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987381582073962,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.17922253906726837,
|
|
"num_tokens": 8868780.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.790824890136719,
|
|
"epoch": 0.4464536418262481,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987339085658848,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.17222894877195358,
|
|
"num_tokens": 8880903.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.63943452835083,
|
|
"epoch": 0.44701521873420563,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987296518005988,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.18767103552818298,
|
|
"num_tokens": 8890335.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.659843158721924,
|
|
"epoch": 0.4475767956421632,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000498725387911674,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.17692393362522124,
|
|
"num_tokens": 8904104.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.791635417938233,
|
|
"epoch": 0.44813837255012073,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004987211168992461,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.1737372562289238,
|
|
"num_tokens": 8915118.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.8336080551147464,
|
|
"epoch": 0.4486999494580783,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000498716838763451,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.1739199563860893,
|
|
"num_tokens": 8927450.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.7899621486663815,
|
|
"epoch": 0.44926152636603583,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000498712553504425,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.17691660374403,
|
|
"num_tokens": 8939902.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.715288209915161,
|
|
"epoch": 0.4498231032739934,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987082611223046,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.17151920199394227,
|
|
"num_tokens": 8951736.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.846401214599609,
|
|
"epoch": 0.45038468018195094,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004987039616172265,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.17475533932447435,
|
|
"num_tokens": 8963283.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.693903541564941,
|
|
"epoch": 0.4509462570899085,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004986996549893273,
|
|
"loss": 5.5566,
|
|
"mean_token_accuracy": 0.18240576684474946,
|
|
"num_tokens": 8974323.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.724124193191528,
|
|
"epoch": 0.451507833997866,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004986953412387445,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.17199651151895523,
|
|
"num_tokens": 8986687.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.737013435363769,
|
|
"epoch": 0.45206941090582353,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004986910203656151,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.17963865846395494,
|
|
"num_tokens": 8997734.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.682125997543335,
|
|
"epoch": 0.4526309878137811,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004986866923700769,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.16775927990674971,
|
|
"num_tokens": 9008743.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.788743591308593,
|
|
"epoch": 0.45319256472173863,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986823572522677,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.17755803614854812,
|
|
"num_tokens": 9019495.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.75370225906372,
|
|
"epoch": 0.4537541416296962,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986780150123254,
|
|
"loss": 5.6549,
|
|
"mean_token_accuracy": 0.1762051537632942,
|
|
"num_tokens": 9029546.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.584637641906738,
|
|
"epoch": 0.45431571853765373,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004986736656503885,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.18269690722227097,
|
|
"num_tokens": 9040393.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.61825590133667,
|
|
"epoch": 0.4548772954456113,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986693091665952,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.17425805628299712,
|
|
"num_tokens": 9050840.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.735077285766602,
|
|
"epoch": 0.45543887235356884,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986649455610845,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.17736514359712602,
|
|
"num_tokens": 9061615.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.668075513839722,
|
|
"epoch": 0.4560004492615264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498660574833995,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.18246414810419082,
|
|
"num_tokens": 9071902.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.6979475021362305,
|
|
"epoch": 0.45656202616948394,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004986561969854661,
|
|
"loss": 5.6891,
|
|
"mean_token_accuracy": 0.17251477837562562,
|
|
"num_tokens": 9083613.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.7372931957244875,
|
|
"epoch": 0.45712360307744143,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986518120156373,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.17594532668590546,
|
|
"num_tokens": 9095678.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.74835467338562,
|
|
"epoch": 0.457685179985399,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000498647419924648,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.1785824254155159,
|
|
"num_tokens": 9106637.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.619346570968628,
|
|
"epoch": 0.45824675689335653,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498643020712638,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.18403517752885817,
|
|
"num_tokens": 9117343.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.788536787033081,
|
|
"epoch": 0.4588083338013141,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986386143797475,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.17341005504131318,
|
|
"num_tokens": 9129315.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.690409708023071,
|
|
"epoch": 0.45936991070927163,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986342009261169,
|
|
"loss": 5.5595,
|
|
"mean_token_accuracy": 0.1751215413212776,
|
|
"num_tokens": 9139701.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.738325071334839,
|
|
"epoch": 0.4599314876172292,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004986297803518865,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.17411129027605057,
|
|
"num_tokens": 9152334.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.694036912918091,
|
|
"epoch": 0.46049306452518673,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986253526571971,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.18084232807159423,
|
|
"num_tokens": 9163277.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.695529365539551,
|
|
"epoch": 0.4610546414331443,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986209178421899,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.17361331433057786,
|
|
"num_tokens": 9174909.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.6283860206604,
|
|
"epoch": 0.46161621834110184,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498616475907006,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.17430782914161683,
|
|
"num_tokens": 9186058.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.702317333221435,
|
|
"epoch": 0.46217779524905933,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986120268517865,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.17791880071163177,
|
|
"num_tokens": 9196919.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.745574617385865,
|
|
"epoch": 0.4627393721570169,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004986075706766736,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.17795812338590622,
|
|
"num_tokens": 9208452.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.727191686630249,
|
|
"epoch": 0.46330094906497443,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986031073818088,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.17488866150379181,
|
|
"num_tokens": 9219605.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.6882342338562015,
|
|
"epoch": 0.463862525972932,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985986369673343,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.1851383090019226,
|
|
"num_tokens": 9230491.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.745537900924683,
|
|
"epoch": 0.46442410288088953,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004985941594333926,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.17329567670822144,
|
|
"num_tokens": 9241768.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.71098141670227,
|
|
"epoch": 0.4649856797888471,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498589674780126,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.17462718188762666,
|
|
"num_tokens": 9253779.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.853395128250122,
|
|
"epoch": 0.46554725669680463,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985851830076775,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.18375394344329835,
|
|
"num_tokens": 9264567.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.630904483795166,
|
|
"epoch": 0.4661088336047622,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004985806841161901,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.17980915904045106,
|
|
"num_tokens": 9275960.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.684050559997559,
|
|
"epoch": 0.46667041051271974,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000498576178105807,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.18097364157438278,
|
|
"num_tokens": 9288305.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.74391131401062,
|
|
"epoch": 0.4672319874206773,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985716649766717,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.18818308413028717,
|
|
"num_tokens": 9299579.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.652613019943237,
|
|
"epoch": 0.4677935643286348,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004985671447289277,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.17804178446531296,
|
|
"num_tokens": 9311221.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.700166797637939,
|
|
"epoch": 0.46835514123659233,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985626173627194,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.17445982992649078,
|
|
"num_tokens": 9322488.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.661394119262695,
|
|
"epoch": 0.4689167181445499,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004985580828781904,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.17750884592533112,
|
|
"num_tokens": 9333672.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.82847146987915,
|
|
"epoch": 0.46947829505250743,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985535412754855,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.17722365707159043,
|
|
"num_tokens": 9344449.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.718812608718872,
|
|
"epoch": 0.470039871960465,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498548992554749,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.17509260326623916,
|
|
"num_tokens": 9355279.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.714748477935791,
|
|
"epoch": 0.47060144886842253,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985444367161259,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.17669070959091188,
|
|
"num_tokens": 9366942.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.70895209312439,
|
|
"epoch": 0.4711630257763801,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985398737597614,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.18356451839208604,
|
|
"num_tokens": 9378129.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.769950532913208,
|
|
"epoch": 0.47172460268433763,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985353036858004,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.17625712752342224,
|
|
"num_tokens": 9388757.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.6727923393249515,
|
|
"epoch": 0.4722861795922952,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985307264943887,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.17768628299236297,
|
|
"num_tokens": 9399112.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.754285669326782,
|
|
"epoch": 0.47284775650025274,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985261421856721,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.17926284223794936,
|
|
"num_tokens": 9410156.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.7768840312957765,
|
|
"epoch": 0.47340933340821023,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985215507597963,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.18103664070367814,
|
|
"num_tokens": 9420402.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.685761165618897,
|
|
"epoch": 0.4739709103161678,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985169522169076,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.17621594071388244,
|
|
"num_tokens": 9431159.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.6776097297668455,
|
|
"epoch": 0.47453248722412533,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985123465571526,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.18199094831943513,
|
|
"num_tokens": 9441737.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.703557729721069,
|
|
"epoch": 0.4750940641320829,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985077337806777,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.1888112410902977,
|
|
"num_tokens": 9452756.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.684602069854736,
|
|
"epoch": 0.47565564104004043,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985031138876299,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.18107137829065323,
|
|
"num_tokens": 9464231.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.750472164154052,
|
|
"epoch": 0.476217217947998,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984984868781563,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.17960380315780639,
|
|
"num_tokens": 9475648.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.721074771881104,
|
|
"epoch": 0.47677879485595553,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004984938527524041,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.1784772664308548,
|
|
"num_tokens": 9486594.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.610937595367432,
|
|
"epoch": 0.4773403717639131,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498489211510521,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.18282184302806853,
|
|
"num_tokens": 9497085.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.731305646896362,
|
|
"epoch": 0.47790194867187064,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004984845631526547,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.17742327749729156,
|
|
"num_tokens": 9509765.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.65969877243042,
|
|
"epoch": 0.47846352557982813,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004984799076789534,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.1776812344789505,
|
|
"num_tokens": 9521341.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.640336179733277,
|
|
"epoch": 0.4790251024877857,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004984752450895649,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.17370839715003966,
|
|
"num_tokens": 9533196.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.740092658996582,
|
|
"epoch": 0.47958667939574323,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498470575384638,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.1697436109185219,
|
|
"num_tokens": 9543687.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.811639451980591,
|
|
"epoch": 0.4801482563037008,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984658985643214,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.17581167370080947,
|
|
"num_tokens": 9555320.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.62182502746582,
|
|
"epoch": 0.48070983321165833,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984612146287638,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.17930686771869658,
|
|
"num_tokens": 9566347.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.640014362335205,
|
|
"epoch": 0.4812714101196159,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984565235781147,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.17868368923664094,
|
|
"num_tokens": 9577111.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.721031665802002,
|
|
"epoch": 0.48183298702757343,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498451825412523,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.17430604100227357,
|
|
"num_tokens": 9586612.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.737975692749023,
|
|
"epoch": 0.482394563935531,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004984471201321386,
|
|
"loss": 5.5658,
|
|
"mean_token_accuracy": 0.1818862810730934,
|
|
"num_tokens": 9597347.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.5932446956634525,
|
|
"epoch": 0.48295614084348854,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004984424077371112,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.18292556703090668,
|
|
"num_tokens": 9608507.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.695942497253418,
|
|
"epoch": 0.4835177177514461,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984376882275909,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.1857465013861656,
|
|
"num_tokens": 9619449.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.632146215438842,
|
|
"epoch": 0.4840792946594036,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984329616037279,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.1781950369477272,
|
|
"num_tokens": 9630613.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.671129417419434,
|
|
"epoch": 0.48464087156736113,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004984282278656727,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.17571799457073212,
|
|
"num_tokens": 9642149.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.759219837188721,
|
|
"epoch": 0.4852024484753187,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004984234870135762,
|
|
"loss": 5.5141,
|
|
"mean_token_accuracy": 0.18522863537073136,
|
|
"num_tokens": 9652960.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.680975103378296,
|
|
"epoch": 0.48576402538327623,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984187390475891,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.18465818613767623,
|
|
"num_tokens": 9662676.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.792536973953247,
|
|
"epoch": 0.4863256022912338,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004984139839678628,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.17387693822383882,
|
|
"num_tokens": 9674138.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.649532985687256,
|
|
"epoch": 0.48688717919919133,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984092217745486,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.17926107197999955,
|
|
"num_tokens": 9685397.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.734627294540405,
|
|
"epoch": 0.4874487561071489,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004984044524677981,
|
|
"loss": 5.7036,
|
|
"mean_token_accuracy": 0.16867997050285338,
|
|
"num_tokens": 9697266.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.731437015533447,
|
|
"epoch": 0.48801033301510643,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004983996760477632,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.17460529655218124,
|
|
"num_tokens": 9707967.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.591812181472778,
|
|
"epoch": 0.488571909923064,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498394892514596,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.18121830374002457,
|
|
"num_tokens": 9718162.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.7490888118743895,
|
|
"epoch": 0.48913348683102154,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983901018684486,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.17766382545232773,
|
|
"num_tokens": 9729439.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.684594535827637,
|
|
"epoch": 0.48969506373897903,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004983853041094739,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.1804145097732544,
|
|
"num_tokens": 9741383.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.638334894180298,
|
|
"epoch": 0.4902566406469366,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983804992378243,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.18215366154909135,
|
|
"num_tokens": 9753050.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.6181640625,
|
|
"epoch": 0.49081821755489413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983756872536532,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.18427116125822068,
|
|
"num_tokens": 9763715.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.644756412506103,
|
|
"epoch": 0.4913797944628517,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004983708681571134,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.19025729298591615,
|
|
"num_tokens": 9774145.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.693837404251099,
|
|
"epoch": 0.49194137137080923,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983660419483586,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.18284793347120284,
|
|
"num_tokens": 9784703.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.675417757034301,
|
|
"epoch": 0.4925029482787668,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004983612086275424,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.1775639608502388,
|
|
"num_tokens": 9795426.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.6640383243560795,
|
|
"epoch": 0.49306452518672433,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983563681948187,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.17796266525983812,
|
|
"num_tokens": 9806539.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.773860692977905,
|
|
"epoch": 0.4936261020946819,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983515206503416,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.17028506398200988,
|
|
"num_tokens": 9816806.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.677014350891113,
|
|
"epoch": 0.49418767900263944,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983466659942655,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.18890158832073212,
|
|
"num_tokens": 9828001.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.56375904083252,
|
|
"epoch": 0.49474925591059693,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983418042267449,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.18355960249900818,
|
|
"num_tokens": 9838773.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.645020055770874,
|
|
"epoch": 0.4953108328185545,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983369353479345,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.185479736328125,
|
|
"num_tokens": 9848680.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.658714008331299,
|
|
"epoch": 0.49587240972651203,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004983320593579895,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.1791000947356224,
|
|
"num_tokens": 9859168.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.607437801361084,
|
|
"epoch": 0.4964339866344696,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983271762570653,
|
|
"loss": 5.5446,
|
|
"mean_token_accuracy": 0.18457687199115752,
|
|
"num_tokens": 9869071.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.691721057891845,
|
|
"epoch": 0.49699556354242713,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498322286045317,
|
|
"loss": 5.5572,
|
|
"mean_token_accuracy": 0.17970811873674392,
|
|
"num_tokens": 9880208.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.713977098464966,
|
|
"epoch": 0.4975571404503847,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983173887229006,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.17773272842168808,
|
|
"num_tokens": 9891192.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.765380144119263,
|
|
"epoch": 0.49811871735834223,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983124842899719,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.17868606448173524,
|
|
"num_tokens": 9903038.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.755488634109497,
|
|
"epoch": 0.4986802942662998,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983075727466871,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.17873362600803375,
|
|
"num_tokens": 9916104.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.645304918289185,
|
|
"epoch": 0.49924187117425733,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983026540932026,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.18384079337120057,
|
|
"num_tokens": 9927094.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.768632221221924,
|
|
"epoch": 0.4998034480822149,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982977283296749,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.17297413796186448,
|
|
"num_tokens": 9937964.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.791966152191162,
|
|
"epoch": 0.5003650249901724,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000498292795456261,
|
|
"loss": 5.6523,
|
|
"mean_token_accuracy": 0.1700085535645485,
|
|
"num_tokens": 9949238.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.746701049804687,
|
|
"epoch": 0.50092660189813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982878554731178,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.18006610572338105,
|
|
"num_tokens": 9960125.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.515468645095825,
|
|
"epoch": 0.5014881788060875,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982829083804028,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.17944588959217073,
|
|
"num_tokens": 9971130.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.591465473175049,
|
|
"epoch": 0.5020497557140451,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004982779541782733,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.19421613365411758,
|
|
"num_tokens": 9981516.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.6657304763793945,
|
|
"epoch": 0.5026113326220026,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004982729928668872,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.176748389005661,
|
|
"num_tokens": 9992360.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.840109014511109,
|
|
"epoch": 0.5031729095299601,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004982680244464024,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.1696069911122322,
|
|
"num_tokens": 10003410.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.757320690155029,
|
|
"epoch": 0.5037344864379176,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004982630489169771,
|
|
"loss": 5.5262,
|
|
"mean_token_accuracy": 0.18171941339969636,
|
|
"num_tokens": 10014974.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.664915466308594,
|
|
"epoch": 0.5042960633458752,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004982580662787697,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.17924250215291976,
|
|
"num_tokens": 10026702.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.661592674255371,
|
|
"epoch": 0.5048576402538327,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982530765319389,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.17660929560661315,
|
|
"num_tokens": 10039318.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.699104309082031,
|
|
"epoch": 0.5054192171617903,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982480796766436,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.17950531989336013,
|
|
"num_tokens": 10049726.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.600860977172852,
|
|
"epoch": 0.5059807940697478,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982430757130429,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.18549245446920395,
|
|
"num_tokens": 10059663.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.559926128387451,
|
|
"epoch": 0.5065423709777054,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004982380646412959,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.18071688264608382,
|
|
"num_tokens": 10071195.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.796983814239502,
|
|
"epoch": 0.5071039478856629,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982330464615625,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.17178147286176682,
|
|
"num_tokens": 10082014.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.739580535888672,
|
|
"epoch": 0.5076655247936205,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982280211740023,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.19065007269382478,
|
|
"num_tokens": 10093156.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.6617120742797855,
|
|
"epoch": 0.508227101701578,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004982229887787753,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.1669050484895706,
|
|
"num_tokens": 10104993.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.640649223327637,
|
|
"epoch": 0.5087886786095356,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982179492760418,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.19023462980985642,
|
|
"num_tokens": 10114590.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.613068056106568,
|
|
"epoch": 0.5093502555174931,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982129026659621,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.18594662100076675,
|
|
"num_tokens": 10125849.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.657345724105835,
|
|
"epoch": 0.5099118324254507,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982078489486972,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.18628225177526475,
|
|
"num_tokens": 10135493.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.673488187789917,
|
|
"epoch": 0.5104734093334082,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004982027881244076,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.17324459552764893,
|
|
"num_tokens": 10146987.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.667150068283081,
|
|
"epoch": 0.5110349862413658,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981977201932549,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.19072613567113877,
|
|
"num_tokens": 10157823.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.636341714859009,
|
|
"epoch": 0.5115965631493233,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981926451554001,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.17967162728309632,
|
|
"num_tokens": 10169305.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.764519214630127,
|
|
"epoch": 0.5121581400572809,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004981875630110048,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.16771657764911652,
|
|
"num_tokens": 10180346.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.689380121231079,
|
|
"epoch": 0.5127197169652384,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004981824737602311,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.18165241479873656,
|
|
"num_tokens": 10190870.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.712971448898315,
|
|
"epoch": 0.513281293873196,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004981773774032409,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.16853156983852385,
|
|
"num_tokens": 10202408.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.589897871017456,
|
|
"epoch": 0.5138428707811534,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981722739401962,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.18729079365730286,
|
|
"num_tokens": 10213367.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.711232328414917,
|
|
"epoch": 0.514404447689111,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049816716337126,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.17564274221658707,
|
|
"num_tokens": 10223865.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.5356724739074705,
|
|
"epoch": 0.5149660245970685,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004981620456965946,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.18685455322265626,
|
|
"num_tokens": 10235268.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.655205965042114,
|
|
"epoch": 0.5155276015050261,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004981569209163633,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.18182720988988876,
|
|
"num_tokens": 10247700.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.695512008666992,
|
|
"epoch": 0.5160891784129836,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981517890307288,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.17631923407316208,
|
|
"num_tokens": 10258553.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.7099940299987795,
|
|
"epoch": 0.5166507553209412,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498146650039855,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.1825244188308716,
|
|
"num_tokens": 10268496.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.700167798995972,
|
|
"epoch": 0.5172123322288987,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981415039439054,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.17473105043172837,
|
|
"num_tokens": 10278803.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.635028409957886,
|
|
"epoch": 0.5177739091368563,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004981363507430436,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.1852840378880501,
|
|
"num_tokens": 10289805.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.645072078704834,
|
|
"epoch": 0.5183354860448138,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004981311904374339,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.18048583418130876,
|
|
"num_tokens": 10300295.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.769038343429566,
|
|
"epoch": 0.5188970629527714,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981260230272405,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.17948028892278672,
|
|
"num_tokens": 10312175.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.620206356048584,
|
|
"epoch": 0.5194586398607289,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981208485126281,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.17945575714111328,
|
|
"num_tokens": 10322888.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.640418910980225,
|
|
"epoch": 0.5200202167686865,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981156668937613,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.18714178800582887,
|
|
"num_tokens": 10333305.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.674282264709473,
|
|
"epoch": 0.520581793676644,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981104781708051,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.1853673964738846,
|
|
"num_tokens": 10344190.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.709659719467163,
|
|
"epoch": 0.5211433705846016,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981052823439247,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.17883440405130385,
|
|
"num_tokens": 10356271.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.784398460388184,
|
|
"epoch": 0.5217049474925591,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981000794132858,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.16792431920766832,
|
|
"num_tokens": 10368756.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.740176439285278,
|
|
"epoch": 0.5222665244005167,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980948693790536,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.18277455866336823,
|
|
"num_tokens": 10380029.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.637017488479614,
|
|
"epoch": 0.5228281013084742,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980896522413943,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.18233832120895385,
|
|
"num_tokens": 10390358.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.6377355575561525,
|
|
"epoch": 0.5233896782164318,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980844280004739,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.1847611367702484,
|
|
"num_tokens": 10401331.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.721519184112549,
|
|
"epoch": 0.5239512551243893,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980791966564589,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.18159477710723876,
|
|
"num_tokens": 10412755.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.598416709899903,
|
|
"epoch": 0.5245128320323468,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980739582095158,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.18742981553077698,
|
|
"num_tokens": 10422698.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.68941478729248,
|
|
"epoch": 0.5250744089403043,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004980687126598111,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.1778789535164833,
|
|
"num_tokens": 10434467.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.638925457000733,
|
|
"epoch": 0.5256359858482619,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980634600075123,
|
|
"loss": 5.5254,
|
|
"mean_token_accuracy": 0.18562276512384415,
|
|
"num_tokens": 10446007.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.721362066268921,
|
|
"epoch": 0.5261975627562194,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004980582002527863,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.18258942365646363,
|
|
"num_tokens": 10457538.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.710667657852173,
|
|
"epoch": 0.526759139664177,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004980529333958008,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.18270418643951417,
|
|
"num_tokens": 10468389.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.5980792999267575,
|
|
"epoch": 0.5273207165721345,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004980476594367233,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.17941105663776397,
|
|
"num_tokens": 10479032.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.661909770965576,
|
|
"epoch": 0.5278822934800921,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004980423783757219,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.1848536789417267,
|
|
"num_tokens": 10490505.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.68026442527771,
|
|
"epoch": 0.5284438703880496,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980370902129646,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.18427593857049943,
|
|
"num_tokens": 10501382.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.720756959915161,
|
|
"epoch": 0.5290054472960072,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00049803179494862,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.17987337410449983,
|
|
"num_tokens": 10512727.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.598056793212891,
|
|
"epoch": 0.5295670242039647,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980264925828563,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.18574607521295547,
|
|
"num_tokens": 10523383.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.697275114059448,
|
|
"epoch": 0.5301286011119223,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980211831158427,
|
|
"loss": 5.4951,
|
|
"mean_token_accuracy": 0.18537654727697372,
|
|
"num_tokens": 10534416.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.641849327087402,
|
|
"epoch": 0.5306901780198798,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980158665477481,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.1823153167963028,
|
|
"num_tokens": 10544291.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.630571889877319,
|
|
"epoch": 0.5312517549278374,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004980105428787419,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.18484325855970382,
|
|
"num_tokens": 10555291.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.667485523223877,
|
|
"epoch": 0.5318133318357949,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980052121089934,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.18038788735866546,
|
|
"num_tokens": 10565812.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.608593130111695,
|
|
"epoch": 0.5323749087437525,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979998742386725,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.18620285838842393,
|
|
"num_tokens": 10577351.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.701065111160278,
|
|
"epoch": 0.53293648565171,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004979945292679492,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.18092228472232819,
|
|
"num_tokens": 10589236.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.547406005859375,
|
|
"epoch": 0.5334980625596676,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979891771969935,
|
|
"loss": 5.5036,
|
|
"mean_token_accuracy": 0.18468379378318786,
|
|
"num_tokens": 10599926.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.729918670654297,
|
|
"epoch": 0.5340596394676251,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497983818025976,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.17615175247192383,
|
|
"num_tokens": 10611495.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.6825721740722654,
|
|
"epoch": 0.5346212163755827,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004979784517550671,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.17843578457832338,
|
|
"num_tokens": 10622455.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.654116153717041,
|
|
"epoch": 0.5351827932835401,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004979730783844379,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.18786576837301255,
|
|
"num_tokens": 10634255.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.6620872020721436,
|
|
"epoch": 0.5357443701914977,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004979676979142595,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.17800870686769485,
|
|
"num_tokens": 10644816.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.670299434661866,
|
|
"epoch": 0.5363059470994552,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497962310344703,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.17793684005737304,
|
|
"num_tokens": 10655449.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.650459432601929,
|
|
"epoch": 0.5368675240074128,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00049795691567594,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.17976024448871614,
|
|
"num_tokens": 10666343.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.660797166824341,
|
|
"epoch": 0.5374291009153703,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979515139081426,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.1788281485438347,
|
|
"num_tokens": 10678511.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.634575414657593,
|
|
"epoch": 0.5379906778233279,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004979461050414822,
|
|
"loss": 5.5465,
|
|
"mean_token_accuracy": 0.1841413825750351,
|
|
"num_tokens": 10690005.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.6316334247589115,
|
|
"epoch": 0.5385522547312854,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004979406890761315,
|
|
"loss": 5.5436,
|
|
"mean_token_accuracy": 0.17784028500318527,
|
|
"num_tokens": 10701062.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.700321769714355,
|
|
"epoch": 0.539113831639243,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004979352660122629,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.19008907526731492,
|
|
"num_tokens": 10711986.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.6882116317749025,
|
|
"epoch": 0.5396754085472005,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004979298358500488,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.17896559238433837,
|
|
"num_tokens": 10722509.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.675091981887817,
|
|
"epoch": 0.5402369854551581,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979243985896624,
|
|
"loss": 5.5132,
|
|
"mean_token_accuracy": 0.17817764729261398,
|
|
"num_tokens": 10733755.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.6327286720275875,
|
|
"epoch": 0.5407985623631156,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004979189542312765,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.18414564430713654,
|
|
"num_tokens": 10744356.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.635139894485474,
|
|
"epoch": 0.5413601392710732,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004979135027750649,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.1847996160387993,
|
|
"num_tokens": 10756474.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.630859756469727,
|
|
"epoch": 0.5419217161790307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979080442212007,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.18072069734334945,
|
|
"num_tokens": 10767551.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.728150081634522,
|
|
"epoch": 0.5424832930869883,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979025785698581,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.18025463372468947,
|
|
"num_tokens": 10778524.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.618912982940674,
|
|
"epoch": 0.5430448699949458,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004978971058212108,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.18504443317651748,
|
|
"num_tokens": 10789798.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.648323202133179,
|
|
"epoch": 0.5436064469029034,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004978916259754331,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.1826815724372864,
|
|
"num_tokens": 10800500.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.689579105377197,
|
|
"epoch": 0.5441680238108609,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004978861390326998,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.18740566074848175,
|
|
"num_tokens": 10812047.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.646303462982178,
|
|
"epoch": 0.5447296007188185,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004978806449931854,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.1772485762834549,
|
|
"num_tokens": 10823272.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.582003116607666,
|
|
"epoch": 0.545291177626776,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004978751438570647,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.18322279006242753,
|
|
"num_tokens": 10834485.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.588191843032837,
|
|
"epoch": 0.5458527545347336,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978696356245129,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.18219852596521377,
|
|
"num_tokens": 10843547.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.649803543090821,
|
|
"epoch": 0.546414331442691,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004978641202957057,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.17482994198799134,
|
|
"num_tokens": 10855890.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.748755216598511,
|
|
"epoch": 0.5469759083506486,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978585978708183,
|
|
"loss": 5.6386,
|
|
"mean_token_accuracy": 0.17877344340085982,
|
|
"num_tokens": 10868060.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.678722620010376,
|
|
"epoch": 0.5475374852586061,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004978530683500267,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.18176424205303193,
|
|
"num_tokens": 10879323.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.583324384689331,
|
|
"epoch": 0.5480990621665637,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004978475317335071,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.1911531627178192,
|
|
"num_tokens": 10890545.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.596029281616211,
|
|
"epoch": 0.5486606390745212,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004978419880214356,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.17998157292604447,
|
|
"num_tokens": 10900761.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.628369331359863,
|
|
"epoch": 0.5492222159824788,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004978364372139887,
|
|
"loss": 5.5132,
|
|
"mean_token_accuracy": 0.18170329928398132,
|
|
"num_tokens": 10911874.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.587182950973511,
|
|
"epoch": 0.5497837928904363,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004978308793113434,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.19111614525318146,
|
|
"num_tokens": 10922949.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.674463272094727,
|
|
"epoch": 0.5503453697983939,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004978253143136762,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.1710948556661606,
|
|
"num_tokens": 10935415.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.619164228439331,
|
|
"epoch": 0.5509069467063514,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004978197422211647,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.19049910753965377,
|
|
"num_tokens": 10946983.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.6017693996429445,
|
|
"epoch": 0.551468523614309,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004978141630339863,
|
|
"loss": 5.5254,
|
|
"mean_token_accuracy": 0.1777789682149887,
|
|
"num_tokens": 10957884.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.614745950698852,
|
|
"epoch": 0.5520301005222665,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004978085767523184,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.18767860978841783,
|
|
"num_tokens": 10968518.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.665773820877075,
|
|
"epoch": 0.5525916774302241,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000497802983376339,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.1804030328989029,
|
|
"num_tokens": 10979621.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.671715879440308,
|
|
"epoch": 0.5531532543381816,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977973829062263,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.18461436331272124,
|
|
"num_tokens": 10990158.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.607434844970703,
|
|
"epoch": 0.5537148312461392,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004977917753421585,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.17894083857536316,
|
|
"num_tokens": 11001732.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.750102519989014,
|
|
"epoch": 0.5542764081540967,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000497786160684314,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.17802729308605195,
|
|
"num_tokens": 11013483.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.734050512313843,
|
|
"epoch": 0.5548379850620543,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977805389328719,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.18021501302719117,
|
|
"num_tokens": 11025423.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.627556943893433,
|
|
"epoch": 0.5553995619700118,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497774910088011,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.18536694645881652,
|
|
"num_tokens": 11037041.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.605755138397217,
|
|
"epoch": 0.5559611388779694,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004977692741499106,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.18177319914102555,
|
|
"num_tokens": 11049206.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.653660297393799,
|
|
"epoch": 0.5565227157859269,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049776363111875,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.17995063811540604,
|
|
"num_tokens": 11060407.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.6308917045593265,
|
|
"epoch": 0.5570842926938844,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004977579809947091,
|
|
"loss": 5.4689,
|
|
"mean_token_accuracy": 0.18350168615579604,
|
|
"num_tokens": 11071269.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.617505025863648,
|
|
"epoch": 0.5576458696018419,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977523237779676,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.18768567889928817,
|
|
"num_tokens": 11082078.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.815405941009521,
|
|
"epoch": 0.5582074465097995,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977466594687057,
|
|
"loss": 5.7032,
|
|
"mean_token_accuracy": 0.17298679202795028,
|
|
"num_tokens": 11094596.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.690718746185302,
|
|
"epoch": 0.558769023417757,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004977409880671039,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.17936454564332963,
|
|
"num_tokens": 11107705.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.621313762664795,
|
|
"epoch": 0.5593306003257146,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977353095733427,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.18743560761213302,
|
|
"num_tokens": 11118152.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.587288951873779,
|
|
"epoch": 0.5598921772336721,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977296239876026,
|
|
"loss": 5.5173,
|
|
"mean_token_accuracy": 0.1785737544298172,
|
|
"num_tokens": 11129261.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.702455472946167,
|
|
"epoch": 0.5604537541416297,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000497723931310065,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.17097220718860626,
|
|
"num_tokens": 11142227.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.73953070640564,
|
|
"epoch": 0.5610153310495872,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977182315409111,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.17793572545051575,
|
|
"num_tokens": 11154277.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.616262149810791,
|
|
"epoch": 0.5615769079575448,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977125246803224,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.17608992308378218,
|
|
"num_tokens": 11164902.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.522751188278198,
|
|
"epoch": 0.5621384848655023,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977068107284803,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.1823316514492035,
|
|
"num_tokens": 11176010.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.63159327507019,
|
|
"epoch": 0.5627000617734599,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004977010896855672,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.18588504046201706,
|
|
"num_tokens": 11187773.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.633604049682617,
|
|
"epoch": 0.5632616386814174,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004976953615517649,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.1863183557987213,
|
|
"num_tokens": 11198420.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.519148445129394,
|
|
"epoch": 0.563823215589375,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000497689626327256,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.19153528958559035,
|
|
"num_tokens": 11208553.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.659325647354126,
|
|
"epoch": 0.5643847924973325,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497683884012223,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.18360450565814973,
|
|
"num_tokens": 11219737.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.576310396194458,
|
|
"epoch": 0.5649463694052901,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004976781346068487,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.18213171809911727,
|
|
"num_tokens": 11230997.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.671642637252807,
|
|
"epoch": 0.5655079463132476,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004976723781113163,
|
|
"loss": 5.5002,
|
|
"mean_token_accuracy": 0.18653760701417924,
|
|
"num_tokens": 11242338.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.690944623947144,
|
|
"epoch": 0.5660695232212052,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976666145258089,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.18355587869882584,
|
|
"num_tokens": 11252671.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.46414008140564,
|
|
"epoch": 0.5666311001291627,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004976608438505103,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.19436000436544418,
|
|
"num_tokens": 11262721.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.609651517868042,
|
|
"epoch": 0.5671926770371203,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004976550660856041,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.18309204429388046,
|
|
"num_tokens": 11274074.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.696449184417725,
|
|
"epoch": 0.5677542539450777,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000497649281231274,
|
|
"loss": 5.4903,
|
|
"mean_token_accuracy": 0.18642679899930953,
|
|
"num_tokens": 11286051.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.733097124099731,
|
|
"epoch": 0.5683158308530353,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004976434892877046,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.1781116783618927,
|
|
"num_tokens": 11298841.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.651134347915649,
|
|
"epoch": 0.5688774077609928,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976376902550802,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.1825672760605812,
|
|
"num_tokens": 11309898.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.692415761947632,
|
|
"epoch": 0.5694389846689504,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004976318841335854,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.18130584359169005,
|
|
"num_tokens": 11322163.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.686931324005127,
|
|
"epoch": 0.5700005615769079,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004976260709234049,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.1760215789079666,
|
|
"num_tokens": 11333405.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.743791007995606,
|
|
"epoch": 0.5705621384848655,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000497620250624724,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.18008355051279068,
|
|
"num_tokens": 11345037.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.672800350189209,
|
|
"epoch": 0.571123715392823,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497614423237728,
|
|
"loss": 5.5477,
|
|
"mean_token_accuracy": 0.18193664401769638,
|
|
"num_tokens": 11356403.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.606851625442505,
|
|
"epoch": 0.5716852923007806,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004976085887626026,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.18535795211791992,
|
|
"num_tokens": 11367913.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.639658451080322,
|
|
"epoch": 0.5722468692087381,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976027471995331,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.1910523518919945,
|
|
"num_tokens": 11378519.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.621802282333374,
|
|
"epoch": 0.5728084461166957,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497596898548706,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.18591468036174774,
|
|
"num_tokens": 11389530.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.502487373352051,
|
|
"epoch": 0.5733700230246532,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975910428103072,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.18977337181568146,
|
|
"num_tokens": 11400468.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.479951047897339,
|
|
"epoch": 0.5739315999326108,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004975851799845233,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.19062579274177552,
|
|
"num_tokens": 11411242.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.702769565582275,
|
|
"epoch": 0.5744931768405683,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497579310071541,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.1868542194366455,
|
|
"num_tokens": 11420909.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.571871185302735,
|
|
"epoch": 0.5750547537485259,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004975734330715471,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.18438702523708345,
|
|
"num_tokens": 11431791.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.716051483154297,
|
|
"epoch": 0.5756163306564834,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004975675489847287,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.17440195232629777,
|
|
"num_tokens": 11443056.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.661809062957763,
|
|
"epoch": 0.576177907564441,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975616578112734,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.1826162040233612,
|
|
"num_tokens": 11453413.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.708344602584839,
|
|
"epoch": 0.5767394844723985,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004975557595513684,
|
|
"loss": 5.7722,
|
|
"mean_token_accuracy": 0.17084766179323196,
|
|
"num_tokens": 11465457.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.775514268875122,
|
|
"epoch": 0.5773010613803561,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004975498542052018,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.188805428147316,
|
|
"num_tokens": 11476899.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.633147573471069,
|
|
"epoch": 0.5778626382883136,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004975439417729615,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.18609003275632857,
|
|
"num_tokens": 11488652.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.707149934768677,
|
|
"epoch": 0.5784242151962711,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004975380222548358,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.1800197258591652,
|
|
"num_tokens": 11499540.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.703618669509888,
|
|
"epoch": 0.5789857921042286,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004975320956510131,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.18386209309101104,
|
|
"num_tokens": 11511156.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.713125944137573,
|
|
"epoch": 0.5795473690121862,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004975261619616822,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.1725510522723198,
|
|
"num_tokens": 11523489.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.670358800888062,
|
|
"epoch": 0.5801089459201437,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004975202211870321,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.1820479080080986,
|
|
"num_tokens": 11534497.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.691202974319458,
|
|
"epoch": 0.5806705228281013,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004975142733272518,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.17964523583650588,
|
|
"num_tokens": 11545585.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.550412511825561,
|
|
"epoch": 0.5812320997360588,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004975083183825306,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.18183948546648027,
|
|
"num_tokens": 11556278.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.600111246109009,
|
|
"epoch": 0.5817936766440164,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004975023563530584,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.18885961621999742,
|
|
"num_tokens": 11568358.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.552606725692749,
|
|
"epoch": 0.5823552535519739,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004974963872390249,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.18873102962970734,
|
|
"num_tokens": 11579777.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.630881118774414,
|
|
"epoch": 0.5829168304599315,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049749041104062,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.18298720717430114,
|
|
"num_tokens": 11591479.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.63812575340271,
|
|
"epoch": 0.583478407367889,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004974844277580343,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.1819496273994446,
|
|
"num_tokens": 11601452.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.516455507278442,
|
|
"epoch": 0.5840399842758466,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004974784373914579,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.1931149885058403,
|
|
"num_tokens": 11611661.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.576290798187256,
|
|
"epoch": 0.5846015611838041,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974724399410818,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.18096472471952438,
|
|
"num_tokens": 11622940.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.671401166915894,
|
|
"epoch": 0.5851631380917617,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974664354070971,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.18270148187875748,
|
|
"num_tokens": 11634290.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.720749235153198,
|
|
"epoch": 0.5857247149997192,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974604237896947,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.17576154172420502,
|
|
"num_tokens": 11645812.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.6433494091033936,
|
|
"epoch": 0.5862862919076768,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004974544050890662,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.18006327599287034,
|
|
"num_tokens": 11657520.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.62378945350647,
|
|
"epoch": 0.5868478688156343,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497448379305403,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.19116243720054626,
|
|
"num_tokens": 11666887.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.733535385131836,
|
|
"epoch": 0.5874094457235919,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974423464388973,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.1788318857550621,
|
|
"num_tokens": 11677337.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.676457786560059,
|
|
"epoch": 0.5879710226315494,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000497436306489741,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.18293983042240142,
|
|
"num_tokens": 11688203.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.618943119049073,
|
|
"epoch": 0.588532599539507,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974302594581264,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.18111439645290375,
|
|
"num_tokens": 11699727.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.68273344039917,
|
|
"epoch": 0.5890941764474645,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004974242053442461,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.18173750787973403,
|
|
"num_tokens": 11710956.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.675672197341919,
|
|
"epoch": 0.589655753355422,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974181441482927,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.19248765856027603,
|
|
"num_tokens": 11721681.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.62633204460144,
|
|
"epoch": 0.5902173302633795,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004974120758704595,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.176412433385849,
|
|
"num_tokens": 11731679.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.692461776733398,
|
|
"epoch": 0.5907789071713371,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004974060005109394,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.17527567744255065,
|
|
"num_tokens": 11743953.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.576653957366943,
|
|
"epoch": 0.5913404840792946,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000497399918069926,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.19086686819791793,
|
|
"num_tokens": 11754091.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.59900393486023,
|
|
"epoch": 0.5919020609872522,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973938285476131,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.1879284217953682,
|
|
"num_tokens": 11764771.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.709254598617553,
|
|
"epoch": 0.5924636378952097,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973877319441943,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.18260716646909714,
|
|
"num_tokens": 11776287.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.686443948745728,
|
|
"epoch": 0.5930252148031673,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973816282598639,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.17622997760772705,
|
|
"num_tokens": 11787142.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.603269577026367,
|
|
"epoch": 0.5935867917111248,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973755174948162,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.1779883787035942,
|
|
"num_tokens": 11798966.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.68326964378357,
|
|
"epoch": 0.5941483686190824,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973693996492458,
|
|
"loss": 5.5915,
|
|
"mean_token_accuracy": 0.178844054043293,
|
|
"num_tokens": 11810529.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.588279819488525,
|
|
"epoch": 0.5947099455270399,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004973632747233475,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.18790995925664902,
|
|
"num_tokens": 11821965.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.693677520751953,
|
|
"epoch": 0.5952715224349975,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004973571427173163,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.17656130492687225,
|
|
"num_tokens": 11833936.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.677950048446656,
|
|
"epoch": 0.595833099342955,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973510036313473,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.18559293895959855,
|
|
"num_tokens": 11845245.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.613375997543335,
|
|
"epoch": 0.5963946762509126,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004973448574656362,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.18298945873975753,
|
|
"num_tokens": 11856010.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.702826690673828,
|
|
"epoch": 0.5969562531588701,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973387042203786,
|
|
"loss": 5.6289,
|
|
"mean_token_accuracy": 0.17898809537291527,
|
|
"num_tokens": 11866194.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.6705591678619385,
|
|
"epoch": 0.5975178300668277,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973325438957704,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.183961620926857,
|
|
"num_tokens": 11877224.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.600674772262574,
|
|
"epoch": 0.5980794069747852,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973263764920079,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.18547880053520202,
|
|
"num_tokens": 11887410.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.559569787979126,
|
|
"epoch": 0.5986409838827428,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004973202020092871,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.18253688961267472,
|
|
"num_tokens": 11898816.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.672144365310669,
|
|
"epoch": 0.5992025607907003,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000497314020447805,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.18159493058919907,
|
|
"num_tokens": 11909220.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.687933444976807,
|
|
"epoch": 0.5997641376986579,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973078318077583,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.1843733549118042,
|
|
"num_tokens": 11919584.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.6041124820709225,
|
|
"epoch": 0.6003257146066153,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000497301636089344,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.17946779429912568,
|
|
"num_tokens": 11929298.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.5917517185211185,
|
|
"epoch": 0.6008872915145729,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004972954332927592,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.18231043517589568,
|
|
"num_tokens": 11939809.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.623062419891357,
|
|
"epoch": 0.6014488684225304,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004972892234182018,
|
|
"loss": 5.3786,
|
|
"mean_token_accuracy": 0.19353800863027573,
|
|
"num_tokens": 11950292.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.539207696914673,
|
|
"epoch": 0.602010445330488,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004972830064658692,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.18720546662807463,
|
|
"num_tokens": 11961774.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.640303707122802,
|
|
"epoch": 0.6025720222384455,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972767824359596,
|
|
"loss": 5.5124,
|
|
"mean_token_accuracy": 0.18192073255777358,
|
|
"num_tokens": 11973351.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.59477915763855,
|
|
"epoch": 0.6031335991464031,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004972705513286709,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.1921800345182419,
|
|
"num_tokens": 11984472.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.605710697174072,
|
|
"epoch": 0.6036951760543606,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004972643131442017,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.18431636095046997,
|
|
"num_tokens": 11994271.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.728161191940307,
|
|
"epoch": 0.6042567529623182,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004972580678827506,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.17849808931350708,
|
|
"num_tokens": 12007647.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.722807598114014,
|
|
"epoch": 0.6048183298702757,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004972518155445163,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.1791459545493126,
|
|
"num_tokens": 12020331.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.620580244064331,
|
|
"epoch": 0.6053799067782333,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004972455561296982,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.1745545595884323,
|
|
"num_tokens": 12031616.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.736928081512451,
|
|
"epoch": 0.6059414836861908,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972392896384952,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.1782309740781784,
|
|
"num_tokens": 12044107.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.592247390747071,
|
|
"epoch": 0.6065030605941484,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004972330160711071,
|
|
"loss": 5.4828,
|
|
"mean_token_accuracy": 0.1844660222530365,
|
|
"num_tokens": 12055747.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.664733409881592,
|
|
"epoch": 0.6070646375021059,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004972267354277336,
|
|
"loss": 5.4886,
|
|
"mean_token_accuracy": 0.1849084123969078,
|
|
"num_tokens": 12067849.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.600799942016602,
|
|
"epoch": 0.6076262144100635,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004972204477085746,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.1845787927508354,
|
|
"num_tokens": 12078534.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.529486417770386,
|
|
"epoch": 0.608187791318021,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972141529138303,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.1845926120877266,
|
|
"num_tokens": 12089534.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.590928316116333,
|
|
"epoch": 0.6087493682259786,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004972078510437013,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.20086879283189774,
|
|
"num_tokens": 12099513.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.642244291305542,
|
|
"epoch": 0.6093109451339361,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972015420983882,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.19047682583332062,
|
|
"num_tokens": 12110106.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.5803914070129395,
|
|
"epoch": 0.6098725220418937,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004971952260780915,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.18757349848747254,
|
|
"num_tokens": 12121302.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.624030303955078,
|
|
"epoch": 0.6104340989498512,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000497188902983013,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.18314958214759827,
|
|
"num_tokens": 12132879.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.5627439498901365,
|
|
"epoch": 0.6109956758578087,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004971825728133535,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.19471229165792464,
|
|
"num_tokens": 12143597.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.64037766456604,
|
|
"epoch": 0.6115572527657662,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004971762355693146,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.18607547134160995,
|
|
"num_tokens": 12156036.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.650599336624145,
|
|
"epoch": 0.6121188296737238,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004971698912510983,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.18842943608760834,
|
|
"num_tokens": 12167305.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.633962774276734,
|
|
"epoch": 0.6126804065816813,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004971635398589066,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.1892700731754303,
|
|
"num_tokens": 12176772.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.573196840286255,
|
|
"epoch": 0.6132419834896389,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004971571813929415,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.18717082887887954,
|
|
"num_tokens": 12187852.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.62188491821289,
|
|
"epoch": 0.6138035603975964,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004971508158534056,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.18409128189086915,
|
|
"num_tokens": 12198574.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.573410844802856,
|
|
"epoch": 0.614365137305554,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004971444432405015,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.19582518339157104,
|
|
"num_tokens": 12209463.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.679037284851074,
|
|
"epoch": 0.6149267142135115,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004971380635544323,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.18178143948316575,
|
|
"num_tokens": 12220993.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.634619903564453,
|
|
"epoch": 0.6154882911214691,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004971316767954009,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.18939948081970215,
|
|
"num_tokens": 12232648.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.610376310348511,
|
|
"epoch": 0.6160498680294266,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971252829636108,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.1851001963019371,
|
|
"num_tokens": 12243931.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.682241296768188,
|
|
"epoch": 0.6166114449373842,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971188820592656,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.18305664509534836,
|
|
"num_tokens": 12254821.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.573378801345825,
|
|
"epoch": 0.6171730218453417,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000497112474082569,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.18516962677240373,
|
|
"num_tokens": 12265440.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.6328226089477536,
|
|
"epoch": 0.6177345987532993,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000497106059033725,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.18394222855567932,
|
|
"num_tokens": 12276636.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.659553098678589,
|
|
"epoch": 0.6182961756612568,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004970996369129381,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.19257683157920838,
|
|
"num_tokens": 12287404.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.635024118423462,
|
|
"epoch": 0.6188577525692144,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004970932077204125,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.17888496816158295,
|
|
"num_tokens": 12299283.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.638094568252564,
|
|
"epoch": 0.6194193294771719,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000497086771456353,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.17845414727926254,
|
|
"num_tokens": 12310281.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.66259069442749,
|
|
"epoch": 0.6199809063851295,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004970803281209646,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.18785741925239563,
|
|
"num_tokens": 12320839.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.587321138381958,
|
|
"epoch": 0.620542483293087,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004970738777144524,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.18615006059408187,
|
|
"num_tokens": 12332845.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.5207594871521,
|
|
"epoch": 0.6211040602010446,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970674202370218,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.19352568089962005,
|
|
"num_tokens": 12343327.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.627544593811035,
|
|
"epoch": 0.621665637109002,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004970609556888785,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.18908988684415817,
|
|
"num_tokens": 12353224.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.607558488845825,
|
|
"epoch": 0.6222272140169596,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004970544840702282,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.1833338037133217,
|
|
"num_tokens": 12363981.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.488410568237304,
|
|
"epoch": 0.6227887909249171,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004970480053812771,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.19403667151927947,
|
|
"num_tokens": 12374769.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.7113910675048825,
|
|
"epoch": 0.6233503678328747,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004970415196222312,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.180233171582222,
|
|
"num_tokens": 12387247.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.701795291900635,
|
|
"epoch": 0.6239119447408322,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004970350267932973,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.1879402741789818,
|
|
"num_tokens": 12398347.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.4646240234375,
|
|
"epoch": 0.6244735216487898,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000497028526894682,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.1876811385154724,
|
|
"num_tokens": 12409763.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.641856956481933,
|
|
"epoch": 0.6250350985567473,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004970220199265923,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.18853815346956254,
|
|
"num_tokens": 12420658.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.721192169189453,
|
|
"epoch": 0.6255966754647049,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004970155058892354,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.1778463289141655,
|
|
"num_tokens": 12433959.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.627422285079956,
|
|
"epoch": 0.6261582523726624,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004970089847828187,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.18300610184669494,
|
|
"num_tokens": 12444756.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.589797878265381,
|
|
"epoch": 0.62671982928062,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970024566075497,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.19408472776412963,
|
|
"num_tokens": 12456114.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.660622072219849,
|
|
"epoch": 0.6272814061885775,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969959213636365,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.18281706124544145,
|
|
"num_tokens": 12466927.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.669159364700318,
|
|
"epoch": 0.6278429830965351,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004969893790512871,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.17609500288963317,
|
|
"num_tokens": 12477834.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.61507248878479,
|
|
"epoch": 0.6284045600044926,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004969828296707097,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.18530827164649963,
|
|
"num_tokens": 12488219.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.693576622009277,
|
|
"epoch": 0.6289661369124502,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004969762732221129,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.18815126568078994,
|
|
"num_tokens": 12498947.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.5714047908782955,
|
|
"epoch": 0.6295277138204077,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004969697097057054,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.1879395291209221,
|
|
"num_tokens": 12510142.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.690112638473511,
|
|
"epoch": 0.6300892907283653,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969631391216964,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.1827300801873207,
|
|
"num_tokens": 12521350.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.430221509933472,
|
|
"epoch": 0.6306508676363228,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969565614702948,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.19246957451105118,
|
|
"num_tokens": 12532579.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.643993520736695,
|
|
"epoch": 0.6312124445442804,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004969499767517104,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.18859467506408692,
|
|
"num_tokens": 12542885.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.758895301818848,
|
|
"epoch": 0.6317740214522379,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004969433849661525,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.17625662684440613,
|
|
"num_tokens": 12554881.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.62832989692688,
|
|
"epoch": 0.6323355983601955,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004969367861138313,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.18294334560632705,
|
|
"num_tokens": 12564626.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.654073858261109,
|
|
"epoch": 0.6328971752681529,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004969301801949565,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.1927139639854431,
|
|
"num_tokens": 12576180.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.586127042770386,
|
|
"epoch": 0.6334587521761105,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000496923567209739,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.18462976068258286,
|
|
"num_tokens": 12587487.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.708962059020996,
|
|
"epoch": 0.634020329084068,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004969169471583889,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.1774803325533867,
|
|
"num_tokens": 12598268.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.689787292480469,
|
|
"epoch": 0.6345819059920256,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004969103200411171,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.18399666398763656,
|
|
"num_tokens": 12609287.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.618821048736573,
|
|
"epoch": 0.6351434828999831,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004969036858581346,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.18731399178504943,
|
|
"num_tokens": 12620317.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.618491840362549,
|
|
"epoch": 0.6357050598079407,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004968970446096527,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.18664504289627076,
|
|
"num_tokens": 12631420.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.610232734680176,
|
|
"epoch": 0.6362666367158982,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000496890396295883,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.1915132462978363,
|
|
"num_tokens": 12641319.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.703640270233154,
|
|
"epoch": 0.6368282136238558,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004968837409170368,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.17883432954549788,
|
|
"num_tokens": 12651662.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.692250299453735,
|
|
"epoch": 0.6373897905318133,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004968770784733263,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.18254605084657669,
|
|
"num_tokens": 12663488.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.578442668914795,
|
|
"epoch": 0.6379513674397709,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004968704089649636,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.18580681681632996,
|
|
"num_tokens": 12675848.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.605468988418579,
|
|
"epoch": 0.6385129443477284,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004968637323921611,
|
|
"loss": 5.4478,
|
|
"mean_token_accuracy": 0.18657159060239792,
|
|
"num_tokens": 12686541.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.5702964782714846,
|
|
"epoch": 0.639074521255686,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004968570487551312,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.18254789412021638,
|
|
"num_tokens": 12698001.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.638297176361084,
|
|
"epoch": 0.6396360981636435,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004968503580540869,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.1814456731081009,
|
|
"num_tokens": 12709069.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.669518947601318,
|
|
"epoch": 0.6401976750716011,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004968436602892411,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.18066763281822204,
|
|
"num_tokens": 12719916.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.654325342178344,
|
|
"epoch": 0.6407592519795586,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004968369554608071,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.175307597219944,
|
|
"num_tokens": 12732079.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.716987562179566,
|
|
"epoch": 0.6413208288875162,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004968302435689985,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.1812366619706154,
|
|
"num_tokens": 12742708.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.721190881729126,
|
|
"epoch": 0.6418824057954737,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968235246140288,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.1829363912343979,
|
|
"num_tokens": 12753952.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.583826637268066,
|
|
"epoch": 0.6424439827034313,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004968167985961121,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.18806836605072022,
|
|
"num_tokens": 12765226.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.558200120925903,
|
|
"epoch": 0.6430055596113888,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004968100655154625,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.19156863093376159,
|
|
"num_tokens": 12776455.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.5882182121276855,
|
|
"epoch": 0.6435671365193463,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968033253722943,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.1893790602684021,
|
|
"num_tokens": 12787054.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.576923036575318,
|
|
"epoch": 0.6441287134273038,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967965781668223,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.185595566034317,
|
|
"num_tokens": 12798223.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.699933433532715,
|
|
"epoch": 0.6446902903352614,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004967898238992613,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.18635158687829972,
|
|
"num_tokens": 12809388.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.6112250804901125,
|
|
"epoch": 0.6452518672432189,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004967830625698262,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.19438131153583527,
|
|
"num_tokens": 12820116.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.559130525588989,
|
|
"epoch": 0.6458134441511765,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004967762941787323,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1912437915802002,
|
|
"num_tokens": 12831590.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.624443244934082,
|
|
"epoch": 0.646375021059134,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004967695187261952,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.1817338526248932,
|
|
"num_tokens": 12843510.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.65950026512146,
|
|
"epoch": 0.6469365979670916,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004967627362124306,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.1846739500761032,
|
|
"num_tokens": 12854907.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.6010960102081295,
|
|
"epoch": 0.6474981748750491,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004967559466376546,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.18443407416343688,
|
|
"num_tokens": 12865753.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.5662477016448975,
|
|
"epoch": 0.6480597517830067,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004967491500020831,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.18745883405208588,
|
|
"num_tokens": 12877116.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.483261585235596,
|
|
"epoch": 0.6486213286909642,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967423463059328,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.18801161795854568,
|
|
"num_tokens": 12887685.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.60209641456604,
|
|
"epoch": 0.6491829055989218,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967355355494201,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.18596958220005036,
|
|
"num_tokens": 12898519.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.616291332244873,
|
|
"epoch": 0.6497444825068793,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496728717732762,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.1925164818763733,
|
|
"num_tokens": 12908400.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.511848735809326,
|
|
"epoch": 0.6503060594148369,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004967218928561755,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.18848345875740052,
|
|
"num_tokens": 12919159.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.548889398574829,
|
|
"epoch": 0.6508676363227944,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004967150609198779,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.1906261995434761,
|
|
"num_tokens": 12929838.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.617793035507202,
|
|
"epoch": 0.651429213230752,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004967082219240869,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.18419611006975173,
|
|
"num_tokens": 12939976.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.644313526153565,
|
|
"epoch": 0.6519907901387095,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967013758690199,
|
|
"loss": 5.4784,
|
|
"mean_token_accuracy": 0.18786637037992476,
|
|
"num_tokens": 12950493.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.536976289749146,
|
|
"epoch": 0.6525523670466671,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966945227548953,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.18538996428251267,
|
|
"num_tokens": 12961267.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.556222343444825,
|
|
"epoch": 0.6531139439546246,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004966876625819309,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.18240580409765245,
|
|
"num_tokens": 12972720.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.702814435958862,
|
|
"epoch": 0.6536755208625822,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004966807953503456,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.18283770978450775,
|
|
"num_tokens": 12984025.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.579570293426514,
|
|
"epoch": 0.6542370977705396,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004966739210603578,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.19309327453374864,
|
|
"num_tokens": 12994422.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.666520357131958,
|
|
"epoch": 0.6547986746784972,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004966670397121862,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.1770310640335083,
|
|
"num_tokens": 13005040.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.577492713928223,
|
|
"epoch": 0.6553602515864547,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004966601513060502,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.1884690821170807,
|
|
"num_tokens": 13015720.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.565152978897094,
|
|
"epoch": 0.6559218284944123,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000496653255842169,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.19025407135486602,
|
|
"num_tokens": 13026269.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.576424646377563,
|
|
"epoch": 0.6564834054023698,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004966463533207621,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.18273550420999526,
|
|
"num_tokens": 13037102.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.545480823516845,
|
|
"epoch": 0.6570449823103274,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004966394437420493,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.1912029430270195,
|
|
"num_tokens": 13047149.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.58607497215271,
|
|
"epoch": 0.6576065592182849,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004966325271062508,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.19068273156881332,
|
|
"num_tokens": 13058196.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.559271764755249,
|
|
"epoch": 0.6581681361262425,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966256034135866,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.18529026210308075,
|
|
"num_tokens": 13067897.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.6258544921875,
|
|
"epoch": 0.6587297130342,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004966186726642772,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.18940753489732742,
|
|
"num_tokens": 13079720.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.49136323928833,
|
|
"epoch": 0.6592912899421576,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004966117348585434,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.18412272036075591,
|
|
"num_tokens": 13090995.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.532344770431519,
|
|
"epoch": 0.6598528668501151,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004966047899966059,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.19188852608203888,
|
|
"num_tokens": 13101945.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.552236652374267,
|
|
"epoch": 0.6604144437580727,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000496597838078686,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.19202605485916138,
|
|
"num_tokens": 13112869.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.593890523910522,
|
|
"epoch": 0.6609760206660302,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496590879105005,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.1842578947544098,
|
|
"num_tokens": 13123242.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.7226128578186035,
|
|
"epoch": 0.6615375975739878,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965839130757845,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.1754072591662407,
|
|
"num_tokens": 13133981.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.603096580505371,
|
|
"epoch": 0.6620991744819453,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004965769399912462,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.1805721253156662,
|
|
"num_tokens": 13144696.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.657627439498901,
|
|
"epoch": 0.6626607513899029,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004965699598516122,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.1863015413284302,
|
|
"num_tokens": 13156674.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.632771635055542,
|
|
"epoch": 0.6632223282978604,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004965629726571047,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.18627859503030778,
|
|
"num_tokens": 13167757.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.641563749313354,
|
|
"epoch": 0.663783905205818,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965559784079463,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.1821975126862526,
|
|
"num_tokens": 13177701.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.644797849655151,
|
|
"epoch": 0.6643454821137755,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004965489771043596,
|
|
"loss": 5.502,
|
|
"mean_token_accuracy": 0.1802292972803116,
|
|
"num_tokens": 13189840.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.495687341690063,
|
|
"epoch": 0.664907059021733,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965419687465676,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.1952889233827591,
|
|
"num_tokens": 13200206.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.558804368972778,
|
|
"epoch": 0.6654686359296905,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004965349533347934,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.19014041423797606,
|
|
"num_tokens": 13211474.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.576401090621948,
|
|
"epoch": 0.6660302128376481,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965279308692602,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.19454576969146728,
|
|
"num_tokens": 13223337.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.687454319000244,
|
|
"epoch": 0.6665917897456056,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965209013501919,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.18555479645729064,
|
|
"num_tokens": 13234977.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.619910097122192,
|
|
"epoch": 0.6671533666535632,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004965138647778122,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.18499454557895662,
|
|
"num_tokens": 13245315.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.601090145111084,
|
|
"epoch": 0.6677149435615207,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000496506821152345,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.1875467360019684,
|
|
"num_tokens": 13255829.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.599292850494384,
|
|
"epoch": 0.6682765204694783,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964997704740147,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.18383944779634476,
|
|
"num_tokens": 13266964.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.650814199447632,
|
|
"epoch": 0.6688380973774358,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000496492712743046,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.18305606842041017,
|
|
"num_tokens": 13279416.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.614626789093018,
|
|
"epoch": 0.6693996742853934,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004964856479596632,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.18227898627519606,
|
|
"num_tokens": 13290633.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.603199243545532,
|
|
"epoch": 0.6699612511933509,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004964785761240915,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.1849165141582489,
|
|
"num_tokens": 13302236.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.599565935134888,
|
|
"epoch": 0.6705228281013085,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004964714972365562,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.19094326645135878,
|
|
"num_tokens": 13315356.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.468915939331055,
|
|
"epoch": 0.671084405009266,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004964644112972824,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.18817158639431,
|
|
"num_tokens": 13326037.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.582581949234009,
|
|
"epoch": 0.6716459819172236,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004964573183064959,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.18724313974380494,
|
|
"num_tokens": 13336278.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.680832004547119,
|
|
"epoch": 0.6722075588251811,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004964502182644225,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.18441837280988693,
|
|
"num_tokens": 13348147.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.571626901626587,
|
|
"epoch": 0.6727691357331387,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004964431111712883,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.1844561904668808,
|
|
"num_tokens": 13360181.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.688418912887573,
|
|
"epoch": 0.6733307126410962,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004964359970273195,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.18414345383644104,
|
|
"num_tokens": 13372258.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.609068918228149,
|
|
"epoch": 0.6738922895490538,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004964288758327426,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.17984251081943511,
|
|
"num_tokens": 13384332.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6738922895490538,
|
|
"eval_entropy": 5.340693081842737,
|
|
"eval_loss": 5.4638800621032715,
|
|
"eval_mean_token_accuracy": 0.19265254150796465,
|
|
"eval_num_tokens": 13384332.0,
|
|
"eval_runtime": 18.3276,
|
|
"eval_samples_per_second": 1692.151,
|
|
"eval_steps_per_second": 211.539,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.5566400527954105,
|
|
"epoch": 0.6744538664570113,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964217475877846,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.17669277787208557,
|
|
"num_tokens": 13396345.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.553837871551513,
|
|
"epoch": 0.6750154433649689,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496414612292672,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.1899270996451378,
|
|
"num_tokens": 13407325.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.606841278076172,
|
|
"epoch": 0.6755770202729264,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004964074699476325,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.19029297381639482,
|
|
"num_tokens": 13417476.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.489629602432251,
|
|
"epoch": 0.6761385971808839,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004964003205528933,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.18573580980300902,
|
|
"num_tokens": 13428792.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.598864126205444,
|
|
"epoch": 0.6767001740888414,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004963931641086819,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.18571581244468688,
|
|
"num_tokens": 13440043.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.673840951919556,
|
|
"epoch": 0.677261750996799,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004963860006152262,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.18955108970403672,
|
|
"num_tokens": 13451637.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.700462055206299,
|
|
"epoch": 0.6778233279047565,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004963788300727546,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.18781284987926483,
|
|
"num_tokens": 13463205.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.526752996444702,
|
|
"epoch": 0.6783849048127141,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004963716524814951,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.1858439788222313,
|
|
"num_tokens": 13474201.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.501279735565186,
|
|
"epoch": 0.6789464817206716,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004963644678416763,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.19022777527570725,
|
|
"num_tokens": 13485439.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.64227328300476,
|
|
"epoch": 0.6795080586286292,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000496357276153527,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.17756075263023377,
|
|
"num_tokens": 13497257.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.6266919612884525,
|
|
"epoch": 0.6800696355365867,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004963500774172763,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.19026937037706376,
|
|
"num_tokens": 13508689.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.552323532104492,
|
|
"epoch": 0.6806312124445443,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496342871633153,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.19614329040050507,
|
|
"num_tokens": 13519392.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.568040800094605,
|
|
"epoch": 0.6811927893525018,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963356588013871,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.18918990045785905,
|
|
"num_tokens": 13530503.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.604642534255982,
|
|
"epoch": 0.6817543662604594,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004963284389222078,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.18509118705987931,
|
|
"num_tokens": 13541668.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.539366006851196,
|
|
"epoch": 0.6823159431684169,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004963212119958453,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.19493595957756044,
|
|
"num_tokens": 13552692.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.542106962203979,
|
|
"epoch": 0.6828775200763745,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004963139780225295,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.18069274425506593,
|
|
"num_tokens": 13563813.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.557859468460083,
|
|
"epoch": 0.683439096984332,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004963067370024909,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.19231165200471878,
|
|
"num_tokens": 13573818.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.657029628753662,
|
|
"epoch": 0.6840006738922896,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962994889359598,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.1794425889849663,
|
|
"num_tokens": 13585416.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.550705862045288,
|
|
"epoch": 0.6845622508002471,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004962922338231673,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.18647874444723128,
|
|
"num_tokens": 13596645.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.602340507507324,
|
|
"epoch": 0.6851238277082047,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004962849716643441,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.18936236798763276,
|
|
"num_tokens": 13607206.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.65163254737854,
|
|
"epoch": 0.6856854046161622,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004962777024597216,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.17971844375133514,
|
|
"num_tokens": 13619418.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.504651784896851,
|
|
"epoch": 0.6862469815241198,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004962704262095314,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.1928666800260544,
|
|
"num_tokens": 13630098.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.544144630432129,
|
|
"epoch": 0.6868085584320772,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004962631429140048,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.19007588028907776,
|
|
"num_tokens": 13641401.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.664184331893921,
|
|
"epoch": 0.6873701353400348,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496255852573374,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.18356149792671203,
|
|
"num_tokens": 13653099.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.651355600357055,
|
|
"epoch": 0.6879317122479923,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004962485551878711,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.18133996427059174,
|
|
"num_tokens": 13665381.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.584286165237427,
|
|
"epoch": 0.6884932891559499,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004962412507577283,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.1873927444219589,
|
|
"num_tokens": 13676767.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.555082511901856,
|
|
"epoch": 0.6890548660639074,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004962339392831783,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.18619124293327333,
|
|
"num_tokens": 13688552.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.61389045715332,
|
|
"epoch": 0.689616442971865,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000496226620764454,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.18677978217601776,
|
|
"num_tokens": 13700160.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.5449512004852295,
|
|
"epoch": 0.6901780198798225,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000496219295201788,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.19177110642194747,
|
|
"num_tokens": 13710828.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.629893827438354,
|
|
"epoch": 0.6907395967877801,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004962119625954141,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.182158163189888,
|
|
"num_tokens": 13721912.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.645375108718872,
|
|
"epoch": 0.6913011736957376,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004962046229455653,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.17926932275295257,
|
|
"num_tokens": 13733662.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.5488136291503904,
|
|
"epoch": 0.6918627506036952,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004961972762524757,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.18828732371330262,
|
|
"num_tokens": 13743699.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.501907682418823,
|
|
"epoch": 0.6924243275116527,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000496189922516379,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.1921059250831604,
|
|
"num_tokens": 13754918.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.590662288665771,
|
|
"epoch": 0.6929859044196103,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004961825617375093,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.1934470385313034,
|
|
"num_tokens": 13764432.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.478909826278686,
|
|
"epoch": 0.6935474813275678,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004961751939161011,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.18627596646547318,
|
|
"num_tokens": 13777049.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.585360860824585,
|
|
"epoch": 0.6941090582355254,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000496167819052389,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.1878596603870392,
|
|
"num_tokens": 13788324.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.6655029296875,
|
|
"epoch": 0.6946706351434829,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961604371466077,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.18126523196697236,
|
|
"num_tokens": 13800443.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.700299835205078,
|
|
"epoch": 0.6952322120514405,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004961530481989923,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.18859920352697374,
|
|
"num_tokens": 13811982.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.553670215606689,
|
|
"epoch": 0.695793788959398,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961456522097782,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.19447244852781295,
|
|
"num_tokens": 13822005.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.508312320709228,
|
|
"epoch": 0.6963553658673556,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961382491792006,
|
|
"loss": 5.3653,
|
|
"mean_token_accuracy": 0.19046358168125152,
|
|
"num_tokens": 13831943.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.6671140670776365,
|
|
"epoch": 0.6969169427753131,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004961308391074953,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.18379076272249223,
|
|
"num_tokens": 13842517.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.5975034713745115,
|
|
"epoch": 0.6974785196832706,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961234219948986,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.1868859350681305,
|
|
"num_tokens": 13853636.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.586635303497315,
|
|
"epoch": 0.6980400965912281,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961159978416461,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.1883652150630951,
|
|
"num_tokens": 13864378.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.590226840972901,
|
|
"epoch": 0.6986016734991857,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004961085666479746,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.19075691550970078,
|
|
"num_tokens": 13874964.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.582704877853393,
|
|
"epoch": 0.6991632504071432,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961011284141206,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.1882073238492012,
|
|
"num_tokens": 13885852.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.557626247406006,
|
|
"epoch": 0.6997248273151008,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004960936831403209,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.1842197448015213,
|
|
"num_tokens": 13896101.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.545677042007446,
|
|
"epoch": 0.7002864042230583,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004960862308268126,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.19189974069595336,
|
|
"num_tokens": 13907129.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.607222080230713,
|
|
"epoch": 0.7008479811310159,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004960787714738329,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.19082145690917968,
|
|
"num_tokens": 13918662.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.638439750671386,
|
|
"epoch": 0.7014095580389734,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004960713050816194,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.1889887794852257,
|
|
"num_tokens": 13930717.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.499991416931152,
|
|
"epoch": 0.701971134946931,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004960638316504098,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.18582768738269806,
|
|
"num_tokens": 13941299.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.674982357025146,
|
|
"epoch": 0.7025327118548885,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960563511804421,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.18850799798965454,
|
|
"num_tokens": 13951807.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.5878418445587155,
|
|
"epoch": 0.7030942887628461,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004960488636719545,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.19256469309329988,
|
|
"num_tokens": 13962994.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.506461191177368,
|
|
"epoch": 0.7036558656708036,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004960413691251852,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.18385552018880844,
|
|
"num_tokens": 13973731.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.574936199188232,
|
|
"epoch": 0.7042174425787612,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004960338675403731,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.18210062384605408,
|
|
"num_tokens": 13983772.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.595711517333984,
|
|
"epoch": 0.7047790194867187,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004960263589177568,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.1921875461935997,
|
|
"num_tokens": 13994935.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.566084194183349,
|
|
"epoch": 0.7053405963946763,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004960188432575757,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.19339964240789415,
|
|
"num_tokens": 14006225.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.575302982330323,
|
|
"epoch": 0.7059021733026338,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960113205600688,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.1957176387310028,
|
|
"num_tokens": 14017693.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.58692193031311,
|
|
"epoch": 0.7064637502105914,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004960037908254757,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.18892760574817657,
|
|
"num_tokens": 14027264.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.598410367965698,
|
|
"epoch": 0.7070253271185489,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004959962540540361,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.1905042588710785,
|
|
"num_tokens": 14039422.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.600617790222168,
|
|
"epoch": 0.7075869040265065,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004959887102459903,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.18246983885765075,
|
|
"num_tokens": 14051619.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.487253332138062,
|
|
"epoch": 0.7081484809344639,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004959811594015781,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.18487099558115005,
|
|
"num_tokens": 14061752.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.582082223892212,
|
|
"epoch": 0.7087100578424215,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004959736015210401,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.19365375488996506,
|
|
"num_tokens": 14072931.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.6021493434906,
|
|
"epoch": 0.709271634750379,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004959660366046169,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.1958826705813408,
|
|
"num_tokens": 14084137.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.623853731155395,
|
|
"epoch": 0.7098332116583366,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004959584646525494,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.18280902206897737,
|
|
"num_tokens": 14096251.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.676043224334717,
|
|
"epoch": 0.7103947885662941,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004959508856650788,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.17153948694467544,
|
|
"num_tokens": 14107844.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.605105686187744,
|
|
"epoch": 0.7109563654742517,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004959432996424463,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.1912011057138443,
|
|
"num_tokens": 14118344.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.5873628616333,
|
|
"epoch": 0.7115179423822092,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004959357065848932,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.19141858518123628,
|
|
"num_tokens": 14128767.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.596859645843506,
|
|
"epoch": 0.7120795192901668,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004959281064926618,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.1780511736869812,
|
|
"num_tokens": 14141593.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.656588983535767,
|
|
"epoch": 0.7126410961981243,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959204993659936,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.18356235921382905,
|
|
"num_tokens": 14151488.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.610148000717163,
|
|
"epoch": 0.7132026731060819,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004959128852051311,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.18654818534851075,
|
|
"num_tokens": 14162399.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.5508141040802,
|
|
"epoch": 0.7137642500140394,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004959052640103167,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.17873288840055465,
|
|
"num_tokens": 14173528.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.603145980834961,
|
|
"epoch": 0.714325826921997,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000495897635781793,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.1897970512509346,
|
|
"num_tokens": 14184119.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.6302038669586185,
|
|
"epoch": 0.7148874038299545,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004958900005198029,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.1851705342531204,
|
|
"num_tokens": 14196225.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.5523652076721195,
|
|
"epoch": 0.7154489807379121,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004958823582245894,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.19252661764621734,
|
|
"num_tokens": 14207541.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.614546823501587,
|
|
"epoch": 0.7160105576458696,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004958747088963961,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.19817578047513962,
|
|
"num_tokens": 14218713.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.465539216995239,
|
|
"epoch": 0.7165721345538272,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004958670525354663,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.19205333143472672,
|
|
"num_tokens": 14229626.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.606721830368042,
|
|
"epoch": 0.7171337114617847,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495859389142044,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.17792723029851915,
|
|
"num_tokens": 14240320.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.746276473999023,
|
|
"epoch": 0.7176952883697423,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000495851718716373,
|
|
"loss": 5.5283,
|
|
"mean_token_accuracy": 0.18661556392908096,
|
|
"num_tokens": 14252233.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.674231624603271,
|
|
"epoch": 0.7182568652776998,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004958440412586977,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.17387946248054503,
|
|
"num_tokens": 14264421.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.658814907073975,
|
|
"epoch": 0.7188184421856574,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004958363567692624,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.18609785437583923,
|
|
"num_tokens": 14275320.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.567907333374023,
|
|
"epoch": 0.7193800190936148,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004958286652483118,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.19679996371269226,
|
|
"num_tokens": 14286099.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.5717933177948,
|
|
"epoch": 0.7199415960015724,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004958209666960909,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.18304425179958345,
|
|
"num_tokens": 14297795.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.542516279220581,
|
|
"epoch": 0.7205031729095299,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004958132611128448,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.18903672099113464,
|
|
"num_tokens": 14309424.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.664888954162597,
|
|
"epoch": 0.7210647498174875,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004958055484988188,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.18454713076353074,
|
|
"num_tokens": 14320763.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.615026235580444,
|
|
"epoch": 0.721626326725445,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004957978288542585,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.18215120434761048,
|
|
"num_tokens": 14331704.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.6207859992980955,
|
|
"epoch": 0.7221879036334026,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004957901021794098,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.1775159329175949,
|
|
"num_tokens": 14343694.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.631306743621826,
|
|
"epoch": 0.7227494805413601,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004957823684745184,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.18715686202049256,
|
|
"num_tokens": 14355408.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.641364526748657,
|
|
"epoch": 0.7233110574493177,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004957746277398309,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.17889882624149323,
|
|
"num_tokens": 14366778.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.564133501052856,
|
|
"epoch": 0.7238726343572752,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004957668799755937,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.19095930755138396,
|
|
"num_tokens": 14377947.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.594542407989502,
|
|
"epoch": 0.7244342112652328,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004957591251820532,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.17944370210170746,
|
|
"num_tokens": 14389571.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.706064939498901,
|
|
"epoch": 0.7249957881731903,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004957513633594567,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.1817486807703972,
|
|
"num_tokens": 14401865.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.598780584335327,
|
|
"epoch": 0.7255573650811479,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004957435945080512,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.19037633687257766,
|
|
"num_tokens": 14413676.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.599891996383667,
|
|
"epoch": 0.7261189419891054,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004957358186280839,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.19079018384218216,
|
|
"num_tokens": 14424675.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.506080102920532,
|
|
"epoch": 0.726680518897063,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004957280357198026,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.19010759592056276,
|
|
"num_tokens": 14437238.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.467310571670533,
|
|
"epoch": 0.7272420958050205,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004957202457834551,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.1930293172597885,
|
|
"num_tokens": 14448003.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.444816923141479,
|
|
"epoch": 0.7278036727129781,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004957124488192893,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.20379856824874878,
|
|
"num_tokens": 14458440.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.591552877426148,
|
|
"epoch": 0.7283652496209356,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004957046448275535,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.18740760833024978,
|
|
"num_tokens": 14470127.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.5049903869628904,
|
|
"epoch": 0.7289268265288932,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004956968338084961,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.18983594626188277,
|
|
"num_tokens": 14480993.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.554078578948975,
|
|
"epoch": 0.7294884034368507,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956890157623661,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.18472287207841873,
|
|
"num_tokens": 14492789.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.641831159591675,
|
|
"epoch": 0.7300499803448082,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956811906894122,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.18235754370689392,
|
|
"num_tokens": 14504528.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.676629447937012,
|
|
"epoch": 0.7306115572527657,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004956733585898836,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.18495407849550247,
|
|
"num_tokens": 14515739.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.654498958587647,
|
|
"epoch": 0.7311731341607233,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004956655194640297,
|
|
"loss": 5.5483,
|
|
"mean_token_accuracy": 0.18190713226795197,
|
|
"num_tokens": 14527120.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.61271858215332,
|
|
"epoch": 0.7317347110686808,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004956576733121,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.18355289846658707,
|
|
"num_tokens": 14539390.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.611499452590943,
|
|
"epoch": 0.7322962879766384,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004956498201343444,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.18246354758739472,
|
|
"num_tokens": 14549905.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.605987453460694,
|
|
"epoch": 0.7328578648845959,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000495641959931013,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.18781792521476745,
|
|
"num_tokens": 14561519.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.532815551757812,
|
|
"epoch": 0.7334194417925535,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004956340927023561,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.19085387885570526,
|
|
"num_tokens": 14572704.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.625210905075074,
|
|
"epoch": 0.733981018700511,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495626218448624,
|
|
"loss": 5.4619,
|
|
"mean_token_accuracy": 0.18819706588983537,
|
|
"num_tokens": 14584055.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.435035753250122,
|
|
"epoch": 0.7345425956084686,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004956183371700676,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.1977975085377693,
|
|
"num_tokens": 14595271.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.572039270401001,
|
|
"epoch": 0.7351041725164261,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004956104488669377,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.19566014111042024,
|
|
"num_tokens": 14605748.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.636803722381591,
|
|
"epoch": 0.7356657494243837,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004956025535394856,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.19630719870328903,
|
|
"num_tokens": 14616295.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.520361518859863,
|
|
"epoch": 0.7362273263323412,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004955946511879626,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.18370181322097778,
|
|
"num_tokens": 14626690.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.545464897155762,
|
|
"epoch": 0.7367889032402988,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004955867418126205,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.1875321537256241,
|
|
"num_tokens": 14637685.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.610912942886353,
|
|
"epoch": 0.7373504801482563,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004955788254137108,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.18240293562412263,
|
|
"num_tokens": 14648098.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.6816717147827145,
|
|
"epoch": 0.7379120570562139,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004955709019914857,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.18223390132188796,
|
|
"num_tokens": 14661134.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.632520055770874,
|
|
"epoch": 0.7384736339641714,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004955629715461977,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.18777064085006714,
|
|
"num_tokens": 14672699.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.632522869110107,
|
|
"epoch": 0.739035210872129,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004955550340780991,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.18437382727861404,
|
|
"num_tokens": 14682994.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.543580532073975,
|
|
"epoch": 0.7395967877800865,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004955470895874427,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.1894711285829544,
|
|
"num_tokens": 14694828.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.589076089859009,
|
|
"epoch": 0.7401583646880441,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004955391380744813,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.1924143135547638,
|
|
"num_tokens": 14705975.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.678030776977539,
|
|
"epoch": 0.7407199415960015,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004955311795394684,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.18800908625125884,
|
|
"num_tokens": 14717717.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.561539220809936,
|
|
"epoch": 0.7412815185039591,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000495523213982657,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.19190507233142853,
|
|
"num_tokens": 14729254.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.600515127182007,
|
|
"epoch": 0.7418430954119166,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004955152414043011,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.1839074894785881,
|
|
"num_tokens": 14739733.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.626922130584717,
|
|
"epoch": 0.7424046723198742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004955072618046543,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.18717766553163528,
|
|
"num_tokens": 14750855.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.559855890274048,
|
|
"epoch": 0.7429662492278317,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954992751839708,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.18215546756982803,
|
|
"num_tokens": 14762762.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.579696178436279,
|
|
"epoch": 0.7435278261357893,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004954912815425048,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.18941166549921035,
|
|
"num_tokens": 14773690.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.557268857955933,
|
|
"epoch": 0.7440894030437468,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000495483280880511,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.1876824051141739,
|
|
"num_tokens": 14785019.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.558713388442993,
|
|
"epoch": 0.7446509799517044,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000495475273198244,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.18793295323848724,
|
|
"num_tokens": 14795638.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.61789026260376,
|
|
"epoch": 0.7452125568596619,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004954672584959588,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.18987994492053986,
|
|
"num_tokens": 14806546.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.5560932636260985,
|
|
"epoch": 0.7457741337676195,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004954592367739104,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.1927689179778099,
|
|
"num_tokens": 14816918.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.564065933227539,
|
|
"epoch": 0.746335710675577,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954512080323546,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.19510701894760132,
|
|
"num_tokens": 14827420.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.624162340164185,
|
|
"epoch": 0.7468972875835346,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004954431722715468,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.18348710536956786,
|
|
"num_tokens": 14839209.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.622735500335693,
|
|
"epoch": 0.7474588644914921,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004954351294917428,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.18125738352537155,
|
|
"num_tokens": 14849916.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.53937783241272,
|
|
"epoch": 0.7480204413994497,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004954270796931989,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.1925006166100502,
|
|
"num_tokens": 14860946.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.7067304134368895,
|
|
"epoch": 0.7485820183074072,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004954190228761712,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.18034299165010453,
|
|
"num_tokens": 14872750.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.619444990158081,
|
|
"epoch": 0.7491435952153648,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004954109590409164,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.18876459449529648,
|
|
"num_tokens": 14883714.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.575121450424194,
|
|
"epoch": 0.7497051721233223,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954028881876911,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.19007978439331055,
|
|
"num_tokens": 14895147.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.534422445297241,
|
|
"epoch": 0.7502667490312799,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004953948103167524,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.19426807910203933,
|
|
"num_tokens": 14905914.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.518728399276734,
|
|
"epoch": 0.7508283259392374,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004953867254283575,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.1902252569794655,
|
|
"num_tokens": 14916988.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.639659214019775,
|
|
"epoch": 0.7513899028471949,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004953786335227636,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.18652891665697097,
|
|
"num_tokens": 14928675.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.696740055084229,
|
|
"epoch": 0.7519514797551524,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004953705346002287,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.19222279787063598,
|
|
"num_tokens": 14939422.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.5664349555969235,
|
|
"epoch": 0.75251305666311,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004953624286610106,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.19126803427934647,
|
|
"num_tokens": 14950156.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.575961589813232,
|
|
"epoch": 0.7530746335710675,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953543157053672,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.19023086428642272,
|
|
"num_tokens": 14960535.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.651915693283081,
|
|
"epoch": 0.7536362104790251,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004953461957335569,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.1879582181572914,
|
|
"num_tokens": 14970975.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.5016919612884525,
|
|
"epoch": 0.7541977873869826,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004953380687458382,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.19777534008026124,
|
|
"num_tokens": 14981204.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.625484371185303,
|
|
"epoch": 0.7547593642949402,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953299347424701,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.18535169959068298,
|
|
"num_tokens": 14991631.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.572710418701172,
|
|
"epoch": 0.7553209412028977,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953217937237114,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.19143273085355758,
|
|
"num_tokens": 15003873.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.588872337341309,
|
|
"epoch": 0.7558825181108553,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004953136456898212,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.1850448876619339,
|
|
"num_tokens": 15014890.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.566850805282593,
|
|
"epoch": 0.7564440950188128,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004953054906410593,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.19501300603151323,
|
|
"num_tokens": 15025037.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.602743625640869,
|
|
"epoch": 0.7570056719267704,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004952973285776848,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.19126145243644715,
|
|
"num_tokens": 15035722.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.58843502998352,
|
|
"epoch": 0.7575672488347279,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004952891594999582,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.1855214387178421,
|
|
"num_tokens": 15047138.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.566651058197022,
|
|
"epoch": 0.7581288257426855,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004952809834081392,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.19618855863809587,
|
|
"num_tokens": 15058559.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.515502166748047,
|
|
"epoch": 0.758690402650643,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004952728003024883,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.18848890960216522,
|
|
"num_tokens": 15070481.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.611682176589966,
|
|
"epoch": 0.7592519795586006,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004952646101832659,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.1941124513745308,
|
|
"num_tokens": 15079844.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.532123327255249,
|
|
"epoch": 0.7598135564665581,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004952564130507331,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.19315824508666993,
|
|
"num_tokens": 15091197.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.529201984405518,
|
|
"epoch": 0.7603751333745157,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952482089051506,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.18419083803892136,
|
|
"num_tokens": 15102130.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.726261377334595,
|
|
"epoch": 0.7609367102824732,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004952399977467796,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.1759365454316139,
|
|
"num_tokens": 15113886.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.548669004440308,
|
|
"epoch": 0.7614982871904308,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004952317795758817,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.18931155055761337,
|
|
"num_tokens": 15125284.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.61614842414856,
|
|
"epoch": 0.7620598640983883,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004952235543927185,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.19022832959890365,
|
|
"num_tokens": 15136486.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.544553995132446,
|
|
"epoch": 0.7626214410063458,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000495215322197552,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.2020503118634224,
|
|
"num_tokens": 15145937.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.479746866226196,
|
|
"epoch": 0.7631830179143033,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004952070829906442,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.19222828149795532,
|
|
"num_tokens": 15156923.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.65769214630127,
|
|
"epoch": 0.7637445948222609,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004951988367722574,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.18949285447597503,
|
|
"num_tokens": 15169793.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.5211550235748295,
|
|
"epoch": 0.7643061717302184,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004951905835426544,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.19952899366617202,
|
|
"num_tokens": 15180679.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.5758857250213625,
|
|
"epoch": 0.764867748638176,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004951823233020976,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.18800788074731828,
|
|
"num_tokens": 15192298.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.582974910736084,
|
|
"epoch": 0.7654293255461335,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004951740560508504,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.18052687644958496,
|
|
"num_tokens": 15204759.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.639478015899658,
|
|
"epoch": 0.7659909024540911,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004951657817891758,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.1900680720806122,
|
|
"num_tokens": 15217166.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.534590148925782,
|
|
"epoch": 0.7665524793620486,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004951575005173373,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.18943656086921692,
|
|
"num_tokens": 15227022.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.585673522949219,
|
|
"epoch": 0.7671140562700062,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004951492122355986,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.19115931093692778,
|
|
"num_tokens": 15239088.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.614662551879883,
|
|
"epoch": 0.7676756331779637,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004951409169442236,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.19073046743869781,
|
|
"num_tokens": 15250263.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.4909275531768795,
|
|
"epoch": 0.7682372100859213,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004951326146434765,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.1913973167538643,
|
|
"num_tokens": 15263014.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.630658292770386,
|
|
"epoch": 0.7687987869938788,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004951243053336214,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.1921733945608139,
|
|
"num_tokens": 15274261.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.50968828201294,
|
|
"epoch": 0.7693603639018364,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004951159890149232,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.19621815532445908,
|
|
"num_tokens": 15284929.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.476413106918335,
|
|
"epoch": 0.7699219408097939,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004951076656876466,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.1924176260828972,
|
|
"num_tokens": 15296622.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.553567743301391,
|
|
"epoch": 0.7704835177177515,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004950993353520564,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.18727268874645234,
|
|
"num_tokens": 15308373.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.549234390258789,
|
|
"epoch": 0.771045094625709,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000495090998008418,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.20021380633115768,
|
|
"num_tokens": 15319705.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.671568155288696,
|
|
"epoch": 0.7716066715336666,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000495082653656997,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.1847941145300865,
|
|
"num_tokens": 15330883.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.592058324813843,
|
|
"epoch": 0.7721682484416241,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004950743022980587,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.18797875940799713,
|
|
"num_tokens": 15342294.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.579819679260254,
|
|
"epoch": 0.7727298253495817,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004950659439318696,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.18958579003810883,
|
|
"num_tokens": 15352615.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.550897216796875,
|
|
"epoch": 0.7732914022575391,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004950575785586952,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.18660882413387297,
|
|
"num_tokens": 15364516.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.552147150039673,
|
|
"epoch": 0.7738529791654967,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004950492061788023,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.18900546729564666,
|
|
"num_tokens": 15374877.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.552751922607422,
|
|
"epoch": 0.7744145560734542,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950408267924573,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.2055146187543869,
|
|
"num_tokens": 15385250.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.562349605560303,
|
|
"epoch": 0.7749761329814118,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004950324403999271,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.1998001366853714,
|
|
"num_tokens": 15397074.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.586512470245362,
|
|
"epoch": 0.7755377098893693,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004950240470014785,
|
|
"loss": 5.4533,
|
|
"mean_token_accuracy": 0.18603235632181167,
|
|
"num_tokens": 15408575.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.603518724441528,
|
|
"epoch": 0.7760992867973269,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004950156465973791,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.19139835834503174,
|
|
"num_tokens": 15419071.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.459807014465332,
|
|
"epoch": 0.7766608637052844,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000495007239187896,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19624956101179122,
|
|
"num_tokens": 15430137.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.453722238540649,
|
|
"epoch": 0.777222440613242,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004949988247732972,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.19548785537481309,
|
|
"num_tokens": 15440661.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.482903480529785,
|
|
"epoch": 0.7777840175211995,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004949904033538504,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.19688933789730073,
|
|
"num_tokens": 15451909.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.645163440704346,
|
|
"epoch": 0.7783455944291571,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000494981974929824,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.18678361624479295,
|
|
"num_tokens": 15462244.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.571831607818604,
|
|
"epoch": 0.7789071713371146,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000494973539501486,
|
|
"loss": 5.4733,
|
|
"mean_token_accuracy": 0.186330346763134,
|
|
"num_tokens": 15473284.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.540014934539795,
|
|
"epoch": 0.7794687482450722,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004949650970691052,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.20325299650430678,
|
|
"num_tokens": 15484964.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.53306770324707,
|
|
"epoch": 0.7800303251530297,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004949566476329505,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.1902560129761696,
|
|
"num_tokens": 15495922.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.607692766189575,
|
|
"epoch": 0.7805919020609873,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004949481911932908,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.1876210853457451,
|
|
"num_tokens": 15507173.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.628160858154297,
|
|
"epoch": 0.7811534789689448,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004949397277503954,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.19035593569278716,
|
|
"num_tokens": 15517720.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.663046026229859,
|
|
"epoch": 0.7817150558769024,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004949312573045338,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.1877150908112526,
|
|
"num_tokens": 15529482.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.625580549240112,
|
|
"epoch": 0.7822766327848599,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004949227798559757,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.1876019760966301,
|
|
"num_tokens": 15540522.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.5804962635040285,
|
|
"epoch": 0.7828382096928175,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004949142954049909,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.1836806833744049,
|
|
"num_tokens": 15552443.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.6723870754241945,
|
|
"epoch": 0.783399786600775,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004949058039518496,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.19679072499275208,
|
|
"num_tokens": 15563418.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.626781797409057,
|
|
"epoch": 0.7839613635087325,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004948973054968222,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.1873273015022278,
|
|
"num_tokens": 15574301.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.675553894042968,
|
|
"epoch": 0.78452294041669,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004948888000401794,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.1845426619052887,
|
|
"num_tokens": 15585125.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.633433628082275,
|
|
"epoch": 0.7850845173246476,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004948802875821918,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.18775734007358552,
|
|
"num_tokens": 15595822.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.497494173049927,
|
|
"epoch": 0.7856460942326051,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004948717681231308,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.19025390297174455,
|
|
"num_tokens": 15606835.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.576907730102539,
|
|
"epoch": 0.7862076711405627,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004948632416632672,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.18685304075479509,
|
|
"num_tokens": 15617287.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.690821409225464,
|
|
"epoch": 0.7867692480485202,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004948547082028728,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.1825042650103569,
|
|
"num_tokens": 15628440.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.6147383689880375,
|
|
"epoch": 0.7873308249564778,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004948461677422193,
|
|
"loss": 5.5564,
|
|
"mean_token_accuracy": 0.17882291078567505,
|
|
"num_tokens": 15640677.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.636997890472412,
|
|
"epoch": 0.7878924018644353,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004948376202815785,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.1947314202785492,
|
|
"num_tokens": 15651941.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.521495580673218,
|
|
"epoch": 0.7884539787723929,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004948290658212225,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.19430001080036163,
|
|
"num_tokens": 15663513.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.495321607589721,
|
|
"epoch": 0.7890155556803504,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004948205043614239,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1904343456029892,
|
|
"num_tokens": 15675548.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.631325149536133,
|
|
"epoch": 0.789577132588308,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004948119359024551,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.19758018851280212,
|
|
"num_tokens": 15685365.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.605079078674317,
|
|
"epoch": 0.7901387094962655,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004948033604445891,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.18862174302339554,
|
|
"num_tokens": 15696112.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.534260034561157,
|
|
"epoch": 0.7907002864042231,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004947947779880988,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.1921730026602745,
|
|
"num_tokens": 15707414.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.574878740310669,
|
|
"epoch": 0.7912618633121806,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004947861885332576,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.19083053171634673,
|
|
"num_tokens": 15719077.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.584549617767334,
|
|
"epoch": 0.7918234402201382,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004947775920803388,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.1844985991716385,
|
|
"num_tokens": 15730497.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.588125467300415,
|
|
"epoch": 0.7923850171280957,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004947689886296162,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.1892986476421356,
|
|
"num_tokens": 15741724.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.608678817749023,
|
|
"epoch": 0.7929465940360533,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000494760378181364,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.18194199055433274,
|
|
"num_tokens": 15751868.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.569334316253662,
|
|
"epoch": 0.7935081709440108,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004947517607358559,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.18530841469764708,
|
|
"num_tokens": 15762783.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.615188217163086,
|
|
"epoch": 0.7940697478519684,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004947431362933666,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.18853361904621124,
|
|
"num_tokens": 15774155.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.63729829788208,
|
|
"epoch": 0.7946313247599258,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947345048541706,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.1820038616657257,
|
|
"num_tokens": 15785034.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.478166913986206,
|
|
"epoch": 0.7951929016678834,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947258664185427,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.19115310162305832,
|
|
"num_tokens": 15795959.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.555428600311279,
|
|
"epoch": 0.7957544785758409,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004947172209867581,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.19701235592365265,
|
|
"num_tokens": 15805561.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.588228178024292,
|
|
"epoch": 0.7963160554837985,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004947085685590919,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.1902380719780922,
|
|
"num_tokens": 15816883.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.508427858352661,
|
|
"epoch": 0.796877632391756,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004946999091358196,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.1908458799123764,
|
|
"num_tokens": 15827753.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.580519294738769,
|
|
"epoch": 0.7974392092997136,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000494691242717217,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.18583096712827682,
|
|
"num_tokens": 15840346.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.611294317245483,
|
|
"epoch": 0.7980007862076711,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004946825693035601,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.18676118105649947,
|
|
"num_tokens": 15851036.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.552220153808594,
|
|
"epoch": 0.7985623631156287,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000494673888895125,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.18933280408382416,
|
|
"num_tokens": 15863154.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.6244823932647705,
|
|
"epoch": 0.7991239400235862,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004946652014921881,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.18316242843866348,
|
|
"num_tokens": 15874543.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.576416826248169,
|
|
"epoch": 0.7996855169315438,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004946565070950259,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.19399106204509736,
|
|
"num_tokens": 15886221.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.5822898864746096,
|
|
"epoch": 0.8002470938395013,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004946478057039153,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.185135854780674,
|
|
"num_tokens": 15897602.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.590000772476197,
|
|
"epoch": 0.8008086707474589,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004946390973191335,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.19016864001750947,
|
|
"num_tokens": 15908030.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.655847978591919,
|
|
"epoch": 0.8013702476554164,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004946303819409575,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.18730378448963164,
|
|
"num_tokens": 15918341.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.603756904602051,
|
|
"epoch": 0.801931824563374,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004946216595696652,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.19159286767244338,
|
|
"num_tokens": 15929144.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.564437055587769,
|
|
"epoch": 0.8024934014713315,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004946129302055338,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.19054533243179322,
|
|
"num_tokens": 15940013.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.606209468841553,
|
|
"epoch": 0.8030549783792891,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004946041938488417,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.1870056852698326,
|
|
"num_tokens": 15950680.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.574912691116333,
|
|
"epoch": 0.8036165552872466,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004945954504998668,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.19101515412330627,
|
|
"num_tokens": 15961462.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.574607276916504,
|
|
"epoch": 0.8041781321952042,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004945867001588877,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.19240275472402574,
|
|
"num_tokens": 15972788.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.6029932498931885,
|
|
"epoch": 0.8047397091031617,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945779428261827,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.19334341436624528,
|
|
"num_tokens": 15983244.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.5632545948028564,
|
|
"epoch": 0.8053012860111193,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000494569178502031,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.18590798676013948,
|
|
"num_tokens": 15994325.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.655714702606201,
|
|
"epoch": 0.8058628629190767,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004945604071867114,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.1890251651406288,
|
|
"num_tokens": 16005237.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.556340026855469,
|
|
"epoch": 0.8064244398270343,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004945516288805035,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.20121381431818008,
|
|
"num_tokens": 16015943.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.519995164871216,
|
|
"epoch": 0.8069860167349918,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004945428435836864,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.19282602965831758,
|
|
"num_tokens": 16026727.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.539057445526123,
|
|
"epoch": 0.8075475936429494,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004945340512965401,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.18519749939441682,
|
|
"num_tokens": 16039021.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.477265882492065,
|
|
"epoch": 0.8081091705509069,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004945252520193443,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.1956339344382286,
|
|
"num_tokens": 16050312.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.5649982452392575,
|
|
"epoch": 0.8086707474588645,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004945164457523795,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.20188669711351395,
|
|
"num_tokens": 16060009.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.505179166793823,
|
|
"epoch": 0.809232324366822,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945076324959258,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.18668977916240692,
|
|
"num_tokens": 16072025.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.573460245132447,
|
|
"epoch": 0.8097939012747796,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004944988122502641,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.1892346352338791,
|
|
"num_tokens": 16083229.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.510738706588745,
|
|
"epoch": 0.8103554781827371,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000494489985015675,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.19452218860387802,
|
|
"num_tokens": 16094936.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.5265261173248295,
|
|
"epoch": 0.8109170550906947,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004944811507924396,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.1953087940812111,
|
|
"num_tokens": 16106182.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.5065110206604,
|
|
"epoch": 0.8114786319986522,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004944723095808393,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.20086771994829178,
|
|
"num_tokens": 16117006.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.495611190795898,
|
|
"epoch": 0.8120402089066098,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004944634613811555,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.19101730436086656,
|
|
"num_tokens": 16128892.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.580922365188599,
|
|
"epoch": 0.8126017858145673,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00049445460619367,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.19277508109807967,
|
|
"num_tokens": 16139953.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.634200191497802,
|
|
"epoch": 0.8131633627225249,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004944457440186648,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.19050092697143556,
|
|
"num_tokens": 16150103.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.575920534133911,
|
|
"epoch": 0.8137249396304824,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004944368748564219,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.18585142195224763,
|
|
"num_tokens": 16161666.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.57649793624878,
|
|
"epoch": 0.81428651653844,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004944279987072238,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.18571154177188873,
|
|
"num_tokens": 16172524.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.591890811920166,
|
|
"epoch": 0.8148480934463975,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004944191155713531,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.19061081856489182,
|
|
"num_tokens": 16183023.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.581477975845337,
|
|
"epoch": 0.8154096703543551,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004944102254490928,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.1964020162820816,
|
|
"num_tokens": 16193504.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.539368200302124,
|
|
"epoch": 0.8159712472623126,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004944013283407257,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.19523604065179825,
|
|
"num_tokens": 16204730.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.513184642791748,
|
|
"epoch": 0.8165328241702701,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943924242465352,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.196284157037735,
|
|
"num_tokens": 16214496.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.5480506896972654,
|
|
"epoch": 0.8170944010782276,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004943835131668049,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.19780391901731492,
|
|
"num_tokens": 16225494.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.476095151901245,
|
|
"epoch": 0.8176559779861852,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004943745951018184,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.1908338949084282,
|
|
"num_tokens": 16236385.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.534617328643799,
|
|
"epoch": 0.8182175548941427,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004943656700518597,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.19612893909215928,
|
|
"num_tokens": 16247300.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.585156726837158,
|
|
"epoch": 0.8187791318021003,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004943567380172129,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.18920427411794663,
|
|
"num_tokens": 16259326.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.5987762928009035,
|
|
"epoch": 0.8193407087100578,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004943477989981627,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.1925815984606743,
|
|
"num_tokens": 16270559.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.578562688827515,
|
|
"epoch": 0.8199022856180154,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004943388529949933,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.18502715826034546,
|
|
"num_tokens": 16283120.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.624129819869995,
|
|
"epoch": 0.8204638625259729,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943299000079899,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.19378956407308578,
|
|
"num_tokens": 16293449.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.560214853286743,
|
|
"epoch": 0.8210254394339305,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004943209400374373,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.182936130464077,
|
|
"num_tokens": 16305144.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.523592615127564,
|
|
"epoch": 0.821587016341888,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000494311973083621,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.19714271277189255,
|
|
"num_tokens": 16316728.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.605225515365601,
|
|
"epoch": 0.8221485932498456,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004943029991468264,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.18578318506479263,
|
|
"num_tokens": 16329117.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.662326240539551,
|
|
"epoch": 0.8227101701578031,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004942940182273393,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.19046420454978943,
|
|
"num_tokens": 16341651.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.668012714385986,
|
|
"epoch": 0.8232717470657607,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004942850303254455,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.19052517265081406,
|
|
"num_tokens": 16353220.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.683514976501465,
|
|
"epoch": 0.8238333239737182,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004942760354414313,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.18775632232427597,
|
|
"num_tokens": 16363748.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.406259441375733,
|
|
"epoch": 0.8243949008816758,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004942670335755831,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.20561690926551818,
|
|
"num_tokens": 16374086.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.534036636352539,
|
|
"epoch": 0.8249564777896333,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004942580247281876,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.19592444747686386,
|
|
"num_tokens": 16384140.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.627853918075561,
|
|
"epoch": 0.8255180546975909,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942490088995315,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.18368045836687089,
|
|
"num_tokens": 16395940.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.53330717086792,
|
|
"epoch": 0.8260796316055484,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004942399860899018,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.19411544054746627,
|
|
"num_tokens": 16406667.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.623126888275147,
|
|
"epoch": 0.826641208513506,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004942309562995862,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.18582515120506288,
|
|
"num_tokens": 16418621.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.4967734813690186,
|
|
"epoch": 0.8272027854214634,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004942219195288716,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.19406825453042983,
|
|
"num_tokens": 16429576.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.604167032241821,
|
|
"epoch": 0.827764362329421,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004942128757780463,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.18338728845119476,
|
|
"num_tokens": 16441004.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.556333732604981,
|
|
"epoch": 0.8283259392373785,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004942038250473979,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.18352732211351394,
|
|
"num_tokens": 16452183.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.57550277709961,
|
|
"epoch": 0.8288875161453361,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941947673372147,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.19016813337802888,
|
|
"num_tokens": 16463552.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.64045729637146,
|
|
"epoch": 0.8294490930532936,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004941857026477851,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.19709848016500472,
|
|
"num_tokens": 16474062.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.659898185729981,
|
|
"epoch": 0.8300106699612512,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004941766309793978,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.18808427900075914,
|
|
"num_tokens": 16487377.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.642703056335449,
|
|
"epoch": 0.8305722468692087,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004941675523323414,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.19426499158143998,
|
|
"num_tokens": 16499704.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.556036043167114,
|
|
"epoch": 0.8311338237771663,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004941584667069052,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.18889748603105544,
|
|
"num_tokens": 16511954.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.464701795578003,
|
|
"epoch": 0.8316954006851238,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004941493741033784,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.1879597932100296,
|
|
"num_tokens": 16522602.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.6242673873901365,
|
|
"epoch": 0.8322569775930814,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004941402745220507,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.18399604558944702,
|
|
"num_tokens": 16534233.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.672506332397461,
|
|
"epoch": 0.8328185545010389,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004941311679632115,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.18548948019742967,
|
|
"num_tokens": 16546120.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.571470165252686,
|
|
"epoch": 0.8333801314089965,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000494122054427151,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.19040597528219222,
|
|
"num_tokens": 16556830.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.5097990989685055,
|
|
"epoch": 0.833941708316954,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004941129339141592,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.18973003774881364,
|
|
"num_tokens": 16567436.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.551469230651856,
|
|
"epoch": 0.8345032852249116,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004941038064245267,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.1923310101032257,
|
|
"num_tokens": 16577807.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.6105536937713625,
|
|
"epoch": 0.8350648621328691,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000494094671958544,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.1939983770251274,
|
|
"num_tokens": 16589745.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.686103296279907,
|
|
"epoch": 0.8356264390408267,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004940855305165019,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.1891957402229309,
|
|
"num_tokens": 16600727.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.581608629226684,
|
|
"epoch": 0.8361880159487842,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004940763820986916,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.18738610297441483,
|
|
"num_tokens": 16611091.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.463036298751831,
|
|
"epoch": 0.8367495928567418,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004940672267054044,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.19423816502094268,
|
|
"num_tokens": 16622550.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.532640647888184,
|
|
"epoch": 0.8373111697646993,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004940580643369316,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.18642989546060562,
|
|
"num_tokens": 16634243.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.515197086334228,
|
|
"epoch": 0.8378727466726568,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004940488949935651,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.18775193393230438,
|
|
"num_tokens": 16645266.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.5769445419311525,
|
|
"epoch": 0.8384343235806143,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004940397186755968,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.1891443446278572,
|
|
"num_tokens": 16654365.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.535280656814575,
|
|
"epoch": 0.8389959004885719,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004940305353833191,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.19563759714365006,
|
|
"num_tokens": 16665251.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.5724844455719,
|
|
"epoch": 0.8395574773965294,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000494021345117024,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.19206673800945281,
|
|
"num_tokens": 16676209.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.561198902130127,
|
|
"epoch": 0.840119054304487,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004940121478770044,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.19329277873039247,
|
|
"num_tokens": 16687213.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.5042799949646,
|
|
"epoch": 0.8406806312124445,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004940029436635531,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.19535597115755082,
|
|
"num_tokens": 16697920.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.487038469314575,
|
|
"epoch": 0.8412422081204021,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004939937324769631,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.1866077497601509,
|
|
"num_tokens": 16707815.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.537863540649414,
|
|
"epoch": 0.8418037850283596,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004939845143175276,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19552522301673889,
|
|
"num_tokens": 16719221.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.4799598217010494,
|
|
"epoch": 0.8423653619363172,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004939752891855404,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.19040751308202744,
|
|
"num_tokens": 16731741.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.528685569763184,
|
|
"epoch": 0.8429269388442747,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004939660570812951,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.19846178591251373,
|
|
"num_tokens": 16742795.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.543195915222168,
|
|
"epoch": 0.8434885157522323,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004939568180050855,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.19046679735183716,
|
|
"num_tokens": 16753139.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.537963581085205,
|
|
"epoch": 0.8440500926601898,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004939475719572059,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.1965207725763321,
|
|
"num_tokens": 16764246.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.591217088699341,
|
|
"epoch": 0.8446116695681474,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004939383189379507,
|
|
"loss": 5.44,
|
|
"mean_token_accuracy": 0.18323310166597367,
|
|
"num_tokens": 16776039.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.645013856887817,
|
|
"epoch": 0.8451732464761049,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004939290589476145,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.19410069435834884,
|
|
"num_tokens": 16786979.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.557646751403809,
|
|
"epoch": 0.8457348233840625,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004939197919864922,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.18700661808252333,
|
|
"num_tokens": 16798113.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.561951494216919,
|
|
"epoch": 0.84629640029202,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004939105180548788,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.18789446204900742,
|
|
"num_tokens": 16809072.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.503936815261841,
|
|
"epoch": 0.8468579771999776,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004939012371530696,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.19951880127191543,
|
|
"num_tokens": 16819548.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.594641065597534,
|
|
"epoch": 0.8474195541079351,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004938919492813601,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.18149147182703018,
|
|
"num_tokens": 16831935.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.553983688354492,
|
|
"epoch": 0.8479811310158927,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938826544400461,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.19485293477773666,
|
|
"num_tokens": 16842961.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.489220714569091,
|
|
"epoch": 0.8485427079238502,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004938733526294234,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.1882145047187805,
|
|
"num_tokens": 16854392.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.568440723419189,
|
|
"epoch": 0.8491042848318077,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004938640438497883,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.18975515365600587,
|
|
"num_tokens": 16865443.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.562778472900391,
|
|
"epoch": 0.8496658617397652,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004938547281014372,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.19442871809005738,
|
|
"num_tokens": 16876854.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.612915849685669,
|
|
"epoch": 0.8502274386477228,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004938454053846666,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.18955429047346115,
|
|
"num_tokens": 16888823.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.517658996582031,
|
|
"epoch": 0.8507890155556803,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004938360756997735,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.19100319892168044,
|
|
"num_tokens": 16898807.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.605509614944458,
|
|
"epoch": 0.8513505924636379,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938267390470547,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.18057783246040343,
|
|
"num_tokens": 16911258.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.655462980270386,
|
|
"epoch": 0.8519121693715954,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938173954268079,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.18679491877555848,
|
|
"num_tokens": 16922557.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.572864532470703,
|
|
"epoch": 0.852473746279553,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004938080448393302,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.18750457763671874,
|
|
"num_tokens": 16935330.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.601666641235352,
|
|
"epoch": 0.8530353231875105,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004937986872849195,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.19467120617628098,
|
|
"num_tokens": 16945361.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.439452743530273,
|
|
"epoch": 0.8535969000954681,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004937893227638738,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.19491867870092391,
|
|
"num_tokens": 16955363.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.473325490951538,
|
|
"epoch": 0.8541584770034256,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004937799512764912,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.19108901768922806,
|
|
"num_tokens": 16965267.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.637543153762818,
|
|
"epoch": 0.8547200539113832,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00049377057282307,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.18720805644989014,
|
|
"num_tokens": 16977528.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.594407081604004,
|
|
"epoch": 0.8552816308193407,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493761187403909,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.18854280263185502,
|
|
"num_tokens": 16987326.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.637516260147095,
|
|
"epoch": 0.8558432077272983,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000493751795019307,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.19094510227441788,
|
|
"num_tokens": 16999127.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.465028858184814,
|
|
"epoch": 0.8564047846352558,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004937423956695629,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.19453594833612442,
|
|
"num_tokens": 17009929.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.596677160263061,
|
|
"epoch": 0.8569663615432134,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004937329893549762,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.1894683614373207,
|
|
"num_tokens": 17020909.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.557248544692993,
|
|
"epoch": 0.8575279384511709,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004937235760758462,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.1899758204817772,
|
|
"num_tokens": 17031358.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.5541972637176515,
|
|
"epoch": 0.8580895153591285,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004937141558324726,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.18958469182252885,
|
|
"num_tokens": 17042566.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.687198305130005,
|
|
"epoch": 0.858651092267086,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004937047286251556,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.18225005269050598,
|
|
"num_tokens": 17054998.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.494508695602417,
|
|
"epoch": 0.8592126691750436,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004936952944541952,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.18676535934209823,
|
|
"num_tokens": 17064876.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.524995040893555,
|
|
"epoch": 0.859774246083001,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004936858533198917,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.19671382158994674,
|
|
"num_tokens": 17075310.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.441866397857666,
|
|
"epoch": 0.8603358229909586,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493676405222546,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.19824785143136978,
|
|
"num_tokens": 17086023.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.516475582122803,
|
|
"epoch": 0.8608973998989161,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004936669501624586,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.19507025331258773,
|
|
"num_tokens": 17097554.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.745598220825196,
|
|
"epoch": 0.8614589768068737,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004936574881399308,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.18330778926610947,
|
|
"num_tokens": 17108890.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.478343725204468,
|
|
"epoch": 0.8620205537148312,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004936480191552637,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.19087933003902435,
|
|
"num_tokens": 17120651.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.593843555450439,
|
|
"epoch": 0.8625821306227888,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004936385432087589,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.19287574738264085,
|
|
"num_tokens": 17131306.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.712613153457641,
|
|
"epoch": 0.8631437075307463,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004936290603007181,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.18163432329893112,
|
|
"num_tokens": 17142779.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.664867258071899,
|
|
"epoch": 0.8637052844387039,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004936195704314432,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.19453293234109878,
|
|
"num_tokens": 17154992.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.579209041595459,
|
|
"epoch": 0.8642668613466614,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004936100736012363,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.19431873708963393,
|
|
"num_tokens": 17166089.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.51043119430542,
|
|
"epoch": 0.864828438254619,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004936005698104,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.18944628089666365,
|
|
"num_tokens": 17175691.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.530090236663819,
|
|
"epoch": 0.8653900151625765,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004935910590592367,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.18704741448163986,
|
|
"num_tokens": 17186466.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.486089611053467,
|
|
"epoch": 0.8659515920705341,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004935815413480494,
|
|
"loss": 5.1671,
|
|
"mean_token_accuracy": 0.20765801668167114,
|
|
"num_tokens": 17198520.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.5385332107543945,
|
|
"epoch": 0.8665131689784916,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000493572016677141,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.18900790959596633,
|
|
"num_tokens": 17210496.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.609238862991333,
|
|
"epoch": 0.8670747458864492,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004935624850468148,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.19409194886684417,
|
|
"num_tokens": 17221631.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.598459625244141,
|
|
"epoch": 0.8676363227944067,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004935529464573742,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.18472131192684174,
|
|
"num_tokens": 17233316.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.533458566665649,
|
|
"epoch": 0.8681978997023643,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004935434009091232,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.19717931002378464,
|
|
"num_tokens": 17245761.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.568277883529663,
|
|
"epoch": 0.8687594766103218,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004935338484023655,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.193367800116539,
|
|
"num_tokens": 17255007.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.517693948745728,
|
|
"epoch": 0.8693210535182794,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004935242889374052,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.19626267850399018,
|
|
"num_tokens": 17265378.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.560853815078735,
|
|
"epoch": 0.8698826304262369,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004935147225145469,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.18695779144763947,
|
|
"num_tokens": 17277202.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.579006814956665,
|
|
"epoch": 0.8704442073341944,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004935051491340951,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.19836185425519942,
|
|
"num_tokens": 17287006.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.529684686660767,
|
|
"epoch": 0.8710057842421519,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004934955687963546,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.20162637680768966,
|
|
"num_tokens": 17297387.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.619344282150268,
|
|
"epoch": 0.8715673611501095,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004934859815016304,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.18597101420164108,
|
|
"num_tokens": 17310364.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.52930178642273,
|
|
"epoch": 0.872128938058067,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004934763872502278,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.19887939989566802,
|
|
"num_tokens": 17321282.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.5981076717376705,
|
|
"epoch": 0.8726905149660246,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004934667860424523,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.18965112715959548,
|
|
"num_tokens": 17331755.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.5537820816040036,
|
|
"epoch": 0.8732520918739821,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004934571778786096,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.18913549780845643,
|
|
"num_tokens": 17342542.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.554932308197022,
|
|
"epoch": 0.8738136687819397,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004934475627590057,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.19172336608171464,
|
|
"num_tokens": 17353150.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.516607284545898,
|
|
"epoch": 0.8743752456898972,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004934379406839466,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.18976504355669022,
|
|
"num_tokens": 17363901.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.556289291381836,
|
|
"epoch": 0.8749368225978548,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004934283116537387,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19671293795108796,
|
|
"num_tokens": 17374429.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.54694504737854,
|
|
"epoch": 0.8754983995058123,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004934186756686888,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.18706863522529601,
|
|
"num_tokens": 17384952.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.519961833953857,
|
|
"epoch": 0.8760599764137699,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004934090327291034,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.18838118463754655,
|
|
"num_tokens": 17397771.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.54427695274353,
|
|
"epoch": 0.8766215533217274,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004933993828352898,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.19747351258993148,
|
|
"num_tokens": 17407748.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.4916332244873045,
|
|
"epoch": 0.877183130229685,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004933897259875551,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.19652994424104692,
|
|
"num_tokens": 17418572.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.428189659118653,
|
|
"epoch": 0.8777447071376425,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004933800621862069,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.195195572078228,
|
|
"num_tokens": 17429909.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.510263919830322,
|
|
"epoch": 0.8783062840456001,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004933703914315527,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.1877536043524742,
|
|
"num_tokens": 17441143.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.5718847751617435,
|
|
"epoch": 0.8788678609535576,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004933607137239006,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1818570911884308,
|
|
"num_tokens": 17452156.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.467211103439331,
|
|
"epoch": 0.8794294378615152,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004933510290635587,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.18754110336303711,
|
|
"num_tokens": 17463873.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.488572645187378,
|
|
"epoch": 0.8799910147694727,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004933413374508353,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.1953457549214363,
|
|
"num_tokens": 17474180.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.557047700881958,
|
|
"epoch": 0.8805525916774303,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004933316388860391,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.1974281042814255,
|
|
"num_tokens": 17486903.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.531964540481567,
|
|
"epoch": 0.8811141685853877,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004933219333694787,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.19225149750709533,
|
|
"num_tokens": 17498790.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.566200590133667,
|
|
"epoch": 0.8816757454933453,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004933122209014634,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.18570789694786072,
|
|
"num_tokens": 17510061.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.541897344589233,
|
|
"epoch": 0.8822373224013028,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004933025014823022,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.18787602335214615,
|
|
"num_tokens": 17522414.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.7290808200836185,
|
|
"epoch": 0.8827988993092604,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932927751123048,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.18252748250961304,
|
|
"num_tokens": 17532745.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.540169048309326,
|
|
"epoch": 0.8833604762172179,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004932830417917808,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.19230471104383468,
|
|
"num_tokens": 17545329.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.600207996368408,
|
|
"epoch": 0.8839220531251755,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049327330152104,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.19264648407697677,
|
|
"num_tokens": 17557789.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.525692653656006,
|
|
"epoch": 0.884483630033133,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932635543003927,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.20039539635181428,
|
|
"num_tokens": 17568338.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.530222415924072,
|
|
"epoch": 0.8850452069410906,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004932538001301491,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.1923265889286995,
|
|
"num_tokens": 17581199.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.433183765411377,
|
|
"epoch": 0.8856067838490481,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004932440390106199,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.19796152859926225,
|
|
"num_tokens": 17592937.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.511492395401001,
|
|
"epoch": 0.8861683607570057,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004932342709421159,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.1928298607468605,
|
|
"num_tokens": 17604003.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.762244844436646,
|
|
"epoch": 0.8867299376649632,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000493224495924948,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.18781370371580125,
|
|
"num_tokens": 17617283.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.553151178359985,
|
|
"epoch": 0.8872915145729208,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004932147139594276,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.19511836171150207,
|
|
"num_tokens": 17628161.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.595506620407105,
|
|
"epoch": 0.8878530914808783,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004932049250458659,
|
|
"loss": 5.4355,
|
|
"mean_token_accuracy": 0.18616373986005783,
|
|
"num_tokens": 17639226.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.523558330535889,
|
|
"epoch": 0.8884146683888359,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004931951291845749,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.20171066969633103,
|
|
"num_tokens": 17652114.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.513261461257935,
|
|
"epoch": 0.8889762452967934,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004931853263758663,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.19566181004047395,
|
|
"num_tokens": 17663280.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.557017707824707,
|
|
"epoch": 0.889537822204751,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004931755166200523,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.191867832839489,
|
|
"num_tokens": 17674445.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.5643792152404785,
|
|
"epoch": 0.8900993991127085,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931656999174452,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.19448838084936143,
|
|
"num_tokens": 17685046.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.464035129547119,
|
|
"epoch": 0.8906609760206661,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004931558762683577,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.20313881784677507,
|
|
"num_tokens": 17695269.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.483704280853272,
|
|
"epoch": 0.8912225529286236,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004931460456731024,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.19425296634435654,
|
|
"num_tokens": 17706296.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.531713676452637,
|
|
"epoch": 0.8917841298365812,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004931362081319925,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.19688325971364976,
|
|
"num_tokens": 17716262.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.531509733200073,
|
|
"epoch": 0.8923457067445386,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004931263636453409,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.19932370036840438,
|
|
"num_tokens": 17726818.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.482756471633911,
|
|
"epoch": 0.8929072836524962,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004931165122134616,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.1955420970916748,
|
|
"num_tokens": 17737112.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.558112096786499,
|
|
"epoch": 0.8934688605604537,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931066538366677,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.19075608253479004,
|
|
"num_tokens": 17747558.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.624970197677612,
|
|
"epoch": 0.8940304374684113,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004930967885152734,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.194711634516716,
|
|
"num_tokens": 17757495.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.523182773590088,
|
|
"epoch": 0.8945920143763688,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004930869162495929,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.19642237722873687,
|
|
"num_tokens": 17767562.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.564392518997193,
|
|
"epoch": 0.8951535912843264,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004930770370399403,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.1890277922153473,
|
|
"num_tokens": 17779800.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.517772150039673,
|
|
"epoch": 0.8957151681922839,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004930671508866303,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.19776757061481476,
|
|
"num_tokens": 17791183.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.536798095703125,
|
|
"epoch": 0.8962767451002415,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004930572577899776,
|
|
"loss": 5.3782,
|
|
"mean_token_accuracy": 0.19149343073368072,
|
|
"num_tokens": 17802547.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.414207029342651,
|
|
"epoch": 0.896838322008199,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004930473577502972,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.19121958166360856,
|
|
"num_tokens": 17815406.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.539687633514404,
|
|
"epoch": 0.8973998989161566,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004930374507679044,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.1906999886035919,
|
|
"num_tokens": 17826516.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.532695722579956,
|
|
"epoch": 0.8979614758241141,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004930275368431146,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.19545603692531585,
|
|
"num_tokens": 17838193.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.494921159744263,
|
|
"epoch": 0.8985230527320717,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004930176159762435,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.19550796896219252,
|
|
"num_tokens": 17849564.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.644647693634033,
|
|
"epoch": 0.8990846296400292,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004930076881676069,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.18880851864814757,
|
|
"num_tokens": 17861874.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.492027664184571,
|
|
"epoch": 0.8996462065479868,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004929977534175211,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.19881611317396164,
|
|
"num_tokens": 17873139.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.596198844909668,
|
|
"epoch": 0.9002077834559443,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004929878117263021,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.1951524645090103,
|
|
"num_tokens": 17883262.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.39709324836731,
|
|
"epoch": 0.9007693603639019,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004929778630942668,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.20346392691135406,
|
|
"num_tokens": 17895041.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.496571445465088,
|
|
"epoch": 0.9013309372718594,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004929679075217317,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.1923908159136772,
|
|
"num_tokens": 17905154.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.519870805740356,
|
|
"epoch": 0.901892514179817,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004929579450090139,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.19168179631233215,
|
|
"num_tokens": 17916287.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.56573634147644,
|
|
"epoch": 0.9024540910877745,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004929479755564305,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.19360852241516113,
|
|
"num_tokens": 17927269.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.545057868957519,
|
|
"epoch": 0.903015667995732,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004929379991642991,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.19359674751758577,
|
|
"num_tokens": 17938142.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.564269065856934,
|
|
"epoch": 0.9035772449036895,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004929280158329373,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.19100251495838166,
|
|
"num_tokens": 17950229.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.524956703186035,
|
|
"epoch": 0.9041388218116471,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000492918025562663,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.20215008556842803,
|
|
"num_tokens": 17961757.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.568588972091675,
|
|
"epoch": 0.9047003987196046,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004929080283537942,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.1838885188102722,
|
|
"num_tokens": 17972564.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.591539764404297,
|
|
"epoch": 0.9052619756275622,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004928980242066492,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.19958072006702424,
|
|
"num_tokens": 17982776.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.613075828552246,
|
|
"epoch": 0.9058235525355197,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004928880131215467,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.19110335111618043,
|
|
"num_tokens": 17994460.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.495513582229615,
|
|
"epoch": 0.9063851294434773,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004928779950988053,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.19202918708324432,
|
|
"num_tokens": 18005744.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.5118756771087645,
|
|
"epoch": 0.9069467063514348,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492867970138744,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.2010786548256874,
|
|
"num_tokens": 18016517.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.563801240921021,
|
|
"epoch": 0.9075082832593924,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004928579382416821,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.18440114259719848,
|
|
"num_tokens": 18027653.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.580761194229126,
|
|
"epoch": 0.9080698601673499,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000492847899407939,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.1872118517756462,
|
|
"num_tokens": 18038741.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.616208171844482,
|
|
"epoch": 0.9086314370753075,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004928378536378341,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.19227632284164428,
|
|
"num_tokens": 18049188.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.517804908752441,
|
|
"epoch": 0.909193013983265,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004928278009316877,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.19608282148838044,
|
|
"num_tokens": 18059979.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.528086566925049,
|
|
"epoch": 0.9097545908912226,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004928177412898195,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.19581507444381713,
|
|
"num_tokens": 18070712.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.545029258728027,
|
|
"epoch": 0.9103161677991801,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004928076747125499,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.199931001663208,
|
|
"num_tokens": 18081372.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.488630485534668,
|
|
"epoch": 0.9108777447071377,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004927976012001995,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.19492287933826447,
|
|
"num_tokens": 18093033.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.424843597412109,
|
|
"epoch": 0.9114393216150952,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004927875207530889,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.19880713671445846,
|
|
"num_tokens": 18104808.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.588267183303833,
|
|
"epoch": 0.9120008985230528,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004927774333715394,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.19131835401058198,
|
|
"num_tokens": 18115450.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.568840837478637,
|
|
"epoch": 0.9125624754310103,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004927673390558718,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.1925457626581192,
|
|
"num_tokens": 18127437.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.559585237503052,
|
|
"epoch": 0.9131240523389679,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004927572378064077,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.19866702407598497,
|
|
"num_tokens": 18137371.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.534928798675537,
|
|
"epoch": 0.9136856292469253,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004927471296234687,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.18997011035680772,
|
|
"num_tokens": 18148332.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.495602798461914,
|
|
"epoch": 0.9142472061548829,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004927370145073767,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.19650344997644426,
|
|
"num_tokens": 18159918.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.546139717102051,
|
|
"epoch": 0.9148087830628404,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004927268924584536,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.19667523950338364,
|
|
"num_tokens": 18170911.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.5385040760040285,
|
|
"epoch": 0.915370359970798,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004927167634770219,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.19550299793481826,
|
|
"num_tokens": 18183089.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.705757141113281,
|
|
"epoch": 0.9159319368787555,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000492706627563404,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.17788413316011428,
|
|
"num_tokens": 18195467.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.664833974838257,
|
|
"epoch": 0.9164935137867131,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004926964847179225,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.19646437764167785,
|
|
"num_tokens": 18206766.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.555621862411499,
|
|
"epoch": 0.9170550906946706,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004926863349409006,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.18730329871177673,
|
|
"num_tokens": 18217840.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.549395895004272,
|
|
"epoch": 0.9176166676026282,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004926761782326613,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.1900315374135971,
|
|
"num_tokens": 18229514.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.539832305908203,
|
|
"epoch": 0.9181782445105857,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004926660145935282,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.18763665854930878,
|
|
"num_tokens": 18241949.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.553296232223511,
|
|
"epoch": 0.9187398214185433,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004926558440238247,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.1925969749689102,
|
|
"num_tokens": 18252938.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.501591348648072,
|
|
"epoch": 0.9193013983265008,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004926456665238746,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.20001359134912491,
|
|
"num_tokens": 18263417.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.581185340881348,
|
|
"epoch": 0.9198629752344584,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004926354820940023,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.19356265366077424,
|
|
"num_tokens": 18275595.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.513322639465332,
|
|
"epoch": 0.9204245521424159,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004926252907345317,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.1961657866835594,
|
|
"num_tokens": 18287510.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.585029029846192,
|
|
"epoch": 0.9209861290503735,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004926150924457874,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.189619542658329,
|
|
"num_tokens": 18298764.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.461826658248901,
|
|
"epoch": 0.921547705958331,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004926048872280943,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.19885462075471877,
|
|
"num_tokens": 18310427.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.511860322952271,
|
|
"epoch": 0.9221092828662886,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000492594675081777,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.1912503346800804,
|
|
"num_tokens": 18322174.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.560267305374145,
|
|
"epoch": 0.9226708597742461,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000492584456007161,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.1939564660191536,
|
|
"num_tokens": 18332372.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.558639049530029,
|
|
"epoch": 0.9232324366822037,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004925742300045716,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.18960395455360413,
|
|
"num_tokens": 18343201.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.463238859176636,
|
|
"epoch": 0.9237940135901612,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004925639970743341,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.19404503852128982,
|
|
"num_tokens": 18354124.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.551952695846557,
|
|
"epoch": 0.9243555904981187,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004925537572167746,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.19655828028917313,
|
|
"num_tokens": 18365148.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.353328037261963,
|
|
"epoch": 0.9249171674060762,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004925435104322192,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.20167331993579865,
|
|
"num_tokens": 18376244.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.502984285354614,
|
|
"epoch": 0.9254787443140338,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492533256720994,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19579968601465225,
|
|
"num_tokens": 18386728.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.5439893245697025,
|
|
"epoch": 0.9260403212219913,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004925229960834256,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.190023934841156,
|
|
"num_tokens": 18397008.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.537467193603516,
|
|
"epoch": 0.9266018981299489,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004925127285198407,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.1979610562324524,
|
|
"num_tokens": 18408348.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.559618806838989,
|
|
"epoch": 0.9271634750379064,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000492502454030566,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.19667190462350845,
|
|
"num_tokens": 18419239.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.562794351577759,
|
|
"epoch": 0.927725051945864,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004924921726159288,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.19114402830600738,
|
|
"num_tokens": 18428918.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.5503216743469235,
|
|
"epoch": 0.9282866288538215,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004924818842762565,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.19460703581571578,
|
|
"num_tokens": 18440361.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.431864595413208,
|
|
"epoch": 0.9288482057617791,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004924715890118768,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.1982790485024452,
|
|
"num_tokens": 18450678.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.526260852813721,
|
|
"epoch": 0.9294097826697366,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004924612868231173,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.19375380724668503,
|
|
"num_tokens": 18462364.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.5141901016235355,
|
|
"epoch": 0.9299713595776942,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004924509777103059,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.19624577909708024,
|
|
"num_tokens": 18472896.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.6403216361999515,
|
|
"epoch": 0.9305329364856517,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004924406616737712,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.18872702419757842,
|
|
"num_tokens": 18484951.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.468882513046265,
|
|
"epoch": 0.9310945133936093,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004924303387138415,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.190618035197258,
|
|
"num_tokens": 18496006.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.577333211898804,
|
|
"epoch": 0.9316560903015668,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004924200088308455,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.1928957387804985,
|
|
"num_tokens": 18508069.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.680202531814575,
|
|
"epoch": 0.9322176672095244,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000492409672025112,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.18332927525043488,
|
|
"num_tokens": 18519746.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.597166538238525,
|
|
"epoch": 0.9327792441174819,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004923993282969703,
|
|
"loss": 5.3919,
|
|
"mean_token_accuracy": 0.19391626119613647,
|
|
"num_tokens": 18530249.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.510491561889649,
|
|
"epoch": 0.9333408210254395,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004923889776467495,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.19663116931915284,
|
|
"num_tokens": 18543306.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.548925256729126,
|
|
"epoch": 0.933902397933397,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004923786200747795,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.18921543955802916,
|
|
"num_tokens": 18555250.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.520346355438233,
|
|
"epoch": 0.9344639748413546,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00049236825558139,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.1940476804971695,
|
|
"num_tokens": 18566378.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.589100122451782,
|
|
"epoch": 0.9350255517493121,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004923578841669108,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.19008611142635345,
|
|
"num_tokens": 18576827.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.543495845794678,
|
|
"epoch": 0.9355871286572696,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004923475058316723,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.19625683426856994,
|
|
"num_tokens": 18589209.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.538624477386475,
|
|
"epoch": 0.9361487055652271,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004923371205760049,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.1962782308459282,
|
|
"num_tokens": 18599367.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.549010801315307,
|
|
"epoch": 0.9367102824731847,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004923267284002394,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.1880643978714943,
|
|
"num_tokens": 18610505.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.571760606765747,
|
|
"epoch": 0.9372718593811422,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004923163293047065,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.19299947321414948,
|
|
"num_tokens": 18622616.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.489560556411743,
|
|
"epoch": 0.9378334362890998,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004923059232897374,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.19942281842231752,
|
|
"num_tokens": 18634127.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.5971208095550535,
|
|
"epoch": 0.9383950131970573,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004922955103556633,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.1894705280661583,
|
|
"num_tokens": 18646196.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.565504455566407,
|
|
"epoch": 0.9389565901050149,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000492285090502816,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.1932822957634926,
|
|
"num_tokens": 18656911.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.56598482131958,
|
|
"epoch": 0.9395181670129724,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004922746637315272,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.19400292932987212,
|
|
"num_tokens": 18667553.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.488044404983521,
|
|
"epoch": 0.94007974392093,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004922642300421288,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.1984151467680931,
|
|
"num_tokens": 18678087.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.594152593612671,
|
|
"epoch": 0.9406413208288875,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000492253789434953,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.18852891623973847,
|
|
"num_tokens": 18689946.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.472784996032715,
|
|
"epoch": 0.9412028977368451,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004922433419103323,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.19805898815393447,
|
|
"num_tokens": 18700944.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.545402860641479,
|
|
"epoch": 0.9417644746448026,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004922328874685993,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.19176025688648224,
|
|
"num_tokens": 18712901.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.508438396453857,
|
|
"epoch": 0.9423260515527602,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004922224261100869,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.2016850456595421,
|
|
"num_tokens": 18724322.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.460203170776367,
|
|
"epoch": 0.9428876284607177,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004922119578351283,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.19443490207195283,
|
|
"num_tokens": 18735315.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.498114824295044,
|
|
"epoch": 0.9434492053686753,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004922014826440566,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.19754667729139327,
|
|
"num_tokens": 18747497.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.559070587158203,
|
|
"epoch": 0.9440107822766328,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004921910005372056,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1890599548816681,
|
|
"num_tokens": 18758835.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.514037370681763,
|
|
"epoch": 0.9445723591845904,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004921805115149088,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.20644183605909347,
|
|
"num_tokens": 18770325.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.42372989654541,
|
|
"epoch": 0.9451339360925479,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004921700155775002,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.20486821979284286,
|
|
"num_tokens": 18781204.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.44708833694458,
|
|
"epoch": 0.9456955130005055,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004921595127253142,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.20296051800251008,
|
|
"num_tokens": 18791899.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.456557559967041,
|
|
"epoch": 0.9462570899084629,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004921490029586852,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.19981097280979157,
|
|
"num_tokens": 18803043.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.5355486392974855,
|
|
"epoch": 0.9468186668164205,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004921384862779475,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.19596886336803437,
|
|
"num_tokens": 18814316.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.505113124847412,
|
|
"epoch": 0.947380243724378,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004921279626834363,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.1921657606959343,
|
|
"num_tokens": 18825490.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.583848571777343,
|
|
"epoch": 0.9479418206323356,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004921174321754865,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.19337199926376342,
|
|
"num_tokens": 18836479.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.5242596626281735,
|
|
"epoch": 0.9485033975402931,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004921068947544335,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.19336270689964294,
|
|
"num_tokens": 18848634.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.4738781452178955,
|
|
"epoch": 0.9490649744482507,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004920963504206128,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.1975503072142601,
|
|
"num_tokens": 18858451.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.5491477966308596,
|
|
"epoch": 0.9496265513562082,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049208579917436,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18220319598913193,
|
|
"num_tokens": 18869561.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.676888704299927,
|
|
"epoch": 0.9501881282641658,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004920752410160113,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.18645843714475632,
|
|
"num_tokens": 18880232.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.599009323120117,
|
|
"epoch": 0.9507497051721233,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004920646759459026,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.18963313698768616,
|
|
"num_tokens": 18892562.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.504174041748047,
|
|
"epoch": 0.9513112820800809,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004920541039643705,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.18966473489999772,
|
|
"num_tokens": 18903566.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.542617750167847,
|
|
"epoch": 0.9518728589880384,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004920435250717515,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.19363329261541368,
|
|
"num_tokens": 18914619.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.631953525543213,
|
|
"epoch": 0.952434435895996,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004920329392683826,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.1911033108830452,
|
|
"num_tokens": 18927039.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.64338002204895,
|
|
"epoch": 0.9529960128039535,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004920223465546006,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.18679868131875993,
|
|
"num_tokens": 18940449.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.570146608352661,
|
|
"epoch": 0.9535575897119111,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004920117469307429,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.19013803601264953,
|
|
"num_tokens": 18950798.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.474750137329101,
|
|
"epoch": 0.9541191666198686,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004920011403971471,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.19593947678804396,
|
|
"num_tokens": 18960958.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.484321451187133,
|
|
"epoch": 0.9546807435278262,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004919905269541508,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.19836883544921874,
|
|
"num_tokens": 18971890.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.442224788665771,
|
|
"epoch": 0.9552423204357837,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000491979906602092,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.20479062646627427,
|
|
"num_tokens": 18982309.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.548309564590454,
|
|
"epoch": 0.9558038973437413,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004919692793413089,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.18700776398181915,
|
|
"num_tokens": 18993648.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.492386817932129,
|
|
"epoch": 0.9563654742516988,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004919586451721396,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.20171947926282882,
|
|
"num_tokens": 19003613.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.536426067352295,
|
|
"epoch": 0.9569270511596563,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004919480040949229,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.19290098994970323,
|
|
"num_tokens": 19014720.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.575037574768066,
|
|
"epoch": 0.9574886280676138,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004919373561099977,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.1914821520447731,
|
|
"num_tokens": 19026635.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.535338544845581,
|
|
"epoch": 0.9580502049755714,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000491926701217703,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.18922464102506636,
|
|
"num_tokens": 19037433.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.514703226089478,
|
|
"epoch": 0.9586117818835289,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004919160394183779,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.19363785088062285,
|
|
"num_tokens": 19047351.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.409635305404663,
|
|
"epoch": 0.9591733587914865,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000491905370712362,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19300709515810013,
|
|
"num_tokens": 19058561.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.536706495285034,
|
|
"epoch": 0.959734935699444,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004918946950999949,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.18782899081707,
|
|
"num_tokens": 19069877.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.588172721862793,
|
|
"epoch": 0.9602965126074016,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004918840125816167,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.1946302592754364,
|
|
"num_tokens": 19081962.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.58874249458313,
|
|
"epoch": 0.9608580895153591,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918733231575673,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.19288556277751923,
|
|
"num_tokens": 19092955.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.56013126373291,
|
|
"epoch": 0.9614196664233167,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004918626268281874,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.20831031501293182,
|
|
"num_tokens": 19103521.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.391353416442871,
|
|
"epoch": 0.9619812433312742,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004918519235938171,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.20273831635713577,
|
|
"num_tokens": 19114190.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.567143535614013,
|
|
"epoch": 0.9625428202392318,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004918412134547976,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.19603607505559922,
|
|
"num_tokens": 19123815.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.591982984542847,
|
|
"epoch": 0.9631043971471893,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004918304964114696,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.189672289788723,
|
|
"num_tokens": 19135805.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.529873991012574,
|
|
"epoch": 0.9636659740551469,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004918197724641747,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.19721402376890182,
|
|
"num_tokens": 19146656.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.496527576446534,
|
|
"epoch": 0.9642275509631044,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000491809041613254,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.18851378262043,
|
|
"num_tokens": 19158271.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.488157129287719,
|
|
"epoch": 0.964789127871062,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004917983038590495,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.19524765014648438,
|
|
"num_tokens": 19168439.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.5969719886779785,
|
|
"epoch": 0.9653507047790195,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004917875592019028,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.19436133950948714,
|
|
"num_tokens": 19179411.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.53089280128479,
|
|
"epoch": 0.9659122816869771,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004917768076421561,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.1942594289779663,
|
|
"num_tokens": 19189377.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.472340726852417,
|
|
"epoch": 0.9664738585949346,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004917660491801518,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.19300363808870316,
|
|
"num_tokens": 19200662.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.553213977813721,
|
|
"epoch": 0.9670354355028922,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004917552838162324,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.19651206880807875,
|
|
"num_tokens": 19211535.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.52828950881958,
|
|
"epoch": 0.9675970124108496,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004917445115507408,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.20595233887434006,
|
|
"num_tokens": 19223402.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.3730659008026125,
|
|
"epoch": 0.9681585893188072,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004917337323840198,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.1950602039694786,
|
|
"num_tokens": 19234976.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.401967573165893,
|
|
"epoch": 0.9687201662267647,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004917229463164128,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.20632344633340835,
|
|
"num_tokens": 19247328.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.549596071243286,
|
|
"epoch": 0.9692817431347223,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004917121533482631,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.19308900684118271,
|
|
"num_tokens": 19259021.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.494666910171508,
|
|
"epoch": 0.9698433200426798,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004917013534799144,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.19566326588392258,
|
|
"num_tokens": 19270021.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.519558572769165,
|
|
"epoch": 0.9704048969506374,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004916905467117104,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.1988176554441452,
|
|
"num_tokens": 19281520.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.510553073883057,
|
|
"epoch": 0.9709664738585949,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004916797330439955,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.19501383155584334,
|
|
"num_tokens": 19292761.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.512772941589356,
|
|
"epoch": 0.9715280507665525,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004916689124771138,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.19256801158189774,
|
|
"num_tokens": 19305022.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.657002687454224,
|
|
"epoch": 0.97208962767451,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004916580850114099,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.18710665106773378,
|
|
"num_tokens": 19316162.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.7019024848937985,
|
|
"epoch": 0.9726512045824676,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004916472506472286,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.1794895797967911,
|
|
"num_tokens": 19327015.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.466433572769165,
|
|
"epoch": 0.9732127814904251,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004916364093849147,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.1921481266617775,
|
|
"num_tokens": 19338384.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.4878956317901615,
|
|
"epoch": 0.9737743583983827,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004916255612248136,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.19537662714719772,
|
|
"num_tokens": 19349846.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.574201202392578,
|
|
"epoch": 0.9743359353063402,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004916147061672706,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.19864263832569123,
|
|
"num_tokens": 19361399.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.46953387260437,
|
|
"epoch": 0.9748975122142978,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004916038442126314,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.1941774532198906,
|
|
"num_tokens": 19371990.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.450600242614746,
|
|
"epoch": 0.9754590891222553,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004915929753612416,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.189889794588089,
|
|
"num_tokens": 19383135.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.57188606262207,
|
|
"epoch": 0.9760206660302129,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004915820996134477,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.19721569567918779,
|
|
"num_tokens": 19393942.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.5107481479644775,
|
|
"epoch": 0.9765822429381704,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004915712169695956,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.20355969816446304,
|
|
"num_tokens": 19404255.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.482605981826782,
|
|
"epoch": 0.977143819846128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000491560327430032,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.19369806498289108,
|
|
"num_tokens": 19415425.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.478675651550293,
|
|
"epoch": 0.9777053967540855,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004915494309951035,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.1986789420247078,
|
|
"num_tokens": 19426050.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.534181356430054,
|
|
"epoch": 0.9782669736620431,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004915385276651573,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.18844764679670334,
|
|
"num_tokens": 19437471.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.606834268569946,
|
|
"epoch": 0.9788285505700005,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004915276174405403,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.19710880815982817,
|
|
"num_tokens": 19449569.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.556399822235107,
|
|
"epoch": 0.9793901274779581,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004915167003215999,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.1865055575966835,
|
|
"num_tokens": 19461630.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.5164985179901125,
|
|
"epoch": 0.9799517043859156,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004915057763086838,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.19505047500133516,
|
|
"num_tokens": 19472626.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.460313415527343,
|
|
"epoch": 0.9805132812938732,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049149484540214,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.19551117867231368,
|
|
"num_tokens": 19483141.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.532111597061157,
|
|
"epoch": 0.9810748582018307,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004914839076023161,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.1976611390709877,
|
|
"num_tokens": 19495052.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.570014095306396,
|
|
"epoch": 0.9816364351097883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004914729629095609,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.18996083587408066,
|
|
"num_tokens": 19506911.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.411376714706421,
|
|
"epoch": 0.9821980120177458,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004914620113242224,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.2014763057231903,
|
|
"num_tokens": 19517812.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.507891321182251,
|
|
"epoch": 0.9827595889257034,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004914510528466495,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.1972219705581665,
|
|
"num_tokens": 19529857.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.512612152099609,
|
|
"epoch": 0.9833211658336609,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004914400874771913,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.19361001551151275,
|
|
"num_tokens": 19541082.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.474521493911743,
|
|
"epoch": 0.9838827427416185,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004914291152161967,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.20073695182800294,
|
|
"num_tokens": 19551266.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.603118085861206,
|
|
"epoch": 0.984444319649576,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000491418136064015,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.18993972539901732,
|
|
"num_tokens": 19563381.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.642356920242309,
|
|
"epoch": 0.9850058965575336,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000491407150020996,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.19175548255443572,
|
|
"num_tokens": 19575078.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.5324841976165775,
|
|
"epoch": 0.9855674734654911,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004913961570874895,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.195944245159626,
|
|
"num_tokens": 19585273.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.422174787521362,
|
|
"epoch": 0.9861290503734487,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913851572638453,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.19594420045614241,
|
|
"num_tokens": 19594245.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.567112445831299,
|
|
"epoch": 0.9866906272814062,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004913741505504138,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.1926957055926323,
|
|
"num_tokens": 19604920.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.595992755889893,
|
|
"epoch": 0.9872522041893638,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004913631369475454,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.18519087582826615,
|
|
"num_tokens": 19616592.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.646543216705322,
|
|
"epoch": 0.9878137810973213,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004913521164555909,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.18781450092792512,
|
|
"num_tokens": 19627359.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.562744998931885,
|
|
"epoch": 0.9883753580052789,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000491341089074901,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.19434441477060319,
|
|
"num_tokens": 19639685.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.433221101760864,
|
|
"epoch": 0.9889369349132364,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000491330054805827,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.20772592425346376,
|
|
"num_tokens": 19650525.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.417998838424682,
|
|
"epoch": 0.9894985118211939,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004913190136487201,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.20130652636289598,
|
|
"num_tokens": 19662241.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.582166242599487,
|
|
"epoch": 0.9900600887291514,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004913079656039318,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.19600186944007875,
|
|
"num_tokens": 19673752.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.505742835998535,
|
|
"epoch": 0.990621665637109,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004912969106718142,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.19588230699300765,
|
|
"num_tokens": 19685309.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.472543382644654,
|
|
"epoch": 0.9911832425450665,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000491285848852719,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.1931264206767082,
|
|
"num_tokens": 19697391.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.5647358894348145,
|
|
"epoch": 0.9917448194530241,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004912747801469984,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.19110726416110993,
|
|
"num_tokens": 19707426.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.604293870925903,
|
|
"epoch": 0.9923063963609816,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000491263704555005,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.1885225474834442,
|
|
"num_tokens": 19719800.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.464602088928222,
|
|
"epoch": 0.9928679732689392,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004912526220770913,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.190777026116848,
|
|
"num_tokens": 19731600.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.548013734817505,
|
|
"epoch": 0.9934295501768967,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004912415327136103,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.19666232466697692,
|
|
"num_tokens": 19742610.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.611991453170776,
|
|
"epoch": 0.9939911270848543,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000491230436464915,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.18092975169420242,
|
|
"num_tokens": 19754207.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.527308797836303,
|
|
"epoch": 0.9945527039928118,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004912193333313589,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.20014742463827134,
|
|
"num_tokens": 19765894.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.51915168762207,
|
|
"epoch": 0.9951142809007694,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004912082233132951,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.19393627494573593,
|
|
"num_tokens": 19777867.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.453359842300415,
|
|
"epoch": 0.9956758578087269,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004911971064110778,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.20460631996393203,
|
|
"num_tokens": 19788346.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.567843103408814,
|
|
"epoch": 0.9962374347166845,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004911859826250607,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.19829422384500503,
|
|
"num_tokens": 19799752.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.520086097717285,
|
|
"epoch": 0.996799011624642,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004911748519555981,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.1933576673269272,
|
|
"num_tokens": 19810387.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.482093811035156,
|
|
"epoch": 0.9973605885325996,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004911637144030444,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.2000111773610115,
|
|
"num_tokens": 19822092.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.602532529830933,
|
|
"epoch": 0.9979221654405571,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004911525699677541,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.18868452161550522,
|
|
"num_tokens": 19833731.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.556239032745362,
|
|
"epoch": 0.9984837423485147,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004911414186500822,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.19372820407152175,
|
|
"num_tokens": 19845101.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.566931819915771,
|
|
"epoch": 0.9990453192564722,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004911302604503837,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.19033107310533523,
|
|
"num_tokens": 19857006.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.492543649673462,
|
|
"epoch": 0.9996068961644298,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004911190953690139,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.20282880812883378,
|
|
"num_tokens": 19868007.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.636637952592638,
|
|
"epoch": 1.0001123153815914,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004911079234063284,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.19759436945120493,
|
|
"num_tokens": 19877897.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.5367574214935305,
|
|
"epoch": 1.000673892289549,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004910967445626826,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.20178501456975936,
|
|
"num_tokens": 19888449.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.504949903488159,
|
|
"epoch": 1.0012354691975065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004910855588384327,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.19473289251327514,
|
|
"num_tokens": 19898998.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.574651193618775,
|
|
"epoch": 1.0017970461054642,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004910743662339348,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.20060208290815354,
|
|
"num_tokens": 19910369.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.584370088577271,
|
|
"epoch": 1.0023586230134216,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004910631667495452,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.20232826024293898,
|
|
"num_tokens": 19921936.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.520488834381103,
|
|
"epoch": 1.0029201999213793,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004910519603856207,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.1978306621313095,
|
|
"num_tokens": 19933943.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.445270347595215,
|
|
"epoch": 1.0034817768293367,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004910407471425179,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.20613135099411012,
|
|
"num_tokens": 19944377.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.4640827655792235,
|
|
"epoch": 1.0040433537372944,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000491029527020594,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.1998417317867279,
|
|
"num_tokens": 19954865.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.414384746551514,
|
|
"epoch": 1.0046049306452518,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004910183000202061,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.20970811694860458,
|
|
"num_tokens": 19965021.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.508528232574463,
|
|
"epoch": 1.0051665075532095,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004910070661417119,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.2020757704973221,
|
|
"num_tokens": 19977068.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.488288688659668,
|
|
"epoch": 1.005728084461167,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004909958253854687,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19643874913454057,
|
|
"num_tokens": 19987994.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.531931591033936,
|
|
"epoch": 1.0062896613691246,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004909845777518347,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.1945202425122261,
|
|
"num_tokens": 19998598.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.491772985458374,
|
|
"epoch": 1.006851238277082,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004909733232411681,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20452140271663666,
|
|
"num_tokens": 20008881.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.464196586608887,
|
|
"epoch": 1.0074128151850397,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004909620618538271,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.2004571110010147,
|
|
"num_tokens": 20019105.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.503272438049317,
|
|
"epoch": 1.007974392092997,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004909507935901702,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.19685523062944413,
|
|
"num_tokens": 20031805.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.505469274520874,
|
|
"epoch": 1.0085359690009548,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909395184505564,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.20482919216156006,
|
|
"num_tokens": 20041493.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.443944120407105,
|
|
"epoch": 1.0090975459089122,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909282364353445,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.2027145132422447,
|
|
"num_tokens": 20052489.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.445522117614746,
|
|
"epoch": 1.0096591228168699,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004909169475448938,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.20171973258256912,
|
|
"num_tokens": 20064252.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.497849702835083,
|
|
"epoch": 1.0102206997248273,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004909056517795638,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.20151090621948242,
|
|
"num_tokens": 20075171.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.44132776260376,
|
|
"epoch": 1.010782276632785,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004908943491397141,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.19850120395421983,
|
|
"num_tokens": 20085746.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.010782276632785,
|
|
"eval_entropy": 5.250292036131789,
|
|
"eval_loss": 5.334287166595459,
|
|
"eval_mean_token_accuracy": 0.20153940353914424,
|
|
"eval_num_tokens": 20085746.0,
|
|
"eval_runtime": 18.5429,
|
|
"eval_samples_per_second": 1672.497,
|
|
"eval_steps_per_second": 209.082,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.4410419940948485,
|
|
"epoch": 1.0113438535407424,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004908830396257045,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.19719308912754058,
|
|
"num_tokens": 20097435.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.482279872894287,
|
|
"epoch": 1.0119054304486998,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004908717232378953,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.1948664203286171,
|
|
"num_tokens": 20108100.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.543497085571289,
|
|
"epoch": 1.0124670073566575,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004908603999766467,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.1986445054411888,
|
|
"num_tokens": 20119042.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.518305063247681,
|
|
"epoch": 1.013028584264615,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004908490698423191,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.1947011813521385,
|
|
"num_tokens": 20130275.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.502834463119507,
|
|
"epoch": 1.0135901611725726,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004908377328352736,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.19602491855621337,
|
|
"num_tokens": 20142523.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.481188154220581,
|
|
"epoch": 1.01415173808053,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004908263889558709,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.20224478244781494,
|
|
"num_tokens": 20153732.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.563956451416016,
|
|
"epoch": 1.0147133149884877,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004908150382044722,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.1976298898458481,
|
|
"num_tokens": 20165136.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.457227039337158,
|
|
"epoch": 1.0152748918964452,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000490803680581439,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.20783225148916246,
|
|
"num_tokens": 20175326.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.4330816745758055,
|
|
"epoch": 1.0158364688044028,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000490792316087133,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.20761604011058807,
|
|
"num_tokens": 20186678.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.448330879211426,
|
|
"epoch": 1.0163980457123603,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004907809447219158,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.20360376238822936,
|
|
"num_tokens": 20196696.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.507216835021973,
|
|
"epoch": 1.016959622620318,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004907695664861498,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.20406801551580428,
|
|
"num_tokens": 20207566.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.487580680847168,
|
|
"epoch": 1.0175211995282754,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004907581813801971,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.19629068821668624,
|
|
"num_tokens": 20218233.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.463364219665527,
|
|
"epoch": 1.018082776436233,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004907467894044202,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20045018047094346,
|
|
"num_tokens": 20228524.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.448998928070068,
|
|
"epoch": 1.0186443533441905,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004907353905591817,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.19845051020383836,
|
|
"num_tokens": 20240821.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.489661836624146,
|
|
"epoch": 1.0192059302521481,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000490723984844845,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.20146978497505189,
|
|
"num_tokens": 20252282.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.511700630187988,
|
|
"epoch": 1.0197675071601056,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004907125722617727,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.20119000375270843,
|
|
"num_tokens": 20263462.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.482121849060059,
|
|
"epoch": 1.0203290840680632,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004907011528103285,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19962276369333268,
|
|
"num_tokens": 20275062.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.530120754241944,
|
|
"epoch": 1.0208906609760207,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004906897264908759,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.19897931814193726,
|
|
"num_tokens": 20286243.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.4663170337677,
|
|
"epoch": 1.0214522378839783,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004906782933037789,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.20016021728515626,
|
|
"num_tokens": 20296929.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.4526386737823485,
|
|
"epoch": 1.0220138147919358,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004906668532494012,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.20495461523532868,
|
|
"num_tokens": 20308354.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.5620592594146725,
|
|
"epoch": 1.0225753916998932,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004906554063281074,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.19592114090919494,
|
|
"num_tokens": 20319487.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.427632188796997,
|
|
"epoch": 1.0231369686078509,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004906439525402618,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.2067782312631607,
|
|
"num_tokens": 20329967.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.530966806411743,
|
|
"epoch": 1.0236985455158083,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004906324918862291,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.19134874939918517,
|
|
"num_tokens": 20341442.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.559245300292969,
|
|
"epoch": 1.024260122423766,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004906210243663742,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.18759590685367583,
|
|
"num_tokens": 20352818.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.557690906524658,
|
|
"epoch": 1.0248216993317234,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004906095499810622,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.2003881424665451,
|
|
"num_tokens": 20364787.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.486217403411866,
|
|
"epoch": 1.025383276239681,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004905980687306586,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.2119112029671669,
|
|
"num_tokens": 20375491.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.528737354278564,
|
|
"epoch": 1.0259448531476385,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004905865806155288,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.19983354806900025,
|
|
"num_tokens": 20386270.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.553527879714966,
|
|
"epoch": 1.0265064300555962,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004905750856360387,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.19466331601142883,
|
|
"num_tokens": 20397953.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.550909996032715,
|
|
"epoch": 1.0270680069635536,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004905635837925543,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.19577167481184005,
|
|
"num_tokens": 20409847.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.538588428497315,
|
|
"epoch": 1.0276295838715113,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004905520750854418,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.1989851713180542,
|
|
"num_tokens": 20420737.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.482498121261597,
|
|
"epoch": 1.0281911607794687,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004905405595150674,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.19797644019126892,
|
|
"num_tokens": 20432395.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.471064615249634,
|
|
"epoch": 1.0287527376874264,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004905290370817982,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.20235833674669265,
|
|
"num_tokens": 20442964.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.484366178512573,
|
|
"epoch": 1.0293143145953838,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000490517507786001,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.1925534725189209,
|
|
"num_tokens": 20454050.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.521790456771851,
|
|
"epoch": 1.0298758915033415,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004905059716280425,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.19311539977788925,
|
|
"num_tokens": 20465335.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.510196018218994,
|
|
"epoch": 1.030437468411299,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004904944286082904,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.19910498410463334,
|
|
"num_tokens": 20476781.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.521581411361694,
|
|
"epoch": 1.0309990453192566,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004904828787271121,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.19900746643543243,
|
|
"num_tokens": 20488599.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.419762468338012,
|
|
"epoch": 1.031560622227214,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004904713219848753,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.20661476403474807,
|
|
"num_tokens": 20498215.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.483515501022339,
|
|
"epoch": 1.0321221991351717,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004904597583819481,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.20741443634033202,
|
|
"num_tokens": 20509764.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.643636274337768,
|
|
"epoch": 1.032683776043129,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004904481879186987,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.19489774852991104,
|
|
"num_tokens": 20521582.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.482099723815918,
|
|
"epoch": 1.0332453529510865,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004904366105954954,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.1953733593225479,
|
|
"num_tokens": 20532050.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.508026027679444,
|
|
"epoch": 1.0338069298590442,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004904250264127067,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.1957683339715004,
|
|
"num_tokens": 20543733.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.5488114833831785,
|
|
"epoch": 1.0343685067670016,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004904134353707018,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.19894588440656663,
|
|
"num_tokens": 20554898.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.450367212295532,
|
|
"epoch": 1.0349300836749593,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004904018374698496,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.20586577653884888,
|
|
"num_tokens": 20565243.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.461126852035522,
|
|
"epoch": 1.0354916605829168,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004903902327105191,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.2046682506799698,
|
|
"num_tokens": 20575321.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.534661293029785,
|
|
"epoch": 1.0360532374908744,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004903786210930803,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.19104113429784775,
|
|
"num_tokens": 20586450.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.596548080444336,
|
|
"epoch": 1.0366148143988319,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004903670026179025,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.20320384353399276,
|
|
"num_tokens": 20596996.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.515645360946655,
|
|
"epoch": 1.0371763913067895,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000490355377285356,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.1962485730648041,
|
|
"num_tokens": 20609136.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.530973243713379,
|
|
"epoch": 1.037737968214747,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903437450958106,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.19661697000265121,
|
|
"num_tokens": 20620246.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.435258626937866,
|
|
"epoch": 1.0382995451227046,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004903321060496369,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.2004723757505417,
|
|
"num_tokens": 20631678.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.4916645050048825,
|
|
"epoch": 1.038861122030662,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004903204601472054,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.20778537839651107,
|
|
"num_tokens": 20643287.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.454440641403198,
|
|
"epoch": 1.0394226989386197,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004903088073888869,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.20316162705421448,
|
|
"num_tokens": 20655091.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.5085302829742435,
|
|
"epoch": 1.0399842758465772,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004902971477750526,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.201905457675457,
|
|
"num_tokens": 20665043.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.4888711929321286,
|
|
"epoch": 1.0405458527545348,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004902854813060736,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.20756309777498244,
|
|
"num_tokens": 20675225.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.500904321670532,
|
|
"epoch": 1.0411074296624923,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004902738079823213,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.19768911749124526,
|
|
"num_tokens": 20686542.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.4465008735656735,
|
|
"epoch": 1.04166900657045,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004902621278041674,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.200796277821064,
|
|
"num_tokens": 20697926.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.500946950912476,
|
|
"epoch": 1.0422305834784074,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004902504407719839,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.19970303028821945,
|
|
"num_tokens": 20707890.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.508155155181885,
|
|
"epoch": 1.042792160386365,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004902387468861429,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.19615509510040283,
|
|
"num_tokens": 20719554.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.454964590072632,
|
|
"epoch": 1.0433537372943225,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004902270461470169,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.20504285842180253,
|
|
"num_tokens": 20730899.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.491695976257324,
|
|
"epoch": 1.04391531420228,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000490215338554978,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.19712646007537843,
|
|
"num_tokens": 20741839.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.514626216888428,
|
|
"epoch": 1.0444768911102376,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004902036241103994,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.2025056853890419,
|
|
"num_tokens": 20753199.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.556609869003296,
|
|
"epoch": 1.045038468018195,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004901919028136539,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.19643863588571547,
|
|
"num_tokens": 20764827.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.543943548202515,
|
|
"epoch": 1.0456000449261527,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004901801746651147,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.2053193300962448,
|
|
"num_tokens": 20774953.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.474718427658081,
|
|
"epoch": 1.04616162183411,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004901684396651554,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.20242761373519896,
|
|
"num_tokens": 20784428.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.520321798324585,
|
|
"epoch": 1.0467231987420678,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004901566978141494,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.20010230988264083,
|
|
"num_tokens": 20795672.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.544550895690918,
|
|
"epoch": 1.0472847756500252,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004901449491124708,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.19763281643390657,
|
|
"num_tokens": 20806972.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.512213659286499,
|
|
"epoch": 1.0478463525579829,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004901331935604936,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.19184947907924652,
|
|
"num_tokens": 20817867.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.4209388256072994,
|
|
"epoch": 1.0484079294659403,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000490121431158592,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.20379920452833175,
|
|
"num_tokens": 20829205.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.492325401306152,
|
|
"epoch": 1.048969506373898,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004901096619071407,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19882977306842803,
|
|
"num_tokens": 20840478.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.48389835357666,
|
|
"epoch": 1.0495310832818554,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004900978858065142,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.20481607764959336,
|
|
"num_tokens": 20850752.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.474141597747803,
|
|
"epoch": 1.050092660189813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004900861028570877,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.19434157013893127,
|
|
"num_tokens": 20862261.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.4965735912323,
|
|
"epoch": 1.0506542370977705,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004900743130592362,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.204218989610672,
|
|
"num_tokens": 20872604.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.437438821792602,
|
|
"epoch": 1.0512158140057282,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004900625164133351,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.21403434127569199,
|
|
"num_tokens": 20882751.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.512645816802978,
|
|
"epoch": 1.0517773909136856,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004900507129197601,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.1953686311841011,
|
|
"num_tokens": 20893809.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.588176441192627,
|
|
"epoch": 1.0523389678216433,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004900389025788871,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.20627430379390715,
|
|
"num_tokens": 20904201.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.513037395477295,
|
|
"epoch": 1.0529005447296007,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000490027085391092,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.19336402118206025,
|
|
"num_tokens": 20915226.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.459571981430054,
|
|
"epoch": 1.0534621216375584,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000490015261356751,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.19386365115642548,
|
|
"num_tokens": 20926040.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.533639812469483,
|
|
"epoch": 1.0540236985455158,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004900034304762408,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.2063665881752968,
|
|
"num_tokens": 20937051.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.51710615158081,
|
|
"epoch": 1.0545852754534732,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000489991592749938,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.2007290944457054,
|
|
"num_tokens": 20947810.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.456969404220581,
|
|
"epoch": 1.055146852361431,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004899797481782193,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.1940768241882324,
|
|
"num_tokens": 20958307.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.423482894897461,
|
|
"epoch": 1.0557084292693883,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004899678967614623,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20511654913425445,
|
|
"num_tokens": 20969493.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.507602119445801,
|
|
"epoch": 1.056270006177346,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004899560385000439,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.19966696798801423,
|
|
"num_tokens": 20980224.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.498609590530395,
|
|
"epoch": 1.0568315830853034,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000489944173394342,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.20217224359512329,
|
|
"num_tokens": 20991282.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.544124364852905,
|
|
"epoch": 1.0573931599932611,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004899323014447342,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.196702940762043,
|
|
"num_tokens": 21002395.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.465450477600098,
|
|
"epoch": 1.0579547369012186,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004899204226515985,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.2016814410686493,
|
|
"num_tokens": 21014136.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.496905088424683,
|
|
"epoch": 1.0585163138091762,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004899085370153133,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.19692542105913163,
|
|
"num_tokens": 21025637.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.609961986541748,
|
|
"epoch": 1.0590778907171337,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004898966445362569,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.19021605104207992,
|
|
"num_tokens": 21036393.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.583573865890503,
|
|
"epoch": 1.0596394676250913,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004898847452148079,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.19952155500650406,
|
|
"num_tokens": 21047339.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.571530866622925,
|
|
"epoch": 1.0602010445330488,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004898728390513454,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.19014095664024352,
|
|
"num_tokens": 21059427.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.514931106567383,
|
|
"epoch": 1.0607626214410064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004898609260462483,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.19008011966943741,
|
|
"num_tokens": 21068666.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.521870851516724,
|
|
"epoch": 1.0613241983489639,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004898490061998961,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.1966691330075264,
|
|
"num_tokens": 21080161.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.4940211296081545,
|
|
"epoch": 1.0618857752569215,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004898370795126681,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.18436074554920195,
|
|
"num_tokens": 21092363.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.460897922515869,
|
|
"epoch": 1.062447352164879,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004898251459849441,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.2044389009475708,
|
|
"num_tokens": 21103683.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.47303957939148,
|
|
"epoch": 1.0630089290728366,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004898132056171041,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.19934820234775544,
|
|
"num_tokens": 21115110.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.479731655120849,
|
|
"epoch": 1.063570505980794,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004898012584095285,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.20533456057310104,
|
|
"num_tokens": 21124327.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.410903263092041,
|
|
"epoch": 1.0641320828887517,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004897893043625975,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.20332737565040587,
|
|
"num_tokens": 21135542.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.450322246551513,
|
|
"epoch": 1.0646936597967092,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004897773434766917,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.20389195382595063,
|
|
"num_tokens": 21147621.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.47804479598999,
|
|
"epoch": 1.0652552367046666,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000489765375752192,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.19994601458311081,
|
|
"num_tokens": 21159725.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.462198066711426,
|
|
"epoch": 1.0658168136126243,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004897534011894793,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.20332340151071548,
|
|
"num_tokens": 21171303.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.601372385025025,
|
|
"epoch": 1.0663783905205817,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004897414197889352,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.19404581785202027,
|
|
"num_tokens": 21183376.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.500764799118042,
|
|
"epoch": 1.0669399674285394,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000489729431550941,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.19385466873645782,
|
|
"num_tokens": 21194365.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.367282915115356,
|
|
"epoch": 1.0675015443364968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004897174364758783,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.20965545922517775,
|
|
"num_tokens": 21206440.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.389557552337647,
|
|
"epoch": 1.0680631212444545,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004897054345641291,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.20427985340356827,
|
|
"num_tokens": 21217188.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.445877599716186,
|
|
"epoch": 1.068624698152412,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004896934258160757,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.19730723649263382,
|
|
"num_tokens": 21227716.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.5419886112213135,
|
|
"epoch": 1.0691862750603696,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004896814102321004,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.19147847592830658,
|
|
"num_tokens": 21241258.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.468100214004517,
|
|
"epoch": 1.069747851968327,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004896693878125857,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.2070148691534996,
|
|
"num_tokens": 21252543.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.479246616363525,
|
|
"epoch": 1.0703094288762847,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004896573585579144,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.1918076604604721,
|
|
"num_tokens": 21264829.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.576599597930908,
|
|
"epoch": 1.070871005784242,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004896453224684695,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.19655757993459702,
|
|
"num_tokens": 21276240.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.513744974136353,
|
|
"epoch": 1.0714325826921998,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896332795446345,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.1970713585615158,
|
|
"num_tokens": 21288877.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.5188404560089115,
|
|
"epoch": 1.0719941596001572,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004896212297867924,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.19586081355810164,
|
|
"num_tokens": 21300147.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.504089069366455,
|
|
"epoch": 1.0725557365081149,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004896091731953271,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20204968452453614,
|
|
"num_tokens": 21309731.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.452112054824829,
|
|
"epoch": 1.0731173134160723,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004895971097706227,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.20036691576242446,
|
|
"num_tokens": 21320358.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.407446575164795,
|
|
"epoch": 1.07367889032403,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004895850395130629,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.20726782083511353,
|
|
"num_tokens": 21331077.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.49783763885498,
|
|
"epoch": 1.0742404672319874,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004895729624230323,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.20174524039030076,
|
|
"num_tokens": 21341304.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.522320508956909,
|
|
"epoch": 1.074802044139945,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004895608785009153,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.20093540102243423,
|
|
"num_tokens": 21353663.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.4882519245147705,
|
|
"epoch": 1.0753636210479025,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004895487877470969,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.1982122004032135,
|
|
"num_tokens": 21364987.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.433423328399658,
|
|
"epoch": 1.07592519795586,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004895366901619617,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.1996244505047798,
|
|
"num_tokens": 21376169.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.458646297454834,
|
|
"epoch": 1.0764867748638176,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004895245857458951,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.19908357709646224,
|
|
"num_tokens": 21387141.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.477552700042724,
|
|
"epoch": 1.077048351771775,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004895124744992825,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.20181487798690795,
|
|
"num_tokens": 21396804.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.413079929351807,
|
|
"epoch": 1.0776099286797327,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004895003564225095,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.20264637023210524,
|
|
"num_tokens": 21406948.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.456643009185791,
|
|
"epoch": 1.0781715055876901,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004894882315159621,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.20026180595159532,
|
|
"num_tokens": 21417560.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.503844118118286,
|
|
"epoch": 1.0787330824956478,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000489476099780026,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.2074314534664154,
|
|
"num_tokens": 21428596.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.504678201675415,
|
|
"epoch": 1.0792946594036052,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004894639612150879,
|
|
"loss": 5.2519,
|
|
"mean_token_accuracy": 0.19095519036054612,
|
|
"num_tokens": 21440004.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.477089548110962,
|
|
"epoch": 1.079856236311563,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004894518158215339,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.20255612432956696,
|
|
"num_tokens": 21451423.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.509946632385254,
|
|
"epoch": 1.0804178132195204,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000489439663599751,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.19738221168518066,
|
|
"num_tokens": 21462065.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.481210231781006,
|
|
"epoch": 1.080979390127478,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000489427504550126,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.20122058242559432,
|
|
"num_tokens": 21473476.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.53668999671936,
|
|
"epoch": 1.0815409670354355,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004894153386730462,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.19648052453994752,
|
|
"num_tokens": 21485591.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.556612586975097,
|
|
"epoch": 1.0821025439433931,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004894031659688988,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.18725701421499252,
|
|
"num_tokens": 21497016.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.500889825820923,
|
|
"epoch": 1.0826641208513506,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004893909864380714,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.203596892952919,
|
|
"num_tokens": 21508179.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.551057958602906,
|
|
"epoch": 1.0832256977593082,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000489378800080952,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.19090113788843155,
|
|
"num_tokens": 21520053.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.555256271362305,
|
|
"epoch": 1.0837872746672657,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004893666068979283,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.20505622625350953,
|
|
"num_tokens": 21530746.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.490418386459351,
|
|
"epoch": 1.0843488515752233,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004893544068893887,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.19350924342870712,
|
|
"num_tokens": 21540829.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.4777881622314455,
|
|
"epoch": 1.0849104284831808,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004893422000557217,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.20501092970371246,
|
|
"num_tokens": 21552337.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.47703742980957,
|
|
"epoch": 1.0854720053911384,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004893299863973159,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.20691147148609162,
|
|
"num_tokens": 21563752.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.595142364501953,
|
|
"epoch": 1.0860335822990959,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004893177659145601,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.19652421176433563,
|
|
"num_tokens": 21574834.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.52602105140686,
|
|
"epoch": 1.0865951592070533,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004893055386078438,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.19250109940767288,
|
|
"num_tokens": 21586674.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.5138664722442625,
|
|
"epoch": 1.087156736115011,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004892933044775558,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.2068254232406616,
|
|
"num_tokens": 21595998.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.530516481399536,
|
|
"epoch": 1.0877183130229684,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004892810635240859,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19769232273101806,
|
|
"num_tokens": 21607122.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.4809962749481205,
|
|
"epoch": 1.088279889930926,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004892688157478238,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.20128984600305558,
|
|
"num_tokens": 21618780.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.501584196090699,
|
|
"epoch": 1.0888414668388835,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004892565611491597,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.19764287024736404,
|
|
"num_tokens": 21628868.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.510531234741211,
|
|
"epoch": 1.0894030437468412,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004892442997284834,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.2131202444434166,
|
|
"num_tokens": 21640189.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.5254988193511965,
|
|
"epoch": 1.0899646206547986,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004892320314861855,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.1985717833042145,
|
|
"num_tokens": 21651452.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.390081071853638,
|
|
"epoch": 1.0905261975627563,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004892197564226568,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.20276168435811998,
|
|
"num_tokens": 21662555.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.492911911010742,
|
|
"epoch": 1.0910877744707137,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004892074745382878,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.20499537289142608,
|
|
"num_tokens": 21673087.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.521473979949951,
|
|
"epoch": 1.0916493513786714,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004891951858334698,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.1981431007385254,
|
|
"num_tokens": 21684084.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.429476976394653,
|
|
"epoch": 1.0922109282866288,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004891828903085939,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.20517684668302535,
|
|
"num_tokens": 21695765.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.502168464660644,
|
|
"epoch": 1.0927725051945865,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004891705879640518,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.19582284688949586,
|
|
"num_tokens": 21707396.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.472166347503662,
|
|
"epoch": 1.093334082102544,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004891582788002351,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.20225154757499694,
|
|
"num_tokens": 21718330.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.534717798233032,
|
|
"epoch": 1.0938956590105016,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004891459628175358,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.19382209032773973,
|
|
"num_tokens": 21729841.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.4919486999511715,
|
|
"epoch": 1.094457235918459,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000489133640016346,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19711797535419465,
|
|
"num_tokens": 21740403.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.513788461685181,
|
|
"epoch": 1.0950188128264167,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004891213103970579,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.2035467028617859,
|
|
"num_tokens": 21750696.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.4346349239349365,
|
|
"epoch": 1.095580389734374,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004891089739600643,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.2001863420009613,
|
|
"num_tokens": 21761324.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.491703033447266,
|
|
"epoch": 1.0961419666423318,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004890966307057581,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.19611945152282714,
|
|
"num_tokens": 21774046.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.5002344131469725,
|
|
"epoch": 1.0967035435502892,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000489084280634532,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.20201218277215957,
|
|
"num_tokens": 21784625.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.590076732635498,
|
|
"epoch": 1.0972651204582466,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004890719237467794,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.1929198160767555,
|
|
"num_tokens": 21795971.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.575134563446045,
|
|
"epoch": 1.0978266973662043,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004890595600428937,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.19657233506441116,
|
|
"num_tokens": 21806624.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.488445997238159,
|
|
"epoch": 1.0983882742741617,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004890471895232684,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.1945949077606201,
|
|
"num_tokens": 21817830.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.4915097713470455,
|
|
"epoch": 1.0989498511821194,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004890348121882978,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.20322116017341613,
|
|
"num_tokens": 21829540.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.59403133392334,
|
|
"epoch": 1.0995114280900768,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004890224280383758,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.1907534271478653,
|
|
"num_tokens": 21840550.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.588469696044922,
|
|
"epoch": 1.1000730049980345,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004890100370738966,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.19541567713022232,
|
|
"num_tokens": 21853366.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.494073343276978,
|
|
"epoch": 1.100634581905992,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004889976392952548,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.20458748936653137,
|
|
"num_tokens": 21863522.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.486305379867554,
|
|
"epoch": 1.1011961588139496,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004889852347028452,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.2018901601433754,
|
|
"num_tokens": 21873988.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.477131366729736,
|
|
"epoch": 1.101757735721907,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004889728232970626,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.2067457914352417,
|
|
"num_tokens": 21884595.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.444918441772461,
|
|
"epoch": 1.1023193126298647,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004889604050783025,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.20805045813322068,
|
|
"num_tokens": 21894643.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.486736869812011,
|
|
"epoch": 1.1028808895378222,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048894798004696,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.20031418800354003,
|
|
"num_tokens": 21906608.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.579413604736328,
|
|
"epoch": 1.1034424664457798,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004889355482034309,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.19743984341621398,
|
|
"num_tokens": 21919386.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.419105434417725,
|
|
"epoch": 1.1040040433537373,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004889231095481111,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.20471443384885787,
|
|
"num_tokens": 21930554.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.567722272872925,
|
|
"epoch": 1.104565620261695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004889106640813964,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.20686606913805008,
|
|
"num_tokens": 21941764.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.497578525543213,
|
|
"epoch": 1.1051271971696524,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004888982118036831,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.20669544637203216,
|
|
"num_tokens": 21951804.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.527990341186523,
|
|
"epoch": 1.10568877407761,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004888857527153679,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.19620731472969055,
|
|
"num_tokens": 21963356.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.493976402282715,
|
|
"epoch": 1.1062503509855675,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004888732868168473,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.20374078899621964,
|
|
"num_tokens": 21973785.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.492531871795654,
|
|
"epoch": 1.1068119278935251,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004888608141085183,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.19806147813796998,
|
|
"num_tokens": 21985057.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.5354889869689945,
|
|
"epoch": 1.1073735048014826,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004888483345907781,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.1994391828775406,
|
|
"num_tokens": 21996554.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.4949273586273195,
|
|
"epoch": 1.10793508170944,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000488835848264024,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1959906116127968,
|
|
"num_tokens": 22008284.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.428800249099732,
|
|
"epoch": 1.1084966586173977,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004888233551286534,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.1934410348534584,
|
|
"num_tokens": 22019322.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.561564016342163,
|
|
"epoch": 1.109058235525355,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004888108551850644,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.19297286570072175,
|
|
"num_tokens": 22031444.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.503013181686401,
|
|
"epoch": 1.1096198124333128,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004887983484336548,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.2070354476571083,
|
|
"num_tokens": 22042704.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.481017303466797,
|
|
"epoch": 1.1101813893412702,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004887858348748229,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.19846556037664415,
|
|
"num_tokens": 22052721.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.489732360839843,
|
|
"epoch": 1.1107429662492279,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000488773314508967,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.19732320606708526,
|
|
"num_tokens": 22063857.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.481310510635376,
|
|
"epoch": 1.1113045431571853,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004887607873364859,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.20645395666360855,
|
|
"num_tokens": 22074777.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.552349948883057,
|
|
"epoch": 1.111866120065143,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004887482533577786,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.1964542105793953,
|
|
"num_tokens": 22085301.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.477337312698364,
|
|
"epoch": 1.1124276969731004,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004887357125732438,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.1997896134853363,
|
|
"num_tokens": 22095635.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.509350395202636,
|
|
"epoch": 1.112989273881058,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000488723164983281,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.19551951587200164,
|
|
"num_tokens": 22105965.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.432709836959839,
|
|
"epoch": 1.1135508507890155,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004887106105882898,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.19945374578237535,
|
|
"num_tokens": 22117122.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.530886936187744,
|
|
"epoch": 1.1141124276969732,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004886980493886699,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.2078508570790291,
|
|
"num_tokens": 22128642.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.505481004714966,
|
|
"epoch": 1.1146740046049306,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004886854813848212,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.2018158420920372,
|
|
"num_tokens": 22140260.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.464072751998901,
|
|
"epoch": 1.1152355815128883,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004886729065771439,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.19367024600505828,
|
|
"num_tokens": 22152460.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.4073858737945555,
|
|
"epoch": 1.1157971584208457,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004886603249660384,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.2067487433552742,
|
|
"num_tokens": 22163134.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.503280973434448,
|
|
"epoch": 1.1163587353288034,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004886477365519052,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.19604033082723618,
|
|
"num_tokens": 22173956.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.429474210739135,
|
|
"epoch": 1.1169203122367608,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004886351413351453,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.20262504518032073,
|
|
"num_tokens": 22185506.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.460846900939941,
|
|
"epoch": 1.1174818891447185,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004886225393161596,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.19867530465126038,
|
|
"num_tokens": 22196934.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.487937927246094,
|
|
"epoch": 1.118043466052676,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004886099304953495,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.19497371315956116,
|
|
"num_tokens": 22209013.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.547253608703613,
|
|
"epoch": 1.1186050429606333,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004885973148731162,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.1963333383202553,
|
|
"num_tokens": 22220890.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.52170877456665,
|
|
"epoch": 1.119166619868591,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004885846924498617,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.2038394808769226,
|
|
"num_tokens": 22232899.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.50853009223938,
|
|
"epoch": 1.1197281967765484,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004885720632259876,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.19859282225370406,
|
|
"num_tokens": 22243839.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.555486106872559,
|
|
"epoch": 1.120289773684506,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004885594272018963,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.20444927960634232,
|
|
"num_tokens": 22253970.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.428713417053222,
|
|
"epoch": 1.1208513505924635,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048854678437799,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.20938242971897125,
|
|
"num_tokens": 22263598.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.381170558929443,
|
|
"epoch": 1.1214129275004212,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004885341347546713,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.19799899458885192,
|
|
"num_tokens": 22274385.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.442514848709107,
|
|
"epoch": 1.1219745044083786,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004885214783323428,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.20370982438325883,
|
|
"num_tokens": 22285837.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.590118503570556,
|
|
"epoch": 1.1225360813163363,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004885088151114076,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.1999982550740242,
|
|
"num_tokens": 22296882.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.4137030124664305,
|
|
"epoch": 1.1230976582242937,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004884961450922691,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.20340922325849534,
|
|
"num_tokens": 22308110.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.424910068511963,
|
|
"epoch": 1.1236592351322514,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004884834682753305,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.20091544836759567,
|
|
"num_tokens": 22318541.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.482576608657837,
|
|
"epoch": 1.1242208120402089,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004884707846609953,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.2010748103260994,
|
|
"num_tokens": 22328713.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.546434640884399,
|
|
"epoch": 1.1247823889481665,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004884580942496677,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.20200125873088837,
|
|
"num_tokens": 22341050.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.487131643295288,
|
|
"epoch": 1.125343965856124,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004884453970417515,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.20382803678512573,
|
|
"num_tokens": 22351184.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.517410516738892,
|
|
"epoch": 1.1259055427640816,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000488432693037651,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.19922498911619185,
|
|
"num_tokens": 22361651.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.583667230606079,
|
|
"epoch": 1.126467119672039,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000488419982237771,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.1941559836268425,
|
|
"num_tokens": 22373672.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.502324390411377,
|
|
"epoch": 1.1270286965799967,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004884072646425157,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19756727069616317,
|
|
"num_tokens": 22384924.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.454204082489014,
|
|
"epoch": 1.1275902734879542,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004883945402522907,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.20443972051143647,
|
|
"num_tokens": 22396091.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.566315364837647,
|
|
"epoch": 1.1281518503959118,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004883818090675005,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.1914006933569908,
|
|
"num_tokens": 22407925.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.477230644226074,
|
|
"epoch": 1.1287134273038693,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004883690710885507,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.20042373687028886,
|
|
"num_tokens": 22417917.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.513657140731811,
|
|
"epoch": 1.1292750042118267,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004883563263158471,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.19767324328422547,
|
|
"num_tokens": 22429836.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.5480509281158445,
|
|
"epoch": 1.1298365811197844,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004883435747497952,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.2008336916565895,
|
|
"num_tokens": 22440720.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.392574453353882,
|
|
"epoch": 1.130398158027742,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004883308163908012,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.1990372806787491,
|
|
"num_tokens": 22452587.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.477315378189087,
|
|
"epoch": 1.1309597349356995,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004883180512392714,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.19615628272295,
|
|
"num_tokens": 22464063.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.49305100440979,
|
|
"epoch": 1.131521311843657,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004883052792956119,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.1990286886692047,
|
|
"num_tokens": 22474956.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.474143362045288,
|
|
"epoch": 1.1320828887516146,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004882925005602296,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.19641708731651306,
|
|
"num_tokens": 22486499.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.467317295074463,
|
|
"epoch": 1.132644465659572,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004882797150335314,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.20911092311143875,
|
|
"num_tokens": 22497736.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.442320251464844,
|
|
"epoch": 1.1332060425675297,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048826692271592434,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.20130472481250763,
|
|
"num_tokens": 22509997.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.471804237365722,
|
|
"epoch": 1.133767619475487,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004882541236078158,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.20238028466701508,
|
|
"num_tokens": 22519721.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.503006458282471,
|
|
"epoch": 1.1343291963834448,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048824131770961316,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.20250243842601776,
|
|
"num_tokens": 22530219.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.478177404403686,
|
|
"epoch": 1.1348907732914022,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048822850502172437,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.1977991431951523,
|
|
"num_tokens": 22541373.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.3583534240722654,
|
|
"epoch": 1.1354523501993599,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004882156855445571,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.1978936955332756,
|
|
"num_tokens": 22552974.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.47052845954895,
|
|
"epoch": 1.1360139271073173,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004882028592785199,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.20185997784137727,
|
|
"num_tokens": 22563468.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.50176215171814,
|
|
"epoch": 1.136575504015275,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048819002622402095,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19243327677249908,
|
|
"num_tokens": 22574386.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.467049503326416,
|
|
"epoch": 1.1371370809232324,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004881771863814688,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.21250028908252716,
|
|
"num_tokens": 22585369.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.3933844566345215,
|
|
"epoch": 1.13769865783119,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048816433975127244,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.19853309094905852,
|
|
"num_tokens": 22595853.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.490254592895508,
|
|
"epoch": 1.1382602347391475,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004881514863338407,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.19892362654209136,
|
|
"num_tokens": 22606596.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.519156503677368,
|
|
"epoch": 1.1388218116471052,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048813862612958307,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.2022962525486946,
|
|
"num_tokens": 22617196.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.390959644317627,
|
|
"epoch": 1.1393833885550626,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004881257591389089,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.20580135732889177,
|
|
"num_tokens": 22627817.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.4578485012054445,
|
|
"epoch": 1.13994496546302,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048811288536222794,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.1920290097594261,
|
|
"num_tokens": 22637877.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.5674621105194095,
|
|
"epoch": 1.1405065423709777,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048810000479995,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.20134719908237458,
|
|
"num_tokens": 22648770.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.6028828620910645,
|
|
"epoch": 1.1410681192789354,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048808711745248524,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.19587359428405762,
|
|
"num_tokens": 22659626.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.490281486511231,
|
|
"epoch": 1.1416296961868928,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048807422332024404,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.19725994616746903,
|
|
"num_tokens": 22669035.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.541837215423584,
|
|
"epoch": 1.1421912730948502,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004880613224036369,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.19945300221443177,
|
|
"num_tokens": 22680536.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.538577556610107,
|
|
"epoch": 1.142752850002808,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048804841470307466,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.2027759462594986,
|
|
"num_tokens": 22692732.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.55800724029541,
|
|
"epoch": 1.1433144269107653,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048803550021896824,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.19247816503047943,
|
|
"num_tokens": 22703677.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.546948051452636,
|
|
"epoch": 1.143876003818723,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004880225789517289,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.198050919175148,
|
|
"num_tokens": 22714826.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.5437095165252686,
|
|
"epoch": 1.1444375807266804,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000488009650901768,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.19580610394477843,
|
|
"num_tokens": 22726013.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.491982555389404,
|
|
"epoch": 1.144999157634638,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048799671606949724,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.19937894344329835,
|
|
"num_tokens": 22737494.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.454474782943725,
|
|
"epoch": 1.1455607345425955,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048798377445532837,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.20814515203237532,
|
|
"num_tokens": 22746916.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.54791669845581,
|
|
"epoch": 1.1461223114505532,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004879708260596736,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.1831280395388603,
|
|
"num_tokens": 22759197.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.499806261062622,
|
|
"epoch": 1.1466838883585107,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004879578708829451,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.19603099375963212,
|
|
"num_tokens": 22770744.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.460432434082032,
|
|
"epoch": 1.1472454652664683,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004879449089255553,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.1988656058907509,
|
|
"num_tokens": 22781989.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.450898599624634,
|
|
"epoch": 1.1478070421744258,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004879319401879171,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.20892556011676788,
|
|
"num_tokens": 22792972.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.507102346420288,
|
|
"epoch": 1.1483686190823834,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048791896467044335,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.20316859632730483,
|
|
"num_tokens": 22802623.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.378831958770752,
|
|
"epoch": 1.1489301959903409,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048790598237354716,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.21608090102672578,
|
|
"num_tokens": 22813564.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.480757570266723,
|
|
"epoch": 1.1494917728982985,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004878929932976419,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.19838955104351044,
|
|
"num_tokens": 22824681.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.475946474075317,
|
|
"epoch": 1.150053349806256,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004878799974431412,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.21043189764022827,
|
|
"num_tokens": 22836030.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.477845621109009,
|
|
"epoch": 1.1506149267142134,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004878669948104588,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19940957129001619,
|
|
"num_tokens": 22847213.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.533801317214966,
|
|
"epoch": 1.151176503622171,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048785398540000867,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.20567964464426042,
|
|
"num_tokens": 22857904.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.459893751144409,
|
|
"epoch": 1.1517380805301287,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048784096921220514,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.1945674955844879,
|
|
"num_tokens": 22868975.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.502845191955567,
|
|
"epoch": 1.1522996574380862,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004878279462474627,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.19862089306116104,
|
|
"num_tokens": 22879463.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.5031791687011715,
|
|
"epoch": 1.1528612343460436,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048781491650619574,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.20160398185253142,
|
|
"num_tokens": 22890382.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.534811544418335,
|
|
"epoch": 1.1534228112540013,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048780187998881944,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.2018798843026161,
|
|
"num_tokens": 22901968.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.562323045730591,
|
|
"epoch": 1.1539843881619587,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004877888366957486,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.2032473862171173,
|
|
"num_tokens": 22912147.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.471665716171264,
|
|
"epoch": 1.1545459650699164,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004877757866273988,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.19547458589076996,
|
|
"num_tokens": 22923744.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.484510517120361,
|
|
"epoch": 1.1551075419778738,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004877627297841853,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.2046474725008011,
|
|
"num_tokens": 22935487.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.455772256851196,
|
|
"epoch": 1.1556691188858315,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004877496661665241,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.20740920752286912,
|
|
"num_tokens": 22946379.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.482706546783447,
|
|
"epoch": 1.156230695793789,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000487736595774831,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.19692771434783934,
|
|
"num_tokens": 22957219.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.408024263381958,
|
|
"epoch": 1.1567922727017466,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048772351860952215,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.20422237664461135,
|
|
"num_tokens": 22967749.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.459511852264404,
|
|
"epoch": 1.157353849609704,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004877104346710139,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.2030824288725853,
|
|
"num_tokens": 22978317.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.487691259384155,
|
|
"epoch": 1.1579154265176617,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000487697343959723,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.19915146082639695,
|
|
"num_tokens": 22988793.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.53210973739624,
|
|
"epoch": 1.158477003425619,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004876842464760661,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.19358340948820113,
|
|
"num_tokens": 23000073.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.523977851867675,
|
|
"epoch": 1.1590385803335768,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048767114222046036,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.19592917412519456,
|
|
"num_tokens": 23011260.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.448660612106323,
|
|
"epoch": 1.1596001572415342,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000487658031193323,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.20451880842447281,
|
|
"num_tokens": 23022129.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.435464477539062,
|
|
"epoch": 1.1601617341494919,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004876449133950714,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.20011816769838334,
|
|
"num_tokens": 23033666.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.490117835998535,
|
|
"epoch": 1.1607233110574493,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004876317888261233,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.20113195925951005,
|
|
"num_tokens": 23044133.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.5075037479400635,
|
|
"epoch": 1.1612848879654067,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048761865748689657,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.19803670346736907,
|
|
"num_tokens": 23055877.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.535925197601318,
|
|
"epoch": 1.1618464648733644,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048760551937780927,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.19392464607954024,
|
|
"num_tokens": 23066811.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.529267263412476,
|
|
"epoch": 1.162408041781322,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048759237449927986,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.19558288305997848,
|
|
"num_tokens": 23078928.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.475747060775757,
|
|
"epoch": 1.1629696186892795,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048757922285172674,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.19854832142591478,
|
|
"num_tokens": 23090685.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.428872299194336,
|
|
"epoch": 1.163531195597237,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048756606443556874,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.20441937446594238,
|
|
"num_tokens": 23101659.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.474255514144898,
|
|
"epoch": 1.1640927725051946,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048755289925122474,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.20072419494390487,
|
|
"num_tokens": 23112970.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.48042368888855,
|
|
"epoch": 1.164654349413152,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004875397272991141,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.19509494602680205,
|
|
"num_tokens": 23125391.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.5485023021697994,
|
|
"epoch": 1.1652159263211097,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000487526548579656,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.19916233271360398,
|
|
"num_tokens": 23138195.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.576639652252197,
|
|
"epoch": 1.1657775032290671,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048751336309327026,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.19873274117708206,
|
|
"num_tokens": 23149378.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.393582820892334,
|
|
"epoch": 1.1663390801370248,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004875001708403766,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.2123129352927208,
|
|
"num_tokens": 23159394.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.5424446105957035,
|
|
"epoch": 1.1669006570449822,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048748697182139503,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.19480357468128204,
|
|
"num_tokens": 23171512.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.478454065322876,
|
|
"epoch": 1.16746223395294,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004874737660367459,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.20331057608127595,
|
|
"num_tokens": 23181635.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.648907423019409,
|
|
"epoch": 1.1680238108608973,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048746055348684967,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.19064105600118636,
|
|
"num_tokens": 23194510.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.580972290039062,
|
|
"epoch": 1.168585387768855,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000487447334172127,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.198215851187706,
|
|
"num_tokens": 23205146.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.490986680984497,
|
|
"epoch": 1.1691469646768125,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048743410809299877,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.19372111409902573,
|
|
"num_tokens": 23216621.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.519704437255859,
|
|
"epoch": 1.1697085415847701,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004874208752498862,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.20009799301624298,
|
|
"num_tokens": 23226401.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.467326879501343,
|
|
"epoch": 1.1702701184927276,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004874076356432106,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.19325624853372575,
|
|
"num_tokens": 23237921.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.513947296142578,
|
|
"epoch": 1.1708316954006852,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048739438927339346,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.20072231888771058,
|
|
"num_tokens": 23250015.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.521986103057861,
|
|
"epoch": 1.1713932723086427,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048738113614085656,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.19534452110528946,
|
|
"num_tokens": 23261243.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.597052812576294,
|
|
"epoch": 1.1719548492166,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000487367876246022,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.19326120764017105,
|
|
"num_tokens": 23273264.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.629784107208252,
|
|
"epoch": 1.1725164261245578,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004873546095893118,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.18722994327545167,
|
|
"num_tokens": 23285031.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.485392332077026,
|
|
"epoch": 1.1730780030325154,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004873413361711485,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.20983369499444962,
|
|
"num_tokens": 23296387.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.506294441223145,
|
|
"epoch": 1.1736395799404729,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048732805599195465,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.20535978972911834,
|
|
"num_tokens": 23307950.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.36795825958252,
|
|
"epoch": 1.1742011568484303,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048731476905215326,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.20732709318399428,
|
|
"num_tokens": 23318424.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.553974437713623,
|
|
"epoch": 1.174762733756388,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004873014753521673,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.19347045868635177,
|
|
"num_tokens": 23330186.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.480014801025391,
|
|
"epoch": 1.1753243106643454,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004872881748924199,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.2114906758069992,
|
|
"num_tokens": 23341878.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.516538190841675,
|
|
"epoch": 1.175885887572303,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004872748676733347,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.1993564784526825,
|
|
"num_tokens": 23352471.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.507667541503906,
|
|
"epoch": 1.1764474644802605,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048726155369533547,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.204272997379303,
|
|
"num_tokens": 23363871.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.60056700706482,
|
|
"epoch": 1.1770090413882182,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000487248232958846,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.19964349567890166,
|
|
"num_tokens": 23376072.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.376241016387939,
|
|
"epoch": 1.1775706182961756,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004872349054642904,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.2059532180428505,
|
|
"num_tokens": 23386670.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.513647174835205,
|
|
"epoch": 1.1781321952041333,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004872215712120932,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.20351502448320388,
|
|
"num_tokens": 23396499.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.526396656036377,
|
|
"epoch": 1.1786937721120907,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004872082302026788,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.20428677797317504,
|
|
"num_tokens": 23407898.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.45545392036438,
|
|
"epoch": 1.1792553490200484,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004871948824364721,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.19804611802101135,
|
|
"num_tokens": 23418877.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.471789598464966,
|
|
"epoch": 1.1798169259280058,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000487181527913898,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.20464356243610382,
|
|
"num_tokens": 23431378.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.50163049697876,
|
|
"epoch": 1.1803785028359635,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048716816663538177,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.2050510376691818,
|
|
"num_tokens": 23442590.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.531225776672363,
|
|
"epoch": 1.180940079743921,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004871547986013488,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.1964708149433136,
|
|
"num_tokens": 23454139.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.519044256210327,
|
|
"epoch": 1.1815016566518786,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004871414238122248,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.20522621124982834,
|
|
"num_tokens": 23464908.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.420411491394043,
|
|
"epoch": 1.182063233559836,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004871280422684355,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.20830591022968292,
|
|
"num_tokens": 23475436.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.506728219985962,
|
|
"epoch": 1.1826248104677934,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048711465397040726,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.19809001833200454,
|
|
"num_tokens": 23487384.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.591058778762817,
|
|
"epoch": 1.183186387375751,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048710125891856604,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.1971176728606224,
|
|
"num_tokens": 23498978.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.446001100540161,
|
|
"epoch": 1.1837479642837088,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048708785711333845,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20474575608968734,
|
|
"num_tokens": 23510825.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.44612832069397,
|
|
"epoch": 1.1843095411916662,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048707444855515124,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.2046925336122513,
|
|
"num_tokens": 23522383.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.573840808868408,
|
|
"epoch": 1.1848711180996236,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004870610332444314,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.20001675486564635,
|
|
"num_tokens": 23534255.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.542532682418823,
|
|
"epoch": 1.1854326950075813,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004870476111816059,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.1952524721622467,
|
|
"num_tokens": 23545888.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.426338148117066,
|
|
"epoch": 1.1859942719155387,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048703418236710234,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.19840923100709915,
|
|
"num_tokens": 23556776.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.558454608917236,
|
|
"epoch": 1.1865558488234964,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004870207468013481,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.20492238104343413,
|
|
"num_tokens": 23569971.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.582506704330444,
|
|
"epoch": 1.1871174257314538,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004870073044847711,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.1988609954714775,
|
|
"num_tokens": 23580751.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.457968473434448,
|
|
"epoch": 1.1876790026394115,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004869938554177993,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.21056124120950698,
|
|
"num_tokens": 23591423.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.470960283279419,
|
|
"epoch": 1.188240579547369,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048698039960086084,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.19630311876535417,
|
|
"num_tokens": 23601552.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.476943254470825,
|
|
"epoch": 1.1888021564553266,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004869669370343843,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.20744584053754805,
|
|
"num_tokens": 23613080.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.469893455505371,
|
|
"epoch": 1.189363733363284,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004869534677187983,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.2042535975575447,
|
|
"num_tokens": 23623559.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.473828744888306,
|
|
"epoch": 1.1899253102712417,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004869399916545317,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.2080959603190422,
|
|
"num_tokens": 23634113.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.40751371383667,
|
|
"epoch": 1.1904868871791991,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004869265088420135,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.21530471593141556,
|
|
"num_tokens": 23645203.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.436509275436402,
|
|
"epoch": 1.1910484640871568,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004869130192816731,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.20164205580949784,
|
|
"num_tokens": 23654880.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.422470331192017,
|
|
"epoch": 1.1916100409951143,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048689952297394,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.21329433470964432,
|
|
"num_tokens": 23664962.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.4792680740356445,
|
|
"epoch": 1.192171617903072,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004868860199192438,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.2096644386649132,
|
|
"num_tokens": 23675288.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.3882146835327145,
|
|
"epoch": 1.1927331948110294,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004868725101180146,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20675718039274216,
|
|
"num_tokens": 23685948.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.548993062973023,
|
|
"epoch": 1.1932947717189868,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004868589935706826,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.19026148021221162,
|
|
"num_tokens": 23696980.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.604699325561524,
|
|
"epoch": 1.1938563486269445,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048684547027767793,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.20159771293401718,
|
|
"num_tokens": 23708644.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.481865644454956,
|
|
"epoch": 1.1944179255349021,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004868319402394314,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.20275103598833083,
|
|
"num_tokens": 23719652.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.471865844726563,
|
|
"epoch": 1.1949795024428596,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048681840345637375,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.1984228014945984,
|
|
"num_tokens": 23731906.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.479325580596924,
|
|
"epoch": 1.195541079350817,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048680485992893597,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.20247800052165985,
|
|
"num_tokens": 23744184.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.492074394226075,
|
|
"epoch": 1.1961026562587747,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048679130965754926,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.209586201608181,
|
|
"num_tokens": 23754807.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.431617641448975,
|
|
"epoch": 1.196664233166732,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004867777526426451,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.19991949200630188,
|
|
"num_tokens": 23765907.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.438200807571411,
|
|
"epoch": 1.1972258100746898,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048676418888465525,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.20301985889673232,
|
|
"num_tokens": 23776217.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.4663983345031735,
|
|
"epoch": 1.1977873869826472,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004867506183840114,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.20937189608812332,
|
|
"num_tokens": 23786170.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.53681902885437,
|
|
"epoch": 1.1983489638906049,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004867370411411459,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.19008873552083969,
|
|
"num_tokens": 23796491.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.482672262191772,
|
|
"epoch": 1.1989105407985623,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048672345715649066,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.20718738734722136,
|
|
"num_tokens": 23807718.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.459001159667968,
|
|
"epoch": 1.19947211770652,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004867098664304785,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.19423828423023223,
|
|
"num_tokens": 23818623.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.442469358444214,
|
|
"epoch": 1.2000336946144774,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004866962689635422,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.20477300137281418,
|
|
"num_tokens": 23829173.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.5257669448852536,
|
|
"epoch": 1.200595271522435,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048668266475611447,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.20550632178783418,
|
|
"num_tokens": 23840689.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.542004776000977,
|
|
"epoch": 1.2011568484303925,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004866690538086286,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.19335527569055558,
|
|
"num_tokens": 23852858.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.472568225860596,
|
|
"epoch": 1.2017184253383502,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048665543612151803,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.20303714275360107,
|
|
"num_tokens": 23864137.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.530020713806152,
|
|
"epoch": 1.2022800022463076,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048664181169521625,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.20412732362747193,
|
|
"num_tokens": 23875087.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.4003839015960695,
|
|
"epoch": 1.2028415791542653,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004866281805301571,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.21323109418153763,
|
|
"num_tokens": 23886521.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.455353403091431,
|
|
"epoch": 1.2034031560622227,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004866145426267746,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.19626407474279403,
|
|
"num_tokens": 23897660.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.50681881904602,
|
|
"epoch": 1.2039647329701804,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000486600897985503,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.1982806697487831,
|
|
"num_tokens": 23910543.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.502576208114624,
|
|
"epoch": 1.2045263098781378,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048658724660677674,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.20709858387708663,
|
|
"num_tokens": 23921687.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.466290473937988,
|
|
"epoch": 1.2050878867860955,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004865735884910305,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.20005795657634734,
|
|
"num_tokens": 23933717.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.484907436370849,
|
|
"epoch": 1.205649463694053,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004865599236386991,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.2004958689212799,
|
|
"num_tokens": 23947764.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.471380090713501,
|
|
"epoch": 1.2062110406020103,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004865462520502177,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.19518380165100097,
|
|
"num_tokens": 23960096.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.530574893951416,
|
|
"epoch": 1.206772617509968,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004865325737260216,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.20091657638549804,
|
|
"num_tokens": 23971573.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.494948863983154,
|
|
"epoch": 1.2073341944179254,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048651888866654624,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20881382524967193,
|
|
"num_tokens": 23982710.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.353890991210937,
|
|
"epoch": 1.207895771325883,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004865051968722275,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.20927162170410157,
|
|
"num_tokens": 23993663.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.496188020706176,
|
|
"epoch": 1.2084573482338405,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048649149834350126,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.19733658134937287,
|
|
"num_tokens": 24005112.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.413522243499756,
|
|
"epoch": 1.2090189251417982,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004864777930808037,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.20889131724834442,
|
|
"num_tokens": 24015855.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.460587835311889,
|
|
"epoch": 1.2095805020497556,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004864640810845711,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.203422649204731,
|
|
"num_tokens": 24027232.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.4891133308410645,
|
|
"epoch": 1.2101420789577133,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004864503623552402,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.2071306213736534,
|
|
"num_tokens": 24039127.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.521038961410523,
|
|
"epoch": 1.2107036558656707,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004864366368932478,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.20046963542699814,
|
|
"num_tokens": 24049821.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.494733905792236,
|
|
"epoch": 1.2112652327736284,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048642290469903083,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.1967984840273857,
|
|
"num_tokens": 24060305.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.453553915023804,
|
|
"epoch": 1.2118268096815858,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048640916577302664,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.2086501255631447,
|
|
"num_tokens": 24071193.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.328098297119141,
|
|
"epoch": 1.2123883865895435,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048639542011567243,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.22395618706941606,
|
|
"num_tokens": 24082380.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.583607387542725,
|
|
"epoch": 1.212949963497501,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004863816677274062,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.20054809898138046,
|
|
"num_tokens": 24093168.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.3980114459991455,
|
|
"epoch": 1.2135115404054586,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048636790860866576,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.20629191547632217,
|
|
"num_tokens": 24105355.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.379767560958863,
|
|
"epoch": 1.214073117313416,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004863541427598889,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.20532530993223191,
|
|
"num_tokens": 24117062.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.568332386016846,
|
|
"epoch": 1.2146346942213737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004863403701815144,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.1973193034529686,
|
|
"num_tokens": 24127770.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.560142278671265,
|
|
"epoch": 1.2151962711293312,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004863265908739805,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.19235835671424867,
|
|
"num_tokens": 24139894.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.482671213150025,
|
|
"epoch": 1.2157578480372888,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004863128048377259,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.21467315554618835,
|
|
"num_tokens": 24150799.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.47534704208374,
|
|
"epoch": 1.2163194249452463,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004862990120731896,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.2008440837264061,
|
|
"num_tokens": 24161406.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.332892799377442,
|
|
"epoch": 1.2168810018532037,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048628521258081096,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.2050155892968178,
|
|
"num_tokens": 24171884.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.4444944858551025,
|
|
"epoch": 1.2174425787611614,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048627140636102906,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.20349437445402146,
|
|
"num_tokens": 24183873.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.542812967300415,
|
|
"epoch": 1.2180041556691188,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004862575934142837,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.20690814703702926,
|
|
"num_tokens": 24194689.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.477800941467285,
|
|
"epoch": 1.2185657325770765,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004862437737410147,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.2035909727215767,
|
|
"num_tokens": 24206675.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.462206697463989,
|
|
"epoch": 1.219127309485034,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004862299473416619,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.2022419825196266,
|
|
"num_tokens": 24218845.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.477483224868775,
|
|
"epoch": 1.2196888863929916,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048621611421666573,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.1971077263355255,
|
|
"num_tokens": 24229889.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.515479469299317,
|
|
"epoch": 1.220250463300949,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004862022743664665,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19931017756462097,
|
|
"num_tokens": 24240729.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.561770343780518,
|
|
"epoch": 1.2208120402089067,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048618842779150494,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.19740921705961229,
|
|
"num_tokens": 24251765.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.506036996841431,
|
|
"epoch": 1.221373617116864,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048617457449222205,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.20241938084363936,
|
|
"num_tokens": 24262273.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.47819414138794,
|
|
"epoch": 1.2219351940248218,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004861607144690587,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.20218585729598998,
|
|
"num_tokens": 24272313.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.537299346923828,
|
|
"epoch": 1.2224967709327792,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004861468477224563,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.19307958632707595,
|
|
"num_tokens": 24283971.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.496476888656616,
|
|
"epoch": 1.2230583478407369,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048613297425285635,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.19803999364376068,
|
|
"num_tokens": 24294357.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.428511428833008,
|
|
"epoch": 1.2236199247486943,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004861190940607007,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.21581820547580718,
|
|
"num_tokens": 24305894.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.464552640914917,
|
|
"epoch": 1.224181501656652,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004861052071464312,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.20914482623338698,
|
|
"num_tokens": 24318506.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.421601057052612,
|
|
"epoch": 1.2247430785646094,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048609131351048994,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.19690526127815247,
|
|
"num_tokens": 24330169.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.420553922653198,
|
|
"epoch": 1.225304655472567,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004860774131533195,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.21600483804941178,
|
|
"num_tokens": 24340063.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.517192745208741,
|
|
"epoch": 1.2258662323805245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048606350607536235,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.20628322958946227,
|
|
"num_tokens": 24351506.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.483851766586303,
|
|
"epoch": 1.2264278092884822,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004860495922770612,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.20055633932352065,
|
|
"num_tokens": 24362168.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.439136695861817,
|
|
"epoch": 1.2269893861964396,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048603567175885926,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.20905566662549974,
|
|
"num_tokens": 24372269.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.506979370117188,
|
|
"epoch": 1.227550963104397,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004860217445211997,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.20569736659526824,
|
|
"num_tokens": 24384368.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.480213165283203,
|
|
"epoch": 1.2281125400123547,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004860078105645259,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.20597250312566756,
|
|
"num_tokens": 24395395.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.417916011810303,
|
|
"epoch": 1.2286741169203121,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004859938698892816,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.210627917945385,
|
|
"num_tokens": 24406709.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.4395898342132565,
|
|
"epoch": 1.2292356938282698,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048597992249591065,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.20055015981197358,
|
|
"num_tokens": 24418574.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.555637359619141,
|
|
"epoch": 1.2297972707362272,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048596596838485704,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.20091564506292342,
|
|
"num_tokens": 24429418.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.54966926574707,
|
|
"epoch": 1.230358847644185,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004859520075565654,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.2043559193611145,
|
|
"num_tokens": 24440301.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.5156091213226315,
|
|
"epoch": 1.2309204245521423,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048593804001147986,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.19491285532712938,
|
|
"num_tokens": 24451987.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.45955638885498,
|
|
"epoch": 1.2314820014601,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004859240657500453,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.20815367996692657,
|
|
"num_tokens": 24461971.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.393483400344849,
|
|
"epoch": 1.2320435783680574,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048591008477270675,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.206189101934433,
|
|
"num_tokens": 24472193.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.426868677139282,
|
|
"epoch": 1.232605155276015,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048589609707990925,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.20046592950820924,
|
|
"num_tokens": 24483075.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.4319836616516115,
|
|
"epoch": 1.2331667321839725,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048588210267209823,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.21398392617702483,
|
|
"num_tokens": 24493070.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.455245113372802,
|
|
"epoch": 1.2337283090919302,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048586810154971935,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.19891325980424882,
|
|
"num_tokens": 24502866.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.448936939239502,
|
|
"epoch": 1.2342898859998876,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048585409371321826,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.2124490886926651,
|
|
"num_tokens": 24514169.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.50441608428955,
|
|
"epoch": 1.2348514629078453,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048584007916304106,
|
|
"loss": 5.2844,
|
|
"mean_token_accuracy": 0.20237704515457153,
|
|
"num_tokens": 24525552.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.459224033355713,
|
|
"epoch": 1.2354130398158027,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048582605789963395,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.20293467342853547,
|
|
"num_tokens": 24536370.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.524840307235718,
|
|
"epoch": 1.2359746167237604,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004858120299234434,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.200814825296402,
|
|
"num_tokens": 24546868.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.51372218132019,
|
|
"epoch": 1.2365361936317179,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048579799523491607,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.19810605496168138,
|
|
"num_tokens": 24558279.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.45882019996643,
|
|
"epoch": 1.2370977705396755,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004857839538344988,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.20627331882715225,
|
|
"num_tokens": 24568321.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.484524583816528,
|
|
"epoch": 1.237659347447633,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048576990572263875,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.19672581553459167,
|
|
"num_tokens": 24579137.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.5218949794769285,
|
|
"epoch": 1.2382209243555904,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004857558508997831,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.20185403227806092,
|
|
"num_tokens": 24591523.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.508745288848877,
|
|
"epoch": 1.238782501263548,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004857417893663794,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.2033970832824707,
|
|
"num_tokens": 24601998.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.440354728698731,
|
|
"epoch": 1.2393440781715055,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004857277211228754,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.20623127669095992,
|
|
"num_tokens": 24612371.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.471588039398194,
|
|
"epoch": 1.2399056550794632,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004857136461697191,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.2028878465294838,
|
|
"num_tokens": 24623350.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.472438955307007,
|
|
"epoch": 1.2404672319874206,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048569956450735853,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.20091035813093186,
|
|
"num_tokens": 24634365.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.533271646499633,
|
|
"epoch": 1.2410288088953783,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048568547613624206,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.20188100636005402,
|
|
"num_tokens": 24645227.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.631623983383179,
|
|
"epoch": 1.2415903858033357,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048567138105681833,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.19973209351301194,
|
|
"num_tokens": 24656807.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.5159214496612545,
|
|
"epoch": 1.2421519627112934,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048565727926953617,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.19795771986246108,
|
|
"num_tokens": 24669021.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.507710886001587,
|
|
"epoch": 1.2427135396192508,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004856431707748445,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.2093920335173607,
|
|
"num_tokens": 24678802.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.482647848129273,
|
|
"epoch": 1.2432751165272085,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004856290555731926,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.2017831951379776,
|
|
"num_tokens": 24688449.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.4542618751525875,
|
|
"epoch": 1.243836693435166,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004856149336650299,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.20047776252031327,
|
|
"num_tokens": 24700272.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.5597772121429445,
|
|
"epoch": 1.2443982703431236,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004856008050508059,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.19514946788549423,
|
|
"num_tokens": 24711949.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.52004075050354,
|
|
"epoch": 1.244959847251081,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004855866697309707,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.20377042442560195,
|
|
"num_tokens": 24723535.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.420146179199219,
|
|
"epoch": 1.2455214241590387,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004855725277059742,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.1968116745352745,
|
|
"num_tokens": 24734915.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.456676816940307,
|
|
"epoch": 1.246083001066996,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004855583789762668,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.21292711943387985,
|
|
"num_tokens": 24745744.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.519069576263428,
|
|
"epoch": 1.2466445779749538,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000485544223542299,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.19853331297636032,
|
|
"num_tokens": 24758158.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.521362209320069,
|
|
"epoch": 1.2472061548829112,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004855300614045214,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.20734099745750428,
|
|
"num_tokens": 24768607.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.509049940109253,
|
|
"epoch": 1.2477677317908689,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048551589256338497,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.20964578688144683,
|
|
"num_tokens": 24779845.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.429672145843506,
|
|
"epoch": 1.2483293086988263,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048550171701934087,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.19642233550548555,
|
|
"num_tokens": 24790049.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.50251202583313,
|
|
"epoch": 1.2488908856067837,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048548753477284053,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.19888308942317962,
|
|
"num_tokens": 24802112.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.482595586776734,
|
|
"epoch": 1.2494524625147414,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004854733458243354,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.19905349165201186,
|
|
"num_tokens": 24812630.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.441510486602783,
|
|
"epoch": 1.250014039422699,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004854591501742773,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.20963779091835022,
|
|
"num_tokens": 24823346.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.450416612625122,
|
|
"epoch": 1.2505756163306565,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048544494782311825,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.19566794931888581,
|
|
"num_tokens": 24834374.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.456074810028076,
|
|
"epoch": 1.251137193238614,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048543073877131037,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.20845172852277755,
|
|
"num_tokens": 24845474.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.470061111450195,
|
|
"epoch": 1.2516987701465716,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048541652301930627,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.20946729183197021,
|
|
"num_tokens": 24857427.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.474793291091919,
|
|
"epoch": 1.252260347054529,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004854023005675585,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.2064740017056465,
|
|
"num_tokens": 24868352.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.468759489059448,
|
|
"epoch": 1.2528219239624867,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004853880714165197,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.19598804265260697,
|
|
"num_tokens": 24878499.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.4192615985870365,
|
|
"epoch": 1.2533835008704441,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048537383556664315,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.2071092739701271,
|
|
"num_tokens": 24888290.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.454580020904541,
|
|
"epoch": 1.2539450777784018,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004853595930183822,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.1995743066072464,
|
|
"num_tokens": 24900201.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.4799065589904785,
|
|
"epoch": 1.2545066546863592,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004853453437721901,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.2094999685883522,
|
|
"num_tokens": 24910895.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.462640762329102,
|
|
"epoch": 1.255068231594317,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004853310878285208,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.20961921215057372,
|
|
"num_tokens": 24922079.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.588731193542481,
|
|
"epoch": 1.2556298085022743,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048531682518782797,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.19737827330827712,
|
|
"num_tokens": 24935093.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.571321868896485,
|
|
"epoch": 1.256191385410232,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048530255585056594,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.1921171188354492,
|
|
"num_tokens": 24947316.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.400997924804687,
|
|
"epoch": 1.2567529623181894,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004852882798171889,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.2131531670689583,
|
|
"num_tokens": 24957255.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.44576096534729,
|
|
"epoch": 1.2573145392261469,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004852739970881515,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.21140680313110352,
|
|
"num_tokens": 24967646.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.5493693351745605,
|
|
"epoch": 1.2578761161341045,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00048525970766390847,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.19423409402370453,
|
|
"num_tokens": 24979748.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.591318559646607,
|
|
"epoch": 1.2584376930420622,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004852454115449148,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.20085525810718535,
|
|
"num_tokens": 24990727.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.476440000534057,
|
|
"epoch": 1.2589992699500197,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004852311087316257,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20607781559228897,
|
|
"num_tokens": 25001912.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.458552312850952,
|
|
"epoch": 1.259560846857977,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004852167992244966,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.20382578670978546,
|
|
"num_tokens": 25012952.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.437438058853149,
|
|
"epoch": 1.2601224237659348,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000485202483023983,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.20419829487800598,
|
|
"num_tokens": 25022851.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.448531246185302,
|
|
"epoch": 1.2606840006738924,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048518816013054083,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.20295158326625823,
|
|
"num_tokens": 25033177.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.458430194854737,
|
|
"epoch": 1.2612455775818499,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048517383054462617,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.211738920211792,
|
|
"num_tokens": 25044140.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.467816305160523,
|
|
"epoch": 1.2618071544898073,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004851594942666952,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.2036068007349968,
|
|
"num_tokens": 25054480.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.52181715965271,
|
|
"epoch": 1.262368731397765,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048514515129720445,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.19436217099428177,
|
|
"num_tokens": 25065673.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.4917021751403805,
|
|
"epoch": 1.2629303083057224,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004851308016366105,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.20191105604171752,
|
|
"num_tokens": 25076691.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.509622240066529,
|
|
"epoch": 1.26349188521368,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048511644528537043,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.2093917742371559,
|
|
"num_tokens": 25087882.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.530025339126587,
|
|
"epoch": 1.2640534621216375,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004851020822439412,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.1939561888575554,
|
|
"num_tokens": 25099325.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.39603967666626,
|
|
"epoch": 1.2646150390295952,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048508771251278015,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.2087145909667015,
|
|
"num_tokens": 25110304.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.47834210395813,
|
|
"epoch": 1.2651766159375526,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004850733360923449,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.20111986100673676,
|
|
"num_tokens": 25121597.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.532899808883667,
|
|
"epoch": 1.2657381928455103,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004850589529830931,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.20000620782375336,
|
|
"num_tokens": 25132817.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.534612512588501,
|
|
"epoch": 1.2662997697534677,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048504456318548285,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.19836081564426422,
|
|
"num_tokens": 25143740.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.497245454788208,
|
|
"epoch": 1.2668613466614254,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004850301666999722,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.2025380551815033,
|
|
"num_tokens": 25155889.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.462749099731445,
|
|
"epoch": 1.2674229235693828,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004850157635270196,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.19970934689044953,
|
|
"num_tokens": 25166043.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.455156898498535,
|
|
"epoch": 1.2679845004773402,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004850013536670836,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.20458008199930192,
|
|
"num_tokens": 25176906.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.429724836349488,
|
|
"epoch": 1.268546077385298,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004849869371206231,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.20375957041978837,
|
|
"num_tokens": 25187803.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.44084792137146,
|
|
"epoch": 1.2691076542932556,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048497251388809697,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.20047487169504166,
|
|
"num_tokens": 25199067.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.531391334533692,
|
|
"epoch": 1.269669231201213,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004849580839699647,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.2041425496339798,
|
|
"num_tokens": 25210768.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.528670406341552,
|
|
"epoch": 1.2702308081091704,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048494364736668554,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.19860792458057402,
|
|
"num_tokens": 25221602.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.489388132095337,
|
|
"epoch": 1.270792385017128,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004849292040787192,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.20189705789089202,
|
|
"num_tokens": 25232791.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.4936682224273685,
|
|
"epoch": 1.2713539619250858,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004849147541065256,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.2056099772453308,
|
|
"num_tokens": 25243962.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.461676120758057,
|
|
"epoch": 1.2719155388330432,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004849002974505649,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.20453756749629975,
|
|
"num_tokens": 25254636.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.4179452419281,
|
|
"epoch": 1.2724771157410006,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048488583411129723,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.2098113253712654,
|
|
"num_tokens": 25265255.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.520189189910889,
|
|
"epoch": 1.2730386926489583,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004848713640891832,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.20414839833974838,
|
|
"num_tokens": 25276721.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.467082977294922,
|
|
"epoch": 1.2736002695569157,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004848568873846835,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.20848419815301894,
|
|
"num_tokens": 25287451.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.451062297821045,
|
|
"epoch": 1.2741618464648734,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048484240399825925,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.20859842747449875,
|
|
"num_tokens": 25298609.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.511391925811767,
|
|
"epoch": 1.2747234233728308,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048482791393037134,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.21195229291915893,
|
|
"num_tokens": 25310058.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.424810981750488,
|
|
"epoch": 1.2752850002807885,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048481341718148137,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.20580505579710007,
|
|
"num_tokens": 25321249.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.473056125640869,
|
|
"epoch": 1.275846577188746,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048479891375205074,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.20340109169483184,
|
|
"num_tokens": 25332603.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.433611011505127,
|
|
"epoch": 1.2764081540967036,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048478440364254136,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.20755458027124404,
|
|
"num_tokens": 25344955.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.4985175132751465,
|
|
"epoch": 1.276969731004661,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004847698868534152,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.1977325290441513,
|
|
"num_tokens": 25356125.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.438800907135009,
|
|
"epoch": 1.2775313079126187,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004847553633851345,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.20874637812376023,
|
|
"num_tokens": 25366969.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.462187433242798,
|
|
"epoch": 1.2780928848205761,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004847408332381616,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.20771000385284424,
|
|
"num_tokens": 25378815.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.406018686294556,
|
|
"epoch": 1.2786544617285336,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048472629641295933,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.21123420149087907,
|
|
"num_tokens": 25389969.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.486202573776245,
|
|
"epoch": 1.2792160386364912,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004847117529099904,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.20197124481201173,
|
|
"num_tokens": 25401443.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.5267997741699215,
|
|
"epoch": 1.279777615544449,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048469720272971797,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.20289596021175385,
|
|
"num_tokens": 25412857.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.422056245803833,
|
|
"epoch": 1.2803391924524063,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004846826458726052,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.20852331668138505,
|
|
"num_tokens": 25423804.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.460014343261719,
|
|
"epoch": 1.2809007693603638,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048466808233911567,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.1975537896156311,
|
|
"num_tokens": 25435686.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.519877672195435,
|
|
"epoch": 1.2814623462683215,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048465351212971313,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1993211105465889,
|
|
"num_tokens": 25446012.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.5258293628692625,
|
|
"epoch": 1.2820239231762791,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004846389352448614,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.20552950650453566,
|
|
"num_tokens": 25457768.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.467868900299072,
|
|
"epoch": 1.2825855000842366,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004846243516850247,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.20224027335643768,
|
|
"num_tokens": 25468706.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.565009307861328,
|
|
"epoch": 1.283147076992194,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004846097614506673,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.1935812532901764,
|
|
"num_tokens": 25479446.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.48779935836792,
|
|
"epoch": 1.2837086539001517,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048459516454225384,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.20170326679944992,
|
|
"num_tokens": 25491090.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.465082311630249,
|
|
"epoch": 1.284270230808109,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000484580560960249,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.20470304638147355,
|
|
"num_tokens": 25502105.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.6167223930358885,
|
|
"epoch": 1.2848318077160668,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004845659507051178,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.1940634533762932,
|
|
"num_tokens": 25513970.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.515455293655395,
|
|
"epoch": 1.2853933846240242,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004845513337773255,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.20010601133108138,
|
|
"num_tokens": 25524508.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.457692861557007,
|
|
"epoch": 1.2859549615319819,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048453671017733755,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.2045575723052025,
|
|
"num_tokens": 25536006.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.434911823272705,
|
|
"epoch": 1.2865165384399393,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004845220799056194,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.20191775411367416,
|
|
"num_tokens": 25545726.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.449568557739258,
|
|
"epoch": 1.287078115347897,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048450744296263685,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.20319970101118087,
|
|
"num_tokens": 25555914.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.541899824142456,
|
|
"epoch": 1.2876396922558544,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048449279934885625,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.1968511551618576,
|
|
"num_tokens": 25568021.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.562679433822632,
|
|
"epoch": 1.288201269163812,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004844781490647435,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.1997581899166107,
|
|
"num_tokens": 25578788.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.5087422847747805,
|
|
"epoch": 1.2887628460717695,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004844634921107654,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.20580427050590516,
|
|
"num_tokens": 25590997.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.496448564529419,
|
|
"epoch": 1.289324422979727,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048444882848738835,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.19701833426952362,
|
|
"num_tokens": 25602810.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.5116242408752445,
|
|
"epoch": 1.2898859998876846,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048443415819507944,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.2029879629611969,
|
|
"num_tokens": 25614251.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.5043682098388675,
|
|
"epoch": 1.2904475767956423,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004844194812343057,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.20158059895038605,
|
|
"num_tokens": 25626162.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.543578577041626,
|
|
"epoch": 1.2910091537035997,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004844047976055344,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.20593275874853134,
|
|
"num_tokens": 25637598.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.53437123298645,
|
|
"epoch": 1.2915707306115571,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048439010730923313,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.2037929877638817,
|
|
"num_tokens": 25648297.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.494385385513306,
|
|
"epoch": 1.2921323075195148,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048437541034586964,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19732092022895814,
|
|
"num_tokens": 25660139.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.498093128204346,
|
|
"epoch": 1.2926938844274725,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048436070671591195,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.2051066741347313,
|
|
"num_tokens": 25671947.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.4780529022216795,
|
|
"epoch": 1.29325546133543,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048434599641982806,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.21382585763931275,
|
|
"num_tokens": 25682059.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.465997362136841,
|
|
"epoch": 1.2938170382433873,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048433127945808645,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.20328839272260665,
|
|
"num_tokens": 25692792.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.520310974121093,
|
|
"epoch": 1.294378615151345,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004843165558311558,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.19922371655702592,
|
|
"num_tokens": 25703253.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.561289644241333,
|
|
"epoch": 1.2949401920593024,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004843018255395048,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.21014227718114853,
|
|
"num_tokens": 25714169.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.48844313621521,
|
|
"epoch": 1.29550176896726,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048428708858360244,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.19755372256040574,
|
|
"num_tokens": 25725827.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.437676239013672,
|
|
"epoch": 1.2960633458752175,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048427234496391816,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.20276845693588258,
|
|
"num_tokens": 25737951.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.492447137832642,
|
|
"epoch": 1.2966249227831752,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048425759468092113,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.200042961537838,
|
|
"num_tokens": 25749676.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.567061138153076,
|
|
"epoch": 1.2971864996911326,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004842428377350811,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.20785724371671677,
|
|
"num_tokens": 25760005.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.521713447570801,
|
|
"epoch": 1.2977480765990903,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048422807412686796,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.19823790788650514,
|
|
"num_tokens": 25770595.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.544219923019409,
|
|
"epoch": 1.2983096535070477,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004842133038567519,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.20140123069286348,
|
|
"num_tokens": 25782301.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.524098014831543,
|
|
"epoch": 1.2988712304150054,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000484198526925203,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.21018299758434295,
|
|
"num_tokens": 25792904.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.5061163902282715,
|
|
"epoch": 1.2994328073229628,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004841837433326919,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.19777555763721466,
|
|
"num_tokens": 25804594.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.449682426452637,
|
|
"epoch": 1.2999943842309205,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004841689530796893,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.20647979229688646,
|
|
"num_tokens": 25816496.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.421622037887573,
|
|
"epoch": 1.300555961138878,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004841541561666661,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.20816075056791306,
|
|
"num_tokens": 25827271.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.4671941757202145,
|
|
"epoch": 1.3011175380468356,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048413935259409343,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.19825071692466736,
|
|
"num_tokens": 25837869.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.468920660018921,
|
|
"epoch": 1.301679114954793,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048412454236244267,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.20389050841331482,
|
|
"num_tokens": 25850244.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.50404920578003,
|
|
"epoch": 1.3022406918627505,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048410972547218545,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.20067277550697327,
|
|
"num_tokens": 25859981.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.4511308670043945,
|
|
"epoch": 1.3028022687707081,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048409490192379337,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.2134354829788208,
|
|
"num_tokens": 25870393.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.493758916854858,
|
|
"epoch": 1.3033638456786658,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004840800717177386,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.20268699079751967,
|
|
"num_tokens": 25882517.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.491518640518189,
|
|
"epoch": 1.3039254225866233,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004840652348544931,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.210752634704113,
|
|
"num_tokens": 25893628.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.541408443450928,
|
|
"epoch": 1.3044869994945807,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004840503913345296,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.19841479361057282,
|
|
"num_tokens": 25904891.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.5108363151550295,
|
|
"epoch": 1.3050485764025384,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004840355411583205,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.20038772523403167,
|
|
"num_tokens": 25914598.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.523006439208984,
|
|
"epoch": 1.3056101533104958,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048402068432633864,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.20795723050832748,
|
|
"num_tokens": 25924412.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.43036117553711,
|
|
"epoch": 1.3061717302184535,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004840058208390572,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.2000311031937599,
|
|
"num_tokens": 25935583.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.402124977111816,
|
|
"epoch": 1.306733307126411,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004839909506969494,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.20920169353485107,
|
|
"num_tokens": 25946949.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.443983554840088,
|
|
"epoch": 1.3072948840343686,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004839760739004886,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.2069692224264145,
|
|
"num_tokens": 25957070.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.472876405715942,
|
|
"epoch": 1.307856460942326,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048396119045014853,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.19443962574005128,
|
|
"num_tokens": 25968375.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.552474069595337,
|
|
"epoch": 1.3084180378502837,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004839463003464032,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.20497116148471833,
|
|
"num_tokens": 25979690.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.547683382034302,
|
|
"epoch": 1.308979614758241,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004839314035897265,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.18798450082540513,
|
|
"num_tokens": 25990660.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.3817956924438475,
|
|
"epoch": 1.3095411916661988,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000483916500180593,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.20716284811496735,
|
|
"num_tokens": 26002158.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.475133323669434,
|
|
"epoch": 1.3101027685741562,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048390159011947706,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.20972815304994583,
|
|
"num_tokens": 26011890.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.463530397415161,
|
|
"epoch": 1.3106643454821139,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004838866734068535,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.20121950060129165,
|
|
"num_tokens": 26023548.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.5041115283966064,
|
|
"epoch": 1.3112259223900713,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048387175004319723,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.20314686000347137,
|
|
"num_tokens": 26034178.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.468225765228271,
|
|
"epoch": 1.311787499298029,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004838568200289834,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20256966054439546,
|
|
"num_tokens": 26045068.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.502616310119629,
|
|
"epoch": 1.3123490762059864,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004838418833646875,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.19715505689382554,
|
|
"num_tokens": 26057400.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.443551826477051,
|
|
"epoch": 1.3129106531139438,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048382694005078485,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.20945798456668854,
|
|
"num_tokens": 26068981.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.514261913299561,
|
|
"epoch": 1.3134722300219015,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048381199008775165,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.20379933714866638,
|
|
"num_tokens": 26078902.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.368212032318115,
|
|
"epoch": 1.3140338069298592,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004837970334760635,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.21504038125276564,
|
|
"num_tokens": 26089891.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.476112031936646,
|
|
"epoch": 1.3145953838378166,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000483782070216197,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.2114596977829933,
|
|
"num_tokens": 26100701.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.431500196456909,
|
|
"epoch": 1.315156960745774,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004837671003086283,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20945687741041183,
|
|
"num_tokens": 26110496.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.376209402084351,
|
|
"epoch": 1.3157185376537317,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004837521237538342,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.2093929022550583,
|
|
"num_tokens": 26120580.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.415511989593506,
|
|
"epoch": 1.3162801145616891,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004837371405522915,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.20422524213790894,
|
|
"num_tokens": 26130936.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.586081886291504,
|
|
"epoch": 1.3168416914696468,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048372215070447734,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.20919155329465866,
|
|
"num_tokens": 26143027.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.442456960678101,
|
|
"epoch": 1.3174032683776042,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048370715421086884,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.20637834221124648,
|
|
"num_tokens": 26152874.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.3580890655517575,
|
|
"epoch": 1.317964845285562,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004836921510719438,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.21124010682106018,
|
|
"num_tokens": 26162781.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.431888771057129,
|
|
"epoch": 1.3185264221935193,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004836771412881795,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.20794233083724975,
|
|
"num_tokens": 26173498.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.450460386276245,
|
|
"epoch": 1.319087999101477,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004836621248600542,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.2120224729180336,
|
|
"num_tokens": 26185090.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.565145063400268,
|
|
"epoch": 1.3196495760094344,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004836471017880459,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.19550777226686478,
|
|
"num_tokens": 26197048.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.479478073120117,
|
|
"epoch": 1.320211152917392,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004836320720726329,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.21105331778526307,
|
|
"num_tokens": 26208037.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.5368914127349855,
|
|
"epoch": 1.3207727298253495,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004836170357142939,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.20094860792160035,
|
|
"num_tokens": 26219345.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.530802631378174,
|
|
"epoch": 1.3213343067333072,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004836019927135076,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.2052782878279686,
|
|
"num_tokens": 26230299.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.565100765228271,
|
|
"epoch": 1.3218958836412646,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004835869430707529,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.19602024257183076,
|
|
"num_tokens": 26241427.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.495163631439209,
|
|
"epoch": 1.3224574605492223,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048357188678650905,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.20612442791461943,
|
|
"num_tokens": 26252051.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.470046281814575,
|
|
"epoch": 1.3230190374571797,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004835568238612553,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.20017378628253937,
|
|
"num_tokens": 26263640.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.6278894424438475,
|
|
"epoch": 1.3235806143651372,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048354175429547155,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.19654083847999573,
|
|
"num_tokens": 26274996.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.555046796798706,
|
|
"epoch": 1.3241421912730948,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004835266780896374,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19163368493318558,
|
|
"num_tokens": 26287859.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.444681644439697,
|
|
"epoch": 1.3247037681810525,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004835115952442329,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.20850852578878404,
|
|
"num_tokens": 26298302.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.498977565765381,
|
|
"epoch": 1.32526534508901,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048349650575973843,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.20786529779434204,
|
|
"num_tokens": 26310755.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.564087867736816,
|
|
"epoch": 1.3258269219969674,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048348140963663436,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.19674757719039918,
|
|
"num_tokens": 26322041.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.54031229019165,
|
|
"epoch": 1.326388498904925,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004834663068754012,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.20908732265233992,
|
|
"num_tokens": 26334028.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.457029247283936,
|
|
"epoch": 1.3269500758128827,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004834511974765202,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.20485637038946153,
|
|
"num_tokens": 26344834.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.447680282592773,
|
|
"epoch": 1.3275116527208402,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048343608144047194,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.20233397036790848,
|
|
"num_tokens": 26354896.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.502441835403443,
|
|
"epoch": 1.3280732296287976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048342095876773825,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.20035932660102845,
|
|
"num_tokens": 26367487.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.478790140151977,
|
|
"epoch": 1.3286348065367553,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004834058294588003,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.20245476067066193,
|
|
"num_tokens": 26379384.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.523544836044311,
|
|
"epoch": 1.3291963834447127,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048339069351413993,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.20244939923286437,
|
|
"num_tokens": 26390268.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.513095426559448,
|
|
"epoch": 1.3297579603526704,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000483375550934239,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.1962406873703003,
|
|
"num_tokens": 26401348.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.460182476043701,
|
|
"epoch": 1.3303195372606278,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004833604017195798,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.19754060208797455,
|
|
"num_tokens": 26411955.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.428775310516357,
|
|
"epoch": 1.3308811141685855,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004833452458706445,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.20982491970062256,
|
|
"num_tokens": 26422200.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.466586017608643,
|
|
"epoch": 1.331442691076543,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004833300833879159,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.21005573570728303,
|
|
"num_tokens": 26433292.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.489848947525024,
|
|
"epoch": 1.3320042679845006,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004833149142718765,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.21193535029888153,
|
|
"num_tokens": 26444003.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.458115196228027,
|
|
"epoch": 1.332565844892458,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004832997385230096,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20870453715324402,
|
|
"num_tokens": 26455743.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.405208873748779,
|
|
"epoch": 1.3331274218004157,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004832845561417981,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.2006188616156578,
|
|
"num_tokens": 26466032.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.477620601654053,
|
|
"epoch": 1.333688998708373,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004832693671287256,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.20560259073972703,
|
|
"num_tokens": 26477660.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.445418500900269,
|
|
"epoch": 1.3342505756163305,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004832541714842757,
|
|
"loss": 5.1439,
|
|
"mean_token_accuracy": 0.2017123743891716,
|
|
"num_tokens": 26488778.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.563361549377442,
|
|
"epoch": 1.3348121525242882,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004832389692089321,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19800051003694535,
|
|
"num_tokens": 26500771.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.458716964721679,
|
|
"epoch": 1.3353737294322459,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048322376030317905,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20982384979724883,
|
|
"num_tokens": 26511786.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.523589372634888,
|
|
"epoch": 1.3359353063402033,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004832085447675007,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.20284539461135864,
|
|
"num_tokens": 26522273.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.614986801147461,
|
|
"epoch": 1.3364968832481607,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048319332260238153,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.19501916617155074,
|
|
"num_tokens": 26536619.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.633136129379272,
|
|
"epoch": 1.3370584601561184,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048317809380830624,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.19646344780921937,
|
|
"num_tokens": 26547807.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.5483640193939205,
|
|
"epoch": 1.337620037064076,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004831628583857597,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.1973729759454727,
|
|
"num_tokens": 26558924.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.479480934143067,
|
|
"epoch": 1.3381816139720335,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048314761633522696,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.20226964205503464,
|
|
"num_tokens": 26570123.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.527596092224121,
|
|
"epoch": 1.338743190879991,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004831323676571934,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.202111853659153,
|
|
"num_tokens": 26582841.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.493057823181152,
|
|
"epoch": 1.3393047677879486,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004831171123521446,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.20995640903711318,
|
|
"num_tokens": 26594397.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.478652811050415,
|
|
"epoch": 1.339866344695906,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004831018504205662,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.2005608335137367,
|
|
"num_tokens": 26605055.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.541445589065551,
|
|
"epoch": 1.3404279216038637,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048308658186294414,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.19142435640096664,
|
|
"num_tokens": 26616110.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.506478548049927,
|
|
"epoch": 1.3409894985118211,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004830713066797646,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.20804618299007416,
|
|
"num_tokens": 26627196.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.517919588088989,
|
|
"epoch": 1.3415510754197788,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048305602487151396,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.20589454770088195,
|
|
"num_tokens": 26637962.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.445713710784912,
|
|
"epoch": 1.3421126523277362,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004830407364386789,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.20405839383602142,
|
|
"num_tokens": 26649366.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.646371698379516,
|
|
"epoch": 1.342674229235694,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000483025441381746,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.19330827742815018,
|
|
"num_tokens": 26662455.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.513785648345947,
|
|
"epoch": 1.3432358061436513,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048301013970120235,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.20398487746715546,
|
|
"num_tokens": 26673467.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.432712984085083,
|
|
"epoch": 1.343797383051609,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048299483139753517,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.21189309954643248,
|
|
"num_tokens": 26684803.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.537512588500976,
|
|
"epoch": 1.3443589599595664,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004829795164712319,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.20224595963954925,
|
|
"num_tokens": 26696886.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.336465549468994,
|
|
"epoch": 1.3449205368675239,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048296419492278023,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.213582181930542,
|
|
"num_tokens": 26708489.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.524859952926636,
|
|
"epoch": 1.3454821137754815,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004829488667526679,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.2031543642282486,
|
|
"num_tokens": 26719599.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.4721612453460695,
|
|
"epoch": 1.3460436906834392,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048293353196138294,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.2075639247894287,
|
|
"num_tokens": 26730359.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.512526750564575,
|
|
"epoch": 1.3466052675913966,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048291819054941375,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.19536158740520476,
|
|
"num_tokens": 26742363.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.538867044448852,
|
|
"epoch": 1.347166844499354,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004829028425172487,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.19938648194074632,
|
|
"num_tokens": 26754058.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.522901821136474,
|
|
"epoch": 1.3477284214073117,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048288748786537656,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.20097279250621797,
|
|
"num_tokens": 26765602.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.3477284214073117,
|
|
"eval_entropy": 5.33797624992408,
|
|
"eval_loss": 5.255058765411377,
|
|
"eval_mean_token_accuracy": 0.20763108459235713,
|
|
"eval_num_tokens": 26765602.0,
|
|
"eval_runtime": 18.6333,
|
|
"eval_samples_per_second": 1664.385,
|
|
"eval_steps_per_second": 208.068,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.497710943222046,
|
|
"epoch": 1.3482899983152694,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004828721265942861,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.20861915051937102,
|
|
"num_tokens": 26776867.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.456263494491577,
|
|
"epoch": 1.3488515752232269,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048285675870446653,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.20104089230298997,
|
|
"num_tokens": 26786383.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.549209451675415,
|
|
"epoch": 1.3494131521311843,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048284138419640724,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.19341230839490892,
|
|
"num_tokens": 26797647.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.535245561599732,
|
|
"epoch": 1.349974729039142,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004828260030705976,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.20190462917089463,
|
|
"num_tokens": 26808674.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.442731857299805,
|
|
"epoch": 1.3505363059470994,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048281061532752734,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.2094086989760399,
|
|
"num_tokens": 26820858.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.466870546340942,
|
|
"epoch": 1.351097882855057,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004827952209676866,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.20888490378856658,
|
|
"num_tokens": 26831432.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.52585654258728,
|
|
"epoch": 1.3516594597630145,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048277981999156534,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.2032280907034874,
|
|
"num_tokens": 26843240.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.585193872451782,
|
|
"epoch": 1.3522210366709722,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048276441239965414,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.20121041536331177,
|
|
"num_tokens": 26853556.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.514213800430298,
|
|
"epoch": 1.3527826135789296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004827489981924434,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.20538239777088166,
|
|
"num_tokens": 26866040.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.422989368438721,
|
|
"epoch": 1.3533441904868873,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048273357737042393,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.21036700159311295,
|
|
"num_tokens": 26876796.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.451252222061157,
|
|
"epoch": 1.3539057673948447,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048271814993408694,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.20285652279853822,
|
|
"num_tokens": 26888081.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.485945558547973,
|
|
"epoch": 1.3544673443028024,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004827027158839233,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.19801271855831146,
|
|
"num_tokens": 26898511.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.54960355758667,
|
|
"epoch": 1.3550289212107598,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004826872752204248,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.20172447860240936,
|
|
"num_tokens": 26909525.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.537680196762085,
|
|
"epoch": 1.3555904981187172,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048267182794408276,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.21051943749189378,
|
|
"num_tokens": 26920267.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.532813501358032,
|
|
"epoch": 1.356152075026675,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004826563740553893,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.20705292224884034,
|
|
"num_tokens": 26931351.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.4343798637390135,
|
|
"epoch": 1.3567136519346326,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004826409135548363,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.20692224949598312,
|
|
"num_tokens": 26942235.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.586331558227539,
|
|
"epoch": 1.35727522884259,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004826254464429161,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.19957375079393386,
|
|
"num_tokens": 26953375.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.496713304519654,
|
|
"epoch": 1.3578368057505474,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048260997272012114,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.2064567819237709,
|
|
"num_tokens": 26965081.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.580369567871093,
|
|
"epoch": 1.358398382658505,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004825944923869441,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.20285850316286086,
|
|
"num_tokens": 26975428.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.522013568878174,
|
|
"epoch": 1.3589599595664628,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048257900544387795,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.2068055212497711,
|
|
"num_tokens": 26987040.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.550219535827637,
|
|
"epoch": 1.3595215364744202,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048256351189141574,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.19899569749832152,
|
|
"num_tokens": 26997931.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.528066730499267,
|
|
"epoch": 1.3600831133823776,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004825480117300508,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.20719457566738128,
|
|
"num_tokens": 27009528.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.397995376586914,
|
|
"epoch": 1.3606446902903353,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048253250496027675,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.21516991555690765,
|
|
"num_tokens": 27020161.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.486592149734497,
|
|
"epoch": 1.3612062671982927,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048251699158258714,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.2062772199511528,
|
|
"num_tokens": 27032246.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.580272674560547,
|
|
"epoch": 1.3617678441062504,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004825014715974761,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.20082351118326186,
|
|
"num_tokens": 27042903.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.577105093002319,
|
|
"epoch": 1.3623294210142078,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048248594500543767,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.19124043732881546,
|
|
"num_tokens": 27054854.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.509222078323364,
|
|
"epoch": 1.3628909979221655,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048247041180696633,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.21499997824430467,
|
|
"num_tokens": 27065021.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.466605091094971,
|
|
"epoch": 1.363452574830123,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004824548720025566,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.19943330585956573,
|
|
"num_tokens": 27075717.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.559400510787964,
|
|
"epoch": 1.3640141517380806,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004824393255927033,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.19467777907848358,
|
|
"num_tokens": 27087310.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.566907358169556,
|
|
"epoch": 1.364575728646038,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048242377257790145,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.19591184109449386,
|
|
"num_tokens": 27100218.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.4706371307373045,
|
|
"epoch": 1.3651373055539957,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048240821295864614,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.21119708120822905,
|
|
"num_tokens": 27111548.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.480509805679321,
|
|
"epoch": 1.3656988824619531,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000482392646735433,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.19908884167671204,
|
|
"num_tokens": 27123434.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.557414245605469,
|
|
"epoch": 1.3662604593699106,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004823770739087574,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.20108610689640044,
|
|
"num_tokens": 27135936.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.641396236419678,
|
|
"epoch": 1.3668220362778682,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004823614944791154,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.18949193954467775,
|
|
"num_tokens": 27148240.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.5515212059021,
|
|
"epoch": 1.367383613185826,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004823459084470031,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20711211115121841,
|
|
"num_tokens": 27159057.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.466819477081299,
|
|
"epoch": 1.3679451900937833,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004823303158129165,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.20519841015338897,
|
|
"num_tokens": 27169189.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.476657962799072,
|
|
"epoch": 1.3685067670017408,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004823147165773523,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20864174962043763,
|
|
"num_tokens": 27180777.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.498700761795044,
|
|
"epoch": 1.3690683439096984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048229911074080715,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.20824373364448548,
|
|
"num_tokens": 27190991.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.495569086074829,
|
|
"epoch": 1.369629920817656,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048228349830377787,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.20435912609100343,
|
|
"num_tokens": 27203776.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.453484535217285,
|
|
"epoch": 1.3701914977256135,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048226787926676165,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.2032044231891632,
|
|
"num_tokens": 27213533.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.524286127090454,
|
|
"epoch": 1.370753074633571,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048225225363025576,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.1985730215907097,
|
|
"num_tokens": 27224832.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.547903442382813,
|
|
"epoch": 1.3713146515415287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048223662139475773,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.19545191377401352,
|
|
"num_tokens": 27237313.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.4937316417694095,
|
|
"epoch": 1.371876228449486,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048222098256076523,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.20180035829544068,
|
|
"num_tokens": 27248159.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.546816825866699,
|
|
"epoch": 1.3724378053574438,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004822053371287763,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.20025649070739746,
|
|
"num_tokens": 27259723.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.488941669464111,
|
|
"epoch": 1.3729993822654012,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004821896850992891,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.20127565562725067,
|
|
"num_tokens": 27270207.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.51983904838562,
|
|
"epoch": 1.3735609591733589,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000482174026472802,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.2073459431529045,
|
|
"num_tokens": 27281243.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.395360708236694,
|
|
"epoch": 1.3741225360813163,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004821583612498135,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.21277892142534255,
|
|
"num_tokens": 27292816.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.462586402893066,
|
|
"epoch": 1.374684112989274,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048214268943082246,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.2059411346912384,
|
|
"num_tokens": 27304254.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.449819040298462,
|
|
"epoch": 1.3752456898972314,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004821270110163278,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.20056548565626145,
|
|
"num_tokens": 27314974.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.517911434173584,
|
|
"epoch": 1.375807266805189,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004821113260068288,
|
|
"loss": 5.209,
|
|
"mean_token_accuracy": 0.20083765387535096,
|
|
"num_tokens": 27326051.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.414068746566772,
|
|
"epoch": 1.3763688437131465,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004820956344028249,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.20370540022850037,
|
|
"num_tokens": 27337589.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.488991069793701,
|
|
"epoch": 1.376930420621104,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048207993620481566,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.20624958723783493,
|
|
"num_tokens": 27348581.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.562966299057007,
|
|
"epoch": 1.3774919975290616,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004820642314133009,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.2079665780067444,
|
|
"num_tokens": 27359963.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.551791048049926,
|
|
"epoch": 1.3780535744370193,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048204852002878073,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.20680660754442215,
|
|
"num_tokens": 27370149.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.422593116760254,
|
|
"epoch": 1.3786151513449767,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048203280205175544,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.2104777306318283,
|
|
"num_tokens": 27381657.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.517114686965942,
|
|
"epoch": 1.3791767282529341,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004820170774827253,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.19657099097967148,
|
|
"num_tokens": 27392679.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.444404411315918,
|
|
"epoch": 1.3797383051608918,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004820013463221912,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.20372104346752168,
|
|
"num_tokens": 27404003.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.490805339813233,
|
|
"epoch": 1.3802998820688495,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000481985608570654,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.2052875280380249,
|
|
"num_tokens": 27414593.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.597330904006958,
|
|
"epoch": 1.380861458976807,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004819698642286147,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.20135324746370314,
|
|
"num_tokens": 27426549.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.530772161483765,
|
|
"epoch": 1.3814230358847643,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048195411329657464,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.2009006306529045,
|
|
"num_tokens": 27439451.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.535411596298218,
|
|
"epoch": 1.381984612792722,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004819383557750353,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.20232640951871872,
|
|
"num_tokens": 27451153.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.42648344039917,
|
|
"epoch": 1.3825461897006794,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048192259166449845,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.20386051684617995,
|
|
"num_tokens": 27462229.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.437086153030395,
|
|
"epoch": 1.383107766608637,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048190682096546606,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.20354376137256622,
|
|
"num_tokens": 27473901.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.4474677562713625,
|
|
"epoch": 1.3836693435165945,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048189104367844034,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.20389060080051422,
|
|
"num_tokens": 27485981.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.470842361450195,
|
|
"epoch": 1.3842309204245522,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048187525980392343,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.2088720366358757,
|
|
"num_tokens": 27495764.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.503725576400757,
|
|
"epoch": 1.3847924973325096,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000481859469342418,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.2061014086008072,
|
|
"num_tokens": 27506602.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.402340269088745,
|
|
"epoch": 1.3853540742404673,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004818436722944269,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.2060158520936966,
|
|
"num_tokens": 27517482.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.485703086853027,
|
|
"epoch": 1.3859156511484247,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004818278686604531,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.21031182259321213,
|
|
"num_tokens": 27528560.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.554609680175782,
|
|
"epoch": 1.3864772280563824,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004818120584409996,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.20360119491815568,
|
|
"num_tokens": 27540019.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.558304309844971,
|
|
"epoch": 1.3870388049643398,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004817962416365701,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.20284420102834702,
|
|
"num_tokens": 27550553.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.5031187534332275,
|
|
"epoch": 1.3876003818722973,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048178041824766796,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.2070542573928833,
|
|
"num_tokens": 27562169.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.458979368209839,
|
|
"epoch": 1.388161958780255,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004817645882747971,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20763352811336516,
|
|
"num_tokens": 27571732.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.4388587474823,
|
|
"epoch": 1.3887235356882126,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004817487517184616,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.21034144908189772,
|
|
"num_tokens": 27584394.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.444096803665161,
|
|
"epoch": 1.38928511259617,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004817329085791657,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.2104029417037964,
|
|
"num_tokens": 27594813.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.404346179962158,
|
|
"epoch": 1.3898466895041275,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004817170588574138,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.21349056512117387,
|
|
"num_tokens": 27605375.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.421451711654663,
|
|
"epoch": 1.3904082664120851,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004817012025537105,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.20624356716871262,
|
|
"num_tokens": 27617066.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.537290143966675,
|
|
"epoch": 1.3909698433200428,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004816853396685608,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.20176378935575484,
|
|
"num_tokens": 27628667.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.471972036361694,
|
|
"epoch": 1.3915314202280002,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048166947020246973,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.207648865878582,
|
|
"num_tokens": 27638858.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.5419025897979735,
|
|
"epoch": 1.3920929971359577,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048165359415594245,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.20475948601961136,
|
|
"num_tokens": 27650518.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.534703350067138,
|
|
"epoch": 1.3926545740439153,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048163771152948473,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.2032874897122383,
|
|
"num_tokens": 27661781.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.466270542144775,
|
|
"epoch": 1.3932161509518728,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000481621822323602,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.2084590569138527,
|
|
"num_tokens": 27673040.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.484113931655884,
|
|
"epoch": 1.3937777278598305,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004816059265388004,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.21026469320058822,
|
|
"num_tokens": 27683541.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.557560443878174,
|
|
"epoch": 1.394339304767788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048159002417558596,
|
|
"loss": 5.2459,
|
|
"mean_token_accuracy": 0.20254075974226,
|
|
"num_tokens": 27693648.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.499498558044434,
|
|
"epoch": 1.3949008816757456,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004815741152344651,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.21289087682962418,
|
|
"num_tokens": 27703920.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.601294136047363,
|
|
"epoch": 1.395462458583703,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004815581997159442,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19846349954605103,
|
|
"num_tokens": 27715869.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.44151029586792,
|
|
"epoch": 1.3960240354916607,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048154227762053003,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20914554446935654,
|
|
"num_tokens": 27726727.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.452362012863159,
|
|
"epoch": 1.396585612399618,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004815263489487298,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.20661979615688325,
|
|
"num_tokens": 27738217.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.518127536773681,
|
|
"epoch": 1.3971471893075758,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004815104137010504,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.2047643929719925,
|
|
"num_tokens": 27749022.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.415575075149536,
|
|
"epoch": 1.3977087662155332,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004814944718779993,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20679193884134292,
|
|
"num_tokens": 27760589.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.557589054107666,
|
|
"epoch": 1.3982703431234906,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004814785234800843,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.2044275000691414,
|
|
"num_tokens": 27772460.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.414005994796753,
|
|
"epoch": 1.3988319200314483,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048146256850781287,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.2072130933403969,
|
|
"num_tokens": 27783921.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.4935948848724365,
|
|
"epoch": 1.399393496939406,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048144660696169327,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.2041731670498848,
|
|
"num_tokens": 27794843.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.53591136932373,
|
|
"epoch": 1.3999550738473634,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048143063884223365,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20303187668323516,
|
|
"num_tokens": 27805973.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.4559375762939455,
|
|
"epoch": 1.4005166507553208,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004814146641499424,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.20391714125871657,
|
|
"num_tokens": 27816916.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.4387753963470455,
|
|
"epoch": 1.4010782276632785,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048139868288532816,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.20127159506082534,
|
|
"num_tokens": 27828077.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.4449605464935305,
|
|
"epoch": 1.4016398045712362,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004813826950488998,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.2075975865125656,
|
|
"num_tokens": 27838502.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.473459959030151,
|
|
"epoch": 1.4022013814791936,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048136670064116645,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.19648669362068177,
|
|
"num_tokens": 27850125.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.47822904586792,
|
|
"epoch": 1.402762958387151,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004813506996626373,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.20432399213314056,
|
|
"num_tokens": 27861099.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.509974575042724,
|
|
"epoch": 1.4033245352951087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004813346921138218,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.20813720524311066,
|
|
"num_tokens": 27872769.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.557191371917725,
|
|
"epoch": 1.4038861122030661,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004813186779952297,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.1981686070561409,
|
|
"num_tokens": 27884448.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.39212999343872,
|
|
"epoch": 1.4044476891110238,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004813026573073708,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.1989894062280655,
|
|
"num_tokens": 27894074.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.5973752498626705,
|
|
"epoch": 1.4050092660189812,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004812866300507554,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.20097675770521164,
|
|
"num_tokens": 27905150.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.541794729232788,
|
|
"epoch": 1.405570842926939,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004812705962258936,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.20288977026939392,
|
|
"num_tokens": 27916471.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.431574487686158,
|
|
"epoch": 1.4061324198348963,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004812545558332961,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.20784371197223664,
|
|
"num_tokens": 27928276.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.507085990905762,
|
|
"epoch": 1.406693996742854,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048123850887347346,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.19724205434322356,
|
|
"num_tokens": 27940417.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.4232011318206785,
|
|
"epoch": 1.4072555736508114,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048122245534693676,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.20738717168569565,
|
|
"num_tokens": 27950490.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.561733770370483,
|
|
"epoch": 1.407817150558769,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004812063952541971,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.19742528349161148,
|
|
"num_tokens": 27962593.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.5874659538269045,
|
|
"epoch": 1.4083787274667265,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048119032859576577,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.19798455983400345,
|
|
"num_tokens": 27973567.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.439869022369384,
|
|
"epoch": 1.408940304374684,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004811742553721545,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.2105448693037033,
|
|
"num_tokens": 27984383.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.551486015319824,
|
|
"epoch": 1.4095018812826416,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048115817558387494,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.1968330919742584,
|
|
"num_tokens": 27995735.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.528323554992676,
|
|
"epoch": 1.4100634581905993,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004811420892314391,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.190450756251812,
|
|
"num_tokens": 28008261.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.452762269973755,
|
|
"epoch": 1.4106250350985567,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004811259963153592,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.2082456961274147,
|
|
"num_tokens": 28019424.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.525183391571045,
|
|
"epoch": 1.4111866120065142,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004811098968361476,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20304550975561142,
|
|
"num_tokens": 28030961.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.54337706565857,
|
|
"epoch": 1.4117481889144718,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000481093790794317,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.20423642098903655,
|
|
"num_tokens": 28042580.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.636703586578369,
|
|
"epoch": 1.4123097658224295,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004810776781903801,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.2045416474342346,
|
|
"num_tokens": 28053435.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.606952381134033,
|
|
"epoch": 1.412871342730387,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048106155902485003,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.1969788745045662,
|
|
"num_tokens": 28065195.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.554935693740845,
|
|
"epoch": 1.4134329196383444,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004810454332982401,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.20080669075250626,
|
|
"num_tokens": 28077457.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.42911319732666,
|
|
"epoch": 1.413994496546302,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004810293010110635,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.20499158650636673,
|
|
"num_tokens": 28087598.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.442728853225708,
|
|
"epoch": 1.4145560734542595,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004810131621638342,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.20429084748029708,
|
|
"num_tokens": 28097232.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.503100204467773,
|
|
"epoch": 1.4151176503622171,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048099701675706583,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.20885875225067138,
|
|
"num_tokens": 28107333.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.517981481552124,
|
|
"epoch": 1.4156792272701746,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004809808647912725,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.1994278609752655,
|
|
"num_tokens": 28117886.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.507156753540039,
|
|
"epoch": 1.4162408041781323,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004809647062669686,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.20488383769989013,
|
|
"num_tokens": 28128884.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.528198766708374,
|
|
"epoch": 1.4168023810860897,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048094854118466856,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.19539733082056046,
|
|
"num_tokens": 28139859.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.6049333095550535,
|
|
"epoch": 1.4173639579940474,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048093236954488715,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.2046104460954666,
|
|
"num_tokens": 28150398.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.462273836135864,
|
|
"epoch": 1.4179255349020048,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004809161913481392,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.21141815185546875,
|
|
"num_tokens": 28160766.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.464865493774414,
|
|
"epoch": 1.4184871118099625,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048090000659493985,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.19815744310617447,
|
|
"num_tokens": 28171583.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.461806726455689,
|
|
"epoch": 1.41904868871792,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048088381528580445,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.20837399661540984,
|
|
"num_tokens": 28183598.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.489366865158081,
|
|
"epoch": 1.4196102656258773,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048086761742124846,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.199583899974823,
|
|
"num_tokens": 28193377.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.462654495239258,
|
|
"epoch": 1.420171842533835,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048085141300178774,
|
|
"loss": 5.0952,
|
|
"mean_token_accuracy": 0.21381045877933502,
|
|
"num_tokens": 28204536.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.437311410903931,
|
|
"epoch": 1.4207334194417927,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048083520202793815,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.2057908907532692,
|
|
"num_tokens": 28215806.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.518252611160278,
|
|
"epoch": 1.42129499634975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004808189845002159,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.20519598424434662,
|
|
"num_tokens": 28226765.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.668955993652344,
|
|
"epoch": 1.4218565732577075,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004808027604191374,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.19559611827135087,
|
|
"num_tokens": 28238077.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.5135125637054445,
|
|
"epoch": 1.4224181501656652,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048078652978521914,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.2035637155175209,
|
|
"num_tokens": 28248992.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.489764595031739,
|
|
"epoch": 1.4229797270736229,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048077029259897797,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.20847177356481553,
|
|
"num_tokens": 28259818.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.45495285987854,
|
|
"epoch": 1.4235413039815803,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048075404886093094,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.2034291073679924,
|
|
"num_tokens": 28271139.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.467867183685303,
|
|
"epoch": 1.4241028808895377,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048073779857159504,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.2086794376373291,
|
|
"num_tokens": 28282093.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.4350916862487795,
|
|
"epoch": 1.4246644577974954,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000480721541731488,
|
|
"loss": 5.0549,
|
|
"mean_token_accuracy": 0.21787738651037217,
|
|
"num_tokens": 28292701.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.411337423324585,
|
|
"epoch": 1.4252260347054528,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048070527834112727,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.20686551928520203,
|
|
"num_tokens": 28303585.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.448253011703491,
|
|
"epoch": 1.4257876116134105,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004806890084010306,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.20877012312412263,
|
|
"num_tokens": 28314583.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.494606924057007,
|
|
"epoch": 1.426349188521368,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048067273191171615,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.2048094391822815,
|
|
"num_tokens": 28325895.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.529941749572754,
|
|
"epoch": 1.4269107654293256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004806564488737022,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.19825132042169571,
|
|
"num_tokens": 28337011.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.590207481384278,
|
|
"epoch": 1.427472342337283,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004806401592875071,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.19873934239149094,
|
|
"num_tokens": 28347468.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.483589458465576,
|
|
"epoch": 1.4280339192452407,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048062386315364964,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.207298082113266,
|
|
"num_tokens": 28357287.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.511699676513672,
|
|
"epoch": 1.4285954961531981,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004806075604726485,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.21166201680898666,
|
|
"num_tokens": 28368508.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.523208045959473,
|
|
"epoch": 1.4291570730611558,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048059125124502304,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.21051563769578935,
|
|
"num_tokens": 28378211.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.4040556907653805,
|
|
"epoch": 1.4297186499691132,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004805749354712924,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.21346246004104613,
|
|
"num_tokens": 28389083.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.490037631988526,
|
|
"epoch": 1.4302802268770707,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000480558613151976,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.2049003228545189,
|
|
"num_tokens": 28399786.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.465353012084961,
|
|
"epoch": 1.4308418037850283,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004805422842875936,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.19791448265314102,
|
|
"num_tokens": 28410650.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.499770164489746,
|
|
"epoch": 1.431403380692986,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048052594887866524,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.19996725618839264,
|
|
"num_tokens": 28421485.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.486325597763061,
|
|
"epoch": 1.4319649576009434,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048050960692571086,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.1964434951543808,
|
|
"num_tokens": 28432469.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.483646011352539,
|
|
"epoch": 1.4325265345089009,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000480493258429251,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.20641259849071503,
|
|
"num_tokens": 28443628.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.574559926986694,
|
|
"epoch": 1.4330881114168585,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000480476903389806,
|
|
"loss": 5.2066,
|
|
"mean_token_accuracy": 0.19910151660442352,
|
|
"num_tokens": 28455106.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.531880712509155,
|
|
"epoch": 1.4336496883248162,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004804605418078968,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.20725723206996918,
|
|
"num_tokens": 28466326.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.507378482818604,
|
|
"epoch": 1.4342112652327736,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048044417368404426,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.19759187251329421,
|
|
"num_tokens": 28477490.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.475937175750732,
|
|
"epoch": 1.434772842140731,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048042779901876946,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.20283553451299668,
|
|
"num_tokens": 28489780.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.581762075424194,
|
|
"epoch": 1.4353344190486887,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004804114178125939,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.20140236020088195,
|
|
"num_tokens": 28500335.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.395640468597412,
|
|
"epoch": 1.4358959959566462,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004803950300660391,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.2116109699010849,
|
|
"num_tokens": 28510680.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.397906732559204,
|
|
"epoch": 1.4364575728646038,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004803786357796269,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.21677436232566832,
|
|
"num_tokens": 28521719.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.488759326934814,
|
|
"epoch": 1.4370191497725613,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048036223495387934,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.20295445919036864,
|
|
"num_tokens": 28531935.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.580298042297363,
|
|
"epoch": 1.437580726680519,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004803458275893185,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.20487633347511292,
|
|
"num_tokens": 28542529.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.500527238845825,
|
|
"epoch": 1.4381423035884764,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004803294136864669,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.20684662759304046,
|
|
"num_tokens": 28554724.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.483481693267822,
|
|
"epoch": 1.438703880496434,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048031299324584716,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.21032027304172515,
|
|
"num_tokens": 28565781.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.531556606292725,
|
|
"epoch": 1.4392654574043915,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000480296566267982,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.20668769329786302,
|
|
"num_tokens": 28576186.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.438735485076904,
|
|
"epoch": 1.4398270343123492,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004802801327533947,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.19661445915699005,
|
|
"num_tokens": 28588240.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.53498911857605,
|
|
"epoch": 1.4403886112203066,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048026369270260814,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.20387566834688187,
|
|
"num_tokens": 28598240.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.503182744979858,
|
|
"epoch": 1.440950188128264,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004802472461161462,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.20545268654823304,
|
|
"num_tokens": 28610091.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.552025842666626,
|
|
"epoch": 1.4415117650362217,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004802307929945322,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.2018478125333786,
|
|
"num_tokens": 28621060.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.56445279121399,
|
|
"epoch": 1.4420733419441794,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048021433333829015,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.2010716676712036,
|
|
"num_tokens": 28632027.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.587222576141357,
|
|
"epoch": 1.4426349188521368,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048019786714794424,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.20118342489004135,
|
|
"num_tokens": 28643959.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.51765718460083,
|
|
"epoch": 1.4431964957600942,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004801813944240186,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.2083578422665596,
|
|
"num_tokens": 28654166.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.526371479034424,
|
|
"epoch": 1.443758072668052,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004801649151670378,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.2033152773976326,
|
|
"num_tokens": 28667975.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.451838731765747,
|
|
"epoch": 1.4443196495760096,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004801484293775265,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.20488449633121492,
|
|
"num_tokens": 28679333.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.4952010154724125,
|
|
"epoch": 1.444881226483967,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004801319370560097,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.2011541396379471,
|
|
"num_tokens": 28689333.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.482318639755249,
|
|
"epoch": 1.4454428033919244,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004801154382030124,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.19327963888645172,
|
|
"num_tokens": 28700625.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.557748794555664,
|
|
"epoch": 1.446004380299882,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048009893281906004,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.19462643712759017,
|
|
"num_tokens": 28711768.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.496714448928833,
|
|
"epoch": 1.4465659572078395,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048008242090467803,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.20154512971639632,
|
|
"num_tokens": 28722521.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.516492414474487,
|
|
"epoch": 1.4471275341157972,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004800659024603923,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.2028385728597641,
|
|
"num_tokens": 28733293.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.525970840454102,
|
|
"epoch": 1.4476891110237546,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048004937748672864,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.200331349670887,
|
|
"num_tokens": 28744351.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.486081600189209,
|
|
"epoch": 1.4482506879317123,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048003284598421327,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.2036825656890869,
|
|
"num_tokens": 28755140.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.471679830551148,
|
|
"epoch": 1.4488122648396697,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004800163079533726,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.1998772531747818,
|
|
"num_tokens": 28767161.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.515220594406128,
|
|
"epoch": 1.4493738417476274,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004799997633947332,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.20970503240823746,
|
|
"num_tokens": 28779501.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.560624885559082,
|
|
"epoch": 1.4499354186555848,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047998321230882174,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.20084631443023682,
|
|
"num_tokens": 28792021.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.468725967407226,
|
|
"epoch": 1.4504969955635425,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047996665469616536,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.20264436453580856,
|
|
"num_tokens": 28802445.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.44990758895874,
|
|
"epoch": 1.4510585724715,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047995009055729114,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.1998769998550415,
|
|
"num_tokens": 28813821.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.507661008834839,
|
|
"epoch": 1.4516201493794574,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004799335198927266,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.20149943828582764,
|
|
"num_tokens": 28824764.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.591539144515991,
|
|
"epoch": 1.452181726287415,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004799169427029993,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.20335527658462524,
|
|
"num_tokens": 28836720.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.480762100219726,
|
|
"epoch": 1.4527433031953727,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047990035898863706,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.2102635085582733,
|
|
"num_tokens": 28848846.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.48568754196167,
|
|
"epoch": 1.4533048801033301,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004798837687501679,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20463081002235411,
|
|
"num_tokens": 28859453.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.478490877151489,
|
|
"epoch": 1.4538664570112876,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004798671719881201,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.19836125671863555,
|
|
"num_tokens": 28869447.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.563143348693847,
|
|
"epoch": 1.4544280339192452,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004798505687030221,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19861640632152558,
|
|
"num_tokens": 28881660.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.525450611114502,
|
|
"epoch": 1.454989610827203,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004798339588954025,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.2004323422908783,
|
|
"num_tokens": 28893128.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.455665922164917,
|
|
"epoch": 1.4555511877351603,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004798173425657903,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.2062700629234314,
|
|
"num_tokens": 28904323.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.532237577438354,
|
|
"epoch": 1.4561127646431178,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004798007197147144,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.20618950575590134,
|
|
"num_tokens": 28915672.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.640072870254516,
|
|
"epoch": 1.4566743415510754,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004797840903427042,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19935886263847352,
|
|
"num_tokens": 28926657.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.449579954147339,
|
|
"epoch": 1.4572359184590329,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047976745445028906,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.20841774642467498,
|
|
"num_tokens": 28938787.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.437258100509643,
|
|
"epoch": 1.4577974953669905,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047975081203799883,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.1978024274110794,
|
|
"num_tokens": 28949836.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.456229257583618,
|
|
"epoch": 1.458359072274948,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047973416310636327,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.20242137163877488,
|
|
"num_tokens": 28960053.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.582259607315064,
|
|
"epoch": 1.4589206491829056,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004797175076559126,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.1987023115158081,
|
|
"num_tokens": 28972698.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.557965040206909,
|
|
"epoch": 1.459482226090863,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047970084568717703,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.1978571742773056,
|
|
"num_tokens": 28984756.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.47187557220459,
|
|
"epoch": 1.4600438029988208,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004796841772006872,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19621590673923492,
|
|
"num_tokens": 28996915.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.495768642425537,
|
|
"epoch": 1.4606053799067782,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047966750219697376,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.2081008017063141,
|
|
"num_tokens": 29007462.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.536022806167603,
|
|
"epoch": 1.4611669568147359,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004796508206765677,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.20109666287899017,
|
|
"num_tokens": 29017790.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.5563554763793945,
|
|
"epoch": 1.4617285337226933,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047963413264000005,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.1972089886665344,
|
|
"num_tokens": 29029536.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.463431692123413,
|
|
"epoch": 1.4622901106306507,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004796174380878023,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.20624855160713196,
|
|
"num_tokens": 29039840.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.5754475593566895,
|
|
"epoch": 1.4628516875386084,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000479600737020506,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.19621271640062332,
|
|
"num_tokens": 29052769.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.492337083816528,
|
|
"epoch": 1.463413264446566,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004795840294386429,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.2086642324924469,
|
|
"num_tokens": 29063645.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.52324275970459,
|
|
"epoch": 1.4639748413545235,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047956731534274483,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.2010996326804161,
|
|
"num_tokens": 29075241.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.580390691757202,
|
|
"epoch": 1.464536418262481,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047955059473334425,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.20309315919876098,
|
|
"num_tokens": 29087592.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.507116031646729,
|
|
"epoch": 1.4650979951704386,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004795338676109733,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.20337121039628983,
|
|
"num_tokens": 29099314.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.447659969329834,
|
|
"epoch": 1.4656595720783963,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004795171339761647,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.2090732201933861,
|
|
"num_tokens": 29111916.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.525622701644897,
|
|
"epoch": 1.4662211489863537,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00047950039382945126,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.20384916067123413,
|
|
"num_tokens": 29122871.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.509528970718383,
|
|
"epoch": 1.4667827258943111,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047948364717136587,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.202441568672657,
|
|
"num_tokens": 29133873.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.429511260986328,
|
|
"epoch": 1.4673443028022688,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047946689400244196,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21140723973512648,
|
|
"num_tokens": 29144995.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.591714143753052,
|
|
"epoch": 1.4679058797102262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047945013432321284,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.2023511901497841,
|
|
"num_tokens": 29156801.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.5448582649230955,
|
|
"epoch": 1.468467456618184,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047943336813421205,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19900913536548615,
|
|
"num_tokens": 29168072.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.4832601070404055,
|
|
"epoch": 1.4690290335261413,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004794165954359736,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.2039378359913826,
|
|
"num_tokens": 29179314.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.540052175521851,
|
|
"epoch": 1.469590610434099,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004793998162290315,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.19900225847959518,
|
|
"num_tokens": 29190808.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.602590322494507,
|
|
"epoch": 1.4701521873420564,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004793830305139199,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.1977110981941223,
|
|
"num_tokens": 29202557.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.484500074386597,
|
|
"epoch": 1.470713764250014,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004793662382911734,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.21441672295331954,
|
|
"num_tokens": 29213959.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.5077259063720705,
|
|
"epoch": 1.4712753411579715,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004793494395613265,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.20909364074468612,
|
|
"num_tokens": 29226069.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.552921390533447,
|
|
"epoch": 1.4718369180659292,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004793326343249144,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.2012652799487114,
|
|
"num_tokens": 29237882.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.494494295120239,
|
|
"epoch": 1.4723984949738866,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004793158225824718,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.2095244124531746,
|
|
"num_tokens": 29248642.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.4406322002410885,
|
|
"epoch": 1.4729600718818443,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047929900433453423,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.19891600906848908,
|
|
"num_tokens": 29260632.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.583199787139892,
|
|
"epoch": 1.4735216487898017,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047928217958163703,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.20301962047815322,
|
|
"num_tokens": 29272563.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.573705434799194,
|
|
"epoch": 1.4740832256977594,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047926534832431615,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.20521591305732728,
|
|
"num_tokens": 29284307.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.466789865493775,
|
|
"epoch": 1.4746448026057168,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004792485105631073,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20379205495119096,
|
|
"num_tokens": 29295413.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.5649176120758055,
|
|
"epoch": 1.4752063795136743,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004792316662985467,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.2123536467552185,
|
|
"num_tokens": 29306612.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.515388441085816,
|
|
"epoch": 1.475767956421632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047921481553117053,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20414846539497375,
|
|
"num_tokens": 29316168.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.534075784683227,
|
|
"epoch": 1.4763295333295896,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047919795826151544,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.20142834186553954,
|
|
"num_tokens": 29326949.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.552636814117432,
|
|
"epoch": 1.476891110237547,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004791810944901183,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.1983877971768379,
|
|
"num_tokens": 29336744.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.50050983428955,
|
|
"epoch": 1.4774526871455045,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004791642242175158,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.20590704977512359,
|
|
"num_tokens": 29346964.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.536026096343994,
|
|
"epoch": 1.4780142640534621,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047914734744424517,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.20866819769144057,
|
|
"num_tokens": 29358689.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.490043449401855,
|
|
"epoch": 1.4785758409614196,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00047913046417084393,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.20249856859445572,
|
|
"num_tokens": 29371243.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.458896970748901,
|
|
"epoch": 1.4791374178693772,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047911357439784947,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.20399961918592452,
|
|
"num_tokens": 29383185.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.373764991760254,
|
|
"epoch": 1.4796989947773347,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047909667812579964,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.21709532737731935,
|
|
"num_tokens": 29393986.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.457058477401733,
|
|
"epoch": 1.4802605716852923,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047907977535523253,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.20191623419523239,
|
|
"num_tokens": 29405407.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.483112812042236,
|
|
"epoch": 1.4808221485932498,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004790628660866861,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.20392364859580994,
|
|
"num_tokens": 29416352.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.45804615020752,
|
|
"epoch": 1.4813837255012074,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004790459503206989,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.21235640197992325,
|
|
"num_tokens": 29428369.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.459068155288696,
|
|
"epoch": 1.4819453024091649,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004790290280578095,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.20606256276369095,
|
|
"num_tokens": 29439276.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.516929292678833,
|
|
"epoch": 1.4825068793171226,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047901209929855675,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.19711132049560548,
|
|
"num_tokens": 29451361.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.509707403182984,
|
|
"epoch": 1.48306845622508,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004789951640434796,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.20525734573602678,
|
|
"num_tokens": 29462977.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.477004051208496,
|
|
"epoch": 1.4836300331330377,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004789782222931173,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.20510006099939346,
|
|
"num_tokens": 29474641.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.4767804622650145,
|
|
"epoch": 1.484191610040995,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047896127404800935,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.21179405003786086,
|
|
"num_tokens": 29485560.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.468793296813965,
|
|
"epoch": 1.4847531869489528,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004789443193086953,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.20467235147953033,
|
|
"num_tokens": 29495872.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.408811283111572,
|
|
"epoch": 1.4853147638569102,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047892735807571505,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.20997899770736694,
|
|
"num_tokens": 29506704.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.4908740520477295,
|
|
"epoch": 1.4858763407648676,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004789103903496086,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.2015948548913002,
|
|
"num_tokens": 29518226.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.527553558349609,
|
|
"epoch": 1.4864379176728253,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004788934161309161,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.21100272834300995,
|
|
"num_tokens": 29529176.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.362975931167602,
|
|
"epoch": 1.486999494580783,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047887643542017836,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.2152286633849144,
|
|
"num_tokens": 29539268.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.469855833053589,
|
|
"epoch": 1.4875610714887404,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047885944821793574,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.19900360852479934,
|
|
"num_tokens": 29550491.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.434439373016358,
|
|
"epoch": 1.4881226483966978,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047884245452472926,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.21064575612545014,
|
|
"num_tokens": 29561520.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.464705848693848,
|
|
"epoch": 1.4886842253046555,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004788254543410999,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.20743813663721083,
|
|
"num_tokens": 29573974.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.436029624938965,
|
|
"epoch": 1.489245802212613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047880844766758914,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.21420436948537827,
|
|
"num_tokens": 29584059.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.569355154037476,
|
|
"epoch": 1.4898073791205706,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047879143450473824,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.19782427698373795,
|
|
"num_tokens": 29595726.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.459931087493897,
|
|
"epoch": 1.490368956028528,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047877441485308917,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.20454682260751725,
|
|
"num_tokens": 29607354.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.495728015899658,
|
|
"epoch": 1.4909305329364857,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047875738871318356,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.2087203860282898,
|
|
"num_tokens": 29618698.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.4124589443206785,
|
|
"epoch": 1.4914921098444431,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004787403560855637,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.20769940614700316,
|
|
"num_tokens": 29629578.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.401314115524292,
|
|
"epoch": 1.4920536867524008,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004787233169707719,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.21234250366687774,
|
|
"num_tokens": 29640277.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.489649629592895,
|
|
"epoch": 1.4926152636603582,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004787062713693507,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.21218884438276292,
|
|
"num_tokens": 29652029.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.500289726257324,
|
|
"epoch": 1.493176840568316,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047868921928184276,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.20104728788137435,
|
|
"num_tokens": 29663191.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.52383246421814,
|
|
"epoch": 1.4937384174762733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004786721607087911,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.2027999922633171,
|
|
"num_tokens": 29674238.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.456110095977783,
|
|
"epoch": 1.494299994384231,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004786550956507389,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.2109331175684929,
|
|
"num_tokens": 29687255.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.412745761871338,
|
|
"epoch": 1.4948615712921884,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004786380241082294,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.20765042603015899,
|
|
"num_tokens": 29699769.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.5386137008667,
|
|
"epoch": 1.495423148200146,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047862094608180623,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.2005414679646492,
|
|
"num_tokens": 29710281.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.42203369140625,
|
|
"epoch": 1.4959847251081035,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004786038615720132,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.20121001154184343,
|
|
"num_tokens": 29720647.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.461383628845215,
|
|
"epoch": 1.496546302016061,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047858677057939427,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.20714598000049592,
|
|
"num_tokens": 29731565.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.475412225723266,
|
|
"epoch": 1.4971078789240186,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047856967310449356,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.20682589411735536,
|
|
"num_tokens": 29743361.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.532949161529541,
|
|
"epoch": 1.4976694558319763,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047855256914785556,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.20206800252199172,
|
|
"num_tokens": 29754799.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.567881965637207,
|
|
"epoch": 1.4982310327399337,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047853545871002476,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.19870063811540603,
|
|
"num_tokens": 29766401.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.406255197525025,
|
|
"epoch": 1.4987926096478912,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047851834179154595,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.2115085557103157,
|
|
"num_tokens": 29778268.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.383055543899536,
|
|
"epoch": 1.4993541865558488,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004785012183929643,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.21305858343839645,
|
|
"num_tokens": 29788551.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.422095823287964,
|
|
"epoch": 1.4999157634638065,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004784840885148249,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.20456785559654236,
|
|
"num_tokens": 29799726.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.547292327880859,
|
|
"epoch": 1.500477340371764,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004784669521576732,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.19940493255853653,
|
|
"num_tokens": 29810615.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.545436143875122,
|
|
"epoch": 1.5010389172797214,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004784498093220549,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.20214506834745408,
|
|
"num_tokens": 29821766.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.440043592453003,
|
|
"epoch": 1.501600494187679,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004784326600085157,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.19981027841567994,
|
|
"num_tokens": 29833724.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.411453723907471,
|
|
"epoch": 1.5021620710956367,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047841550421760164,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.20726653039455414,
|
|
"num_tokens": 29845057.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.564109468460083,
|
|
"epoch": 1.502723648003594,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047839834194985916,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.20515116006135942,
|
|
"num_tokens": 29855649.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.413768148422241,
|
|
"epoch": 1.5032852249115516,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004783811732058345,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.2132214531302452,
|
|
"num_tokens": 29866873.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.4703161239624025,
|
|
"epoch": 1.5038468018195092,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047836399798607446,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.2132996290922165,
|
|
"num_tokens": 29877690.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.445072174072266,
|
|
"epoch": 1.5044083787274667,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047834681629112583,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.22065869867801666,
|
|
"num_tokens": 29888461.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.428515481948852,
|
|
"epoch": 1.5049699556354241,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004783296281215357,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.2057355150580406,
|
|
"num_tokens": 29900559.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.425696229934692,
|
|
"epoch": 1.5055315325433818,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004783124334778513,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.2091197356581688,
|
|
"num_tokens": 29910815.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.507459020614624,
|
|
"epoch": 1.5060931094513395,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004782952323606202,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.20958788245916365,
|
|
"num_tokens": 29923262.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.443155193328858,
|
|
"epoch": 1.506654686359297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004782780247703901,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.21308889538049697,
|
|
"num_tokens": 29934744.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.612390518188477,
|
|
"epoch": 1.5072162632672543,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004782608107077088,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.20269352346658706,
|
|
"num_tokens": 29945828.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.378164148330688,
|
|
"epoch": 1.507777840175212,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047824359017312445,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.20988098680973052,
|
|
"num_tokens": 29956964.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.4697184562683105,
|
|
"epoch": 1.5083394170831697,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004782263631671854,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.20542096048593522,
|
|
"num_tokens": 29968004.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.494173574447632,
|
|
"epoch": 1.508900993991127,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047820912969044014,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.20844811499118804,
|
|
"num_tokens": 29978237.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.465075826644897,
|
|
"epoch": 1.5094625708990845,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047819188974343734,
|
|
"loss": 5.1891,
|
|
"mean_token_accuracy": 0.19899044185876846,
|
|
"num_tokens": 29988379.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.489539909362793,
|
|
"epoch": 1.5100241478070422,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004781746433267259,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.20161818265914916,
|
|
"num_tokens": 29999024.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.515763425827027,
|
|
"epoch": 1.5105857247149999,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047815739044085515,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.21352389007806777,
|
|
"num_tokens": 30009411.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.452477169036865,
|
|
"epoch": 1.5111473016229573,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047814013108637423,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.20740083307027818,
|
|
"num_tokens": 30020746.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.530014944076538,
|
|
"epoch": 1.5117088785309147,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047812286526383274,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.2060213178396225,
|
|
"num_tokens": 30032568.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.553374528884888,
|
|
"epoch": 1.5122704554388724,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004781055929737804,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.20265100747346879,
|
|
"num_tokens": 30042772.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.474301099777222,
|
|
"epoch": 1.51283203234683,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047808831421676724,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.20398659855127335,
|
|
"num_tokens": 30053842.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.543632650375367,
|
|
"epoch": 1.5133936092547875,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004780710289933435,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.20971821248531342,
|
|
"num_tokens": 30064744.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.476887607574463,
|
|
"epoch": 1.513955186162745,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004780537373040593,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.20243102461099624,
|
|
"num_tokens": 30075475.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.449625825881958,
|
|
"epoch": 1.5145167630707026,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047803643914946537,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.20403434336185455,
|
|
"num_tokens": 30087189.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.510852861404419,
|
|
"epoch": 1.51507833997866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004780191345301125,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.19888321310281754,
|
|
"num_tokens": 30099263.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.49517126083374,
|
|
"epoch": 1.5156399168866175,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047800182344655165,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.2001742199063301,
|
|
"num_tokens": 30110925.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.520921945571899,
|
|
"epoch": 1.5162014937945751,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000477984505899334,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.19932752549648286,
|
|
"num_tokens": 30122708.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.501361465454101,
|
|
"epoch": 1.5167630707025328,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047796718188901095,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.2093779504299164,
|
|
"num_tokens": 30133624.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.426353406906128,
|
|
"epoch": 1.5173246476104902,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047794985141613413,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.2071457713842392,
|
|
"num_tokens": 30144501.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.429036474227905,
|
|
"epoch": 1.5178862245184477,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047793251448125526,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.2179270550608635,
|
|
"num_tokens": 30156351.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.53757610321045,
|
|
"epoch": 1.5184478014264053,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004779151710849265,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.20284938514232637,
|
|
"num_tokens": 30167445.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.5032368183135985,
|
|
"epoch": 1.519009378334363,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004778978212276999,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.19641199558973313,
|
|
"num_tokens": 30179054.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.568577909469605,
|
|
"epoch": 1.5195709552423204,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004778804649101281,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.2017212316393852,
|
|
"num_tokens": 30189412.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.526495933532715,
|
|
"epoch": 1.5201325321502779,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004778631021327636,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.20768623054027557,
|
|
"num_tokens": 30200775.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.47779483795166,
|
|
"epoch": 1.5206941090582355,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004778457328961592,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20526157915592194,
|
|
"num_tokens": 30212121.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.451785564422607,
|
|
"epoch": 1.5212556859661932,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047782835720086797,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.21280179619789125,
|
|
"num_tokens": 30222814.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.4849693298339846,
|
|
"epoch": 1.5218172628741506,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004778109750474432,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.20432359129190444,
|
|
"num_tokens": 30232414.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.531924057006836,
|
|
"epoch": 1.522378839782108,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004777935864364383,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.1977408856153488,
|
|
"num_tokens": 30243479.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.5508355617523195,
|
|
"epoch": 1.5229404166900657,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000477776191368407,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.20580054074525833,
|
|
"num_tokens": 30254721.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.537122440338135,
|
|
"epoch": 1.5235019935980234,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004777587898439031,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.20640988200902938,
|
|
"num_tokens": 30266962.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.458136892318725,
|
|
"epoch": 1.5240635705059808,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047774138186348073,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.20772131979465486,
|
|
"num_tokens": 30278773.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.411289405822754,
|
|
"epoch": 1.5246251474139383,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004777239674276941,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.21641917824745177,
|
|
"num_tokens": 30289631.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.4793037414550785,
|
|
"epoch": 1.525186724321896,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004777065465370977,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.2031054228544235,
|
|
"num_tokens": 30301433.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.526590633392334,
|
|
"epoch": 1.5257483012298534,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004776891191922463,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.21175598502159118,
|
|
"num_tokens": 30312695.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.457058715820312,
|
|
"epoch": 1.5263098781378108,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004776716853936947,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.20283032059669495,
|
|
"num_tokens": 30324254.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.553344297409057,
|
|
"epoch": 1.5268714550457685,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000477654245141998,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.2078992784023285,
|
|
"num_tokens": 30335389.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.484821748733521,
|
|
"epoch": 1.5274330319537262,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004776367984377116,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.20853031575679778,
|
|
"num_tokens": 30346627.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.469391489028931,
|
|
"epoch": 1.5279946088616836,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047761934528139086,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.20480407476425172,
|
|
"num_tokens": 30358215.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.4812877655029295,
|
|
"epoch": 1.528556185769641,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004776018856735916,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.2078840509057045,
|
|
"num_tokens": 30369793.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.476767349243164,
|
|
"epoch": 1.5291177626775987,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004775844196148698,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.21620226204395293,
|
|
"num_tokens": 30380200.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.438009214401245,
|
|
"epoch": 1.5296793395855564,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047756694710578146,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.20048674046993256,
|
|
"num_tokens": 30392282.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.621533679962158,
|
|
"epoch": 1.5302409164935138,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000477549468146883,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.1895761713385582,
|
|
"num_tokens": 30405365.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.569594287872315,
|
|
"epoch": 1.5308024934014712,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004775319827387309,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.20755211859941483,
|
|
"num_tokens": 30416513.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.462335252761841,
|
|
"epoch": 1.531364070309429,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004775144908818818,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.21490433663129807,
|
|
"num_tokens": 30427245.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.5180927276611325,
|
|
"epoch": 1.5319256472173866,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047749699257689296,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.2047941878437996,
|
|
"num_tokens": 30438437.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.484821891784668,
|
|
"epoch": 1.532487224125344,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004774794878243212,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.20468412041664125,
|
|
"num_tokens": 30449726.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.532321739196777,
|
|
"epoch": 1.5330488010333014,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000477461976624724,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.20309188812971116,
|
|
"num_tokens": 30460024.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.564656686782837,
|
|
"epoch": 1.533610377941259,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047744445897865905,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.19931226521730422,
|
|
"num_tokens": 30471981.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.475303745269775,
|
|
"epoch": 1.5341719548492168,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000477426934886684,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.2168190598487854,
|
|
"num_tokens": 30483143.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.437289047241211,
|
|
"epoch": 1.5347335317571742,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00047740940434935677,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.20214163810014724,
|
|
"num_tokens": 30495049.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.504056930541992,
|
|
"epoch": 1.5352951086651316,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004773918673672356,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.2028219670057297,
|
|
"num_tokens": 30506736.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.643737554550171,
|
|
"epoch": 1.5358566855730893,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047737432394087887,
|
|
"loss": 5.2822,
|
|
"mean_token_accuracy": 0.20126508176326752,
|
|
"num_tokens": 30520130.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.601519966125489,
|
|
"epoch": 1.5364182624810467,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047735677407084525,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19707034677267074,
|
|
"num_tokens": 30531480.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.4217840194702145,
|
|
"epoch": 1.5369798393890042,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004773392177576934,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.20188380777835846,
|
|
"num_tokens": 30541760.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.50836067199707,
|
|
"epoch": 1.5375414162969618,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004773216550019824,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.21123403012752534,
|
|
"num_tokens": 30551162.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.481827259063721,
|
|
"epoch": 1.5381029932049195,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047730408580427136,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.21225329637527465,
|
|
"num_tokens": 30562601.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.520240020751953,
|
|
"epoch": 1.538664570112877,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047728651016511994,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.20996954441070556,
|
|
"num_tokens": 30573923.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.509811305999756,
|
|
"epoch": 1.5392261470208344,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047726892808508744,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.19744402468204497,
|
|
"num_tokens": 30586400.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.552778863906861,
|
|
"epoch": 1.539787723928792,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004772513395647339,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.2044590473175049,
|
|
"num_tokens": 30598317.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.544968748092652,
|
|
"epoch": 1.5403493008367497,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004772337446046192,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.20729033201932906,
|
|
"num_tokens": 30609413.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.559598350524903,
|
|
"epoch": 1.5409108777447071,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047721614320530366,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.20487160682678224,
|
|
"num_tokens": 30619252.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.471631097793579,
|
|
"epoch": 1.5414724546526646,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047719853536734764,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.20828672349452973,
|
|
"num_tokens": 30630477.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.450305080413818,
|
|
"epoch": 1.5420340315606222,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004771809210913119,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.20389546006917952,
|
|
"num_tokens": 30641977.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.539410209655761,
|
|
"epoch": 1.54259560846858,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047716330037775724,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.20712922811508178,
|
|
"num_tokens": 30653547.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.498406505584716,
|
|
"epoch": 1.5431571853765373,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004771456732272446,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.20314196944236756,
|
|
"num_tokens": 30664270.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.609901714324951,
|
|
"epoch": 1.5437187622844948,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047712803964033545,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.19120927900075912,
|
|
"num_tokens": 30677172.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.4861444473266605,
|
|
"epoch": 1.5442803391924524,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047711039961759107,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.20292863696813584,
|
|
"num_tokens": 30688657.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.512343835830689,
|
|
"epoch": 1.54484191610041,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004770927531595731,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.19902028441429137,
|
|
"num_tokens": 30699103.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.474597215652466,
|
|
"epoch": 1.5454034930083675,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00047707510026684353,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.2035523146390915,
|
|
"num_tokens": 30711352.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.603694868087769,
|
|
"epoch": 1.545965069916325,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047705744093996447,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.20089204758405685,
|
|
"num_tokens": 30722224.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.589910173416138,
|
|
"epoch": 1.5465266468242826,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000477039775179498,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.19765597730875015,
|
|
"num_tokens": 30733113.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.531174230575561,
|
|
"epoch": 1.54708822373224,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047702210298600684,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.20557555854320525,
|
|
"num_tokens": 30744903.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.525029134750366,
|
|
"epoch": 1.5476498006401975,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047700442436005356,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.2011084794998169,
|
|
"num_tokens": 30756034.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.486435651779175,
|
|
"epoch": 1.5482113775481552,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000476986739302201,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.20784447938203812,
|
|
"num_tokens": 30766139.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.533721828460694,
|
|
"epoch": 1.5487729544561128,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047696904781301233,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.20075527727603912,
|
|
"num_tokens": 30777505.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.473288536071777,
|
|
"epoch": 1.5493345313640703,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004769513498930508,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.21480127722024916,
|
|
"num_tokens": 30788520.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.465898036956787,
|
|
"epoch": 1.5498961082720277,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047693364554288,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.20923046469688417,
|
|
"num_tokens": 30799051.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.484107637405396,
|
|
"epoch": 1.5504576851799854,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047691593476306373,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.21759435087442397,
|
|
"num_tokens": 30809375.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.41463074684143,
|
|
"epoch": 1.551019262087943,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004768982175541656,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.20877809971570968,
|
|
"num_tokens": 30821330.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.548021125793457,
|
|
"epoch": 1.5515808389959005,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047688049391675006,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.20204879939556122,
|
|
"num_tokens": 30832366.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.531372928619385,
|
|
"epoch": 1.552142415903858,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004768627638513813,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.19820235818624496,
|
|
"num_tokens": 30843550.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.461021995544433,
|
|
"epoch": 1.5527039928118156,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004768450273586237,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.2135595604777336,
|
|
"num_tokens": 30854727.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.522839593887329,
|
|
"epoch": 1.5532655697197733,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047682728443904223,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.20604489445686341,
|
|
"num_tokens": 30865594.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.5110289573669435,
|
|
"epoch": 1.5538271466277307,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047680953509320176,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.20804133415222167,
|
|
"num_tokens": 30877386.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.625910520553589,
|
|
"epoch": 1.5543887235356881,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004767917793216674,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.2048236533999443,
|
|
"num_tokens": 30889052.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.463327217102051,
|
|
"epoch": 1.5549503004436458,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00047677401712500455,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.203556627035141,
|
|
"num_tokens": 30900524.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.491235780715942,
|
|
"epoch": 1.5555118773516035,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004767562485037787,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.19668810367584227,
|
|
"num_tokens": 30911770.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.4694685459136965,
|
|
"epoch": 1.556073454259561,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047673847345855566,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.21358945071697236,
|
|
"num_tokens": 30921662.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.590263843536377,
|
|
"epoch": 1.5566350311675183,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004767206919899014,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.20531008243560792,
|
|
"num_tokens": 30934138.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.4994810104370115,
|
|
"epoch": 1.557196608075476,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000476702904098382,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.20128104984760284,
|
|
"num_tokens": 30945561.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.428599691390991,
|
|
"epoch": 1.5577581849834334,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000476685109784564,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.213369320333004,
|
|
"num_tokens": 30957210.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.498833703994751,
|
|
"epoch": 1.5583197618913909,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047666730904901377,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.20479903668165206,
|
|
"num_tokens": 30968782.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.529136514663696,
|
|
"epoch": 1.5588813387993485,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047664950189229833,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.20577918887138366,
|
|
"num_tokens": 30981239.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.511603307723999,
|
|
"epoch": 1.5594429157073062,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004766316883149845,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.20832204073667526,
|
|
"num_tokens": 30991773.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.585292005538941,
|
|
"epoch": 1.5600044926152636,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047661386831763955,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.20602088421583176,
|
|
"num_tokens": 31002646.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.475190448760986,
|
|
"epoch": 1.560566069523221,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047659604190083076,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.208974127471447,
|
|
"num_tokens": 31014405.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.46570053100586,
|
|
"epoch": 1.5611276464311787,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047657820906512585,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20883622169494628,
|
|
"num_tokens": 31025529.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.600479364395142,
|
|
"epoch": 1.5616892233391364,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047656036981109256,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.20243748277425766,
|
|
"num_tokens": 31037558.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.398086309432983,
|
|
"epoch": 1.5622508002470938,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047654252413929896,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.21317218095064164,
|
|
"num_tokens": 31048918.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.411939907073974,
|
|
"epoch": 1.5628123771550513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047652467205031317,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.2072877213358879,
|
|
"num_tokens": 31060149.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.48187141418457,
|
|
"epoch": 1.563373954063009,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047650681354470363,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.20952920466661454,
|
|
"num_tokens": 31071197.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.548346519470215,
|
|
"epoch": 1.5639355309709666,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047648894862303907,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.20812699049711228,
|
|
"num_tokens": 31083385.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.507502603530884,
|
|
"epoch": 1.564497107878924,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047647107728588826,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.19633434116840362,
|
|
"num_tokens": 31094807.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.500847196578979,
|
|
"epoch": 1.5650586847868815,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047645319953382024,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.2171564519405365,
|
|
"num_tokens": 31105622.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.4800575256347654,
|
|
"epoch": 1.5656202616948391,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047643531536740405,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.20897001326084136,
|
|
"num_tokens": 31115684.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.439977502822876,
|
|
"epoch": 1.5661818386027968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004764174247872094,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.21622350960969924,
|
|
"num_tokens": 31126449.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.471349430084229,
|
|
"epoch": 1.5667434155107542,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047639952779380586,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.22042266726493837,
|
|
"num_tokens": 31136894.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.516318655014038,
|
|
"epoch": 1.5673049924187117,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004763816243877632,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.20859655141830444,
|
|
"num_tokens": 31147131.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.450875759124756,
|
|
"epoch": 1.5678665693266693,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004763637145696515,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.21142487972974777,
|
|
"num_tokens": 31157903.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.512451887130737,
|
|
"epoch": 1.5684281462346268,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000476345798340041,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.2031385764479637,
|
|
"num_tokens": 31169087.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.56552267074585,
|
|
"epoch": 1.5689897231425842,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004763278756995022,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.1983257755637169,
|
|
"num_tokens": 31180253.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.548069763183594,
|
|
"epoch": 1.5695513000505419,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047630994664860576,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.20129527151584625,
|
|
"num_tokens": 31191857.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.547407436370849,
|
|
"epoch": 1.5701128769584995,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004762920111879226,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.20188904255628587,
|
|
"num_tokens": 31201868.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.52050518989563,
|
|
"epoch": 1.570674453866457,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004762740693180237,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.21104699075222016,
|
|
"num_tokens": 31212716.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.516161298751831,
|
|
"epoch": 1.5712360307744144,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047625612103948035,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.20028822273015975,
|
|
"num_tokens": 31224823.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.471108484268188,
|
|
"epoch": 1.571797607682372,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004762381663528641,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.20956494212150573,
|
|
"num_tokens": 31236798.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.55687313079834,
|
|
"epoch": 1.5723591845903298,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004762202052587466,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.19922939389944078,
|
|
"num_tokens": 31248687.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.54927430152893,
|
|
"epoch": 1.5729207614982872,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004762022377576996,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.20339844673871993,
|
|
"num_tokens": 31258385.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.551198863983155,
|
|
"epoch": 1.5734823384062446,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004761842638502954,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.20624431371688842,
|
|
"num_tokens": 31269308.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.555184555053711,
|
|
"epoch": 1.5740439153142023,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004761662835371062,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.20891218036413192,
|
|
"num_tokens": 31279900.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.509614515304565,
|
|
"epoch": 1.57460549222216,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004761482968187045,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.21258582621812822,
|
|
"num_tokens": 31290456.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.4654899597167965,
|
|
"epoch": 1.5751670691301174,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004761303036956631,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.20676697343587874,
|
|
"num_tokens": 31301398.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.591618299484253,
|
|
"epoch": 1.5757286460380748,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004761123041685547,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.20271494537591933,
|
|
"num_tokens": 31311149.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.390266036987304,
|
|
"epoch": 1.5762902229460325,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004760942982379526,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.21390655487775803,
|
|
"num_tokens": 31321099.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.465894937515259,
|
|
"epoch": 1.5768517998539902,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047607628590443004,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.19988189190626143,
|
|
"num_tokens": 31331872.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.606632232666016,
|
|
"epoch": 1.5774133767619476,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047605826716856056,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.2001311331987381,
|
|
"num_tokens": 31342024.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.53103666305542,
|
|
"epoch": 1.577974953669905,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004760402420309178,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.20974744707345963,
|
|
"num_tokens": 31351857.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.464332008361817,
|
|
"epoch": 1.5785365305778627,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004760222104920759,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.20659637749195098,
|
|
"num_tokens": 31362609.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.455795955657959,
|
|
"epoch": 1.5790981074858201,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004760041725526088,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.20812906473875045,
|
|
"num_tokens": 31373129.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.521220302581787,
|
|
"epoch": 1.5796596843937776,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047598612821309077,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.20941095650196076,
|
|
"num_tokens": 31383109.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.422174882888794,
|
|
"epoch": 1.5802212613017352,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004759680774740966,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.207935830950737,
|
|
"num_tokens": 31393603.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.538989925384522,
|
|
"epoch": 1.580782838209693,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004759500203362008,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.20376333743333816,
|
|
"num_tokens": 31404011.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.478257417678833,
|
|
"epoch": 1.5813444151176503,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004759319567999785,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.20603875815868378,
|
|
"num_tokens": 31414239.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.430261421203613,
|
|
"epoch": 1.5819059920256078,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004759138868660048,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.2029196098446846,
|
|
"num_tokens": 31425055.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.513593482971191,
|
|
"epoch": 1.5824675689335654,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047589581053485494,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.2112995520234108,
|
|
"num_tokens": 31435537.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.612093544006347,
|
|
"epoch": 1.583029145841523,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047587772780710455,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.20365289300680162,
|
|
"num_tokens": 31446056.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.539382648468018,
|
|
"epoch": 1.5835907227494805,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047585963868332945,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.20694277584552764,
|
|
"num_tokens": 31457452.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.444889116287231,
|
|
"epoch": 1.584152299657438,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004758415431641055,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.20541950762271882,
|
|
"num_tokens": 31469038.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.493869113922119,
|
|
"epoch": 1.5847138765653956,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004758234412500089,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.20774050652980805,
|
|
"num_tokens": 31481069.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.528741693496704,
|
|
"epoch": 1.5852754534733533,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047580533294161616,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.20174793154001236,
|
|
"num_tokens": 31491393.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.523884439468384,
|
|
"epoch": 1.5858370303813107,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004757872182395036,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.20396298170089722,
|
|
"num_tokens": 31502627.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.612882232666015,
|
|
"epoch": 1.5863986072892682,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047576909714424823,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.1998291313648224,
|
|
"num_tokens": 31513995.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.470041418075562,
|
|
"epoch": 1.5869601841972258,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047575096965642687,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.2040459543466568,
|
|
"num_tokens": 31524625.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.466579246520996,
|
|
"epoch": 1.5875217611051835,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047573283577661684,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.20684442967176436,
|
|
"num_tokens": 31535940.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.54838457107544,
|
|
"epoch": 1.588083338013141,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004757146955053955,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.20960248857736588,
|
|
"num_tokens": 31546557.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.495844507217408,
|
|
"epoch": 1.5886449149210984,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047569654884334036,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.20312196314334868,
|
|
"num_tokens": 31559335.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.491610288619995,
|
|
"epoch": 1.589206491829056,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004756783957910292,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.20121697187423707,
|
|
"num_tokens": 31570698.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.534782934188843,
|
|
"epoch": 1.5897680687370135,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047566023634904015,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.20380691438913345,
|
|
"num_tokens": 31582524.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.525614452362061,
|
|
"epoch": 1.590329645644971,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004756420705179513,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.20496306717395782,
|
|
"num_tokens": 31593399.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.4807273864746096,
|
|
"epoch": 1.5908912225529286,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004756238982983412,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.20107705593109132,
|
|
"num_tokens": 31604169.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.485166120529175,
|
|
"epoch": 1.5914527994608862,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004756057196907883,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.20821118354797363,
|
|
"num_tokens": 31614671.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.469596862792969,
|
|
"epoch": 1.5920143763688437,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047558753469587154,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.20804425626993178,
|
|
"num_tokens": 31625793.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.49620361328125,
|
|
"epoch": 1.5925759532768011,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047556934331416986,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.21601589620113373,
|
|
"num_tokens": 31637632.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.490736627578736,
|
|
"epoch": 1.5931375301847588,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004755511455462624,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.2110592842102051,
|
|
"num_tokens": 31648314.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.529680156707764,
|
|
"epoch": 1.5936991070927164,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004755329413927287,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.21219900697469712,
|
|
"num_tokens": 31659152.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.510613059997558,
|
|
"epoch": 1.5942606840006739,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004755147308541485,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.21111447662115096,
|
|
"num_tokens": 31669837.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.487071561813354,
|
|
"epoch": 1.5948222609086313,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047549651393110145,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.20197851955890656,
|
|
"num_tokens": 31680663.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.542351865768433,
|
|
"epoch": 1.595383837816589,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047547829062416757,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.2049282968044281,
|
|
"num_tokens": 31691484.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.433208179473877,
|
|
"epoch": 1.5959454147245467,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047546006093392726,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.19904022216796874,
|
|
"num_tokens": 31701642.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.4712308883667,
|
|
"epoch": 1.596506991632504,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004754418248609608,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.20917803198099136,
|
|
"num_tokens": 31714203.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.56931324005127,
|
|
"epoch": 1.5970685685404615,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004754235824058489,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.20883245915174484,
|
|
"num_tokens": 31725890.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.475087976455688,
|
|
"epoch": 1.5976301454484192,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004754053335691724,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.2175416648387909,
|
|
"num_tokens": 31738058.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.477308559417724,
|
|
"epoch": 1.5981917223563769,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047538707835151237,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.2089747190475464,
|
|
"num_tokens": 31748983.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.525931692123413,
|
|
"epoch": 1.5987532992643343,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047536881675345,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.21125872433185577,
|
|
"num_tokens": 31760083.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.4588775634765625,
|
|
"epoch": 1.5993148761722917,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004753505487755669,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.2110219731926918,
|
|
"num_tokens": 31771627.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.510487604141235,
|
|
"epoch": 1.5998764530802494,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047533227441844453,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.21248581856489182,
|
|
"num_tokens": 31783476.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.529943895339966,
|
|
"epoch": 1.6004380299882068,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047531399368266485,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.202347794175148,
|
|
"num_tokens": 31794072.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.444291877746582,
|
|
"epoch": 1.6009996068961643,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004752957065688099,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.20871025919914246,
|
|
"num_tokens": 31803613.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.570786333084106,
|
|
"epoch": 1.601561183804122,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000475277413077462,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.20525702089071274,
|
|
"num_tokens": 31815018.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.457907485961914,
|
|
"epoch": 1.6021227607120796,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047525911320920363,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.21406297534704208,
|
|
"num_tokens": 31825603.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.510598087310791,
|
|
"epoch": 1.602684337620037,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004752408069646174,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.2097071021795273,
|
|
"num_tokens": 31835988.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.474997854232788,
|
|
"epoch": 1.6032459145279945,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047522249434428623,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.20599400699138642,
|
|
"num_tokens": 31846378.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.582466268539429,
|
|
"epoch": 1.6038074914359521,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004752041753487931,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.19926570355892181,
|
|
"num_tokens": 31858836.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.498513889312744,
|
|
"epoch": 1.6043690683439098,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004751858499787215,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.20483269691467285,
|
|
"num_tokens": 31869315.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.544049406051636,
|
|
"epoch": 1.6049306452518672,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004751675182346547,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.19466543048620225,
|
|
"num_tokens": 31880527.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.5217209815979,
|
|
"epoch": 1.6054922221598247,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047514918011717656,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.20663195997476577,
|
|
"num_tokens": 31891890.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.520876455307007,
|
|
"epoch": 1.6060537990677823,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047513083562687085,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.20794738084077835,
|
|
"num_tokens": 31902735.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.521262550354004,
|
|
"epoch": 1.60661537597574,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004751124847643217,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.1980630487203598,
|
|
"num_tokens": 31914504.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.564070701599121,
|
|
"epoch": 1.6071769528836974,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004750941275301135,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.2067003846168518,
|
|
"num_tokens": 31925287.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.503963279724121,
|
|
"epoch": 1.6077385297916549,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004750757639248306,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.20966226756572723,
|
|
"num_tokens": 31935845.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.523820209503174,
|
|
"epoch": 1.6083001066996125,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047505739394905776,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.20767951756715775,
|
|
"num_tokens": 31946771.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.467599010467529,
|
|
"epoch": 1.6088616836075702,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047503901760338003,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.20403459817171096,
|
|
"num_tokens": 31957733.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.51614785194397,
|
|
"epoch": 1.6094232605155276,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047502063488838225,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.21314722746610643,
|
|
"num_tokens": 31967809.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.40363621711731,
|
|
"epoch": 1.609984837423485,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047500224580464994,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.21084758937358855,
|
|
"num_tokens": 31978673.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.46619062423706,
|
|
"epoch": 1.6105464143314427,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047498385035276856,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20746192783117295,
|
|
"num_tokens": 31990535.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.498496055603027,
|
|
"epoch": 1.6111079912394002,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004749654485333238,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.20520116686820983,
|
|
"num_tokens": 32002164.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.582311677932739,
|
|
"epoch": 1.6116695681473576,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047494704034690163,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.19657331109046935,
|
|
"num_tokens": 32013651.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.518664598464966,
|
|
"epoch": 1.6122311450553153,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047492862579408816,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.20603531897068023,
|
|
"num_tokens": 32025128.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.491609573364258,
|
|
"epoch": 1.612792721963273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047491020487546966,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.19748383462429048,
|
|
"num_tokens": 32036359.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.504091453552246,
|
|
"epoch": 1.6133542988712304,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004748917775916327,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.2130243107676506,
|
|
"num_tokens": 32047803.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.522450160980225,
|
|
"epoch": 1.6139158757791878,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047487334394316405,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.20228989720344542,
|
|
"num_tokens": 32060156.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.5255029678344725,
|
|
"epoch": 1.6144774526871455,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004748549039306506,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.2096383512020111,
|
|
"num_tokens": 32071398.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.404280805587769,
|
|
"epoch": 1.6150390295951031,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004748364575546795,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.22011851370334626,
|
|
"num_tokens": 32082472.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.491269493103028,
|
|
"epoch": 1.6156006065030606,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047481800481583806,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20366136580705643,
|
|
"num_tokens": 32093103.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.521625947952271,
|
|
"epoch": 1.616162183411018,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004747995457147139,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.2120617374777794,
|
|
"num_tokens": 32104526.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.5507323265075685,
|
|
"epoch": 1.6167237603189757,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047478108025189467,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.2018842250108719,
|
|
"num_tokens": 32116018.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.456138563156128,
|
|
"epoch": 1.6172853372269334,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047476260842796837,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.21306261867284776,
|
|
"num_tokens": 32127385.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.518598365783691,
|
|
"epoch": 1.6178469141348908,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004747441302435231,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.20497215539216995,
|
|
"num_tokens": 32137376.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.5564898490905765,
|
|
"epoch": 1.6184084910428482,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047472564569914726,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.2023552641272545,
|
|
"num_tokens": 32148263.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.4821004390716555,
|
|
"epoch": 1.618970067950806,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047470715479542945,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.20465493500232695,
|
|
"num_tokens": 32161323.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.534792232513428,
|
|
"epoch": 1.6195316448587636,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004746886575329584,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.20013921409845353,
|
|
"num_tokens": 32172294.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.449883699417114,
|
|
"epoch": 1.620093221766721,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047467015391232305,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.20108656883239745,
|
|
"num_tokens": 32182619.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.46030707359314,
|
|
"epoch": 1.6206547986746784,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047465164393411245,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20513459295034409,
|
|
"num_tokens": 32193078.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.490632152557373,
|
|
"epoch": 1.621216375582636,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00047463312759891615,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.19976680278778075,
|
|
"num_tokens": 32204134.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.552781248092652,
|
|
"epoch": 1.6217779524905935,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004746146049073236,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.20101729035377502,
|
|
"num_tokens": 32215136.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.498780536651611,
|
|
"epoch": 1.622339529398551,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047459607585992466,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.20641239434480668,
|
|
"num_tokens": 32225727.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.503843021392822,
|
|
"epoch": 1.6229011063065086,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047457754045730923,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.20309060513973237,
|
|
"num_tokens": 32236376.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.470147657394409,
|
|
"epoch": 1.6234626832144663,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047455899870006745,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.2148394763469696,
|
|
"num_tokens": 32247202.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.478876209259033,
|
|
"epoch": 1.6240242601224237,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004745404505887899,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.1999010130763054,
|
|
"num_tokens": 32258625.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.529998874664306,
|
|
"epoch": 1.6245858370303812,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004745218961240669,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.20891457051038742,
|
|
"num_tokens": 32269288.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.490398693084717,
|
|
"epoch": 1.6251474139383388,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004745033353064893,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.20569542199373245,
|
|
"num_tokens": 32279888.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.49157018661499,
|
|
"epoch": 1.6257089908462965,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004744847681366482,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.20816861391067504,
|
|
"num_tokens": 32291153.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.432019186019898,
|
|
"epoch": 1.626270567754254,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047446619461513466,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.2124658703804016,
|
|
"num_tokens": 32302291.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.497696256637573,
|
|
"epoch": 1.6268321446622114,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004744476147425402,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.21082286536693573,
|
|
"num_tokens": 32312015.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.496169710159302,
|
|
"epoch": 1.627393721570169,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047442902851945634,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.2040254682302475,
|
|
"num_tokens": 32323967.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.503342580795288,
|
|
"epoch": 1.6279552984781267,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047441043594647486,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.2027018189430237,
|
|
"num_tokens": 32336181.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.490545606613159,
|
|
"epoch": 1.6285168753860841,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047439183702418765,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.21339438557624818,
|
|
"num_tokens": 32346843.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.539705467224121,
|
|
"epoch": 1.6290784522940416,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047437323175318716,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.20333948433399202,
|
|
"num_tokens": 32358511.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.497409677505493,
|
|
"epoch": 1.6296400292019992,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047435462013406554,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.21146943867206575,
|
|
"num_tokens": 32370319.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.478574895858765,
|
|
"epoch": 1.630201606109957,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004743360021674155,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.20364509522914886,
|
|
"num_tokens": 32381455.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.487223100662232,
|
|
"epoch": 1.6307631830179143,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047431737785382996,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.2062406286597252,
|
|
"num_tokens": 32392553.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.649754285812378,
|
|
"epoch": 1.6313247599258718,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047429874719390165,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.20804242193698883,
|
|
"num_tokens": 32404736.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.550062084197998,
|
|
"epoch": 1.6318863368338294,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047428011018822404,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.21046534031629563,
|
|
"num_tokens": 32415089.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.439131164550782,
|
|
"epoch": 1.6324479137417869,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047426146683739043,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.20431715101003647,
|
|
"num_tokens": 32426814.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.429586172103882,
|
|
"epoch": 1.6330094906497443,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047424281714199436,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.19958620965480806,
|
|
"num_tokens": 32437173.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.554585266113281,
|
|
"epoch": 1.633571067557702,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047422416110262975,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.20347480177879335,
|
|
"num_tokens": 32448597.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.592492246627808,
|
|
"epoch": 1.6341326444656596,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047420549871989053,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.19817086458206176,
|
|
"num_tokens": 32460906.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.55376935005188,
|
|
"epoch": 1.634694221373617,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000474186829994371,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20685041546821595,
|
|
"num_tokens": 32473756.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.533232259750366,
|
|
"epoch": 1.6352557982815745,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047416815492666564,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.20323118269443513,
|
|
"num_tokens": 32483912.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.559123420715332,
|
|
"epoch": 1.6358173751895322,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004741494735173689,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20607447177171706,
|
|
"num_tokens": 32493899.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.525972604751587,
|
|
"epoch": 1.6363789520974898,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004741307857670757,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.2071796551346779,
|
|
"num_tokens": 32505215.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.542680406570435,
|
|
"epoch": 1.6369405290054473,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047411209167638106,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.20296425521373748,
|
|
"num_tokens": 32517288.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.59092345237732,
|
|
"epoch": 1.6375021059134047,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004740933912458801,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.20166926234960555,
|
|
"num_tokens": 32529705.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.601557016372681,
|
|
"epoch": 1.6380636828213624,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047407468447616845,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.2084883466362953,
|
|
"num_tokens": 32540868.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.466597270965576,
|
|
"epoch": 1.63862525972932,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047405597136784166,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.2075276106595993,
|
|
"num_tokens": 32552129.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.476538467407226,
|
|
"epoch": 1.6391868366372775,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004740372519214955,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.21320233792066573,
|
|
"num_tokens": 32563059.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.525065946578979,
|
|
"epoch": 1.639748413545235,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047401852613772604,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.19434441328048707,
|
|
"num_tokens": 32576628.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.593358755111694,
|
|
"epoch": 1.6403099904531926,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004739997940171295,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.2061586484313011,
|
|
"num_tokens": 32589138.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.601528263092041,
|
|
"epoch": 1.6408715673611503,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047398105556030234,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.20538681000471115,
|
|
"num_tokens": 32601865.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.521421623229981,
|
|
"epoch": 1.6414331442691077,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047396231076784123,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.20738897919654847,
|
|
"num_tokens": 32612439.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.484326887130737,
|
|
"epoch": 1.6419947211770651,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004739435596403429,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.20397649854421615,
|
|
"num_tokens": 32623002.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.5277598857879635,
|
|
"epoch": 1.6425562980850228,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004739248021784046,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.21135000586509706,
|
|
"num_tokens": 32632529.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.535961771011353,
|
|
"epoch": 1.6431178749929805,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004739060383826234,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.20454904288053513,
|
|
"num_tokens": 32643584.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.589264297485352,
|
|
"epoch": 1.6436794519009377,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047388726825359673,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.20723938047885895,
|
|
"num_tokens": 32655899.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.49917197227478,
|
|
"epoch": 1.6442410288088953,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047386849179192235,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.2018896907567978,
|
|
"num_tokens": 32666747.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.501293039321899,
|
|
"epoch": 1.644802605716853,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047384970899819813,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20657505244016647,
|
|
"num_tokens": 32678025.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.485420179367066,
|
|
"epoch": 1.6453641826248104,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004738309198730219,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.2125275254249573,
|
|
"num_tokens": 32688894.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.531338453292847,
|
|
"epoch": 1.6459257595327679,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047381212441699217,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.20239147543907166,
|
|
"num_tokens": 32699530.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.552163457870483,
|
|
"epoch": 1.6464873364407255,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004737933226307072,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.20569521188735962,
|
|
"num_tokens": 32710969.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.574315690994263,
|
|
"epoch": 1.6470489133486832,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047377451451476586,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.21007982343435289,
|
|
"num_tokens": 32723715.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.481144523620605,
|
|
"epoch": 1.6476104902566406,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004737557000697668,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.20332159698009492,
|
|
"num_tokens": 32735406.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.503858280181885,
|
|
"epoch": 1.648172067164598,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004737368792963092,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.19877180755138396,
|
|
"num_tokens": 32746123.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.500765943527222,
|
|
"epoch": 1.6487336440725557,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047371805219499223,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.2059953734278679,
|
|
"num_tokens": 32757172.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.449332046508789,
|
|
"epoch": 1.6492952209805134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047369921876641547,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.2118603691458702,
|
|
"num_tokens": 32767810.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.463953924179077,
|
|
"epoch": 1.6498567978884708,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047368037901117854,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.205161751806736,
|
|
"num_tokens": 32779723.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.639746761322021,
|
|
"epoch": 1.6504183747964283,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004736615329298812,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.19091157913208007,
|
|
"num_tokens": 32793378.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.552375459671021,
|
|
"epoch": 1.650979951704386,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047364268052312367,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.20871386379003526,
|
|
"num_tokens": 32805643.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.537127876281739,
|
|
"epoch": 1.6515415286123436,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004736238217915061,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.20744625478982925,
|
|
"num_tokens": 32818275.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.440152931213379,
|
|
"epoch": 1.652103105520301,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047360495673562906,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.2129007548093796,
|
|
"num_tokens": 32829548.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.465337944030762,
|
|
"epoch": 1.6526646824282585,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004735860853560931,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.20571417212486268,
|
|
"num_tokens": 32841472.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.554783010482788,
|
|
"epoch": 1.6532262593362161,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047356720765349926,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.20708245635032654,
|
|
"num_tokens": 32852589.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.531922197341919,
|
|
"epoch": 1.6537878362441738,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004735483236284485,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20953336656093596,
|
|
"num_tokens": 32863100.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.556757020950317,
|
|
"epoch": 1.654349413152131,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047352943328154203,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.20559762120246888,
|
|
"num_tokens": 32874912.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.446209669113159,
|
|
"epoch": 1.6549109900600887,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047351053661338145,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.20853865295648574,
|
|
"num_tokens": 32886249.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.452624559402466,
|
|
"epoch": 1.6554725669680463,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004734916336245684,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.1998305231332779,
|
|
"num_tokens": 32898010.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.465862083435058,
|
|
"epoch": 1.6560341438760038,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004734727243157047,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.21430115699768065,
|
|
"num_tokens": 32909103.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.426941967010498,
|
|
"epoch": 1.6565957207839612,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047345380868739253,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.21115503907203675,
|
|
"num_tokens": 32919612.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.461702489852906,
|
|
"epoch": 1.6571572976919189,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004734348867402341,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.20875051319599153,
|
|
"num_tokens": 32930072.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.605593681335449,
|
|
"epoch": 1.6577188745998765,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004734159584748319,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.20444159656763078,
|
|
"num_tokens": 32941984.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.4927342414855955,
|
|
"epoch": 1.658280451507834,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047339702389178874,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.2091891199350357,
|
|
"num_tokens": 32952767.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.490417575836181,
|
|
"epoch": 1.6588420284157914,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047337808299170725,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.20587593764066697,
|
|
"num_tokens": 32964553.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.536509418487549,
|
|
"epoch": 1.659403605323749,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047335913577519075,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.20756087005138396,
|
|
"num_tokens": 32975526.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.469053030014038,
|
|
"epoch": 1.6599651822317067,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047334018224284244,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.2083336442708969,
|
|
"num_tokens": 32987025.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.564931917190552,
|
|
"epoch": 1.6605267591396642,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004733212223952657,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.20191528797149658,
|
|
"num_tokens": 32997447.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.587018918991089,
|
|
"epoch": 1.6610883360476216,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047330225623306443,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.20856438726186752,
|
|
"num_tokens": 33007432.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.518340444564819,
|
|
"epoch": 1.6616499129555793,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047328328375684237,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.20972497165203094,
|
|
"num_tokens": 33018547.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.492754220962524,
|
|
"epoch": 1.662211489863537,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004732643049672036,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.2139618068933487,
|
|
"num_tokens": 33029092.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.447445726394653,
|
|
"epoch": 1.6627730667714944,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004732453198647525,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.20555349439382553,
|
|
"num_tokens": 33040498.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.607267093658447,
|
|
"epoch": 1.6633346436794518,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004732263284500936,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.19671256542205812,
|
|
"num_tokens": 33052203.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.557122850418091,
|
|
"epoch": 1.6638962205874095,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004732073307238314,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.21115904599428176,
|
|
"num_tokens": 33063453.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.501421356201172,
|
|
"epoch": 1.6644577974953672,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000473188326686571,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.2093341112136841,
|
|
"num_tokens": 33075511.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.486883115768433,
|
|
"epoch": 1.6650193744033244,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047316931633891736,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.20641575902700424,
|
|
"num_tokens": 33086094.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.605405616760254,
|
|
"epoch": 1.665580951311282,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004731502996814759,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.19993088990449906,
|
|
"num_tokens": 33096430.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.498559284210205,
|
|
"epoch": 1.6661425282192397,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047313127671485194,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.20785554498434067,
|
|
"num_tokens": 33108040.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.47330117225647,
|
|
"epoch": 1.6667041051271971,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004731122474396514,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.21026920080184935,
|
|
"num_tokens": 33118282.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.529913711547851,
|
|
"epoch": 1.6672656820351546,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047309321185648,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.20363523662090302,
|
|
"num_tokens": 33130308.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.607587432861328,
|
|
"epoch": 1.6678272589431122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047307416996594386,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.20614560544490815,
|
|
"num_tokens": 33140260.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.499615859985352,
|
|
"epoch": 1.66838883585107,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004730551217686495,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.20391936004161834,
|
|
"num_tokens": 33152064.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.529804039001465,
|
|
"epoch": 1.6689504127590273,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004730360672652031,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.2086590051651001,
|
|
"num_tokens": 33164057.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.504351711273193,
|
|
"epoch": 1.6695119896669848,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047301700645621154,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.20850137025117874,
|
|
"num_tokens": 33175281.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.453760719299316,
|
|
"epoch": 1.6700735665749424,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004729979393422817,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.20928108990192412,
|
|
"num_tokens": 33186615.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.505376863479614,
|
|
"epoch": 1.6706351434829,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004729788659240206,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.20612355172634125,
|
|
"num_tokens": 33198693.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.548443984985352,
|
|
"epoch": 1.6711967203908575,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004729597862020358,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.21152067929506302,
|
|
"num_tokens": 33209743.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.509635639190674,
|
|
"epoch": 1.671758297298815,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047294070017693453,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.21623341143131256,
|
|
"num_tokens": 33220907.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.572060441970825,
|
|
"epoch": 1.6723198742067726,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047292160784932454,
|
|
"loss": 5.2488,
|
|
"mean_token_accuracy": 0.19755345284938813,
|
|
"num_tokens": 33232278.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.566012716293335,
|
|
"epoch": 1.6728814511147303,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047290250921981386,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.20761940479278565,
|
|
"num_tokens": 33243920.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.513976001739502,
|
|
"epoch": 1.6734430280226877,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047288340428901053,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.20490152686834334,
|
|
"num_tokens": 33254467.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.435889434814453,
|
|
"epoch": 1.6740046049306452,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047286429305752283,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.1981410041451454,
|
|
"num_tokens": 33265536.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.5406880378723145,
|
|
"epoch": 1.6745661818386028,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047284517552595933,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.20062946379184723,
|
|
"num_tokens": 33277233.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.501961708068848,
|
|
"epoch": 1.6751277587465605,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004728260516949287,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.21106498688459396,
|
|
"num_tokens": 33287873.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.500721406936646,
|
|
"epoch": 1.6756893356545177,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004728069215650399,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.2044158697128296,
|
|
"num_tokens": 33298888.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.396541404724121,
|
|
"epoch": 1.6762509125624754,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004727877851369019,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.21114853024482727,
|
|
"num_tokens": 33309607.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.48534665107727,
|
|
"epoch": 1.676812489470433,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047276864241112417,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.2132483720779419,
|
|
"num_tokens": 33320582.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.478933715820313,
|
|
"epoch": 1.6773740663783905,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004727494933883161,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20961587131023407,
|
|
"num_tokens": 33332145.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.656535196304321,
|
|
"epoch": 1.677935643286348,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004727303380690876,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1967095524072647,
|
|
"num_tokens": 33343963.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.526269817352295,
|
|
"epoch": 1.6784972201943056,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004727111764540484,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.2103969618678093,
|
|
"num_tokens": 33354931.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.509067583084106,
|
|
"epoch": 1.6790587971022632,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047269200854380854,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.20347004532814025,
|
|
"num_tokens": 33365686.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.570708417892456,
|
|
"epoch": 1.6796203740102207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047267283433897854,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.21373405307531357,
|
|
"num_tokens": 33377099.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.531235218048096,
|
|
"epoch": 1.6801819509181781,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047265365384016887,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.20051005631685256,
|
|
"num_tokens": 33389477.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.57527379989624,
|
|
"epoch": 1.6807435278261358,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047263446704799017,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.20374889075756072,
|
|
"num_tokens": 33401970.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.556231307983398,
|
|
"epoch": 1.6813051047340934,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047261527396305343,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.2050409808754921,
|
|
"num_tokens": 33412986.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.5193078994750975,
|
|
"epoch": 1.6818666816420509,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047259607458596966,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.20288967937231064,
|
|
"num_tokens": 33424717.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.4239830493927,
|
|
"epoch": 1.6824282585500083,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047257686891735023,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.2110334187746048,
|
|
"num_tokens": 33436713.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.631931352615356,
|
|
"epoch": 1.682989835457966,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047255765695780665,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.19914182871580124,
|
|
"num_tokens": 33447532.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.450236034393311,
|
|
"epoch": 1.6835514123659236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004725384387079507,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.20723284035921097,
|
|
"num_tokens": 33458530.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.507376098632813,
|
|
"epoch": 1.684112989273881,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047251921416839425,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.20504726618528366,
|
|
"num_tokens": 33469617.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.529239845275879,
|
|
"epoch": 1.6846745661818385,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004724999833397494,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.21377594769001007,
|
|
"num_tokens": 33479622.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.6846745661818385,
|
|
"eval_entropy": 5.316571311419361,
|
|
"eval_loss": 5.198622226715088,
|
|
"eval_mean_token_accuracy": 0.21254836167368596,
|
|
"eval_num_tokens": 33479622.0,
|
|
"eval_runtime": 18.4226,
|
|
"eval_samples_per_second": 1683.426,
|
|
"eval_steps_per_second": 210.449,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.438818120956421,
|
|
"epoch": 1.6852361430897962,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004724807462226285,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.21773632615804672,
|
|
"num_tokens": 33490907.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.498456001281738,
|
|
"epoch": 1.6857977199977539,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000472461502817644,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.21337104141712188,
|
|
"num_tokens": 33501884.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.479980897903443,
|
|
"epoch": 1.6863592969057113,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004724422531254087,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.2102030411362648,
|
|
"num_tokens": 33512106.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.503008317947388,
|
|
"epoch": 1.6869208738136687,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004724229971465355,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.20934080481529235,
|
|
"num_tokens": 33522889.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.507996988296509,
|
|
"epoch": 1.6874824507216264,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004724037348816375,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.21031084954738616,
|
|
"num_tokens": 33534601.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.553902435302734,
|
|
"epoch": 1.6880440276295838,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000472384466331328,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.20659746527671813,
|
|
"num_tokens": 33545300.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.58875298500061,
|
|
"epoch": 1.6886056045375413,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004723651914962205,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.20590228885412215,
|
|
"num_tokens": 33555581.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.548143720626831,
|
|
"epoch": 1.689167181445499,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047234591037692884,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.20394685715436936,
|
|
"num_tokens": 33566902.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.550398445129394,
|
|
"epoch": 1.6897287583534566,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047232662297406683,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.2062677875161171,
|
|
"num_tokens": 33578316.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.529061031341553,
|
|
"epoch": 1.690290335261414,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004723073292882485,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.20007457435131074,
|
|
"num_tokens": 33590242.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.51369080543518,
|
|
"epoch": 1.6908519121693715,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047228802932008836,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.21447079181671141,
|
|
"num_tokens": 33601277.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.478628158569336,
|
|
"epoch": 1.6914134890773291,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004722687230702009,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.2029808282852173,
|
|
"num_tokens": 33612423.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.571339750289917,
|
|
"epoch": 1.6919750659852868,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004722494105392007,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.2006903186440468,
|
|
"num_tokens": 33624250.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.543212032318115,
|
|
"epoch": 1.6925366428932442,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004722300917277029,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.20656684786081314,
|
|
"num_tokens": 33636379.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.51194396018982,
|
|
"epoch": 1.6930982198012017,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004722107666363224,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.2014857977628708,
|
|
"num_tokens": 33648296.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.4272552013397215,
|
|
"epoch": 1.6936597967091593,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004721914352656746,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.19866518378257753,
|
|
"num_tokens": 33659438.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.566656684875488,
|
|
"epoch": 1.694221373617117,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000472172097616375,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.20243166834115983,
|
|
"num_tokens": 33670893.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.5885590553283695,
|
|
"epoch": 1.6947829505250744,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004721527536890394,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.20969391614198685,
|
|
"num_tokens": 33681487.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.508446455001831,
|
|
"epoch": 1.6953445274330319,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004721334034842836,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.21368263363838197,
|
|
"num_tokens": 33692925.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.481455898284912,
|
|
"epoch": 1.6959061043409895,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004721140470027238,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.20401386320590972,
|
|
"num_tokens": 33703559.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.504066276550293,
|
|
"epoch": 1.6964676812489472,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047209468424497627,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.2068984717130661,
|
|
"num_tokens": 33715041.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.498052167892456,
|
|
"epoch": 1.6970292581569046,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004720753152116576,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.21243081837892533,
|
|
"num_tokens": 33726334.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.526127433776855,
|
|
"epoch": 1.697590835064862,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047205593990338443,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.21221263110637664,
|
|
"num_tokens": 33738663.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.434542274475097,
|
|
"epoch": 1.6981524119728197,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004720365583207737,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.2130644991993904,
|
|
"num_tokens": 33749202.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.464500379562378,
|
|
"epoch": 1.6987139888807772,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004720171704644425,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.22025048583745957,
|
|
"num_tokens": 33759809.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.466862630844116,
|
|
"epoch": 1.6992755657887346,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004719977763350083,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20842666178941727,
|
|
"num_tokens": 33771374.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.4942854881286625,
|
|
"epoch": 1.6998371426966923,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047197837593308833,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.20769901126623153,
|
|
"num_tokens": 33781645.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.529838562011719,
|
|
"epoch": 1.70039871960465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004719589692593006,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.21381760090589524,
|
|
"num_tokens": 33793032.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.637299346923828,
|
|
"epoch": 1.7009602965126074,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004719395563142629,
|
|
"loss": 5.3046,
|
|
"mean_token_accuracy": 0.19407058209180833,
|
|
"num_tokens": 33805116.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.5761443138122555,
|
|
"epoch": 1.7015218734205648,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004719201370985933,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.20634932368993758,
|
|
"num_tokens": 33817135.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.497506427764892,
|
|
"epoch": 1.7020834503285225,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047190071161291007,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.20723895877599716,
|
|
"num_tokens": 33830187.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.45423436164856,
|
|
"epoch": 1.7026450272364801,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047188127985783195,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.20408200472593307,
|
|
"num_tokens": 33841297.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.553744792938232,
|
|
"epoch": 1.7032066041444376,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047186184183397754,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.2075769290328026,
|
|
"num_tokens": 33852888.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.5326683044433596,
|
|
"epoch": 1.703768181052395,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047184239754196564,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.20400886684656144,
|
|
"num_tokens": 33865165.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.460555791854858,
|
|
"epoch": 1.7043297579603527,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004718229469824155,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.2133168339729309,
|
|
"num_tokens": 33875865.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.567928647994995,
|
|
"epoch": 1.7048913348683103,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047180349015594634,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.19818955957889556,
|
|
"num_tokens": 33887519.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.458078241348266,
|
|
"epoch": 1.7054529117762678,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004717840270631778,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.2173545241355896,
|
|
"num_tokens": 33898762.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.434399366378784,
|
|
"epoch": 1.7060144886842252,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047176455770472946,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.21127595752477646,
|
|
"num_tokens": 33911109.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.602588415145874,
|
|
"epoch": 1.706576065592183,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047174508208122135,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.19339240044355394,
|
|
"num_tokens": 33922741.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.541716814041138,
|
|
"epoch": 1.7071376425001406,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004717256001932735,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.20576345175504684,
|
|
"num_tokens": 33933234.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.504639911651611,
|
|
"epoch": 1.707699219408098,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047170611204150624,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.20525936037302017,
|
|
"num_tokens": 33943667.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.4808698177337645,
|
|
"epoch": 1.7082607963160554,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004716866176265401,
|
|
"loss": 5.0391,
|
|
"mean_token_accuracy": 0.2215789332985878,
|
|
"num_tokens": 33954499.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.473364400863647,
|
|
"epoch": 1.708822373224013,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047166711694899573,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.21548214107751845,
|
|
"num_tokens": 33964700.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.468194770812988,
|
|
"epoch": 1.7093839501319705,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047164761000949404,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.21116143018007277,
|
|
"num_tokens": 33977759.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.568966102600098,
|
|
"epoch": 1.709945527039928,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004716280968086563,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.20069896876811982,
|
|
"num_tokens": 33990019.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.550789070129395,
|
|
"epoch": 1.7105071039478856,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004716085773471036,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.21076780557632446,
|
|
"num_tokens": 34000663.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.437687921524048,
|
|
"epoch": 1.7110686808558433,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047158905162545756,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.2131303295493126,
|
|
"num_tokens": 34012768.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.427396154403686,
|
|
"epoch": 1.7116302577638007,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047156951964433984,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20983005911111832,
|
|
"num_tokens": 34025801.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.406450843811035,
|
|
"epoch": 1.7121918346717582,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047154998140437246,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.22341188341379165,
|
|
"num_tokens": 34036553.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.538007688522339,
|
|
"epoch": 1.7127534115797158,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047153043690617737,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.20719002783298493,
|
|
"num_tokens": 34048352.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.504406118392945,
|
|
"epoch": 1.7133149884876735,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000471510886150377,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.21575670391321183,
|
|
"num_tokens": 34059617.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.453175973892212,
|
|
"epoch": 1.713876565395631,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004714913291375938,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20592924505472182,
|
|
"num_tokens": 34071176.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.469746494293213,
|
|
"epoch": 1.7144381423035884,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047147176586845036,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.20745603293180465,
|
|
"num_tokens": 34081883.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.545697641372681,
|
|
"epoch": 1.714999719211546,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004714521963435698,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.2037190780043602,
|
|
"num_tokens": 34092938.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.508347225189209,
|
|
"epoch": 1.7155612961195037,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047143262056357506,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.2124995544552803,
|
|
"num_tokens": 34104758.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.45482497215271,
|
|
"epoch": 1.7161228730274611,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047141303852908965,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.212249818444252,
|
|
"num_tokens": 34114752.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.551207399368286,
|
|
"epoch": 1.7166844499354186,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004713934502407367,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.20259924829006196,
|
|
"num_tokens": 34125547.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.604827737808227,
|
|
"epoch": 1.7172460268433762,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004713738556991402,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.20419570058584213,
|
|
"num_tokens": 34136085.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.511700868606567,
|
|
"epoch": 1.717807603751334,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000471354254904924,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.2156902864575386,
|
|
"num_tokens": 34147536.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.523502779006958,
|
|
"epoch": 1.7183691806592913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047133464785871216,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.21014749258756638,
|
|
"num_tokens": 34158238.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.454774665832519,
|
|
"epoch": 1.7189307575672488,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000471315034561129,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.21901054084300994,
|
|
"num_tokens": 34169793.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.53254508972168,
|
|
"epoch": 1.7194923344752064,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047129541501279897,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.21539418995380402,
|
|
"num_tokens": 34179753.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.576645088195801,
|
|
"epoch": 1.7200539113831639,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004712757892143468,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.20442438423633574,
|
|
"num_tokens": 34189947.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.5585410594940186,
|
|
"epoch": 1.7206154882911213,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047125615716639744,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.21104196608066558,
|
|
"num_tokens": 34201197.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.5432576656341555,
|
|
"epoch": 1.721177065199079,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004712365188695758,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.21798444986343385,
|
|
"num_tokens": 34212762.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.525516605377197,
|
|
"epoch": 1.7217386421070366,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004712168743245074,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.2105293780565262,
|
|
"num_tokens": 34223928.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.4293735980987545,
|
|
"epoch": 1.722300219014994,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047119722353181754,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.21491488814353943,
|
|
"num_tokens": 34233888.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.594287347793579,
|
|
"epoch": 1.7228617959229515,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047117756649213204,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.20540930926799775,
|
|
"num_tokens": 34245894.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.522965764999389,
|
|
"epoch": 1.7234233728309092,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004711579032060767,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.2163873791694641,
|
|
"num_tokens": 34256288.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.493509531021118,
|
|
"epoch": 1.7239849497388668,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004711382336742777,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.1990893602371216,
|
|
"num_tokens": 34266515.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.570713758468628,
|
|
"epoch": 1.7245465266468243,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004711185578973612,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.20334623903036117,
|
|
"num_tokens": 34278681.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.547233915328979,
|
|
"epoch": 1.7251081035547817,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004710988758759538,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.21123499870300294,
|
|
"num_tokens": 34289161.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.4862024784088135,
|
|
"epoch": 1.7256696804627394,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004710791876106821,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.2074348121881485,
|
|
"num_tokens": 34300323.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.496757936477661,
|
|
"epoch": 1.726231257370697,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047105949310217304,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.2033353105187416,
|
|
"num_tokens": 34311558.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.477128744125366,
|
|
"epoch": 1.7267928342786545,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004710397923510537,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.204802106320858,
|
|
"num_tokens": 34323573.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.519707679748535,
|
|
"epoch": 1.727354411186612,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047102008535795134,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.20573066771030427,
|
|
"num_tokens": 34334698.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.536962556838989,
|
|
"epoch": 1.7279159880945696,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004710003721234934,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.21931411176919938,
|
|
"num_tokens": 34345948.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.486470317840576,
|
|
"epoch": 1.7284775650025272,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047098065264830754,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.20488250851631165,
|
|
"num_tokens": 34359067.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.403467988967895,
|
|
"epoch": 1.7290391419104847,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047096092693302174,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.21255055218935012,
|
|
"num_tokens": 34370895.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.456294536590576,
|
|
"epoch": 1.7296007188184421,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047094119497826406,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.20448546558618547,
|
|
"num_tokens": 34382039.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.583296203613282,
|
|
"epoch": 1.7301622957263998,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047092145678466273,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.2051682636141777,
|
|
"num_tokens": 34392939.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.600519132614136,
|
|
"epoch": 1.7307238726343572,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004709017123528462,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.20728372782468796,
|
|
"num_tokens": 34404402.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.451113653182984,
|
|
"epoch": 1.7312854495423147,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047088196168344315,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.21088985353708267,
|
|
"num_tokens": 34415563.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.571055889129639,
|
|
"epoch": 1.7318470264502723,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047086220477708256,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.19848778247833251,
|
|
"num_tokens": 34426993.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.6282066822052,
|
|
"epoch": 1.73240860335823,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047084244163439335,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.21679207384586335,
|
|
"num_tokens": 34436697.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.532117605209351,
|
|
"epoch": 1.7329701802661874,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004708226722560049,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20943532437086104,
|
|
"num_tokens": 34448076.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.514684820175171,
|
|
"epoch": 1.7335317571741449,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004708028966425465,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.20650691241025926,
|
|
"num_tokens": 34460369.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.556631803512573,
|
|
"epoch": 1.7340933340821025,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047078311479464797,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.20173815488815308,
|
|
"num_tokens": 34472693.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.633963537216187,
|
|
"epoch": 1.7346549109900602,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047076332671293917,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.2098808318376541,
|
|
"num_tokens": 34485258.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.587327194213867,
|
|
"epoch": 1.7352164878980176,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047074353239805005,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.1998230591416359,
|
|
"num_tokens": 34496450.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.479771566390991,
|
|
"epoch": 1.735778064805975,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004707237318506111,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.20950842797756195,
|
|
"num_tokens": 34508062.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.486682176589966,
|
|
"epoch": 1.7363396417139327,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047070392507125245,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.21514298319816588,
|
|
"num_tokens": 34519817.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.528709077835083,
|
|
"epoch": 1.7369012186218904,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000470684112060605,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.20981157273054124,
|
|
"num_tokens": 34532628.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.566078424453735,
|
|
"epoch": 1.7374627955298478,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047066429281929944,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.20714856386184693,
|
|
"num_tokens": 34543558.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.632712745666504,
|
|
"epoch": 1.7380243724378053,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000470644467347967,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.1981491580605507,
|
|
"num_tokens": 34553720.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.522532367706299,
|
|
"epoch": 1.738585949345763,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047062463564723884,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.20849983096122743,
|
|
"num_tokens": 34564641.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.527465867996216,
|
|
"epoch": 1.7391475262537206,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004706047977177464,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.20714931190013885,
|
|
"num_tokens": 34576470.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.578290271759033,
|
|
"epoch": 1.739709103161678,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047058495356012135,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.20375586599111556,
|
|
"num_tokens": 34589158.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.581265830993653,
|
|
"epoch": 1.7402706800696355,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047056510317499545,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.21564017832279206,
|
|
"num_tokens": 34599192.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.509003448486328,
|
|
"epoch": 1.7408322569775931,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047054524656300087,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.20996153950691224,
|
|
"num_tokens": 34611922.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.568729019165039,
|
|
"epoch": 1.7413938338855506,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047052538372476985,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.207971753180027,
|
|
"num_tokens": 34623618.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.5565633296966555,
|
|
"epoch": 1.741955410793508,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047050551466093466,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.20202002078294753,
|
|
"num_tokens": 34635057.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.535366535186768,
|
|
"epoch": 1.7425169877014657,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004704856393721281,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.20469735115766524,
|
|
"num_tokens": 34647527.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.486370515823364,
|
|
"epoch": 1.7430785646094233,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047046575785898297,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.20820453613996506,
|
|
"num_tokens": 34658615.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.548802995681763,
|
|
"epoch": 1.7436401415173808,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004704458701221323,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20270924121141434,
|
|
"num_tokens": 34668485.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.507441711425781,
|
|
"epoch": 1.7442017184253382,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004704259761622094,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.21183994859457017,
|
|
"num_tokens": 34681181.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.488143014907837,
|
|
"epoch": 1.7447632953332959,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047040607597984745,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.20615969002246856,
|
|
"num_tokens": 34692954.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.4641509532928465,
|
|
"epoch": 1.7453248722412535,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004703861695756804,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.21279972642660142,
|
|
"num_tokens": 34705120.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.539261817932129,
|
|
"epoch": 1.745886449149211,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004703662569503419,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.20432802736759187,
|
|
"num_tokens": 34716589.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.544753456115723,
|
|
"epoch": 1.7464480260571684,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047034633810446604,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20914374738931657,
|
|
"num_tokens": 34727551.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.535815048217773,
|
|
"epoch": 1.747009602965126,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004703264130386869,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.210514073073864,
|
|
"num_tokens": 34738887.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.50035080909729,
|
|
"epoch": 1.7475711798730837,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047030648175363913,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.20960502773523332,
|
|
"num_tokens": 34750264.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.528809213638306,
|
|
"epoch": 1.7481327567810412,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004702865442499572,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.20176070630550386,
|
|
"num_tokens": 34761335.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.514657306671142,
|
|
"epoch": 1.7486943336889986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004702666005282759,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.21168359965085984,
|
|
"num_tokens": 34772237.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.509405088424683,
|
|
"epoch": 1.7492559105969563,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004702466505892304,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.2107226222753525,
|
|
"num_tokens": 34784648.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.547906398773193,
|
|
"epoch": 1.749817487504914,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047022669443345575,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.20931770354509355,
|
|
"num_tokens": 34794505.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.51340651512146,
|
|
"epoch": 1.7503790644128714,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047020673206158743,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.21276241689920425,
|
|
"num_tokens": 34804887.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.587835741043091,
|
|
"epoch": 1.7509406413208288,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000470186763474261,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.219209922850132,
|
|
"num_tokens": 34816814.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.5220552444458,
|
|
"epoch": 1.7515022182287865,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004701667886721125,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.21753370463848115,
|
|
"num_tokens": 34827251.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.54765739440918,
|
|
"epoch": 1.752063795136744,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004701468076557776,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.2019860789179802,
|
|
"num_tokens": 34839010.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.549758529663086,
|
|
"epoch": 1.7526253720447014,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047012682042589277,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.20789893716573715,
|
|
"num_tokens": 34850435.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.465995454788208,
|
|
"epoch": 1.753186948952659,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047010682698309423,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.21566492766141893,
|
|
"num_tokens": 34861222.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.583275842666626,
|
|
"epoch": 1.7537485258606167,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004700868273280186,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.19312662333250047,
|
|
"num_tokens": 34872650.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.579497814178467,
|
|
"epoch": 1.7543101027685741,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047006682146130273,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.21583060920238495,
|
|
"num_tokens": 34883201.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.589488887786866,
|
|
"epoch": 1.7548716796765316,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004700468093835837,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.19411680549383165,
|
|
"num_tokens": 34895936.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.507888412475586,
|
|
"epoch": 1.7554332565844892,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047002679109549864,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.21315869092941284,
|
|
"num_tokens": 34906491.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.508119392395019,
|
|
"epoch": 1.755994833492447,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047000676659768477,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.20971388071775438,
|
|
"num_tokens": 34918300.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.466775226593017,
|
|
"epoch": 1.7565564104004043,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004699867358907799,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.20105886906385423,
|
|
"num_tokens": 34928573.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.5751166343688965,
|
|
"epoch": 1.7571179873083618,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004699666989754217,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.2078736960887909,
|
|
"num_tokens": 34940378.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.497947359085083,
|
|
"epoch": 1.7576795642163194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004699466558522482,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.2063285529613495,
|
|
"num_tokens": 34951627.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.562273931503296,
|
|
"epoch": 1.758241141124277,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046992660652189755,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20723684132099152,
|
|
"num_tokens": 34961428.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.608083963394165,
|
|
"epoch": 1.7588027180322345,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046990655098500824,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.2027660444378853,
|
|
"num_tokens": 34973736.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.580296564102173,
|
|
"epoch": 1.759364294940192,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046988648924221866,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.21466245949268342,
|
|
"num_tokens": 34984510.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.5448531150817875,
|
|
"epoch": 1.7599258718481496,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004698664212941677,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.21427819430828093,
|
|
"num_tokens": 34995218.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.387213945388794,
|
|
"epoch": 1.7604874487561073,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046984634714149437,
|
|
"loss": 4.9293,
|
|
"mean_token_accuracy": 0.21984669864177703,
|
|
"num_tokens": 35006681.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.527961301803589,
|
|
"epoch": 1.7610490256640647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004698262667848377,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.21282058209180832,
|
|
"num_tokens": 35017341.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.479950666427612,
|
|
"epoch": 1.7616106025720222,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046980618022483714,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.21611244827508927,
|
|
"num_tokens": 35027718.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.548923635482788,
|
|
"epoch": 1.7621721794799798,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046978608746213224,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.20750688761472702,
|
|
"num_tokens": 35038100.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.528478193283081,
|
|
"epoch": 1.7627337563879373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004697659884973628,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.21353391706943511,
|
|
"num_tokens": 35049077.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.643156576156616,
|
|
"epoch": 1.7632953332958947,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004697458833311687,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.2029811829328537,
|
|
"num_tokens": 35060685.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.482378196716309,
|
|
"epoch": 1.7638569102038524,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004697257719641902,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.21427740007638932,
|
|
"num_tokens": 35072122.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.570088624954224,
|
|
"epoch": 1.76441848711181,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004697056543970676,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.21045320779085158,
|
|
"num_tokens": 35082427.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.57336277961731,
|
|
"epoch": 1.7649800640197675,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046968553063044146,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.20829980075359344,
|
|
"num_tokens": 35093061.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.575496482849121,
|
|
"epoch": 1.765541640927725,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046966540066495247,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.20336901992559434,
|
|
"num_tokens": 35103226.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.562266302108765,
|
|
"epoch": 1.7661032178356826,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046964526450124164,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.20798999667167664,
|
|
"num_tokens": 35113977.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.515879106521607,
|
|
"epoch": 1.7666647947436402,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046962512213995,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.20797832161188126,
|
|
"num_tokens": 35125132.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.500045537948608,
|
|
"epoch": 1.7672263716515977,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046960497358171913,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.20934769213199617,
|
|
"num_tokens": 35135266.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.5643127918243405,
|
|
"epoch": 1.7677879485595551,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00046958481882719035,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.2194843038916588,
|
|
"num_tokens": 35146268.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.510785150527954,
|
|
"epoch": 1.7683495254675128,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046956465787700554,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.2110315293073654,
|
|
"num_tokens": 35157046.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.602212142944336,
|
|
"epoch": 1.7689111023754704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046954449073180644,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.1994991272687912,
|
|
"num_tokens": 35167624.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.589691162109375,
|
|
"epoch": 1.7694726792834279,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004695243173922354,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.2036835417151451,
|
|
"num_tokens": 35178987.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.474059677124023,
|
|
"epoch": 1.7700342561913853,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046950413785893465,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.21146183013916015,
|
|
"num_tokens": 35189804.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.575754880905151,
|
|
"epoch": 1.770595833099343,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046948395213254667,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20608992129564285,
|
|
"num_tokens": 35200677.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.462579393386841,
|
|
"epoch": 1.7711574100073006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004694637602137143,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.20970450192689896,
|
|
"num_tokens": 35211570.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.451878833770752,
|
|
"epoch": 1.771718986915258,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004694435621030803,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20630280822515487,
|
|
"num_tokens": 35222451.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.610853767395019,
|
|
"epoch": 1.7722805638232155,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046942335780128785,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.19730931520462036,
|
|
"num_tokens": 35233588.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.5950500011444095,
|
|
"epoch": 1.7728421407311732,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00046940314730898035,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.19788164794445037,
|
|
"num_tokens": 35245766.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.502189970016479,
|
|
"epoch": 1.7734037176391306,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004693829306268012,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.20533297210931778,
|
|
"num_tokens": 35255635.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.576853847503662,
|
|
"epoch": 1.773965294547088,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004693627077553942,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.2052821323275566,
|
|
"num_tokens": 35269342.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.549467706680298,
|
|
"epoch": 1.7745268714550457,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004693424786954031,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.20662458688020707,
|
|
"num_tokens": 35280735.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.570686388015747,
|
|
"epoch": 1.7750884483630034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046932224344747224,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.2020970270037651,
|
|
"num_tokens": 35290803.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.518099641799926,
|
|
"epoch": 1.7756500252709608,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046930200201224573,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.20478644371032714,
|
|
"num_tokens": 35301811.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.563992023468018,
|
|
"epoch": 1.7762116021789183,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004692817543903681,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.200000561773777,
|
|
"num_tokens": 35313374.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.588944721221924,
|
|
"epoch": 1.776773179086876,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000469261500582484,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.21314590573310851,
|
|
"num_tokens": 35323272.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.587257671356201,
|
|
"epoch": 1.7773347559948336,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046924124058923843,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.19435863345861434,
|
|
"num_tokens": 35335720.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.535213136672974,
|
|
"epoch": 1.777896332902791,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004692209744112765,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.20621997565031053,
|
|
"num_tokens": 35347621.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.717250013351441,
|
|
"epoch": 1.7784579098107485,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004692007020492433,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.19571279883384704,
|
|
"num_tokens": 35360611.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.599717903137207,
|
|
"epoch": 1.7790194867187061,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004691804235037845,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.20136249363422393,
|
|
"num_tokens": 35372242.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.526900863647461,
|
|
"epoch": 1.7795810636266638,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004691601387755456,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.2117035061120987,
|
|
"num_tokens": 35385718.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.581648683547973,
|
|
"epoch": 1.7801426405346212,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046913984786517275,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.20246124714612962,
|
|
"num_tokens": 35398298.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.558437967300415,
|
|
"epoch": 1.7807042174425787,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046911955077331177,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.20896803736686706,
|
|
"num_tokens": 35408765.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.457685136795044,
|
|
"epoch": 1.7812657943505363,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046909924750060893,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.2104242593050003,
|
|
"num_tokens": 35418547.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.552804279327392,
|
|
"epoch": 1.781827371258494,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004690789380477109,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.20718699246644973,
|
|
"num_tokens": 35428743.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.488613224029541,
|
|
"epoch": 1.7823889481664514,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004690586224152641,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.21142317354679108,
|
|
"num_tokens": 35439557.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.572359561920166,
|
|
"epoch": 1.7829505250744089,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004690383006039156,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.2034531280398369,
|
|
"num_tokens": 35452041.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.605137777328491,
|
|
"epoch": 1.7835121019823665,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004690179726143123,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20897858887910842,
|
|
"num_tokens": 35463283.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.590687465667725,
|
|
"epoch": 1.784073678890324,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004689976384471014,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.21187433749437332,
|
|
"num_tokens": 35475802.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.492111015319824,
|
|
"epoch": 1.7846352557982814,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004689772981029306,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.21204737871885299,
|
|
"num_tokens": 35486322.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.54534420967102,
|
|
"epoch": 1.785196832706239,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004689569515824473,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.20867445319890976,
|
|
"num_tokens": 35497021.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.506159257888794,
|
|
"epoch": 1.7857584096141967,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004689365988862995,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.2183620199561119,
|
|
"num_tokens": 35507579.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.486914920806885,
|
|
"epoch": 1.7863199865221542,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046891624001513515,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.20554888844490052,
|
|
"num_tokens": 35518131.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.551437330245972,
|
|
"epoch": 1.7868815634301116,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046889587496960257,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.20174983143806458,
|
|
"num_tokens": 35529577.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.587335014343262,
|
|
"epoch": 1.7874431403380693,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046887550375034997,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.21506631672382354,
|
|
"num_tokens": 35541555.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.5035933494567875,
|
|
"epoch": 1.788004717246027,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046885512635802627,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.2110618159174919,
|
|
"num_tokens": 35552596.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.432600021362305,
|
|
"epoch": 1.7885662941539844,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004688347427932801,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.20498508363962173,
|
|
"num_tokens": 35564962.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.566061878204346,
|
|
"epoch": 1.7891278710619418,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046881435305676055,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.20194629281759263,
|
|
"num_tokens": 35576436.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.542887926101685,
|
|
"epoch": 1.7896894479698995,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046879395714911686,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.20952823907136917,
|
|
"num_tokens": 35587467.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.607672166824341,
|
|
"epoch": 1.7902510248778571,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046877355507099846,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.19979766458272935,
|
|
"num_tokens": 35600302.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.577974510192871,
|
|
"epoch": 1.7908126017858146,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004687531468230549,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.21042991280555726,
|
|
"num_tokens": 35611757.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.4939733982086185,
|
|
"epoch": 1.791374178693772,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004687327324059359,
|
|
"loss": 5.2106,
|
|
"mean_token_accuracy": 0.20078481286764144,
|
|
"num_tokens": 35621991.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.48218936920166,
|
|
"epoch": 1.7919357556017297,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004687123118202916,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.2052402451634407,
|
|
"num_tokens": 35633744.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.513424110412598,
|
|
"epoch": 1.7924973325096873,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004686918850667722,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.21686308532953263,
|
|
"num_tokens": 35645523.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.5917768478393555,
|
|
"epoch": 1.7930589094176448,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000468671452146028,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.20542020797729493,
|
|
"num_tokens": 35657670.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.481680631637573,
|
|
"epoch": 1.7936204863256022,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046865101305870965,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.2098682388663292,
|
|
"num_tokens": 35668149.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.49529538154602,
|
|
"epoch": 1.7941820632335599,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000468630567805468,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.21022680252790452,
|
|
"num_tokens": 35680225.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.464673280715942,
|
|
"epoch": 1.7947436401415173,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000468610116386954,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.21202036887407302,
|
|
"num_tokens": 35691042.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.541771793365479,
|
|
"epoch": 1.7953052170494748,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004685896588038187,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.20334921032190323,
|
|
"num_tokens": 35702895.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.551415252685547,
|
|
"epoch": 1.7958667939574324,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004685691950567136,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.21224344968795777,
|
|
"num_tokens": 35714765.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.571813869476318,
|
|
"epoch": 1.79642837086539,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046854872514629035,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.19754154235124588,
|
|
"num_tokens": 35725832.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.50899748802185,
|
|
"epoch": 1.7969899477733475,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004685282490732005,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.2143542781472206,
|
|
"num_tokens": 35736619.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.448057842254639,
|
|
"epoch": 1.797551524681305,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046850776683809623,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.20760646611452102,
|
|
"num_tokens": 35748243.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.526572418212891,
|
|
"epoch": 1.7981131015892626,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004684872784416295,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20479226261377334,
|
|
"num_tokens": 35759126.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.603467798233032,
|
|
"epoch": 1.7986746784972203,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004684667838844529,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.21089577823877334,
|
|
"num_tokens": 35770998.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.514874505996704,
|
|
"epoch": 1.7992362554051777,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004684462831672188,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.21367083489894867,
|
|
"num_tokens": 35782835.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.489229679107666,
|
|
"epoch": 1.7997978323131352,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046842577629058006,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.20171952694654466,
|
|
"num_tokens": 35792828.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.602787160873413,
|
|
"epoch": 1.8003594092210928,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004684052632551896,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.20132363438606263,
|
|
"num_tokens": 35804449.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.52608551979065,
|
|
"epoch": 1.8009209861290505,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046838474406170046,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.20893020033836365,
|
|
"num_tokens": 35815903.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.477285242080688,
|
|
"epoch": 1.801482563037008,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046836421871076616,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.21274147033691407,
|
|
"num_tokens": 35827872.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.50567307472229,
|
|
"epoch": 1.8020441399449654,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004683436872030401,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.215439136326313,
|
|
"num_tokens": 35838864.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.463530349731445,
|
|
"epoch": 1.802605716852923,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046832314953917605,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.20756640434265136,
|
|
"num_tokens": 35850178.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.519075918197632,
|
|
"epoch": 1.8031672937608807,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046830260571982795,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.21045697778463363,
|
|
"num_tokens": 35861904.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.402062654495239,
|
|
"epoch": 1.8037288706688381,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004682820557456499,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21434694528579712,
|
|
"num_tokens": 35872977.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.610428237915039,
|
|
"epoch": 1.8042904475767956,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00046826149961729625,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.2051602065563202,
|
|
"num_tokens": 35886094.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.507781839370727,
|
|
"epoch": 1.8048520244847532,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046824093733542144,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.21879759281873704,
|
|
"num_tokens": 35897557.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.568304967880249,
|
|
"epoch": 1.8054136013927107,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046822036890068033,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.19885764867067338,
|
|
"num_tokens": 35910605.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.512652063369751,
|
|
"epoch": 1.8059751783006681,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046819979431372773,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.21547006964683532,
|
|
"num_tokens": 35921062.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.533285522460938,
|
|
"epoch": 1.8065367552086258,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046817921357521865,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.2074277639389038,
|
|
"num_tokens": 35932385.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.468472242355347,
|
|
"epoch": 1.8070983321165834,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046815862668580854,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.21234085857868196,
|
|
"num_tokens": 35943628.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.5487886428833,
|
|
"epoch": 1.8076599090245409,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004681380336461528,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.19492993205785752,
|
|
"num_tokens": 35955074.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.590322875976563,
|
|
"epoch": 1.8082214859324983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046811743445690724,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.2098372220993042,
|
|
"num_tokens": 35966200.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.451094007492065,
|
|
"epoch": 1.808783062840456,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004680968291187276,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.21802327334880828,
|
|
"num_tokens": 35975638.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.447217702865601,
|
|
"epoch": 1.8093446397484136,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004680762176322701,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.21439190357923507,
|
|
"num_tokens": 35986486.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.475198554992676,
|
|
"epoch": 1.809906216656371,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046805559999819093,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.22283555418252946,
|
|
"num_tokens": 35996612.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.421088600158692,
|
|
"epoch": 1.8104677935643285,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004680349762171465,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.21139468401670455,
|
|
"num_tokens": 36006936.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.541531610488891,
|
|
"epoch": 1.8110293704722862,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004680143462897936,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.20159294009208678,
|
|
"num_tokens": 36019562.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.530387020111084,
|
|
"epoch": 1.8115909473802438,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004679937102167891,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.20976870208978654,
|
|
"num_tokens": 36029585.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.4941212177276615,
|
|
"epoch": 1.8121525242882013,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046797306799879,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.21129994094371796,
|
|
"num_tokens": 36041495.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.513312959671021,
|
|
"epoch": 1.8127141011961587,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046795241963645356,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.2083157256245613,
|
|
"num_tokens": 36052087.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.507216501235962,
|
|
"epoch": 1.8132756781041164,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004679317651304373,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.2146862581372261,
|
|
"num_tokens": 36065011.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.562868356704712,
|
|
"epoch": 1.813837255012074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004679111044813987,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.21212920248508454,
|
|
"num_tokens": 36075912.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.5113975524902346,
|
|
"epoch": 1.8143988319200315,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046789043768999573,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.20590389966964723,
|
|
"num_tokens": 36086757.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.499164056777954,
|
|
"epoch": 1.814960408827989,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004678697647568865,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.21010294705629348,
|
|
"num_tokens": 36097319.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.528844118118286,
|
|
"epoch": 1.8155219857359466,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046784908568272903,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.20655940473079681,
|
|
"num_tokens": 36108416.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.4616447448730465,
|
|
"epoch": 1.8160835626439042,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000467828400468182,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.20799020379781724,
|
|
"num_tokens": 36120833.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.576100063323975,
|
|
"epoch": 1.8166451395518615,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046780770911390387,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.20404674261808395,
|
|
"num_tokens": 36132348.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.554430341720581,
|
|
"epoch": 1.8172067164598191,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004677870116205534,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.2119983658194542,
|
|
"num_tokens": 36142829.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.5574586391448975,
|
|
"epoch": 1.8177682933677768,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046776630798878985,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.20637548118829727,
|
|
"num_tokens": 36155931.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.544053077697754,
|
|
"epoch": 1.8183298702757342,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004677455982192723,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.20079542994499205,
|
|
"num_tokens": 36167591.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.488490009307862,
|
|
"epoch": 1.8188914471836917,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046772488231266004,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.21541092544794083,
|
|
"num_tokens": 36178867.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.373026275634766,
|
|
"epoch": 1.8194530240916493,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046770416026961284,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.22355683594942094,
|
|
"num_tokens": 36190691.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.602883815765381,
|
|
"epoch": 1.820014600999607,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004676834320907904,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.202303346991539,
|
|
"num_tokens": 36202222.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.53536467552185,
|
|
"epoch": 1.8205761779075644,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004676626977768528,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.21713785380125045,
|
|
"num_tokens": 36214303.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.510617733001709,
|
|
"epoch": 1.8211377548155219,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046764195732846013,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.21478829383850098,
|
|
"num_tokens": 36224440.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.422286701202393,
|
|
"epoch": 1.8216993317234795,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046762121074627285,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.2107176423072815,
|
|
"num_tokens": 36235445.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.508383846282959,
|
|
"epoch": 1.8222609086314372,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046760045803095153,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.21572389751672744,
|
|
"num_tokens": 36247024.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.593313932418823,
|
|
"epoch": 1.8228224855393946,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004675796991831569,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.20840420573949814,
|
|
"num_tokens": 36257406.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.519710731506348,
|
|
"epoch": 1.823384062447352,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046755893420355,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.21076567769050597,
|
|
"num_tokens": 36270266.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.518761825561524,
|
|
"epoch": 1.8239456393553097,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004675381630927919,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.20063205510377885,
|
|
"num_tokens": 36281470.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.5073127269744875,
|
|
"epoch": 1.8245072162632674,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046751738585154405,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.21204541325569154,
|
|
"num_tokens": 36293315.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.575473165512085,
|
|
"epoch": 1.8250687931712248,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046749660248046794,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.21476247906684875,
|
|
"num_tokens": 36304688.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.584457445144653,
|
|
"epoch": 1.8256303700791823,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046747581298022537,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.21231947988271713,
|
|
"num_tokens": 36315773.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.560157251358032,
|
|
"epoch": 1.82619194698714,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004674550173514782,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.21049715131521224,
|
|
"num_tokens": 36327914.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.57236909866333,
|
|
"epoch": 1.8267535238950976,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046743421559488875,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.19859042167663574,
|
|
"num_tokens": 36339617.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.640665578842163,
|
|
"epoch": 1.8273151008030548,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046741340771111917,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.19839200675487517,
|
|
"num_tokens": 36350768.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.515523767471313,
|
|
"epoch": 1.8278766777110125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046739259370083205,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.21197623610496522,
|
|
"num_tokens": 36361267.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.553961133956909,
|
|
"epoch": 1.8284382546189701,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004673717735646902,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.20907451212406158,
|
|
"num_tokens": 36373259.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.571514225006103,
|
|
"epoch": 1.8289998315269276,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004673509473033564,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20686480402946472,
|
|
"num_tokens": 36384295.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.567991781234741,
|
|
"epoch": 1.829561408434885,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046733011491749383,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.21408538818359374,
|
|
"num_tokens": 36394928.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.501218271255493,
|
|
"epoch": 1.8301229853428427,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004673092764077658,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.2142808184027672,
|
|
"num_tokens": 36407038.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.606045722961426,
|
|
"epoch": 1.8306845622508003,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004672884317748359,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.2036679580807686,
|
|
"num_tokens": 36418221.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.544824266433716,
|
|
"epoch": 1.8312461391587578,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004672675810193677,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.21289408802986146,
|
|
"num_tokens": 36429036.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.558088541030884,
|
|
"epoch": 1.8318077160667152,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046724672414202514,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.20961279273033143,
|
|
"num_tokens": 36439851.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.534616327285766,
|
|
"epoch": 1.8323692929746729,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004672258611434724,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.20912074148654938,
|
|
"num_tokens": 36451612.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.58637638092041,
|
|
"epoch": 1.8329308698826305,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046720499202437354,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.20227876007556916,
|
|
"num_tokens": 36462883.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.529001998901367,
|
|
"epoch": 1.833492446790588,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004671841167853933,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.21931282132864,
|
|
"num_tokens": 36473609.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.542405462265014,
|
|
"epoch": 1.8340540236985454,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004671632354271962,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.21173172295093537,
|
|
"num_tokens": 36484058.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.543933629989624,
|
|
"epoch": 1.834615600606503,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046714234795044724,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.21218518316745758,
|
|
"num_tokens": 36496445.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.460747385025025,
|
|
"epoch": 1.8351771775144607,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004671214543558113,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.21281379610300064,
|
|
"num_tokens": 36507553.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.497470712661743,
|
|
"epoch": 1.8357387544224182,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004671005546439538,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.21427890807390212,
|
|
"num_tokens": 36517887.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.506145286560058,
|
|
"epoch": 1.8363003313303756,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046707964881554005,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.21216657459735871,
|
|
"num_tokens": 36529185.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.520971775054932,
|
|
"epoch": 1.8368619082383333,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046705873687123586,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.2110397547483444,
|
|
"num_tokens": 36539473.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.57681360244751,
|
|
"epoch": 1.837423485146291,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046703781881170703,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.2078295737504959,
|
|
"num_tokens": 36549603.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.572166967391968,
|
|
"epoch": 1.8379850620542482,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046701689463761947,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.21299584805965424,
|
|
"num_tokens": 36560394.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.550047588348389,
|
|
"epoch": 1.8385466389622058,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046699596434963953,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.2070128485560417,
|
|
"num_tokens": 36570657.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.445622348785401,
|
|
"epoch": 1.8391082158701635,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004669750279484337,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.21390848457813263,
|
|
"num_tokens": 36580810.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.4724555015563965,
|
|
"epoch": 1.839669792778121,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004669540854346685,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.21288266777992249,
|
|
"num_tokens": 36592981.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.4226325988769535,
|
|
"epoch": 1.8402313696860784,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046693313680901073,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.21457228660583497,
|
|
"num_tokens": 36604130.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.438716268539428,
|
|
"epoch": 1.840792946594036,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046691218207212744,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.21119638681411743,
|
|
"num_tokens": 36614833.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.581739234924316,
|
|
"epoch": 1.8413545235019937,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004668912212246859,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.2121249571442604,
|
|
"num_tokens": 36625306.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.6323521614074705,
|
|
"epoch": 1.8419161004099511,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046687025426735335,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.20473585426807403,
|
|
"num_tokens": 36637396.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.5168181419372555,
|
|
"epoch": 1.8424776773179086,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004668492812007976,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.2055605709552765,
|
|
"num_tokens": 36648175.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.535448980331421,
|
|
"epoch": 1.8430392542258662,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004668283020256863,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.20751039385795594,
|
|
"num_tokens": 36659876.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.547568941116333,
|
|
"epoch": 1.843600831133824,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046680731674268744,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.21007374972105025,
|
|
"num_tokens": 36671168.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.489198637008667,
|
|
"epoch": 1.8441624080417813,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004667863253524692,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.2142185240983963,
|
|
"num_tokens": 36680987.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.50673279762268,
|
|
"epoch": 1.8447239849497388,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046676532785569995,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.2092178627848625,
|
|
"num_tokens": 36692396.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.537379217147827,
|
|
"epoch": 1.8452855618576964,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004667443242530484,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.21501348316669464,
|
|
"num_tokens": 36702696.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.47165322303772,
|
|
"epoch": 1.845847138765654,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046672331454518314,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.21769247949123383,
|
|
"num_tokens": 36713582.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.476025676727295,
|
|
"epoch": 1.8464087156736115,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004667022987327732,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.21578407287597656,
|
|
"num_tokens": 36724324.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.5395183086395265,
|
|
"epoch": 1.846970292581569,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004666812768164877,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.21609731167554855,
|
|
"num_tokens": 36736369.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.602626037597656,
|
|
"epoch": 1.8475318694895266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046666024879699606,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.21095730513334274,
|
|
"num_tokens": 36748047.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.590544605255127,
|
|
"epoch": 1.8480934463974843,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046663921467496766,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.21858651638031007,
|
|
"num_tokens": 36758943.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.57470703125,
|
|
"epoch": 1.8486550233054415,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004666181744510724,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.2062245413661003,
|
|
"num_tokens": 36769807.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.486791515350342,
|
|
"epoch": 1.8492166002133992,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046659712812598017,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.2191978543996811,
|
|
"num_tokens": 36780370.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.4681905746459964,
|
|
"epoch": 1.8497781771213568,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046657607570036103,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.2149543970823288,
|
|
"num_tokens": 36789757.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.4939703941345215,
|
|
"epoch": 1.8503397540293143,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046655501717488533,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.20607143193483352,
|
|
"num_tokens": 36800531.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.591684103012085,
|
|
"epoch": 1.8509013309372717,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004665339525502236,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.20733258426189421,
|
|
"num_tokens": 36811666.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.550846433639526,
|
|
"epoch": 1.8514629078452294,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046651288182704653,
|
|
"loss": 5.0234,
|
|
"mean_token_accuracy": 0.2130743607878685,
|
|
"num_tokens": 36822443.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.517094850540161,
|
|
"epoch": 1.852024484753187,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004664918050060251,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.21349021196365356,
|
|
"num_tokens": 36835517.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.554904556274414,
|
|
"epoch": 1.8525860616611445,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004664707220878302,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.21717120260000228,
|
|
"num_tokens": 36845177.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.503123378753662,
|
|
"epoch": 1.853147638569102,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004664496330731334,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.2091933697462082,
|
|
"num_tokens": 36855821.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.560890436172485,
|
|
"epoch": 1.8537092154770596,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004664285379626059,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.198876316845417,
|
|
"num_tokens": 36866254.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.484575986862183,
|
|
"epoch": 1.8542707923850172,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046640743675691954,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.20981743633747102,
|
|
"num_tokens": 36876348.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.548911666870117,
|
|
"epoch": 1.8548323692929747,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004663863294567462,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20481101870536805,
|
|
"num_tokens": 36888088.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.67602653503418,
|
|
"epoch": 1.8553939462009321,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004663652160627579,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.2013300970196724,
|
|
"num_tokens": 36900203.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.579442548751831,
|
|
"epoch": 1.8559555231088898,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046634409657562683,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.21193958222866058,
|
|
"num_tokens": 36911321.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.558789300918579,
|
|
"epoch": 1.8565171000168474,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004663229709960255,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.2056431367993355,
|
|
"num_tokens": 36922562.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.517946004867554,
|
|
"epoch": 1.8570786769248049,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00046630183932462664,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.2038568913936615,
|
|
"num_tokens": 36933923.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.532702159881592,
|
|
"epoch": 1.8576402538327623,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004662807015621031,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.20751660019159318,
|
|
"num_tokens": 36945203.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.54712061882019,
|
|
"epoch": 1.85820183074072,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046625955770912764,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.2063692808151245,
|
|
"num_tokens": 36956094.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.550728845596313,
|
|
"epoch": 1.8587634076486776,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046623840776637384,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.20702403485774995,
|
|
"num_tokens": 36967375.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.436285829544067,
|
|
"epoch": 1.859324984556635,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004662172517345149,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.209367972612381,
|
|
"num_tokens": 36977674.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.554156970977783,
|
|
"epoch": 1.8598865614645925,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004661960896142245,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.21132284104824067,
|
|
"num_tokens": 36990241.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.527145862579346,
|
|
"epoch": 1.8604481383725502,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046617492140617654,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.20171399116516114,
|
|
"num_tokens": 37002322.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.5814286231994625,
|
|
"epoch": 1.8610097152805076,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004661537471110448,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.20499605536460877,
|
|
"num_tokens": 37014524.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.506622838973999,
|
|
"epoch": 1.861571292188465,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004661325667295037,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.22121130526065827,
|
|
"num_tokens": 37025057.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.481692934036255,
|
|
"epoch": 1.8621328690964227,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004661113802622275,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.2080416902899742,
|
|
"num_tokens": 37035311.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.5131415843963625,
|
|
"epoch": 1.8626944460043804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004660901877098908,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.2095095083117485,
|
|
"num_tokens": 37046275.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.535091686248779,
|
|
"epoch": 1.8632560229123378,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004660689890731685,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.21219531297683716,
|
|
"num_tokens": 37057658.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.490896129608155,
|
|
"epoch": 1.8638175998202953,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046604778435273546,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.21808335036039353,
|
|
"num_tokens": 37067946.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.402779531478882,
|
|
"epoch": 1.864379176728253,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046602657354926686,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.2129659801721573,
|
|
"num_tokens": 37078881.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.53774733543396,
|
|
"epoch": 1.8649407536362106,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000466005356663438,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.20113817006349563,
|
|
"num_tokens": 37090474.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.565539932250976,
|
|
"epoch": 1.865502330544168,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046598413369592463,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.20688705146312714,
|
|
"num_tokens": 37101527.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.527318239212036,
|
|
"epoch": 1.8660639074521255,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004659629046474023,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.20322408378124238,
|
|
"num_tokens": 37112615.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.502759170532227,
|
|
"epoch": 1.8666254843600831,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000465941669518547,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.2154079332947731,
|
|
"num_tokens": 37122922.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.494392251968383,
|
|
"epoch": 1.8671870612680408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004659204283100349,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21930739730596543,
|
|
"num_tokens": 37133215.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.398241329193115,
|
|
"epoch": 1.8677486381759982,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046589918102254237,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.21610959023237228,
|
|
"num_tokens": 37144292.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.476335525512695,
|
|
"epoch": 1.8683102150839557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004658779276567458,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.20896967202425004,
|
|
"num_tokens": 37155623.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.58779468536377,
|
|
"epoch": 1.8688717919919133,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046585666821332203,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.20569302439689635,
|
|
"num_tokens": 37165406.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.570563507080078,
|
|
"epoch": 1.869433368899871,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046583540269294794,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.21078147739171982,
|
|
"num_tokens": 37175522.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.516193771362305,
|
|
"epoch": 1.8699949458078284,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004658141310963006,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.21157218664884567,
|
|
"num_tokens": 37186745.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.4357702255249025,
|
|
"epoch": 1.8705565227157859,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004657928534240573,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.21521993726491928,
|
|
"num_tokens": 37197357.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.553435611724853,
|
|
"epoch": 1.8711180996237435,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004657715696768955,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.2095891937613487,
|
|
"num_tokens": 37209839.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.591492223739624,
|
|
"epoch": 1.871679676531701,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000465750279855493,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.2008549913764,
|
|
"num_tokens": 37221314.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.503515529632568,
|
|
"epoch": 1.8722412534396584,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004657289839605276,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.21047773510217666,
|
|
"num_tokens": 37233372.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.564987373352051,
|
|
"epoch": 1.872802830347616,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004657076819926774,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.20977456271648406,
|
|
"num_tokens": 37244758.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.574359369277954,
|
|
"epoch": 1.8733644072555737,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004656863739526206,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.2066573217511177,
|
|
"num_tokens": 37255848.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.502698564529419,
|
|
"epoch": 1.8739259841635312,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046566505984103575,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.21638241708278655,
|
|
"num_tokens": 37266010.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.440232658386231,
|
|
"epoch": 1.8744875610714886,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004656437396586014,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.20583205819129943,
|
|
"num_tokens": 37278445.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.5707227230072025,
|
|
"epoch": 1.8750491379794463,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004656224134059964,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.2049315243959427,
|
|
"num_tokens": 37291181.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.645757675170898,
|
|
"epoch": 1.875610714887404,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046560108108389985,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.20448590964078903,
|
|
"num_tokens": 37302333.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.489307069778443,
|
|
"epoch": 1.8761722917953614,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000465579742692991,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.21503279358148575,
|
|
"num_tokens": 37312754.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.594323921203613,
|
|
"epoch": 1.8767338687033188,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004655583982339492,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.21674154102802276,
|
|
"num_tokens": 37323335.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.529937028884888,
|
|
"epoch": 1.8772954456112765,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004655370477074541,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.21087792962789537,
|
|
"num_tokens": 37334332.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.498416805267334,
|
|
"epoch": 1.8778570225192341,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004655156911141855,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.2112417235970497,
|
|
"num_tokens": 37344770.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.528967046737671,
|
|
"epoch": 1.8784185994271916,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004654943284548234,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.21072051376104356,
|
|
"num_tokens": 37356009.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.393898296356201,
|
|
"epoch": 1.878980176335149,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046547295973004807,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.2177809625864029,
|
|
"num_tokens": 37367823.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.485453510284424,
|
|
"epoch": 1.8795417532431067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046545158494053966,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.20670478492975236,
|
|
"num_tokens": 37378156.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.571795463562012,
|
|
"epoch": 1.8801033301510643,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046543020408697905,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.21011139154434205,
|
|
"num_tokens": 37388378.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.501275968551636,
|
|
"epoch": 1.8806649070590218,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046540881717004685,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.20925726741552353,
|
|
"num_tokens": 37398457.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.516232633590699,
|
|
"epoch": 1.8812264839669792,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004653874241904241,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.20725387930870057,
|
|
"num_tokens": 37409341.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.509982681274414,
|
|
"epoch": 1.8817880608749369,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004653660251487919,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.2158171609044075,
|
|
"num_tokens": 37420081.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.4820160388946535,
|
|
"epoch": 1.8823496377828943,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046534462004583154,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.22708788216114045,
|
|
"num_tokens": 37430707.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.545451688766479,
|
|
"epoch": 1.8829112146908518,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004653232088822248,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20654281377792358,
|
|
"num_tokens": 37441250.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.522458028793335,
|
|
"epoch": 1.8834727915988094,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004653017916586532,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.20377702713012696,
|
|
"num_tokens": 37452909.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.5662932872772215,
|
|
"epoch": 1.884034368506767,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004652803683757987,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.20477454513311386,
|
|
"num_tokens": 37463833.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.476609563827514,
|
|
"epoch": 1.8845959454147245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004652589390343436,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.21673983931541443,
|
|
"num_tokens": 37473967.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.557993698120117,
|
|
"epoch": 1.885157522322682,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046523750363497,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.2164803549647331,
|
|
"num_tokens": 37484748.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.511367893218994,
|
|
"epoch": 1.8857190992306396,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004652160621783605,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20454054921865464,
|
|
"num_tokens": 37495757.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.517141962051392,
|
|
"epoch": 1.8862806761385973,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046519461466519785,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.20811372101306916,
|
|
"num_tokens": 37506612.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.474361085891724,
|
|
"epoch": 1.8868422530465547,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004651731610961649,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.22285923212766648,
|
|
"num_tokens": 37518639.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.49378547668457,
|
|
"epoch": 1.8874038299545122,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004651517014719446,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.20704616606235504,
|
|
"num_tokens": 37530020.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.482843494415283,
|
|
"epoch": 1.8879654068624698,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004651302357932206,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21112889796495438,
|
|
"num_tokens": 37540737.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.430828619003296,
|
|
"epoch": 1.8885269837704275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000465108764060676,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.2100732296705246,
|
|
"num_tokens": 37551091.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.526059961318969,
|
|
"epoch": 1.889088560678385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046508728627499464,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.2065451979637146,
|
|
"num_tokens": 37561904.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.6243750095367435,
|
|
"epoch": 1.8896501375863424,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004650658024368604,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.20226893424987794,
|
|
"num_tokens": 37573532.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.598481225967407,
|
|
"epoch": 1.8902117144943,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004650443125469573,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.21551499366760254,
|
|
"num_tokens": 37584886.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.505048942565918,
|
|
"epoch": 1.8907732914022577,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004650228166059695,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.2084640920162201,
|
|
"num_tokens": 37595190.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.479953813552856,
|
|
"epoch": 1.8913348683102151,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004650013146145816,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.21100073009729386,
|
|
"num_tokens": 37605776.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.6064040184021,
|
|
"epoch": 1.8918964452181726,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004649798065734781,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.20467308163642883,
|
|
"num_tokens": 37616882.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.6429443359375,
|
|
"epoch": 1.8924580221261302,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046495829248334393,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.20677735954523085,
|
|
"num_tokens": 37628528.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.566906881332398,
|
|
"epoch": 1.8930195990340877,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004649367723448641,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.20676727890968322,
|
|
"num_tokens": 37640502.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.460350036621094,
|
|
"epoch": 1.8935811759420451,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046491524615872366,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.21357525885105133,
|
|
"num_tokens": 37652845.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.567919158935547,
|
|
"epoch": 1.8941427528500028,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046489371392560816,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.20296514630317689,
|
|
"num_tokens": 37665418.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.556247186660767,
|
|
"epoch": 1.8947043297579604,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046487217564620317,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.20513799786567688,
|
|
"num_tokens": 37676429.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.566342973709107,
|
|
"epoch": 1.8952659066659179,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004648506313211945,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.2117600455880165,
|
|
"num_tokens": 37686779.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.505152845382691,
|
|
"epoch": 1.8958274835738753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046482908095126803,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.20294010788202285,
|
|
"num_tokens": 37697665.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.5910351276397705,
|
|
"epoch": 1.896389060481833,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046480752453711,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.2092644155025482,
|
|
"num_tokens": 37708987.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.433376407623291,
|
|
"epoch": 1.8969506373897906,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004647859620794068,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.21685654819011688,
|
|
"num_tokens": 37720335.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.572321987152099,
|
|
"epoch": 1.897512214297748,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046476439357884497,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.20310602933168412,
|
|
"num_tokens": 37731586.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.568728733062744,
|
|
"epoch": 1.8980737912057055,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046474281903611126,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.212124602496624,
|
|
"num_tokens": 37742907.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.574461841583252,
|
|
"epoch": 1.8986353681136632,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046472123845189253,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.20538633316755295,
|
|
"num_tokens": 37753787.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.508903694152832,
|
|
"epoch": 1.8991969450216208,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000464699651826876,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.2097575083374977,
|
|
"num_tokens": 37766047.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.509543323516846,
|
|
"epoch": 1.8997585219295783,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046467805916174907,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.20766380429267883,
|
|
"num_tokens": 37777651.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.482913398742676,
|
|
"epoch": 1.9003200988375357,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046465646045719915,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.21107212603092193,
|
|
"num_tokens": 37788527.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.469332361221314,
|
|
"epoch": 1.9008816757454934,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004646348557139139,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.20701346546411514,
|
|
"num_tokens": 37800727.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.507780456542969,
|
|
"epoch": 1.901443252653451,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046461324493258133,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.21568891704082488,
|
|
"num_tokens": 37812332.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.543201446533203,
|
|
"epoch": 1.9020048295614085,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046459162811388955,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.20960883647203446,
|
|
"num_tokens": 37823665.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.44745135307312,
|
|
"epoch": 1.902566406469366,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645700052585267,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.22817832231521606,
|
|
"num_tokens": 37833793.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.419557285308838,
|
|
"epoch": 1.9031279833773236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004645483763671815,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.2224147215485573,
|
|
"num_tokens": 37844104.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.545752286911011,
|
|
"epoch": 1.903689560285281,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046452674144054236,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.21561252623796462,
|
|
"num_tokens": 37853920.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.526240348815918,
|
|
"epoch": 1.9042511371932385,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046450510047929826,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.2111707553267479,
|
|
"num_tokens": 37865749.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.48956823348999,
|
|
"epoch": 1.9048127141011961,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046448345348413833,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.21271543502807616,
|
|
"num_tokens": 37876259.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.554007482528687,
|
|
"epoch": 1.9053742910091538,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004644618004557517,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.21010176986455917,
|
|
"num_tokens": 37887186.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.461946439743042,
|
|
"epoch": 1.9059358679171112,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004644401413948279,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.21595332026481628,
|
|
"num_tokens": 37898210.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.507249116897583,
|
|
"epoch": 1.9064974448250687,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004644184763020565,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.21390532851219177,
|
|
"num_tokens": 37909332.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.506443309783935,
|
|
"epoch": 1.9070590217330263,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004643968051781273,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.2087691217660904,
|
|
"num_tokens": 37919796.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.539094257354736,
|
|
"epoch": 1.907620598640984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004643751280237305,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.20642016977071762,
|
|
"num_tokens": 37931135.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.599572229385376,
|
|
"epoch": 1.9081821755489414,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004643534448395561,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.2079877033829689,
|
|
"num_tokens": 37942302.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.500601673126221,
|
|
"epoch": 1.9087437524568989,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004643317556262946,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.2056230843067169,
|
|
"num_tokens": 37954188.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.514197158813476,
|
|
"epoch": 1.9093053293648565,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046431006038463653,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20216042250394822,
|
|
"num_tokens": 37964778.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.624696540832519,
|
|
"epoch": 1.9098669062728142,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004642883591152727,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.20339809507131576,
|
|
"num_tokens": 37976384.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.577062940597534,
|
|
"epoch": 1.9104284831807716,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004642666518188942,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.207042296230793,
|
|
"num_tokens": 37986975.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.6483241558074955,
|
|
"epoch": 1.910990060088729,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046424493849619205,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.20538949072360993,
|
|
"num_tokens": 37999255.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.61256890296936,
|
|
"epoch": 1.9115516369966867,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046422321914785757,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.20605721324682236,
|
|
"num_tokens": 38010436.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.437765741348267,
|
|
"epoch": 1.9121132139046444,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046420149377458255,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.21763782799243928,
|
|
"num_tokens": 38021537.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.475924301147461,
|
|
"epoch": 1.9126747908126018,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046417976237705846,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.21263266503810882,
|
|
"num_tokens": 38033396.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.458413124084473,
|
|
"epoch": 1.9132363677205593,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046415802495597744,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.22390799075365067,
|
|
"num_tokens": 38044917.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.5102643966674805,
|
|
"epoch": 1.913797944628517,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046413628151203154,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.21149980127811432,
|
|
"num_tokens": 38057002.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.4493897438049315,
|
|
"epoch": 1.9143595215364744,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046411453204591303,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.22078332155942917,
|
|
"num_tokens": 38068023.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.582755041122437,
|
|
"epoch": 1.9149210984444318,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046409277655831455,
|
|
"loss": 5.2347,
|
|
"mean_token_accuracy": 0.20125416219234465,
|
|
"num_tokens": 38080137.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.557947635650635,
|
|
"epoch": 1.9154826753523895,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004640710150499287,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.21779264956712724,
|
|
"num_tokens": 38090078.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.565938138961792,
|
|
"epoch": 1.9160442522603471,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046404924752144834,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.20974833369255066,
|
|
"num_tokens": 38101410.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.530655002593994,
|
|
"epoch": 1.9166058291683046,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046402747397356666,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.21350363045930862,
|
|
"num_tokens": 38111610.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.507906341552735,
|
|
"epoch": 1.917167406076262,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004640056944069768,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.20914530158042907,
|
|
"num_tokens": 38122947.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.487457752227783,
|
|
"epoch": 1.9177289829842197,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004639839088223725,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.21768011748790742,
|
|
"num_tokens": 38133083.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.546312952041626,
|
|
"epoch": 1.9182905598921773,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046396211722044716,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.2180164024233818,
|
|
"num_tokens": 38142941.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.583755588531494,
|
|
"epoch": 1.9188521368001348,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046394031960189473,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.2079913794994354,
|
|
"num_tokens": 38154269.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.482344007492065,
|
|
"epoch": 1.9194137137080922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004639185159674093,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.21370075643062592,
|
|
"num_tokens": 38164153.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.52473669052124,
|
|
"epoch": 1.9199752906160499,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046389670631768494,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.20169034600257874,
|
|
"num_tokens": 38174704.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.643307733535766,
|
|
"epoch": 1.9205368675240075,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004638748906534162,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.20285269916057586,
|
|
"num_tokens": 38186292.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.563044166564941,
|
|
"epoch": 1.921098444431965,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004638530689752977,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.21039002388715744,
|
|
"num_tokens": 38197419.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.537201261520385,
|
|
"epoch": 1.9216600213399224,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046383124128402433,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.20291815996170043,
|
|
"num_tokens": 38208276.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.44485445022583,
|
|
"epoch": 1.92222159824788,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046380940758029095,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.21589064002037048,
|
|
"num_tokens": 38220276.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.530895328521728,
|
|
"epoch": 1.9227831751558377,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046378756786479274,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20697960555553435,
|
|
"num_tokens": 38230760.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.480640172958374,
|
|
"epoch": 1.9233447520637952,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004637657221382252,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.2160651281476021,
|
|
"num_tokens": 38241769.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.539589738845825,
|
|
"epoch": 1.9239063289717526,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046374387040128384,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.20628338009119035,
|
|
"num_tokens": 38252800.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.457486295700074,
|
|
"epoch": 1.9244679058797103,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046372201265466444,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.2151569426059723,
|
|
"num_tokens": 38264319.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.493738269805908,
|
|
"epoch": 1.9250294827876677,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000463700148899063,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.2167115181684494,
|
|
"num_tokens": 38275118.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.570563745498657,
|
|
"epoch": 1.9255910596956252,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004636782791351756,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.20407831072807311,
|
|
"num_tokens": 38286264.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.5667924880981445,
|
|
"epoch": 1.9261526366035828,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004636564033636987,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.21711552441120147,
|
|
"num_tokens": 38297603.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.58396954536438,
|
|
"epoch": 1.9267142135115405,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046363452158532857,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19902312755584717,
|
|
"num_tokens": 38308760.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.562836742401123,
|
|
"epoch": 1.927275790419498,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004636126338007622,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.20938654989004135,
|
|
"num_tokens": 38320807.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.483173847198486,
|
|
"epoch": 1.9278373673274554,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004635907400106965,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.2037514105439186,
|
|
"num_tokens": 38331087.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.4919843673706055,
|
|
"epoch": 1.928398944235413,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004635688402158285,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.21199412047863006,
|
|
"num_tokens": 38341659.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.482517910003662,
|
|
"epoch": 1.9289605211433707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046354693441685537,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.21311705112457274,
|
|
"num_tokens": 38351371.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.478672742843628,
|
|
"epoch": 1.9295220980513281,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046352502261447475,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.21578599363565446,
|
|
"num_tokens": 38362677.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.453496217727661,
|
|
"epoch": 1.9300836749592856,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004635031048093843,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.21475907117128373,
|
|
"num_tokens": 38372882.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.532922601699829,
|
|
"epoch": 1.9306452518672432,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004634811810022819,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.20463451743125916,
|
|
"num_tokens": 38383401.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.574401617050171,
|
|
"epoch": 1.931206828775201,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046345925119386556,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.20473548620939255,
|
|
"num_tokens": 38394733.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.614757061004639,
|
|
"epoch": 1.9317684056831583,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004634373153848336,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.21301571875810624,
|
|
"num_tokens": 38406482.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.573880910873413,
|
|
"epoch": 1.9323299825911158,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004634153735758845,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.21222549974918364,
|
|
"num_tokens": 38417366.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.533652353286743,
|
|
"epoch": 1.9328915594990734,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004633934257677167,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.21627578139305115,
|
|
"num_tokens": 38428440.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.514242553710938,
|
|
"epoch": 1.933453136407031,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004633714719610292,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.21086566001176835,
|
|
"num_tokens": 38438471.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.540092515945434,
|
|
"epoch": 1.9340147133149885,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046334951215652097,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.21402105391025544,
|
|
"num_tokens": 38448990.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.604200601577759,
|
|
"epoch": 1.934576290222946,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046332754635489126,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.20453506857156753,
|
|
"num_tokens": 38460990.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.597727823257446,
|
|
"epoch": 1.9351378671309036,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004633055745568394,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.19894421845674515,
|
|
"num_tokens": 38471672.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.513748741149902,
|
|
"epoch": 1.935699444038861,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046328359676306506,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.21639675945043563,
|
|
"num_tokens": 38483248.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.551661777496338,
|
|
"epoch": 1.9362610209468185,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000463261612974268,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.2122338205575943,
|
|
"num_tokens": 38494795.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.472085475921631,
|
|
"epoch": 1.9368225978547762,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004632396231911481,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.21374958455562593,
|
|
"num_tokens": 38505276.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.612254476547241,
|
|
"epoch": 1.9373841747627338,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004632176274144056,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.200038443505764,
|
|
"num_tokens": 38515536.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.550712013244629,
|
|
"epoch": 1.9379457516706913,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046319562564474083,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.2115021675825119,
|
|
"num_tokens": 38525579.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.633426094055176,
|
|
"epoch": 1.9385073285786487,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046317361788285436,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.20304927676916124,
|
|
"num_tokens": 38536963.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.5235512256622314,
|
|
"epoch": 1.9390689054866064,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004631516041294469,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.20551202744245528,
|
|
"num_tokens": 38547497.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.578391695022583,
|
|
"epoch": 1.939630482394564,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004631295843852194,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20966936498880387,
|
|
"num_tokens": 38558840.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.533300971984863,
|
|
"epoch": 1.9401920593025215,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000463107558650873,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.22005430459976197,
|
|
"num_tokens": 38568670.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.52360782623291,
|
|
"epoch": 1.940753636210479,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046308552692710895,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.21423203200101854,
|
|
"num_tokens": 38578565.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.472231435775757,
|
|
"epoch": 1.9413152131184366,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046306348921462876,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.20934834331274033,
|
|
"num_tokens": 38589126.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.563221740722656,
|
|
"epoch": 1.9418767900263942,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004630414455141342,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.20694131255149842,
|
|
"num_tokens": 38601008.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.556043577194214,
|
|
"epoch": 1.9424383669343517,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000463019395826327,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.20897576957941055,
|
|
"num_tokens": 38611756.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.559178686141967,
|
|
"epoch": 1.9429999438423091,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046299734015190934,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.20646020621061326,
|
|
"num_tokens": 38623156.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.585256099700928,
|
|
"epoch": 1.9435615207502668,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046297527849158344,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.21329659074544907,
|
|
"num_tokens": 38633920.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.538552570343017,
|
|
"epoch": 1.9441230976582244,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004629532108460519,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.20484120547771453,
|
|
"num_tokens": 38644744.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.524242496490478,
|
|
"epoch": 1.9446846745661819,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046293113721601706,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.21750595569610595,
|
|
"num_tokens": 38656524.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.494972133636475,
|
|
"epoch": 1.9452462514741393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046290905760218193,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.21507811695337295,
|
|
"num_tokens": 38668386.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.508021640777588,
|
|
"epoch": 1.945807828382097,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046288697200524964,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.21251172423362732,
|
|
"num_tokens": 38678498.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.644032382965088,
|
|
"epoch": 1.9463694052900544,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046286488042592325,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.1974894344806671,
|
|
"num_tokens": 38690084.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.504043865203857,
|
|
"epoch": 1.9469309821980119,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004628427828649062,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20662968903779982,
|
|
"num_tokens": 38701282.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.5063971996307375,
|
|
"epoch": 1.9474925591059695,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046282067932290204,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.21475324928760528,
|
|
"num_tokens": 38713012.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.443633079528809,
|
|
"epoch": 1.9480541360139272,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004627985698006146,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.21442062854766847,
|
|
"num_tokens": 38723179.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.541174507141113,
|
|
"epoch": 1.9486157129218846,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000462776454298748,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.21327205747365952,
|
|
"num_tokens": 38733729.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.595817804336548,
|
|
"epoch": 1.949177289829842,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046275433281800613,
|
|
"loss": 5.0398,
|
|
"mean_token_accuracy": 0.21615110486745834,
|
|
"num_tokens": 38743139.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.572773027420044,
|
|
"epoch": 1.9497388667377997,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004627322053590935,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.20333731174468994,
|
|
"num_tokens": 38754697.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.5216961860656735,
|
|
"epoch": 1.9503004436457574,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004627100719227147,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.2122903898358345,
|
|
"num_tokens": 38765999.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.550380992889404,
|
|
"epoch": 1.9508620205537148,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046268793250957437,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.20666968524456025,
|
|
"num_tokens": 38776912.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.61203784942627,
|
|
"epoch": 1.9514235974616723,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046266578712037747,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20703037977218627,
|
|
"num_tokens": 38787296.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.581075811386109,
|
|
"epoch": 1.95198517436963,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046264363575582916,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.2023640215396881,
|
|
"num_tokens": 38798013.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.472200870513916,
|
|
"epoch": 1.9525467512775876,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004626214784166347,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.21581537425518035,
|
|
"num_tokens": 38808842.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.551672697067261,
|
|
"epoch": 1.953108328185545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004625993151034995,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.2125583618879318,
|
|
"num_tokens": 38819094.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.556599903106689,
|
|
"epoch": 1.9536699050935025,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004625771458171294,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.21296963095664978,
|
|
"num_tokens": 38830348.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.529864501953125,
|
|
"epoch": 1.9542314820014601,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046255497055823025,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.21492030769586562,
|
|
"num_tokens": 38841927.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.425311136245727,
|
|
"epoch": 1.9547930589094178,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004625327893275082,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.21380352228879929,
|
|
"num_tokens": 38852817.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.4474457740783695,
|
|
"epoch": 1.9553546358173752,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046251060212566927,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.20570324659347533,
|
|
"num_tokens": 38864181.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.57304835319519,
|
|
"epoch": 1.9559162127253327,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004624884089534201,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.20897260904312134,
|
|
"num_tokens": 38873827.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.540204763412476,
|
|
"epoch": 1.9564777896332903,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004624662098114672,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.21176061779260635,
|
|
"num_tokens": 38884540.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.4860655784606935,
|
|
"epoch": 1.9570393665412478,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046244400470051754,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.21487388163805007,
|
|
"num_tokens": 38895600.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.490882778167725,
|
|
"epoch": 1.9576009434492052,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000462421793621278,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.2136705845594406,
|
|
"num_tokens": 38906166.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.450088691711426,
|
|
"epoch": 1.9581625203571629,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000462399576574456,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.2173195719718933,
|
|
"num_tokens": 38916247.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.583024311065674,
|
|
"epoch": 1.9587240972651205,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004623773535607587,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.20860417932271957,
|
|
"num_tokens": 38928276.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.598361539840698,
|
|
"epoch": 1.959285674173078,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004623551245808938,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.21725967079401015,
|
|
"num_tokens": 38939460.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.557952976226806,
|
|
"epoch": 1.9598472510810354,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004623328896355691,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.21660240292549132,
|
|
"num_tokens": 38950381.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.4686182022094725,
|
|
"epoch": 1.960408827988993,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046231064872549244,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.2113172620534897,
|
|
"num_tokens": 38961312.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.511214828491211,
|
|
"epoch": 1.9609704048969507,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046228840185137215,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.21168972849845885,
|
|
"num_tokens": 38974030.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.585795879364014,
|
|
"epoch": 1.9615319818049082,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004622661490139165,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.21141708195209502,
|
|
"num_tokens": 38984640.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.476103448867798,
|
|
"epoch": 1.9620935587128656,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004622438902138341,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.2089663788676262,
|
|
"num_tokens": 38996206.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.465241861343384,
|
|
"epoch": 1.9626551356208233,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046222162545183357,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.22666339129209517,
|
|
"num_tokens": 39007765.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.532366609573364,
|
|
"epoch": 1.963216712528781,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046219935472862386,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.2109432950615883,
|
|
"num_tokens": 39020691.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.478905963897705,
|
|
"epoch": 1.9637782894367384,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046217707804491404,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.21581480503082276,
|
|
"num_tokens": 39032003.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.581487989425659,
|
|
"epoch": 1.9643398663446958,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004621547954014135,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.2137787476181984,
|
|
"num_tokens": 39042783.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.525836992263794,
|
|
"epoch": 1.9649014432526535,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004621325067988317,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.21396191269159318,
|
|
"num_tokens": 39054395.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.467428731918335,
|
|
"epoch": 1.9654630201606111,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046211021223787827,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.22057829946279525,
|
|
"num_tokens": 39064619.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.578430652618408,
|
|
"epoch": 1.9660245970685686,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046208791171926315,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.20586671233177184,
|
|
"num_tokens": 39076112.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.536594295501709,
|
|
"epoch": 1.966586173976526,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046206560524369636,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.21347022503614427,
|
|
"num_tokens": 39087669.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.468212032318116,
|
|
"epoch": 1.9671477508844837,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046204329281188816,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.21031794399023057,
|
|
"num_tokens": 39098506.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.511419296264648,
|
|
"epoch": 1.9677093277924411,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004620209744245489,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.2149295523762703,
|
|
"num_tokens": 39109441.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.508411693572998,
|
|
"epoch": 1.9682709047003986,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046199865008238937,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.21826178431510926,
|
|
"num_tokens": 39119765.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.432800006866455,
|
|
"epoch": 1.9688324816083562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004619763197861203,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.21757411509752272,
|
|
"num_tokens": 39129794.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.43766827583313,
|
|
"epoch": 1.9693940585163139,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046195398353645256,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.2201285481452942,
|
|
"num_tokens": 39140095.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.543271398544311,
|
|
"epoch": 1.9699556354242713,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004619316413340976,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.2129354476928711,
|
|
"num_tokens": 39150855.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.512868785858155,
|
|
"epoch": 1.9705172123322288,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046190929317976664,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.21503619700670243,
|
|
"num_tokens": 39161455.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.540415287017822,
|
|
"epoch": 1.9710787892401864,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004618869390741713,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.2074664607644081,
|
|
"num_tokens": 39173199.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.568149137496948,
|
|
"epoch": 1.971640366148144,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004618645790180233,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.2154535487294197,
|
|
"num_tokens": 39183145.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.57268009185791,
|
|
"epoch": 1.9722019430561015,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004618422130120347,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.20578706860542298,
|
|
"num_tokens": 39194900.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.617141342163086,
|
|
"epoch": 1.972763519964059,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004618198410569175,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.20499056875705718,
|
|
"num_tokens": 39206651.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.471738338470459,
|
|
"epoch": 1.9733250968720166,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046179746315338414,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.21581955403089523,
|
|
"num_tokens": 39217635.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.505668878555298,
|
|
"epoch": 1.9738866737799743,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046177507930214714,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.20993542224168776,
|
|
"num_tokens": 39227937.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.497661399841308,
|
|
"epoch": 1.9744482506879317,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004617526895039191,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.2153066262602806,
|
|
"num_tokens": 39238776.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.530492210388184,
|
|
"epoch": 1.9750098275958892,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046173029375941305,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.20963399410247802,
|
|
"num_tokens": 39250043.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.490529346466064,
|
|
"epoch": 1.9755714045038468,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000461707892069342,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.21589126735925673,
|
|
"num_tokens": 39261440.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.553455448150634,
|
|
"epoch": 1.9761329814118045,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046168548443441926,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.20587861984968187,
|
|
"num_tokens": 39272151.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.635009860992431,
|
|
"epoch": 1.976694558319762,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004616630708553583,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.20198908746242522,
|
|
"num_tokens": 39284794.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.521396350860596,
|
|
"epoch": 1.9772561352277194,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046164065133287276,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.20164939165115356,
|
|
"num_tokens": 39296660.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.586849975585937,
|
|
"epoch": 1.977817712135677,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004616182258676765,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20741496831178666,
|
|
"num_tokens": 39308609.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.535411643981933,
|
|
"epoch": 1.9783792890436345,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004615957944604835,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.21429578363895416,
|
|
"num_tokens": 39319295.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.561042022705078,
|
|
"epoch": 1.978940865951592,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004615733571120081,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.21016430258750915,
|
|
"num_tokens": 39330874.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.482918167114258,
|
|
"epoch": 1.9795024428595496,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004615509138229646,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.20817878544330598,
|
|
"num_tokens": 39343574.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.53778486251831,
|
|
"epoch": 1.9800640197675072,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046152846459406765,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.21468739807605744,
|
|
"num_tokens": 39355761.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.625328588485718,
|
|
"epoch": 1.9806255966754647,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004615060094260321,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.19849087297916412,
|
|
"num_tokens": 39368116.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.568085098266602,
|
|
"epoch": 1.9811871735834221,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046148354831957285,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.21681325882673264,
|
|
"num_tokens": 39378619.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.648974895477295,
|
|
"epoch": 1.9817487504913798,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046146108127540506,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.20518871396780014,
|
|
"num_tokens": 39391595.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.605383253097534,
|
|
"epoch": 1.9823103273993374,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004614386082942442,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.20777889490127563,
|
|
"num_tokens": 39402494.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.5148481845855715,
|
|
"epoch": 1.9828719043072949,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004614161293768057,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.21133727729320526,
|
|
"num_tokens": 39413371.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.490719795227051,
|
|
"epoch": 1.9834334812152523,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046139364452380536,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.2053956612944603,
|
|
"num_tokens": 39424170.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.63933310508728,
|
|
"epoch": 1.98399505812321,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000461371153735959,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.21014932692050933,
|
|
"num_tokens": 39434438.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.586469125747681,
|
|
"epoch": 1.9845566350311676,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046134865701398287,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.20836083889007567,
|
|
"num_tokens": 39445116.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.553479099273682,
|
|
"epoch": 1.985118211939125,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046132615435859326,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.21417894065380097,
|
|
"num_tokens": 39457296.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.574789381027221,
|
|
"epoch": 1.9856797888470825,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046130364577050655,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.21389496475458145,
|
|
"num_tokens": 39468499.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.551934814453125,
|
|
"epoch": 1.9862413657550402,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046128113125043957,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.21557849198579787,
|
|
"num_tokens": 39479594.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.506387615203858,
|
|
"epoch": 1.9868029426629978,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046125861079910913,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.2108874261379242,
|
|
"num_tokens": 39490048.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.507823657989502,
|
|
"epoch": 1.9873645195709553,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004612360844172322,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.20899199545383454,
|
|
"num_tokens": 39501454.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.562158298492432,
|
|
"epoch": 1.9879260964789127,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046121355210552626,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.21908157467842101,
|
|
"num_tokens": 39512782.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.5318502426147464,
|
|
"epoch": 1.9884876733868704,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004611910138647085,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.2139375701546669,
|
|
"num_tokens": 39524342.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.546502542495728,
|
|
"epoch": 1.989049250294828,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046116846969549666,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.21419524848461152,
|
|
"num_tokens": 39534744.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.566409969329834,
|
|
"epoch": 1.9896108272027853,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004611459195986085,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.20666988641023637,
|
|
"num_tokens": 39547729.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.511389541625976,
|
|
"epoch": 1.990172404110743,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046112336357476217,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.21356502920389175,
|
|
"num_tokens": 39558194.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.504845714569091,
|
|
"epoch": 1.9907339810187006,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004611008016246757,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.21564444303512573,
|
|
"num_tokens": 39568265.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.560939455032349,
|
|
"epoch": 1.991295557926658,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046107823374906754,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.2053941935300827,
|
|
"num_tokens": 39578936.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.574691200256348,
|
|
"epoch": 1.9918571348346155,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046105565994865614,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.2063526600599289,
|
|
"num_tokens": 39590180.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.53535041809082,
|
|
"epoch": 1.9924187117425731,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004610330802241605,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.2059251070022583,
|
|
"num_tokens": 39601226.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.489303255081177,
|
|
"epoch": 1.9929802886505308,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004610104945762994,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.21041792035102844,
|
|
"num_tokens": 39613119.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.562147045135498,
|
|
"epoch": 1.9935418655584882,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000460987903005792,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.21277548223733903,
|
|
"num_tokens": 39625269.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.57768759727478,
|
|
"epoch": 1.9941034424664457,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004609653055133576,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.21713250875473022,
|
|
"num_tokens": 39635883.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.4991984367370605,
|
|
"epoch": 1.9946650193744033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046094270209971576,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.21675409227609635,
|
|
"num_tokens": 39646425.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.525304317474365,
|
|
"epoch": 1.995226596282361,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004609200927655862,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.20852875262498854,
|
|
"num_tokens": 39658874.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.532296180725098,
|
|
"epoch": 1.9957881731903184,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004608974775116888,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.20884482562541962,
|
|
"num_tokens": 39670401.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.523931837081909,
|
|
"epoch": 1.9963497500982759,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004608748563387436,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.21318133622407914,
|
|
"num_tokens": 39681005.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.640678453445434,
|
|
"epoch": 1.9969113270062335,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004608522292474708,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.203190116584301,
|
|
"num_tokens": 39692311.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.522746515274048,
|
|
"epoch": 1.9974729039141912,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004608295962385911,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.22136407792568208,
|
|
"num_tokens": 39702782.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.513634586334229,
|
|
"epoch": 1.9980344808221486,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046080695731282484,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.2058110222220421,
|
|
"num_tokens": 39713497.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.492972707748413,
|
|
"epoch": 1.998596057730106,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000460784312470893,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.2045883819460869,
|
|
"num_tokens": 39724355.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.594556045532227,
|
|
"epoch": 1.9991576346380637,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046076166171351673,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.2078570008277893,
|
|
"num_tokens": 39736523.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.524101591110229,
|
|
"epoch": 1.9997192115460214,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000460739005041417,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.20865403562784196,
|
|
"num_tokens": 39746297.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.400149027506511,
|
|
"epoch": 2.000224630763183,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004607163424553153,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.2246797432502111,
|
|
"num_tokens": 39755163.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.544808769226075,
|
|
"epoch": 2.0007862076711405,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046069367395593325,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.21021504551172257,
|
|
"num_tokens": 39766444.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.5336751461029055,
|
|
"epoch": 2.001347784579098,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004606709995439926,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.21726296991109847,
|
|
"num_tokens": 39778051.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.567335700988769,
|
|
"epoch": 2.001909361487056,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046064831922021534,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.20907945036888123,
|
|
"num_tokens": 39787850.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.539879226684571,
|
|
"epoch": 2.002470938395013,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004606256329853235,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.21280573457479476,
|
|
"num_tokens": 39799428.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.643998432159424,
|
|
"epoch": 2.0030325153029707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004606029408400396,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.2088302940130234,
|
|
"num_tokens": 39811688.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.557725143432617,
|
|
"epoch": 2.0035940922109283,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004605802427850861,
|
|
"loss": 4.9771,
|
|
"mean_token_accuracy": 0.21628450006246566,
|
|
"num_tokens": 39822243.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.539982843399048,
|
|
"epoch": 2.004155669118886,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046055753882118564,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.22084437310695648,
|
|
"num_tokens": 39833699.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.642644357681275,
|
|
"epoch": 2.004717246026843,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004605348289490611,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.2039476901292801,
|
|
"num_tokens": 39844177.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.573115873336792,
|
|
"epoch": 2.005278822934801,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004605121131694358,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.21485641449689866,
|
|
"num_tokens": 39856008.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.522624588012695,
|
|
"epoch": 2.0058403998427585,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004604893914830328,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.21174250692129135,
|
|
"num_tokens": 39866209.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.573738288879395,
|
|
"epoch": 2.006401976750716,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046046666389057563,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.2123565286397934,
|
|
"num_tokens": 39876986.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.493557691574097,
|
|
"epoch": 2.0069635536586734,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000460443930392788,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.2160379856824875,
|
|
"num_tokens": 39886994.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.535713386535645,
|
|
"epoch": 2.007525130566631,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046042119099039367,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.21428238451480866,
|
|
"num_tokens": 39897514.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.691252183914185,
|
|
"epoch": 2.0080867074745887,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046039844568411667,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.20700039118528366,
|
|
"num_tokens": 39909102.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.543731689453125,
|
|
"epoch": 2.0086482843825464,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004603756944746813,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.21812902688980101,
|
|
"num_tokens": 39919450.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.4558703899383545,
|
|
"epoch": 2.0092098612905036,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046035293736281185,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.21015089452266694,
|
|
"num_tokens": 39930362.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.479996681213379,
|
|
"epoch": 2.0097714381984613,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004603301743492331,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.21296755522489547,
|
|
"num_tokens": 39942047.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.5753922939300535,
|
|
"epoch": 2.010333015106419,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004603074054346696,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.21316401958465575,
|
|
"num_tokens": 39954870.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.549271440505981,
|
|
"epoch": 2.0108945920143766,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004602846306198465,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.21981048285961152,
|
|
"num_tokens": 39966345.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.457373476028442,
|
|
"epoch": 2.011456168922334,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004602618499054889,
|
|
"loss": 4.9334,
|
|
"mean_token_accuracy": 0.22474265843629837,
|
|
"num_tokens": 39976453.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.514410209655762,
|
|
"epoch": 2.0120177458302915,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004602390632923221,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.2167578309774399,
|
|
"num_tokens": 39988990.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.4707094669342045,
|
|
"epoch": 2.012579322738249,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046021627078107177,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.21356691867113115,
|
|
"num_tokens": 39999131.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.579091596603393,
|
|
"epoch": 2.0131408996462063,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046019347237246343,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.2145446628332138,
|
|
"num_tokens": 40010197.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.502016067504883,
|
|
"epoch": 2.013702476554164,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004601706680672232,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.2263324022293091,
|
|
"num_tokens": 40021388.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.542990827560425,
|
|
"epoch": 2.0142640534621217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004601478578660771,
|
|
"loss": 5.025,
|
|
"mean_token_accuracy": 0.2211916610598564,
|
|
"num_tokens": 40032485.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.538036060333252,
|
|
"epoch": 2.0148256303700793,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004601250417697513,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.20418212711811065,
|
|
"num_tokens": 40043465.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.5100280284881595,
|
|
"epoch": 2.0153872072780366,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004601022197789724,
|
|
"loss": 5.0036,
|
|
"mean_token_accuracy": 0.22179241180419923,
|
|
"num_tokens": 40054934.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.531148195266724,
|
|
"epoch": 2.015948784185994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004600793918944671,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.21299399435520172,
|
|
"num_tokens": 40066159.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.437638425827027,
|
|
"epoch": 2.016510361093952,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004600565581169621,
|
|
"loss": 4.949,
|
|
"mean_token_accuracy": 0.2247659981250763,
|
|
"num_tokens": 40076169.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.5515776634216305,
|
|
"epoch": 2.0170719380019095,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046003371844718455,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.21908964365720748,
|
|
"num_tokens": 40086852.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.4918300151824955,
|
|
"epoch": 2.0176335149098668,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046001087288586164,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.21181115210056306,
|
|
"num_tokens": 40097588.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.544072866439819,
|
|
"epoch": 2.0181950918178244,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004599880214337208,
|
|
"loss": 4.9301,
|
|
"mean_token_accuracy": 0.22367971241474152,
|
|
"num_tokens": 40108797.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.523689603805542,
|
|
"epoch": 2.018756668725782,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004599651640914896,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.20883471369743348,
|
|
"num_tokens": 40119700.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.504896354675293,
|
|
"epoch": 2.0193182456337397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004599423008598957,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.20920757651329042,
|
|
"num_tokens": 40131611.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.504035139083863,
|
|
"epoch": 2.019879822541697,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045991943173966744,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.22403908222913743,
|
|
"num_tokens": 40142186.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.521868753433227,
|
|
"epoch": 2.0204413994496546,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004598965567315326,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.21480491012334824,
|
|
"num_tokens": 40153856.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.487589502334595,
|
|
"epoch": 2.0210029763576123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004598736758362198,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.22226784378290176,
|
|
"num_tokens": 40164158.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.5302434921264645,
|
|
"epoch": 2.02156455326557,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045985078905445734,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.21440796852111815,
|
|
"num_tokens": 40176751.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.02156455326557,
|
|
"eval_entropy": 5.269512628629585,
|
|
"eval_loss": 5.155724048614502,
|
|
"eval_mean_token_accuracy": 0.2163117056290206,
|
|
"eval_num_tokens": 40176751.0,
|
|
"eval_runtime": 18.5401,
|
|
"eval_samples_per_second": 1672.748,
|
|
"eval_steps_per_second": 209.114,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.549198293685913,
|
|
"epoch": 2.022126130173527,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045982789638697414,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.21308056116104127,
|
|
"num_tokens": 40188000.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.574025869369507,
|
|
"epoch": 2.022687707081485,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045980499783449897,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.21425278931856157,
|
|
"num_tokens": 40199177.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.522935104370117,
|
|
"epoch": 2.0232492839894425,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045978209339776104,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.21253984570503234,
|
|
"num_tokens": 40210082.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.547569942474365,
|
|
"epoch": 2.0238108608973997,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045975918307748965,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.20945159196853638,
|
|
"num_tokens": 40222503.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.544736242294311,
|
|
"epoch": 2.0243724378053574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004597362668744141,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.2214244544506073,
|
|
"num_tokens": 40233690.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.591527318954467,
|
|
"epoch": 2.024934014713315,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004597133447892642,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.2125295653939247,
|
|
"num_tokens": 40246274.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.568734264373779,
|
|
"epoch": 2.0254955916212727,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004596904168227698,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.21355525702238082,
|
|
"num_tokens": 40257469.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.492108726501465,
|
|
"epoch": 2.02605716852923,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045966748297566085,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.21670556515455247,
|
|
"num_tokens": 40268982.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.602134370803833,
|
|
"epoch": 2.0266187454371876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045964454324866767,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.2161030352115631,
|
|
"num_tokens": 40280301.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.536135625839234,
|
|
"epoch": 2.0271803223451452,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045962159764252055,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.2231851577758789,
|
|
"num_tokens": 40292058.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.495514297485352,
|
|
"epoch": 2.027741899253103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004595986461579502,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.2163448378443718,
|
|
"num_tokens": 40301957.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.5304834842681885,
|
|
"epoch": 2.02830347616106,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045957568879568736,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.2157497823238373,
|
|
"num_tokens": 40313645.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.553220129013061,
|
|
"epoch": 2.0288650530690178,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045955272555646306,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.21030271500349046,
|
|
"num_tokens": 40324416.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.630068016052246,
|
|
"epoch": 2.0294266299769754,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004595297564410083,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.20850412100553511,
|
|
"num_tokens": 40335596.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.603425788879394,
|
|
"epoch": 2.029988206884933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045950678145005456,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.21317447125911712,
|
|
"num_tokens": 40346426.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.49308671951294,
|
|
"epoch": 2.0305497837928903,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004594838005843333,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.22117944657802582,
|
|
"num_tokens": 40357435.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.493851184844971,
|
|
"epoch": 2.031111360700848,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045946081384457633,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.21941529214382172,
|
|
"num_tokens": 40367332.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.488730335235596,
|
|
"epoch": 2.0316729376088056,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045943782123151556,
|
|
"loss": 4.977,
|
|
"mean_token_accuracy": 0.21202434599399567,
|
|
"num_tokens": 40378571.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.48906512260437,
|
|
"epoch": 2.0322345145167633,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004594148227458829,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.2180194988846779,
|
|
"num_tokens": 40389467.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.517788314819336,
|
|
"epoch": 2.0327960914247205,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004593918183884108,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.21901678740978242,
|
|
"num_tokens": 40399785.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.479944038391113,
|
|
"epoch": 2.033357668332678,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004593688081598318,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.21436334103345872,
|
|
"num_tokens": 40409862.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.529167556762696,
|
|
"epoch": 2.033919245240636,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045934579206087837,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.2075735703110695,
|
|
"num_tokens": 40421627.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.580882883071899,
|
|
"epoch": 2.034480822148593,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045932277009228336,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.20690350979566574,
|
|
"num_tokens": 40433327.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.4671272277832035,
|
|
"epoch": 2.0350423990565507,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045929974225477986,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.2191910058259964,
|
|
"num_tokens": 40444217.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.51528844833374,
|
|
"epoch": 2.0356039759645084,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045927670854910117,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.2142879009246826,
|
|
"num_tokens": 40454760.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.581777477264405,
|
|
"epoch": 2.036165552872466,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004592536689759806,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.21007806360721587,
|
|
"num_tokens": 40464638.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.5642409324646,
|
|
"epoch": 2.0367271297804233,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045923062353615167,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.21262783259153367,
|
|
"num_tokens": 40474911.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.513956546783447,
|
|
"epoch": 2.037288706688381,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045920757223034833,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.2066647633910179,
|
|
"num_tokens": 40485369.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.577337598800659,
|
|
"epoch": 2.0378502835963386,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004591845150593044,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.21490490734577178,
|
|
"num_tokens": 40495955.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.585052490234375,
|
|
"epoch": 2.0384118605042962,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045916145202375407,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.21477008163928984,
|
|
"num_tokens": 40506633.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.580796098709106,
|
|
"epoch": 2.0389734374122535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004591383831244317,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.20815157145261765,
|
|
"num_tokens": 40516868.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.482523679733276,
|
|
"epoch": 2.039535014320211,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045911530836207173,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.22435269355773926,
|
|
"num_tokens": 40528873.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.571136808395385,
|
|
"epoch": 2.0400965912281688,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045909222773740904,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.20917679667472838,
|
|
"num_tokens": 40539124.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.5263182640075685,
|
|
"epoch": 2.0406581681361264,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045906914125117833,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.21597191989421843,
|
|
"num_tokens": 40550264.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.397745513916016,
|
|
"epoch": 2.0412197450440837,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00045904604890411476,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.23051743507385253,
|
|
"num_tokens": 40562319.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.499158573150635,
|
|
"epoch": 2.0417813219520413,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045902295069695373,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.21669725924730301,
|
|
"num_tokens": 40573962.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.553386449813843,
|
|
"epoch": 2.042342898859999,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004589998466304305,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.20986466854810715,
|
|
"num_tokens": 40584620.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.534596538543701,
|
|
"epoch": 2.0429044757679566,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045897673670528086,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.21855893731117249,
|
|
"num_tokens": 40596670.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.523368549346924,
|
|
"epoch": 2.043466052675914,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004589536209222404,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.21968463361263274,
|
|
"num_tokens": 40607742.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.490007972717285,
|
|
"epoch": 2.0440276295838715,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004589304992820454,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.22218126207590103,
|
|
"num_tokens": 40618873.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.480503845214844,
|
|
"epoch": 2.044589206491829,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000458907371785432,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.21438578516244888,
|
|
"num_tokens": 40630327.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.459205102920532,
|
|
"epoch": 2.0451507833997864,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004588842384331366,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.21939602196216584,
|
|
"num_tokens": 40641515.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.554535579681397,
|
|
"epoch": 2.045712360307744,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045886109922589564,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.2165316164493561,
|
|
"num_tokens": 40652123.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.570946931838989,
|
|
"epoch": 2.0462739372157017,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045883795416444594,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.21497640609741211,
|
|
"num_tokens": 40662895.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.474454259872436,
|
|
"epoch": 2.0468355141236594,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045881480324952455,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.22605957537889482,
|
|
"num_tokens": 40673243.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.504793500900268,
|
|
"epoch": 2.0473970910316166,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045879164648186853,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.22019459158182145,
|
|
"num_tokens": 40683861.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.54004602432251,
|
|
"epoch": 2.0479586679395743,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00045876848386221513,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.2146880954504013,
|
|
"num_tokens": 40694995.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.531828737258911,
|
|
"epoch": 2.048520244847532,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045874531539130204,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.22110143601894378,
|
|
"num_tokens": 40705203.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.5120530128479,
|
|
"epoch": 2.0490818217554896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045872214106986684,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.21435001492500305,
|
|
"num_tokens": 40716439.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.462933731079102,
|
|
"epoch": 2.049643398663447,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045869896089864733,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.21915362030267715,
|
|
"num_tokens": 40727436.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.495873832702637,
|
|
"epoch": 2.0502049755714045,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004586757748783817,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.2216123789548874,
|
|
"num_tokens": 40738423.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.664797306060791,
|
|
"epoch": 2.050766552479362,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045865258300980817,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.21310991048812866,
|
|
"num_tokens": 40749506.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.534401750564575,
|
|
"epoch": 2.05132812938732,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045862938529366514,
|
|
"loss": 4.991,
|
|
"mean_token_accuracy": 0.22689682394266128,
|
|
"num_tokens": 40762165.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.5597230911254885,
|
|
"epoch": 2.051889706295277,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004586061817306913,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.21092639565467836,
|
|
"num_tokens": 40774043.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.469715261459351,
|
|
"epoch": 2.0524512832032347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045858297232162536,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.21920158863067626,
|
|
"num_tokens": 40784758.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.565918445587158,
|
|
"epoch": 2.0530128601111923,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045855975706720644,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.22422015219926833,
|
|
"num_tokens": 40794735.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.469548606872559,
|
|
"epoch": 2.05357443701915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004585365359681736,
|
|
"loss": 4.8739,
|
|
"mean_token_accuracy": 0.2241354152560234,
|
|
"num_tokens": 40805491.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.540817403793335,
|
|
"epoch": 2.054136013927107,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045851330902526633,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.21352482587099075,
|
|
"num_tokens": 40816945.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.593065071105957,
|
|
"epoch": 2.054697590835065,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045849007623922406,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.21693609058856964,
|
|
"num_tokens": 40828199.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.565926647186279,
|
|
"epoch": 2.0552591677430225,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004584668376107867,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.21096058040857316,
|
|
"num_tokens": 40839618.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.476931381225586,
|
|
"epoch": 2.0558207446509797,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000458443593140694,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.21896931827068328,
|
|
"num_tokens": 40851078.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.523434638977051,
|
|
"epoch": 2.0563823215589374,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045842034282968615,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.21856656968593596,
|
|
"num_tokens": 40862397.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.487672901153564,
|
|
"epoch": 2.056943898466895,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004583970866785035,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.2125122904777527,
|
|
"num_tokens": 40872739.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.574951314926148,
|
|
"epoch": 2.0575054753748527,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045837382468788643,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.2147699162364006,
|
|
"num_tokens": 40884723.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.552813291549683,
|
|
"epoch": 2.05806705228281,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004583505568585757,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.21697946041822433,
|
|
"num_tokens": 40895927.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.493740367889404,
|
|
"epoch": 2.0586286291907676,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045832728319131205,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.21043577939271926,
|
|
"num_tokens": 40906504.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.508602285385132,
|
|
"epoch": 2.0591902060987253,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004583040036868367,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.22333117872476577,
|
|
"num_tokens": 40918420.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.532529592514038,
|
|
"epoch": 2.059751783006683,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004582807183458907,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.21341959834098817,
|
|
"num_tokens": 40929665.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.560612773895263,
|
|
"epoch": 2.06031335991464,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045825742716921553,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.20817126780748368,
|
|
"num_tokens": 40941134.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.5766698837280275,
|
|
"epoch": 2.060874936822598,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004582341301575529,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.21771006733179094,
|
|
"num_tokens": 40953230.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.473542642593384,
|
|
"epoch": 2.0614365137305555,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045821082731164445,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.2198336750268936,
|
|
"num_tokens": 40964398.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.539514636993408,
|
|
"epoch": 2.061998090638513,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004581875186322322,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.21719024777412416,
|
|
"num_tokens": 40975561.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.519362545013427,
|
|
"epoch": 2.0625596675464704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045816420412005826,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.22280608415603637,
|
|
"num_tokens": 40986393.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.527361059188843,
|
|
"epoch": 2.063121244454428,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045814088377586505,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.22000495493412017,
|
|
"num_tokens": 40998143.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.538071250915527,
|
|
"epoch": 2.0636828213623857,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045811755760039513,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.21375838667154312,
|
|
"num_tokens": 41009747.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.519709491729737,
|
|
"epoch": 2.0642443982703433,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045809422559439113,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.2222708359360695,
|
|
"num_tokens": 41023146.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.567487478256226,
|
|
"epoch": 2.0648059751783006,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045807088775859595,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20882596373558043,
|
|
"num_tokens": 41034138.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.507336568832398,
|
|
"epoch": 2.065367552086258,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004580475440937527,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.21948317289352418,
|
|
"num_tokens": 41045457.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.52087435722351,
|
|
"epoch": 2.065929128994216,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045802419460060464,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.22218984812498094,
|
|
"num_tokens": 41056264.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.571684122085571,
|
|
"epoch": 2.066490705902173,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004580008392798953,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.20863872915506362,
|
|
"num_tokens": 41067206.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.424915170669555,
|
|
"epoch": 2.0670522828101308,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045797747813236815,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.2168671414256096,
|
|
"num_tokens": 41077897.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.550539636611939,
|
|
"epoch": 2.0676138597180884,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045795411115876725,
|
|
"loss": 4.9597,
|
|
"mean_token_accuracy": 0.222679702937603,
|
|
"num_tokens": 41088964.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.517605257034302,
|
|
"epoch": 2.068175436626046,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045793073835983644,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.22103417664766312,
|
|
"num_tokens": 41098818.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.558111906051636,
|
|
"epoch": 2.0687370135340033,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045790735973631996,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.21062125414609909,
|
|
"num_tokens": 41111222.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.542374038696289,
|
|
"epoch": 2.069298590441961,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045788397528896224,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.21517515033483506,
|
|
"num_tokens": 41122875.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.5616912841796875,
|
|
"epoch": 2.0698601673499186,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045786058501850774,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.20752818137407303,
|
|
"num_tokens": 41133869.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.547346067428589,
|
|
"epoch": 2.0704217442578763,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045783718892570136,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.21632641106843947,
|
|
"num_tokens": 41144482.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.470992708206177,
|
|
"epoch": 2.0709833211658335,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000457813787011288,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.213502736389637,
|
|
"num_tokens": 41154997.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.47327995300293,
|
|
"epoch": 2.071544898073791,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004577903792760127,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.21373361051082612,
|
|
"num_tokens": 41167852.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.533638668060303,
|
|
"epoch": 2.072106474981749,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004577669657206209,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.22193729728460312,
|
|
"num_tokens": 41178364.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.531085109710693,
|
|
"epoch": 2.0726680518897065,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004577435463458579,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.20689199566841127,
|
|
"num_tokens": 41190003.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.5010009765625,
|
|
"epoch": 2.0732296287976637,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004577201211524696,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.2177928254008293,
|
|
"num_tokens": 41201574.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.459332513809204,
|
|
"epoch": 2.0737912057056214,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004576966901412018,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.22743515968322753,
|
|
"num_tokens": 41211913.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.479449462890625,
|
|
"epoch": 2.074352782613579,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045767325331280044,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.21661066263914108,
|
|
"num_tokens": 41222626.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.531780099868774,
|
|
"epoch": 2.0749143595215367,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004576498106680119,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.2065993994474411,
|
|
"num_tokens": 41234321.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.537492752075195,
|
|
"epoch": 2.075475936429494,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004576263622075826,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.22540858387947083,
|
|
"num_tokens": 41244889.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.574927234649659,
|
|
"epoch": 2.0760375133374516,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000457602907932259,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.2121771454811096,
|
|
"num_tokens": 41255710.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.5522619724273685,
|
|
"epoch": 2.0765990902454092,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045757944784278803,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.2174464300274849,
|
|
"num_tokens": 41265786.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.499475145339966,
|
|
"epoch": 2.0771606671533664,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004575559819399166,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.20700334012508392,
|
|
"num_tokens": 41276755.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.551458692550659,
|
|
"epoch": 2.077722244061324,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045753251022439195,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.21863020807504654,
|
|
"num_tokens": 41287219.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.541563510894775,
|
|
"epoch": 2.0782838209692818,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004575090326969614,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.21486709117889405,
|
|
"num_tokens": 41297356.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.43753490447998,
|
|
"epoch": 2.0788453978772394,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004574855493583723,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.22694522142410278,
|
|
"num_tokens": 41307219.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.507160997390747,
|
|
"epoch": 2.0794069747851966,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045746206020937276,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.21076433211565018,
|
|
"num_tokens": 41318827.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.5366068363189695,
|
|
"epoch": 2.0799685516931543,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045743856525071034,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.21590386778116227,
|
|
"num_tokens": 41329497.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.5172998905181885,
|
|
"epoch": 2.080530128601112,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045741506448313327,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.2192310005426407,
|
|
"num_tokens": 41340577.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.534938955307007,
|
|
"epoch": 2.0810917055090696,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045739155790738975,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.20807409882545472,
|
|
"num_tokens": 41351685.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.659194040298462,
|
|
"epoch": 2.081653282417027,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045736804552422836,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.20492146015167237,
|
|
"num_tokens": 41363053.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.6148539066314695,
|
|
"epoch": 2.0822148593249845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004573445273343976,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.21256203055381775,
|
|
"num_tokens": 41374847.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.50603461265564,
|
|
"epoch": 2.082776436232942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004573210033386464,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.2090951308608055,
|
|
"num_tokens": 41386114.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.477655696868896,
|
|
"epoch": 2.0833380131409,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004572974735377238,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.22227341085672378,
|
|
"num_tokens": 41397842.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.5065587043762205,
|
|
"epoch": 2.083899590048857,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004572739379323788,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.2141299694776535,
|
|
"num_tokens": 41409824.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.474079608917236,
|
|
"epoch": 2.0844611669568147,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045725039652336105,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.21283385306596755,
|
|
"num_tokens": 41422260.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.546798515319824,
|
|
"epoch": 2.0850227438647724,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004572268493114199,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.2189578279852867,
|
|
"num_tokens": 41433068.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.488735580444336,
|
|
"epoch": 2.08558432077273,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004572032962973052,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.2214657336473465,
|
|
"num_tokens": 41443759.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.564065742492676,
|
|
"epoch": 2.0861458976806873,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045717973748176695,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.21580453366041183,
|
|
"num_tokens": 41453876.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.508271360397339,
|
|
"epoch": 2.086707474588645,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045715617286555516,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.2163911372423172,
|
|
"num_tokens": 41464731.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.566312837600708,
|
|
"epoch": 2.0872690514966026,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045713260244942017,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.2106520876288414,
|
|
"num_tokens": 41476288.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.588855981826782,
|
|
"epoch": 2.08783062840456,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004571090262341125,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.219941708445549,
|
|
"num_tokens": 41485968.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.5432130813598635,
|
|
"epoch": 2.0883922053125175,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045708544422038284,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.2195397987961769,
|
|
"num_tokens": 41496393.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.505523729324341,
|
|
"epoch": 2.088953782220475,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004570618564089819,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.21787617355585098,
|
|
"num_tokens": 41507539.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.583041477203369,
|
|
"epoch": 2.089515359128433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045703826280066095,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20442859083414078,
|
|
"num_tokens": 41517845.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.5032820224761965,
|
|
"epoch": 2.09007693603639,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004570146633961711,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.2191273331642151,
|
|
"num_tokens": 41528204.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.548489141464233,
|
|
"epoch": 2.0906385129443477,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045699105819626374,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.2125561699271202,
|
|
"num_tokens": 41538425.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.545513534545899,
|
|
"epoch": 2.0912000898523053,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004569674472016904,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.21241150796413422,
|
|
"num_tokens": 41548762.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.470192575454712,
|
|
"epoch": 2.091761666760263,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004569438304132031,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.22166640013456346,
|
|
"num_tokens": 41559003.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.493101644515991,
|
|
"epoch": 2.09232324366822,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045692020783155376,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.22018514573574066,
|
|
"num_tokens": 41569630.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.589190244674683,
|
|
"epoch": 2.092884820576178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004568965794574943,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21811107993125917,
|
|
"num_tokens": 41580671.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.597703123092652,
|
|
"epoch": 2.0934463974841355,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004568729452917772,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.2144458457827568,
|
|
"num_tokens": 41592475.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.528413915634156,
|
|
"epoch": 2.094007974392093,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045684930533515506,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.2116728663444519,
|
|
"num_tokens": 41603675.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.489026069641113,
|
|
"epoch": 2.0945695513000504,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045682565958838045,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.21594933718442916,
|
|
"num_tokens": 41614684.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.497425937652588,
|
|
"epoch": 2.095131128208008,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004568020080522063,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.2121972158551216,
|
|
"num_tokens": 41625368.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.529268646240235,
|
|
"epoch": 2.0956927051159657,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004567783507273858,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.2122389256954193,
|
|
"num_tokens": 41636542.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.629591989517212,
|
|
"epoch": 2.0962542820239234,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045675468761467204,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.21272533684968947,
|
|
"num_tokens": 41646654.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.653371000289917,
|
|
"epoch": 2.0968158589318806,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045673101871481853,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.20621210783720018,
|
|
"num_tokens": 41659160.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.53422360420227,
|
|
"epoch": 2.0973774358398383,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004567073440285789,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.2189180627465248,
|
|
"num_tokens": 41670864.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.503535461425781,
|
|
"epoch": 2.097939012747796,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045668366355670697,
|
|
"loss": 4.9322,
|
|
"mean_token_accuracy": 0.22036776393651963,
|
|
"num_tokens": 41681947.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.544990539550781,
|
|
"epoch": 2.098500589655753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004566599772999567,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.20848125070333481,
|
|
"num_tokens": 41692625.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.612517786026001,
|
|
"epoch": 2.099062166563711,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045663628525908237,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20956804007291793,
|
|
"num_tokens": 41703118.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.543115043640137,
|
|
"epoch": 2.0996237434716685,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004566125874348382,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.215149362385273,
|
|
"num_tokens": 41713910.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.5220794677734375,
|
|
"epoch": 2.100185320379626,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045658888382797886,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.2193838968873024,
|
|
"num_tokens": 41725290.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.598251533508301,
|
|
"epoch": 2.1007468972875833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045656517443925897,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.21997752636671067,
|
|
"num_tokens": 41736265.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.596303272247314,
|
|
"epoch": 2.101308474195541,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004565414592694336,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.21144890934228897,
|
|
"num_tokens": 41746702.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.649960279464722,
|
|
"epoch": 2.1018700511034987,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004565177383192577,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.21310562789440154,
|
|
"num_tokens": 41758570.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.618712854385376,
|
|
"epoch": 2.1024316280114563,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045649401158948664,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.22016775608062744,
|
|
"num_tokens": 41769507.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.5382997512817385,
|
|
"epoch": 2.1029932049194136,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004564702790808758,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.22360603362321854,
|
|
"num_tokens": 41780558.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.471005487442016,
|
|
"epoch": 2.103554781827371,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004564465407941809,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.2195887491106987,
|
|
"num_tokens": 41790518.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.565407133102417,
|
|
"epoch": 2.104116358735329,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045642279673015787,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.21414467096328735,
|
|
"num_tokens": 41800329.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.508545732498169,
|
|
"epoch": 2.1046779356432865,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004563990468895625,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.22545723468065262,
|
|
"num_tokens": 41811231.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.4285486221313475,
|
|
"epoch": 2.1052395125512438,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004563752912731512,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.21966057568788527,
|
|
"num_tokens": 41821544.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.4880739688873295,
|
|
"epoch": 2.1058010894592014,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004563515298816803,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21148284375667573,
|
|
"num_tokens": 41832371.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.531317281723022,
|
|
"epoch": 2.106362666367159,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045632776271590624,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.21408658027648925,
|
|
"num_tokens": 41842828.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.436685180664062,
|
|
"epoch": 2.1069242432751167,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004563039897765859,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.22080860584974288,
|
|
"num_tokens": 41855128.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.538449239730835,
|
|
"epoch": 2.107485820183074,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004562802110644764,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.2160661995410919,
|
|
"num_tokens": 41866258.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.527034616470337,
|
|
"epoch": 2.1080473970910316,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045625642658033447,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.21431404650211333,
|
|
"num_tokens": 41877713.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.5503411293029785,
|
|
"epoch": 2.1086089739989893,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045623263632491766,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.22339871972799302,
|
|
"num_tokens": 41888592.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.523071956634522,
|
|
"epoch": 2.1091705509069465,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045620884029898344,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.2084177777171135,
|
|
"num_tokens": 41901024.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.541215467453003,
|
|
"epoch": 2.109732127814904,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045618503850328954,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.21602447777986528,
|
|
"num_tokens": 41911184.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.555560779571533,
|
|
"epoch": 2.110293704722862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004561612309385936,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.20961519777774812,
|
|
"num_tokens": 41922799.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.56822714805603,
|
|
"epoch": 2.1108552816308195,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045613741760565385,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.22040800452232362,
|
|
"num_tokens": 41933223.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.502315092086792,
|
|
"epoch": 2.1114168585387767,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004561135985052285,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.21301469057798386,
|
|
"num_tokens": 41944288.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.486654901504517,
|
|
"epoch": 2.1119784354467344,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000456089773638076,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.2170302003622055,
|
|
"num_tokens": 41954312.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.539671850204468,
|
|
"epoch": 2.112540012354692,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004560659430049548,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.21468989551067352,
|
|
"num_tokens": 41966871.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.494918775558472,
|
|
"epoch": 2.1131015892626497,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004560421066066237,
|
|
"loss": 4.9771,
|
|
"mean_token_accuracy": 0.22104116827249526,
|
|
"num_tokens": 41979087.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.5665263652801515,
|
|
"epoch": 2.113663166170607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045601826444384175,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.21273400485515595,
|
|
"num_tokens": 41989867.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.474567508697509,
|
|
"epoch": 2.1142247430785646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045599441651736805,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.21981464177370072,
|
|
"num_tokens": 42001205.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.613169622421265,
|
|
"epoch": 2.1147863199865222,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045597056282796196,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.20847452878952027,
|
|
"num_tokens": 42012466.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.358591222763062,
|
|
"epoch": 2.11534789689448,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004559467033763829,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.22475890517234803,
|
|
"num_tokens": 42022517.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.504048204421997,
|
|
"epoch": 2.115909473802437,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004559228381633907,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.22479359358549117,
|
|
"num_tokens": 42032253.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.557393646240234,
|
|
"epoch": 2.1164710507103948,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045589896718974517,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.21828524619340897,
|
|
"num_tokens": 42042943.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.50439190864563,
|
|
"epoch": 2.1170326276183524,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004558750904562063,
|
|
"loss": 4.9466,
|
|
"mean_token_accuracy": 0.2219982698559761,
|
|
"num_tokens": 42054302.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.502996778488159,
|
|
"epoch": 2.11759420452631,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004558512079635345,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.20553006380796432,
|
|
"num_tokens": 42064810.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.49647970199585,
|
|
"epoch": 2.1181557814342673,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004558273197124899,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.2118490755558014,
|
|
"num_tokens": 42076468.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.472165966033936,
|
|
"epoch": 2.118717358342225,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045580342570383347,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.21086026579141617,
|
|
"num_tokens": 42087488.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.540000581741333,
|
|
"epoch": 2.1192789352501826,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004557795259383258,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.20888414978981018,
|
|
"num_tokens": 42099992.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.56486964225769,
|
|
"epoch": 2.11984051215814,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045575562041672794,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.21594969928264618,
|
|
"num_tokens": 42111073.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.516195917129517,
|
|
"epoch": 2.1204020890660975,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045573170913980094,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.2096027508378029,
|
|
"num_tokens": 42121413.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.589652824401855,
|
|
"epoch": 2.120963665974055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045570779210830627,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.21759434044361115,
|
|
"num_tokens": 42132239.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.54151406288147,
|
|
"epoch": 2.121525242882013,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004556838693230054,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.2150577872991562,
|
|
"num_tokens": 42143124.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.579726505279541,
|
|
"epoch": 2.12208681978997,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045565994078466005,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.2146812692284584,
|
|
"num_tokens": 42152653.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.554957389831543,
|
|
"epoch": 2.1226483966979277,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045563600649403213,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.21511798948049546,
|
|
"num_tokens": 42162734.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.587404203414917,
|
|
"epoch": 2.1232099736058854,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004556120664518838,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.20573456287384034,
|
|
"num_tokens": 42175312.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.5642307758331295,
|
|
"epoch": 2.123771550513843,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004555881206589771,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.21760369688272477,
|
|
"num_tokens": 42186512.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.524470853805542,
|
|
"epoch": 2.1243331274218002,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004555641691160746,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.2138931855559349,
|
|
"num_tokens": 42197698.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.467374563217163,
|
|
"epoch": 2.124894704329758,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000455540211823939,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.21584801524877548,
|
|
"num_tokens": 42208761.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.540195894241333,
|
|
"epoch": 2.1254562812377156,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045551624878333296,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.21215835809707642,
|
|
"num_tokens": 42218920.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.584498453140259,
|
|
"epoch": 2.1260178581456732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045549227999501957,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.21782009452581405,
|
|
"num_tokens": 42229819.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.493132734298706,
|
|
"epoch": 2.1265794350536305,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045546830545976203,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.21027763187885284,
|
|
"num_tokens": 42241189.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.458577299118042,
|
|
"epoch": 2.127141011961588,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045544432517832356,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.21862312257289887,
|
|
"num_tokens": 42252665.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.484634828567505,
|
|
"epoch": 2.1277025888695458,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045542033915146787,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.21516856253147126,
|
|
"num_tokens": 42264514.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.562056827545166,
|
|
"epoch": 2.1282641657775034,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045539634737995857,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.21302230060100555,
|
|
"num_tokens": 42275229.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.536616659164428,
|
|
"epoch": 2.1288257426854607,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045537234986455964,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.22011323720216752,
|
|
"num_tokens": 42286819.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.545035123825073,
|
|
"epoch": 2.1293873195934183,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004553483466060351,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.2187291592359543,
|
|
"num_tokens": 42298329.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.448916006088257,
|
|
"epoch": 2.129948896501376,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045532433760514925,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.21440186351537704,
|
|
"num_tokens": 42308813.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.52543363571167,
|
|
"epoch": 2.130510473409333,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004553003228626665,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.2147231787443161,
|
|
"num_tokens": 42321264.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.466197824478149,
|
|
"epoch": 2.131072050317291,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004552763023793517,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.22051683962345123,
|
|
"num_tokens": 42332301.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.500431060791016,
|
|
"epoch": 2.1316336272252485,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004552522761559694,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.21532465219497682,
|
|
"num_tokens": 42343424.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.51498556137085,
|
|
"epoch": 2.132195204133206,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045522824419328475,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.2126910239458084,
|
|
"num_tokens": 42354350.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.487677097320557,
|
|
"epoch": 2.1327567810411634,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045520420649206283,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.21782296746969224,
|
|
"num_tokens": 42365110.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.505533361434937,
|
|
"epoch": 2.133318357949121,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004551801630530692,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.21415982991456986,
|
|
"num_tokens": 42376345.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.513575029373169,
|
|
"epoch": 2.1338799348570787,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004551561138770693,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.21424249261617662,
|
|
"num_tokens": 42387161.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.545553922653198,
|
|
"epoch": 2.1344415117650364,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045513205896482875,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.22075556069612504,
|
|
"num_tokens": 42397468.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.515636301040649,
|
|
"epoch": 2.1350030886729936,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045510799831711366,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.21767112016677856,
|
|
"num_tokens": 42408547.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.44897141456604,
|
|
"epoch": 2.1355646655809513,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045508393193469,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.21812683790922166,
|
|
"num_tokens": 42420383.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.515880727767945,
|
|
"epoch": 2.136126242488909,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004550598598183241,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.21474861353635788,
|
|
"num_tokens": 42431723.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.598240900039673,
|
|
"epoch": 2.1366878193968666,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004550357819687825,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.22021651715040208,
|
|
"num_tokens": 42443740.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.455708599090576,
|
|
"epoch": 2.137249396304824,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004550116983868317,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.22340772151947022,
|
|
"num_tokens": 42454288.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.499245119094849,
|
|
"epoch": 2.1378109732127815,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004549876090732386,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.2172301083803177,
|
|
"num_tokens": 42467576.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.566356468200683,
|
|
"epoch": 2.138372550120739,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004549635140287703,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.2158939376473427,
|
|
"num_tokens": 42477839.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.448543357849121,
|
|
"epoch": 2.138934127028697,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045493941325419385,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.21673736870288848,
|
|
"num_tokens": 42489875.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.57632999420166,
|
|
"epoch": 2.139495703936654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004549153067502768,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20932964086532593,
|
|
"num_tokens": 42500946.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.52412896156311,
|
|
"epoch": 2.1400572808446117,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045489119451778645,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.2192263722419739,
|
|
"num_tokens": 42511503.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.6086663722991945,
|
|
"epoch": 2.1406188577525693,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004548670765574908,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.20217859148979186,
|
|
"num_tokens": 42523436.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.546270513534546,
|
|
"epoch": 2.1411804346605265,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045484295287015757,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.2141008883714676,
|
|
"num_tokens": 42534777.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.577837753295898,
|
|
"epoch": 2.141742011568484,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004548188234565551,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.21755864322185517,
|
|
"num_tokens": 42545803.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.597606611251831,
|
|
"epoch": 2.142303588476442,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045479468831745144,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.2134004145860672,
|
|
"num_tokens": 42556803.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.564235973358154,
|
|
"epoch": 2.1428651653843995,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004547705474536152,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.2080395132303238,
|
|
"num_tokens": 42568357.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.520560932159424,
|
|
"epoch": 2.1434267422923567,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045474640086581506,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.21689723283052445,
|
|
"num_tokens": 42578990.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.540421009063721,
|
|
"epoch": 2.1439883192003144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045472224855481975,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.21855953931808472,
|
|
"num_tokens": 42589823.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.47597599029541,
|
|
"epoch": 2.144549896108272,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045469809052139844,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.21367120742797852,
|
|
"num_tokens": 42600508.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.5063213348388675,
|
|
"epoch": 2.1451114730162297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045467392676632016,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21950806826353073,
|
|
"num_tokens": 42611061.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.556859493255615,
|
|
"epoch": 2.145673049924187,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004546497572903543,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.21893983334302902,
|
|
"num_tokens": 42621936.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.534170627593994,
|
|
"epoch": 2.1462346268321446,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004546255820942706,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.21796200126409532,
|
|
"num_tokens": 42632880.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.511006641387939,
|
|
"epoch": 2.1467962037401023,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004546014011788386,
|
|
"loss": 4.9506,
|
|
"mean_token_accuracy": 0.22620653808116914,
|
|
"num_tokens": 42642819.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.495692396163941,
|
|
"epoch": 2.14735778064806,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004545772145448284,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.21462429463863372,
|
|
"num_tokens": 42654581.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.559412431716919,
|
|
"epoch": 2.147919357556017,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045455302219301,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.2108849033713341,
|
|
"num_tokens": 42665323.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.645131063461304,
|
|
"epoch": 2.148480934463975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004545288241241538,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.21075834482908248,
|
|
"num_tokens": 42676465.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.535731410980224,
|
|
"epoch": 2.1490425113719325,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004545046203390302,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.21114521473646164,
|
|
"num_tokens": 42688242.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.493396472930908,
|
|
"epoch": 2.14960408827989,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045448041083840973,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.2204976886510849,
|
|
"num_tokens": 42699498.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.599176979064941,
|
|
"epoch": 2.1501656651878474,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045445619562306354,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.21387781649827958,
|
|
"num_tokens": 42710330.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.59142107963562,
|
|
"epoch": 2.150727242095805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045443197469376243,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.21371834725141525,
|
|
"num_tokens": 42721210.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.576825189590454,
|
|
"epoch": 2.1512888190037627,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004544077480512776,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.22123272866010665,
|
|
"num_tokens": 42732272.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.632673454284668,
|
|
"epoch": 2.15185039591172,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045438351569638055,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.2056201606988907,
|
|
"num_tokens": 42745737.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.540906000137329,
|
|
"epoch": 2.1524119728196776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045435927762984277,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.21575257331132888,
|
|
"num_tokens": 42756405.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.521462488174438,
|
|
"epoch": 2.152973549727635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000454335033852436,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.20317659378051758,
|
|
"num_tokens": 42767991.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.562756586074829,
|
|
"epoch": 2.153535126635593,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004543107843649322,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.20633765012025834,
|
|
"num_tokens": 42779177.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.529184722900391,
|
|
"epoch": 2.15409670354355,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004542865291681035,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.22091633975505828,
|
|
"num_tokens": 42789748.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.577623271942139,
|
|
"epoch": 2.1546582804515078,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045426226826272213,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.2182063341140747,
|
|
"num_tokens": 42802741.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.558766031265259,
|
|
"epoch": 2.1552198573594654,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004542380016495607,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.21303504705429077,
|
|
"num_tokens": 42813091.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.56272702217102,
|
|
"epoch": 2.155781434267423,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045421372932939177,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.21624734848737717,
|
|
"num_tokens": 42823711.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.525273656845092,
|
|
"epoch": 2.1563430111753803,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004541894513029881,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.20034964382648468,
|
|
"num_tokens": 42835057.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.64562873840332,
|
|
"epoch": 2.156904588083338,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045416516757112286,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.213261941075325,
|
|
"num_tokens": 42846784.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.529669666290284,
|
|
"epoch": 2.1574661649912956,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045414087813456925,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.2172635242342949,
|
|
"num_tokens": 42857618.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.540901041030883,
|
|
"epoch": 2.1580277418992533,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004541165829941006,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.2144450858235359,
|
|
"num_tokens": 42869076.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.519642353057861,
|
|
"epoch": 2.1585893188072105,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004540922821504904,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.2211889162659645,
|
|
"num_tokens": 42879714.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.58187575340271,
|
|
"epoch": 2.159150895715168,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004540679756045125,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.21891047507524491,
|
|
"num_tokens": 42890187.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.52135329246521,
|
|
"epoch": 2.159712472623126,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004540436633569407,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.2170883074402809,
|
|
"num_tokens": 42900713.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.518402242660523,
|
|
"epoch": 2.1602740495310835,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045401934540854937,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.2161787837743759,
|
|
"num_tokens": 42911703.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.490769529342652,
|
|
"epoch": 2.1608356264390407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004539950217601127,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.22082522809505462,
|
|
"num_tokens": 42922684.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.569446086883545,
|
|
"epoch": 2.1613972033469984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045397069241240497,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.21173642724752426,
|
|
"num_tokens": 42933095.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.559128522872925,
|
|
"epoch": 2.161958780254956,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000453946357366201,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.21481601446866988,
|
|
"num_tokens": 42944508.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.463350105285644,
|
|
"epoch": 2.1625203571629132,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045392201662227565,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.22176207304000856,
|
|
"num_tokens": 42954902.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.518652057647705,
|
|
"epoch": 2.163081934070871,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045389767018140395,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.21910975128412247,
|
|
"num_tokens": 42965165.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.542084693908691,
|
|
"epoch": 2.1636435109788286,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045387331804436096,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.2188021257519722,
|
|
"num_tokens": 42975025.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.591358375549317,
|
|
"epoch": 2.1642050878867862,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004538489602119222,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.21958980560302735,
|
|
"num_tokens": 42986666.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.555608463287354,
|
|
"epoch": 2.1647666647947434,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004538245966848632,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.21376760751008989,
|
|
"num_tokens": 42998607.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.52857813835144,
|
|
"epoch": 2.165328241702701,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045380022746395953,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.2152646377682686,
|
|
"num_tokens": 43009969.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.654322624206543,
|
|
"epoch": 2.1658898186106588,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045377585254998743,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.21598292142152786,
|
|
"num_tokens": 43023255.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.551023721694946,
|
|
"epoch": 2.1664513955186164,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004537514719437228,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.2110632613301277,
|
|
"num_tokens": 43033995.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.571728992462158,
|
|
"epoch": 2.1670129724265736,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045372708564594196,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.20954176038503647,
|
|
"num_tokens": 43046239.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.496667432785034,
|
|
"epoch": 2.1675745493345313,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045370269365742143,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.22540967166423798,
|
|
"num_tokens": 43057262.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.538082122802734,
|
|
"epoch": 2.168136126242489,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045367829597893776,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.2116882935166359,
|
|
"num_tokens": 43068495.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.520704317092895,
|
|
"epoch": 2.1686977031504466,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045365389261126793,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.21844674944877623,
|
|
"num_tokens": 43080706.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.451546144485474,
|
|
"epoch": 2.169259280058404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045362948355518883,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.22425546497106552,
|
|
"num_tokens": 43091444.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.576201248168945,
|
|
"epoch": 2.1698208569663615,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004536050688114777,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.21008505225181578,
|
|
"num_tokens": 43103648.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.617871189117432,
|
|
"epoch": 2.170382433874319,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045358064838091187,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.21464405655860902,
|
|
"num_tokens": 43116183.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.528388786315918,
|
|
"epoch": 2.170944010782277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045355622226426903,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.20965142250061036,
|
|
"num_tokens": 43126557.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.51220121383667,
|
|
"epoch": 2.171505587690234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045353179046232674,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.2092260479927063,
|
|
"num_tokens": 43137753.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.572681474685669,
|
|
"epoch": 2.1720671645981917,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000453507352975863,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.2125249460339546,
|
|
"num_tokens": 43148461.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.529364967346192,
|
|
"epoch": 2.1726287415061494,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045348290980565595,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.22016704231500625,
|
|
"num_tokens": 43161174.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.569588565826416,
|
|
"epoch": 2.1731903184141066,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045345846095248376,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.21005191206932067,
|
|
"num_tokens": 43172844.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.460982608795166,
|
|
"epoch": 2.1737518953220643,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045343400641712503,
|
|
"loss": 4.9748,
|
|
"mean_token_accuracy": 0.21764014661312103,
|
|
"num_tokens": 43183476.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.5826763153076175,
|
|
"epoch": 2.174313472230022,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045340954620035827,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.21271572709083558,
|
|
"num_tokens": 43195563.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.587401008605957,
|
|
"epoch": 2.1748750491379796,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045338508030296246,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.21748223304748535,
|
|
"num_tokens": 43206067.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.5337413311004635,
|
|
"epoch": 2.175436626045937,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045336060872571646,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.21637769788503647,
|
|
"num_tokens": 43216912.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.576226377487183,
|
|
"epoch": 2.1759982029538945,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004533361314693994,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.21172242015600204,
|
|
"num_tokens": 43228746.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.577840185165405,
|
|
"epoch": 2.176559779861852,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045331164853479084,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.21900693625211715,
|
|
"num_tokens": 43241228.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.550479888916016,
|
|
"epoch": 2.17712135676981,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045328715992267024,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.2172549843788147,
|
|
"num_tokens": 43252916.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.507442378997803,
|
|
"epoch": 2.177682933677767,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045326266563381734,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.22316396087408066,
|
|
"num_tokens": 43264357.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.510592412948609,
|
|
"epoch": 2.1782445105857247,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045323816566901205,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.2135193094611168,
|
|
"num_tokens": 43274547.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.469988679885864,
|
|
"epoch": 2.1788060874936823,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004532136600290343,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.21870780885219573,
|
|
"num_tokens": 43284225.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.5489856719970705,
|
|
"epoch": 2.17936766440164,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004531891487146646,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.21287041604518891,
|
|
"num_tokens": 43295218.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.493258285522461,
|
|
"epoch": 2.179929241309597,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004531646317266833,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.21756806522607802,
|
|
"num_tokens": 43305169.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.513334846496582,
|
|
"epoch": 2.180490818217555,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045314010906587096,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.21757705360651017,
|
|
"num_tokens": 43317119.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.570352983474732,
|
|
"epoch": 2.1810523951255125,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045311558073300853,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.22099003195762634,
|
|
"num_tokens": 43327800.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.4404679298400875,
|
|
"epoch": 2.18161397203347,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004530910467288769,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.21183538436889648,
|
|
"num_tokens": 43338607.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.555451154708862,
|
|
"epoch": 2.1821755489414274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045306650705425727,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.2220939040184021,
|
|
"num_tokens": 43350621.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.568552923202515,
|
|
"epoch": 2.182737125849385,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045304196170993093,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.2193496987223625,
|
|
"num_tokens": 43360327.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.475370073318482,
|
|
"epoch": 2.1832987027573427,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004530174106966795,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.21596528589725494,
|
|
"num_tokens": 43371538.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.558160877227783,
|
|
"epoch": 2.1838602796653,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045299285401528475,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.20922524034976958,
|
|
"num_tokens": 43381818.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.537407684326172,
|
|
"epoch": 2.1844218565732576,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004529682916665285,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.20841564387083053,
|
|
"num_tokens": 43391977.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.575194263458252,
|
|
"epoch": 2.1849834334812153,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045294372365119276,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.21441450864076614,
|
|
"num_tokens": 43403657.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.480862140655518,
|
|
"epoch": 2.185545010389173,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004529191499700598,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.21399512141942978,
|
|
"num_tokens": 43414325.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.6482741355896,
|
|
"epoch": 2.18610658729713,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004528945706239122,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.2092905730009079,
|
|
"num_tokens": 43425864.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.57762451171875,
|
|
"epoch": 2.186668164205088,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045286998561353236,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.21413282603025435,
|
|
"num_tokens": 43437135.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.6503777503967285,
|
|
"epoch": 2.1872297411130455,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004528453949397033,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.21257788687944412,
|
|
"num_tokens": 43448603.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.524881601333618,
|
|
"epoch": 2.187791318021003,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045282079860320786,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.22483819127082824,
|
|
"num_tokens": 43460316.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.482131481170654,
|
|
"epoch": 2.1883528949289603,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045279619660482925,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.22239234000444413,
|
|
"num_tokens": 43471869.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.520337963104248,
|
|
"epoch": 2.188914471836918,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045277158894535075,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.2138853520154953,
|
|
"num_tokens": 43484004.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.585912418365479,
|
|
"epoch": 2.1894760487448757,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045274697562555584,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.21174642890691758,
|
|
"num_tokens": 43494401.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.504145669937134,
|
|
"epoch": 2.1900376256528333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004527223566462284,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.2136768579483032,
|
|
"num_tokens": 43505437.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.492135667800904,
|
|
"epoch": 2.1905992025607905,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004526977320081522,
|
|
"loss": 4.947,
|
|
"mean_token_accuracy": 0.22581539750099183,
|
|
"num_tokens": 43516177.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.530815839767456,
|
|
"epoch": 2.191160779468748,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004526731017121111,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.21821716129779817,
|
|
"num_tokens": 43527070.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.57179069519043,
|
|
"epoch": 2.191722356376706,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045264846575888973,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.21274439692497255,
|
|
"num_tokens": 43538247.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.566407203674316,
|
|
"epoch": 2.1922839332846635,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045262382414927235,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.22045524567365646,
|
|
"num_tokens": 43549994.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.589530420303345,
|
|
"epoch": 2.1928455101926208,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045259917688404336,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.21873417794704436,
|
|
"num_tokens": 43562171.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.568601894378662,
|
|
"epoch": 2.1934070871005784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004525745239639877,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.20919926911592485,
|
|
"num_tokens": 43572308.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.518997478485107,
|
|
"epoch": 2.193968664008536,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045254986538989045,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.21937488466501237,
|
|
"num_tokens": 43583565.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.559282684326172,
|
|
"epoch": 2.1945302409164933,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004525252011625366,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.2107415422797203,
|
|
"num_tokens": 43595921.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.5454244136810305,
|
|
"epoch": 2.195091817824451,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004525005312827114,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.22067110985517502,
|
|
"num_tokens": 43606957.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.520418977737426,
|
|
"epoch": 2.1956533947324086,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004524758557512005,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.22220480740070342,
|
|
"num_tokens": 43616983.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.474819803237915,
|
|
"epoch": 2.1962149716403663,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004524511745687895,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.22349600344896317,
|
|
"num_tokens": 43626951.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.4872802734375,
|
|
"epoch": 2.1967765485483235,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004524264877362643,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.21460592597723008,
|
|
"num_tokens": 43638446.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.579897928237915,
|
|
"epoch": 2.197338125456281,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045240179525441094,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21486959457397461,
|
|
"num_tokens": 43649646.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.568695402145385,
|
|
"epoch": 2.197899702364239,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004523770971240156,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.21529057621955872,
|
|
"num_tokens": 43661633.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.525893926620483,
|
|
"epoch": 2.1984612792721965,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004523523933458647,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.21261367648839952,
|
|
"num_tokens": 43672671.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.542205810546875,
|
|
"epoch": 2.1990228561801537,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004523276839207448,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.21360018402338027,
|
|
"num_tokens": 43683426.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.5453041076660154,
|
|
"epoch": 2.1995844330881114,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045230296884944264,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.21418690532445908,
|
|
"num_tokens": 43694460.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.4960967063903805,
|
|
"epoch": 2.200146009996069,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045227824813274517,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.22718592882156372,
|
|
"num_tokens": 43706047.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.488912057876587,
|
|
"epoch": 2.2007075869040267,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004522535217714396,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21907835751771926,
|
|
"num_tokens": 43715879.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.523978757858276,
|
|
"epoch": 2.201269163811984,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004522287897663131,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.21633038967847823,
|
|
"num_tokens": 43726870.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.532400989532471,
|
|
"epoch": 2.2018307407199416,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045220405211815327,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.20967280715703965,
|
|
"num_tokens": 43739116.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.564774847030639,
|
|
"epoch": 2.202392317627899,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045217930882774754,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.2163477674126625,
|
|
"num_tokens": 43750239.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.59723801612854,
|
|
"epoch": 2.202953894535857,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045215455989588396,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.21149891018867492,
|
|
"num_tokens": 43762391.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.529277706146241,
|
|
"epoch": 2.203515471443814,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045212980532335055,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.21562150716781617,
|
|
"num_tokens": 43773514.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.532941198348999,
|
|
"epoch": 2.2040770483517718,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045210504511093534,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.21361519098281861,
|
|
"num_tokens": 43784617.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.645305395126343,
|
|
"epoch": 2.2046386252597294,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004520802792594269,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.21212921291589737,
|
|
"num_tokens": 43795396.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.564464139938354,
|
|
"epoch": 2.2052002021676866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045205550776961366,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.2093094229698181,
|
|
"num_tokens": 43805512.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.588630342483521,
|
|
"epoch": 2.2057617790756443,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004520307306422844,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.2099342331290245,
|
|
"num_tokens": 43815874.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.653163242340088,
|
|
"epoch": 2.206323355983602,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045200594787822795,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.21176334768533706,
|
|
"num_tokens": 43827948.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.5756142139434814,
|
|
"epoch": 2.2068849328915596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004519811594782335,
|
|
"loss": 4.9835,
|
|
"mean_token_accuracy": 0.21863894015550614,
|
|
"num_tokens": 43838306.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.494722461700439,
|
|
"epoch": 2.207446509799517,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045195636544309033,
|
|
"loss": 5.0117,
|
|
"mean_token_accuracy": 0.2187864288687706,
|
|
"num_tokens": 43848716.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.593022298812866,
|
|
"epoch": 2.2080080867074745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045193156577358784,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.21508534103631974,
|
|
"num_tokens": 43859707.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.529709815979004,
|
|
"epoch": 2.208569663615432,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004519067604705157,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.2247368723154068,
|
|
"num_tokens": 43870599.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.596689510345459,
|
|
"epoch": 2.20913124052339,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045188194953466363,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.21690400391817094,
|
|
"num_tokens": 43881843.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.4353804111480715,
|
|
"epoch": 2.209692817431347,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045185713296682175,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.21520331650972366,
|
|
"num_tokens": 43892206.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.51749997138977,
|
|
"epoch": 2.2102543943393047,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045183231076778005,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.21758174300193786,
|
|
"num_tokens": 43905255.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.563086652755738,
|
|
"epoch": 2.2108159712472624,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045180748293832906,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.21019697785377503,
|
|
"num_tokens": 43917774.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.517612552642822,
|
|
"epoch": 2.21137754815522,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045178264947925924,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.22029122561216355,
|
|
"num_tokens": 43929127.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.571838998794556,
|
|
"epoch": 2.2119391250631772,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045175781039136133,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.2150412917137146,
|
|
"num_tokens": 43942558.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.528672361373902,
|
|
"epoch": 2.212500701971135,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004517329656754261,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.21187555491924287,
|
|
"num_tokens": 43952966.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.566435289382935,
|
|
"epoch": 2.2130622788790926,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004517081153322448,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.2125861391425133,
|
|
"num_tokens": 43964725.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.518968105316162,
|
|
"epoch": 2.2136238557870502,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004516832593626085,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.22868142426013946,
|
|
"num_tokens": 43976356.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.4467627048492435,
|
|
"epoch": 2.2141854326950074,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004516583977673087,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.2184616968035698,
|
|
"num_tokens": 43987732.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.557591772079467,
|
|
"epoch": 2.214747009602965,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045163353054713704,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.20970811545848847,
|
|
"num_tokens": 43998701.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.59496111869812,
|
|
"epoch": 2.2153085865109228,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004516086577028852,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.21673598736524582,
|
|
"num_tokens": 44008978.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.550060367584228,
|
|
"epoch": 2.21587016341888,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004515837792353453,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.21926363408565522,
|
|
"num_tokens": 44018928.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.521185493469238,
|
|
"epoch": 2.2164317403268377,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004515588951453093,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.21327116340398788,
|
|
"num_tokens": 44030044.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.388719940185547,
|
|
"epoch": 2.2169933172347953,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004515340054335696,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.21906359791755675,
|
|
"num_tokens": 44041851.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.489683341979981,
|
|
"epoch": 2.217554894142753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004515091101009188,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.21963817477226258,
|
|
"num_tokens": 44051871.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.580018472671509,
|
|
"epoch": 2.21811647105071,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004514842091481493,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.2077604427933693,
|
|
"num_tokens": 44063222.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.624531507492065,
|
|
"epoch": 2.218678047958668,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004514593025760543,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.21299233734607698,
|
|
"num_tokens": 44075020.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.5403228282928465,
|
|
"epoch": 2.2192396248666255,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045143439038542653,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.20626766234636307,
|
|
"num_tokens": 44086696.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.544500160217285,
|
|
"epoch": 2.219801201774583,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004514094725770594,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.21750151813030244,
|
|
"num_tokens": 44096768.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.486742734909058,
|
|
"epoch": 2.2203627786825404,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045138454915174625,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.2196403995156288,
|
|
"num_tokens": 44108008.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.534741735458374,
|
|
"epoch": 2.220924355590498,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045135962011028064,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.21578315198421477,
|
|
"num_tokens": 44119231.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.491272592544556,
|
|
"epoch": 2.2214859324984557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004513346854534564,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.212676802277565,
|
|
"num_tokens": 44129264.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.570010709762573,
|
|
"epoch": 2.2220475094064134,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004513097451820673,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.20742704421281816,
|
|
"num_tokens": 44141234.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.555457878112793,
|
|
"epoch": 2.2226090863143706,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045128479929690756,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.22058322727680207,
|
|
"num_tokens": 44151751.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.393948650360107,
|
|
"epoch": 2.2231706632223283,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004512598477987714,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.2202011078596115,
|
|
"num_tokens": 44162687.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.475763940811158,
|
|
"epoch": 2.223732240130286,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045123489068845334,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.22543394863605498,
|
|
"num_tokens": 44173758.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.533033800125122,
|
|
"epoch": 2.2242938170382436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045120992796674804,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.21814768016338348,
|
|
"num_tokens": 44184176.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.533380556106567,
|
|
"epoch": 2.224855393946201,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004511849596344503,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.2058999866247177,
|
|
"num_tokens": 44195155.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.608782482147217,
|
|
"epoch": 2.2254169708541585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045115998569235507,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.21260946691036225,
|
|
"num_tokens": 44207139.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.604257965087891,
|
|
"epoch": 2.225978547762116,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045113500614125756,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.21317875981330872,
|
|
"num_tokens": 44218317.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.588312387466431,
|
|
"epoch": 2.2265401246700733,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004511100209819532,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.2164520725607872,
|
|
"num_tokens": 44228700.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.457471466064453,
|
|
"epoch": 2.227101701578031,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045108503021523737,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.2218073606491089,
|
|
"num_tokens": 44239991.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.383003282546997,
|
|
"epoch": 2.2276632784859887,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045106003384190604,
|
|
"loss": 4.8587,
|
|
"mean_token_accuracy": 0.22161413580179215,
|
|
"num_tokens": 44250224.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.450273084640503,
|
|
"epoch": 2.2282248553939463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045103503186275486,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.21791945695877074,
|
|
"num_tokens": 44261403.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.49015326499939,
|
|
"epoch": 2.2287864323019035,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045101002427857997,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.21159991919994353,
|
|
"num_tokens": 44272935.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.506404209136963,
|
|
"epoch": 2.229348009209861,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045098501109017765,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.22323381155729294,
|
|
"num_tokens": 44283458.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.490182971954345,
|
|
"epoch": 2.229909586117819,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045095999229834437,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.21557433754205704,
|
|
"num_tokens": 44294847.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.532952928543091,
|
|
"epoch": 2.2304711630257765,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004509349679038767,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.21393141895532608,
|
|
"num_tokens": 44306395.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.548343229293823,
|
|
"epoch": 2.2310327399337337,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045090993790757137,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.22145644277334214,
|
|
"num_tokens": 44317452.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.506434297561645,
|
|
"epoch": 2.2315943168416914,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004508849023102253,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.22264577597379684,
|
|
"num_tokens": 44329862.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.556842184066772,
|
|
"epoch": 2.232155893749649,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004508598611126359,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.2099307656288147,
|
|
"num_tokens": 44340334.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.615594100952149,
|
|
"epoch": 2.2327174706576067,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004508348143156002,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.21084987819194795,
|
|
"num_tokens": 44351810.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.681191158294678,
|
|
"epoch": 2.233279047565564,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045080976191991587,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.20679444968700408,
|
|
"num_tokens": 44365143.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.566488027572632,
|
|
"epoch": 2.2338406244735216,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004507847039263805,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21756814569234847,
|
|
"num_tokens": 44375895.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.517352056503296,
|
|
"epoch": 2.2344022013814793,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000450759640335792,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.21248935908079147,
|
|
"num_tokens": 44387378.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.507291460037232,
|
|
"epoch": 2.234963778289437,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004507345711489484,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.22973885238170624,
|
|
"num_tokens": 44398460.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.477328300476074,
|
|
"epoch": 2.235525355197394,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045070949636664785,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.22029970437288285,
|
|
"num_tokens": 44409885.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.465685033798218,
|
|
"epoch": 2.236086932105352,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004506844159896888,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.22506236433982849,
|
|
"num_tokens": 44420897.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.549086856842041,
|
|
"epoch": 2.2366485090133095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004506593300188698,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.20991718024015427,
|
|
"num_tokens": 44432691.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.570152235031128,
|
|
"epoch": 2.2372100859212667,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004506342384549897,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.21302432268857957,
|
|
"num_tokens": 44444731.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.612523221969605,
|
|
"epoch": 2.2377716628292244,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004506091412988472,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.22509962022304536,
|
|
"num_tokens": 44456959.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.560497570037842,
|
|
"epoch": 2.238333239737182,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045058403855124165,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.2186114341020584,
|
|
"num_tokens": 44468970.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.502913951873779,
|
|
"epoch": 2.2388948166451397,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004505589302129721,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.22123550921678542,
|
|
"num_tokens": 44480485.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.554518699645996,
|
|
"epoch": 2.239456393553097,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004505338162848382,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.21267967522144318,
|
|
"num_tokens": 44492890.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.648462200164795,
|
|
"epoch": 2.2400179704610546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004505086967676395,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.2012655720114708,
|
|
"num_tokens": 44504743.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.559561634063721,
|
|
"epoch": 2.240579547369012,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004504835716621757,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.21329739242792128,
|
|
"num_tokens": 44514998.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.492208814620971,
|
|
"epoch": 2.24114112427697,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004504584409692471,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.2208435744047165,
|
|
"num_tokens": 44527530.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.604158020019531,
|
|
"epoch": 2.241702701184927,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045043330468965364,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.20708687454462052,
|
|
"num_tokens": 44540939.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.59348464012146,
|
|
"epoch": 2.2422642780928848,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045040816282419566,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.2138330116868019,
|
|
"num_tokens": 44551557.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.521318960189819,
|
|
"epoch": 2.2428258550008424,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045038301537367374,
|
|
"loss": 4.947,
|
|
"mean_token_accuracy": 0.22158707827329635,
|
|
"num_tokens": 44561969.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.45359525680542,
|
|
"epoch": 2.2433874319088,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045035786233888864,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.21300098896026612,
|
|
"num_tokens": 44573542.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.564398670196534,
|
|
"epoch": 2.2439490088167573,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045033270372064123,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.22024468779563905,
|
|
"num_tokens": 44583720.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.516009569168091,
|
|
"epoch": 2.244510585724715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045030753951973243,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.21652544885873795,
|
|
"num_tokens": 44595314.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.655755090713501,
|
|
"epoch": 2.2450721626326726,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045028236973696363,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.21337980777025223,
|
|
"num_tokens": 44608569.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.563026285171508,
|
|
"epoch": 2.2456337395406303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004502571943731362,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.20827787816524507,
|
|
"num_tokens": 44619389.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.56637020111084,
|
|
"epoch": 2.2461953164485875,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004502320134290517,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.2114649310708046,
|
|
"num_tokens": 44629945.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.586146402359009,
|
|
"epoch": 2.246756893356545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045020682690551203,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20879678428173065,
|
|
"num_tokens": 44640741.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.583372688293457,
|
|
"epoch": 2.247318470264503,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045018163480331887,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.22068547755479812,
|
|
"num_tokens": 44651312.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.444302129745483,
|
|
"epoch": 2.24788004717246,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045015643712327465,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.2150447130203247,
|
|
"num_tokens": 44663156.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.461149883270264,
|
|
"epoch": 2.2484416240804177,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004501312338661815,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.2205791652202606,
|
|
"num_tokens": 44673479.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.550459289550782,
|
|
"epoch": 2.2490032009883754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004501060250328419,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.21790316849946975,
|
|
"num_tokens": 44684207.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.5620849609375,
|
|
"epoch": 2.249564777896333,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004500808106240586,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.2203519731760025,
|
|
"num_tokens": 44695611.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.516868305206299,
|
|
"epoch": 2.2501263548042907,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004500555906406343,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.2142522543668747,
|
|
"num_tokens": 44707061.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.609898710250855,
|
|
"epoch": 2.250687931712248,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004500303650833722,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.2093170925974846,
|
|
"num_tokens": 44719366.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.5576979637146,
|
|
"epoch": 2.2512495086202056,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004500051339530754,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.21783564388751983,
|
|
"num_tokens": 44730578.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.523629474639892,
|
|
"epoch": 2.2518110855281632,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004499798972505472,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.2194340407848358,
|
|
"num_tokens": 44740620.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.535042858123779,
|
|
"epoch": 2.2523726624361204,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044995465497659127,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.2215449407696724,
|
|
"num_tokens": 44751518.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.563789319992066,
|
|
"epoch": 2.252934239344078,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004499294071320112,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.21834387332201005,
|
|
"num_tokens": 44761563.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.587675380706787,
|
|
"epoch": 2.2534958162520358,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000449904153717611,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.21342722624540328,
|
|
"num_tokens": 44773330.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.5110067367553714,
|
|
"epoch": 2.2540573931599934,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004498788947341947,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.2162868231534958,
|
|
"num_tokens": 44786198.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.433059930801392,
|
|
"epoch": 2.2546189700679506,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004498536301825665,
|
|
"loss": 4.9578,
|
|
"mean_token_accuracy": 0.21830971986055375,
|
|
"num_tokens": 44797643.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.463837623596191,
|
|
"epoch": 2.2551805469759083,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000449828360063531,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.22378237843513488,
|
|
"num_tokens": 44808283.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.50068359375,
|
|
"epoch": 2.255742123883866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044980308437789267,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.22039248347282409,
|
|
"num_tokens": 44817699.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.553688859939575,
|
|
"epoch": 2.2563037007918236,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004497778031264564,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.21051016598939895,
|
|
"num_tokens": 44828428.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.495239162445069,
|
|
"epoch": 2.256865277699781,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044975251631002694,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.20912570506334305,
|
|
"num_tokens": 44839288.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.5699258804321286,
|
|
"epoch": 2.2574268546077385,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004497272239294097,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.2097405970096588,
|
|
"num_tokens": 44850250.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.571021223068238,
|
|
"epoch": 2.257988431515696,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004497019259854099,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.2156917542219162,
|
|
"num_tokens": 44862186.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.588415288925171,
|
|
"epoch": 2.2585500084236534,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044967662247883295,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.21009773015975952,
|
|
"num_tokens": 44874266.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.557514381408692,
|
|
"epoch": 2.259111585331611,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044965131341048454,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.21682303845882417,
|
|
"num_tokens": 44885783.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.528659248352051,
|
|
"epoch": 2.2596731622395687,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004496259987811707,
|
|
"loss": 4.9265,
|
|
"mean_token_accuracy": 0.22552106231451036,
|
|
"num_tokens": 44896972.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.540951347351074,
|
|
"epoch": 2.2602347391475264,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004496006785916973,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.22040268182754516,
|
|
"num_tokens": 44907414.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.544600534439087,
|
|
"epoch": 2.260796316055484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044957535284287055,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.2188276693224907,
|
|
"num_tokens": 44917150.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.521452903747559,
|
|
"epoch": 2.2613578929634413,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044955002153549686,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.21709963977336882,
|
|
"num_tokens": 44928927.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.5657548904418945,
|
|
"epoch": 2.261919469871399,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004495246846703828,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.21543173342943192,
|
|
"num_tokens": 44938987.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.527096509933472,
|
|
"epoch": 2.2624810467793566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044949934224833505,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.2191598653793335,
|
|
"num_tokens": 44950395.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.4986073017120365,
|
|
"epoch": 2.263042623687314,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004494739942701606,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.22144171297550203,
|
|
"num_tokens": 44961389.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.623337841033935,
|
|
"epoch": 2.2636042005952715,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044944864073666655,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.20748314559459685,
|
|
"num_tokens": 44973142.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.4913952350616455,
|
|
"epoch": 2.264165777503229,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044942328164866,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.21886357367038728,
|
|
"num_tokens": 44983831.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.552133464813233,
|
|
"epoch": 2.2647273544111868,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004493979170069486,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.2154310092329979,
|
|
"num_tokens": 44996386.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.512030076980591,
|
|
"epoch": 2.265288931319144,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044937254681233984,
|
|
"loss": 4.9795,
|
|
"mean_token_accuracy": 0.21679970920085906,
|
|
"num_tokens": 45007607.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.4887309074401855,
|
|
"epoch": 2.2658505082271017,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044934717106564164,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.21727257519960402,
|
|
"num_tokens": 45019637.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.51179780960083,
|
|
"epoch": 2.2664120851350593,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044932178976766183,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.21711268723011018,
|
|
"num_tokens": 45031329.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.528307819366455,
|
|
"epoch": 2.266973662043017,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044929640291920865,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.21597458720207213,
|
|
"num_tokens": 45042539.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.445019197463989,
|
|
"epoch": 2.267535238950974,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004492710105210904,
|
|
"loss": 4.8957,
|
|
"mean_token_accuracy": 0.22614268511533736,
|
|
"num_tokens": 45054021.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.5942624568939205,
|
|
"epoch": 2.268096815858932,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044924561257411554,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.21082842350006104,
|
|
"num_tokens": 45065912.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.55033688545227,
|
|
"epoch": 2.2686583927668895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004492202090790928,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.22585199475288392,
|
|
"num_tokens": 45075965.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.511345624923706,
|
|
"epoch": 2.2692199696748467,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004491948000368311,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.21590015441179275,
|
|
"num_tokens": 45086676.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.4824512004852295,
|
|
"epoch": 2.2697815465828044,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044916938544813936,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.2201997771859169,
|
|
"num_tokens": 45097747.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.531192493438721,
|
|
"epoch": 2.270343123490762,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044914396531382686,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.22607287913560867,
|
|
"num_tokens": 45107506.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.5217968940734865,
|
|
"epoch": 2.2709047003987197,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044911853963470295,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.2209517166018486,
|
|
"num_tokens": 45119939.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.583072471618652,
|
|
"epoch": 2.2714662773066774,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004490931084115772,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.2077132433652878,
|
|
"num_tokens": 45133749.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.581585216522217,
|
|
"epoch": 2.2720278542146346,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044906767164525936,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.20419533997774125,
|
|
"num_tokens": 45144696.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.522469520568848,
|
|
"epoch": 2.2725894311225923,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004490422293365594,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.21814119517803193,
|
|
"num_tokens": 45154921.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.455430269241333,
|
|
"epoch": 2.27315100803055,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004490167814862872,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.22235162258148194,
|
|
"num_tokens": 45164769.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.585930061340332,
|
|
"epoch": 2.273712584938507,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004489913280952533,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.2177905783057213,
|
|
"num_tokens": 45176619.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.5092638492584225,
|
|
"epoch": 2.274274161846465,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004489658691642681,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.21165461093187332,
|
|
"num_tokens": 45186508.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.649955749511719,
|
|
"epoch": 2.2748357387544225,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044894040469414207,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.2068465456366539,
|
|
"num_tokens": 45198213.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.549337005615234,
|
|
"epoch": 2.27539731566238,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044891493468568607,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.20787788331508636,
|
|
"num_tokens": 45209328.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.547964668273925,
|
|
"epoch": 2.2759588925703373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044888945913971106,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.2215050458908081,
|
|
"num_tokens": 45219722.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.623567390441894,
|
|
"epoch": 2.276520469478295,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044886397805702835,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.20761454105377197,
|
|
"num_tokens": 45230377.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.593324375152588,
|
|
"epoch": 2.2770820463862527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044883849143844914,
|
|
"loss": 4.991,
|
|
"mean_token_accuracy": 0.21900904774665833,
|
|
"num_tokens": 45241598.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.662901735305786,
|
|
"epoch": 2.2776436232942103,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004488129992847848,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.2096794605255127,
|
|
"num_tokens": 45253153.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.563160848617554,
|
|
"epoch": 2.2782052002021675,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004487875015968473,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.21875222027301788,
|
|
"num_tokens": 45264523.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.490442228317261,
|
|
"epoch": 2.278766777110125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004487619983754483,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.2054273769259453,
|
|
"num_tokens": 45275320.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.556008911132812,
|
|
"epoch": 2.279328354018083,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044873648962139983,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.2169485718011856,
|
|
"num_tokens": 45286704.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.560254907608032,
|
|
"epoch": 2.27988993092604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004487109753355142,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.21584808677434922,
|
|
"num_tokens": 45299098.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.55738000869751,
|
|
"epoch": 2.2804515078339977,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004486854555186037,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.21309285312891008,
|
|
"num_tokens": 45309995.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.651138257980347,
|
|
"epoch": 2.2810130847419554,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004486599301714809,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.2144736334681511,
|
|
"num_tokens": 45321711.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.531801223754883,
|
|
"epoch": 2.281574661649913,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004486343992949587,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.21501812636852263,
|
|
"num_tokens": 45332401.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.619429302215576,
|
|
"epoch": 2.2821362385578707,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044860886288984977,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.21457785964012147,
|
|
"num_tokens": 45344138.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.530912637710571,
|
|
"epoch": 2.282697815465828,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004485833209569674,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.2153177008032799,
|
|
"num_tokens": 45355913.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.518161487579346,
|
|
"epoch": 2.2832593923737856,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004485577734971247,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.22190685719251632,
|
|
"num_tokens": 45367342.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.5661438465118405,
|
|
"epoch": 2.2838209692817433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044853222051113525,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.21667560189962387,
|
|
"num_tokens": 45377866.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.552828359603882,
|
|
"epoch": 2.2843825461897005,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044850666199981244,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.212368743121624,
|
|
"num_tokens": 45389346.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.4791888236999515,
|
|
"epoch": 2.284944123097658,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044848109796397035,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.21977948397397995,
|
|
"num_tokens": 45400112.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.493206357955932,
|
|
"epoch": 2.285505700005616,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044845552840442276,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.21429039537906647,
|
|
"num_tokens": 45411666.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.528914976119995,
|
|
"epoch": 2.2860672769135735,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044842995332198393,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.22800276875495912,
|
|
"num_tokens": 45423631.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.424667024612427,
|
|
"epoch": 2.2866288538215307,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044840437271746807,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.22075561732053756,
|
|
"num_tokens": 45434697.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.553386545181274,
|
|
"epoch": 2.2871904307294884,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004483787865916898,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.2099434331059456,
|
|
"num_tokens": 45446637.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.490387439727783,
|
|
"epoch": 2.287752007637446,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044835319494546366,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.21978358477354049,
|
|
"num_tokens": 45456750.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.531871891021728,
|
|
"epoch": 2.2883135845454037,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044832759777960456,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.22017927318811417,
|
|
"num_tokens": 45469383.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.587072420120239,
|
|
"epoch": 2.288875161453361,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004483019950949276,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.2176695868372917,
|
|
"num_tokens": 45479668.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.534901285171509,
|
|
"epoch": 2.2894367383613186,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004482763868922478,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.2142357721924782,
|
|
"num_tokens": 45490888.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.542763662338257,
|
|
"epoch": 2.289998315269276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004482507731723807,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.20956908464431762,
|
|
"num_tokens": 45501973.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.495853662490845,
|
|
"epoch": 2.2905598921772334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004482251539361418,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.2153966471552849,
|
|
"num_tokens": 45513171.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.4775315284729,
|
|
"epoch": 2.291121469085191,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004481995291843467,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.21818083077669143,
|
|
"num_tokens": 45523642.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.618212699890137,
|
|
"epoch": 2.2916830459931488,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004481738989178115,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.21844496726989746,
|
|
"num_tokens": 45534467.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.597053575515747,
|
|
"epoch": 2.2922446229011064,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004481482631373522,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.21103395968675615,
|
|
"num_tokens": 45545902.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.52041654586792,
|
|
"epoch": 2.292806199809064,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044812262184378503,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.22026856243610382,
|
|
"num_tokens": 45556270.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.420521974563599,
|
|
"epoch": 2.2933677767170213,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044809697503792647,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.22204917073249816,
|
|
"num_tokens": 45566773.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.516954803466797,
|
|
"epoch": 2.293929353624979,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00044807132272059306,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.2129496991634369,
|
|
"num_tokens": 45578819.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.572612476348877,
|
|
"epoch": 2.2944909305329366,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004480456648926016,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.21145374774932862,
|
|
"num_tokens": 45589128.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.5841700553894045,
|
|
"epoch": 2.295052507440894,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004480200015547691,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.21818899512290954,
|
|
"num_tokens": 45600253.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.58355450630188,
|
|
"epoch": 2.2956140843488515,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044799433270791255,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.21824310570955277,
|
|
"num_tokens": 45611258.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.599572992324829,
|
|
"epoch": 2.296175661256809,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004479686583528494,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.22142475396394729,
|
|
"num_tokens": 45622720.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.448921394348145,
|
|
"epoch": 2.296737238164767,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004479429784903971,
|
|
"loss": 4.9643,
|
|
"mean_token_accuracy": 0.2170537605881691,
|
|
"num_tokens": 45634748.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.494162225723267,
|
|
"epoch": 2.297298815072724,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004479172931213733,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.21449365913867952,
|
|
"num_tokens": 45645735.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.517126989364624,
|
|
"epoch": 2.2978603919806817,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004478916022465958,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.2181713104248047,
|
|
"num_tokens": 45656309.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.525501394271851,
|
|
"epoch": 2.2984219688886394,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004478659058668827,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.2205560863018036,
|
|
"num_tokens": 45667925.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.545886611938476,
|
|
"epoch": 2.298983545796597,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044784020398305204,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.21295666992664336,
|
|
"num_tokens": 45679352.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.5517518520355225,
|
|
"epoch": 2.2995451227045542,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004478144965959222,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.21120673418045044,
|
|
"num_tokens": 45689723.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.61044921875,
|
|
"epoch": 2.300106699612512,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044778878370631183,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.21071393489837648,
|
|
"num_tokens": 45701270.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.518991756439209,
|
|
"epoch": 2.3006682765204696,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044776306531503957,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.22724733352661133,
|
|
"num_tokens": 45711409.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.513414144515991,
|
|
"epoch": 2.301229853428427,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044773734142292425,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.22134487479925155,
|
|
"num_tokens": 45722032.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.491001605987549,
|
|
"epoch": 2.3017914303363844,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004477116120307851,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.22053560018539428,
|
|
"num_tokens": 45733211.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.599780130386352,
|
|
"epoch": 2.302353007244342,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004476858771394412,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.21524703055620192,
|
|
"num_tokens": 45744585.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.5914829730987545,
|
|
"epoch": 2.3029145841522998,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004476601367497119,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.21591112166643142,
|
|
"num_tokens": 45756040.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.555652809143067,
|
|
"epoch": 2.3034761610602574,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000447634390862417,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.21629776060581207,
|
|
"num_tokens": 45767717.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.568176507949829,
|
|
"epoch": 2.3040377379682146,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044760863947837607,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.20778287053108216,
|
|
"num_tokens": 45778326.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.5201863765716555,
|
|
"epoch": 2.3045993148761723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044758288259840904,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.22379937171936035,
|
|
"num_tokens": 45789780.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.539891576766967,
|
|
"epoch": 2.30516089178413,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004475571202233363,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.21007108837366104,
|
|
"num_tokens": 45801686.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.523296546936035,
|
|
"epoch": 2.305722468692087,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004475313523539778,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.2177070274949074,
|
|
"num_tokens": 45812123.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.56872525215149,
|
|
"epoch": 2.306284045600045,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044750557899115407,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.21415327191352845,
|
|
"num_tokens": 45822863.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.549906826019287,
|
|
"epoch": 2.3068456225080025,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004474798001356859,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.21723354756832122,
|
|
"num_tokens": 45833585.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.402116775512695,
|
|
"epoch": 2.30740719941596,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000447454015788394,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.2280719980597496,
|
|
"num_tokens": 45844745.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.485522127151489,
|
|
"epoch": 2.3079687763239174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004474282259500992,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.21622924953699113,
|
|
"num_tokens": 45856018.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.603788185119629,
|
|
"epoch": 2.308530353231875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000447402430621623,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.21803035885095595,
|
|
"num_tokens": 45867182.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.604681015014648,
|
|
"epoch": 2.3090919301398327,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004473766298037865,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.2074447453022003,
|
|
"num_tokens": 45880116.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.566930103302002,
|
|
"epoch": 2.3096535070477904,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044735082349741116,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.21119752228260041,
|
|
"num_tokens": 45891143.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.544876909255981,
|
|
"epoch": 2.3102150839557476,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044732501170331886,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.21742914170026778,
|
|
"num_tokens": 45901443.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.598289442062378,
|
|
"epoch": 2.3107766608637053,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004472991944223313,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.21090299487113953,
|
|
"num_tokens": 45913313.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.61094102859497,
|
|
"epoch": 2.311338237771663,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044727337165527056,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.2086179792881012,
|
|
"num_tokens": 45925248.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.678539419174195,
|
|
"epoch": 2.31189981467962,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044724754340295887,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.20594068020582199,
|
|
"num_tokens": 45936366.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.496601915359497,
|
|
"epoch": 2.312461391587578,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004472217096662186,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.2273688033223152,
|
|
"num_tokens": 45947732.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.51069450378418,
|
|
"epoch": 2.3130229684955355,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004471958704458723,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.2205262303352356,
|
|
"num_tokens": 45958655.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.59760274887085,
|
|
"epoch": 2.313584545403493,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00044717002574274267,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.22164296358823776,
|
|
"num_tokens": 45970767.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.499763870239258,
|
|
"epoch": 2.314146122311451,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004471441755576527,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.22416990101337433,
|
|
"num_tokens": 45981063.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.45285930633545,
|
|
"epoch": 2.314707699219408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044711831989142534,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.22699189484119414,
|
|
"num_tokens": 45991963.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.528799629211425,
|
|
"epoch": 2.3152692761273657,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044709245874488405,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.20754514187574385,
|
|
"num_tokens": 46003460.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.552969264984131,
|
|
"epoch": 2.3158308530353233,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004470665921188519,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.21430490165948868,
|
|
"num_tokens": 46014338.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.460175943374634,
|
|
"epoch": 2.3163924299432805,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044704072001415285,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.22450425773859023,
|
|
"num_tokens": 46025282.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.553340053558349,
|
|
"epoch": 2.316954006851238,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044701484243161055,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.21811945885419845,
|
|
"num_tokens": 46035303.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.501015901565552,
|
|
"epoch": 2.317515583759196,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000446988959372049,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.21988661140203475,
|
|
"num_tokens": 46046336.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.442528772354126,
|
|
"epoch": 2.3180771606671535,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004469630708362922,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.21539134234189988,
|
|
"num_tokens": 46056862.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.652857112884521,
|
|
"epoch": 2.3186387375751107,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004469371768251646,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.20941803157329558,
|
|
"num_tokens": 46067785.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.540560960769653,
|
|
"epoch": 2.3192003144830684,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004469112773394906,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.20536191910505294,
|
|
"num_tokens": 46080553.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.554146575927734,
|
|
"epoch": 2.319761891391026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004468853723800948,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.21138229966163635,
|
|
"num_tokens": 46090985.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.592115163803101,
|
|
"epoch": 2.3203234682989837,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004468594619478021,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.21202754974365234,
|
|
"num_tokens": 46101990.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.45998182296753,
|
|
"epoch": 2.320885045206941,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004468335460434375,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.22131047993898392,
|
|
"num_tokens": 46112853.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.516283941268921,
|
|
"epoch": 2.3214466221148986,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004468076246678261,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.21390710771083832,
|
|
"num_tokens": 46123508.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.695815849304199,
|
|
"epoch": 2.3220081990228563,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044678169782179334,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.21122835278511048,
|
|
"num_tokens": 46135394.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.645047426223755,
|
|
"epoch": 2.3225697759308135,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044675576550616466,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.2159384310245514,
|
|
"num_tokens": 46146838.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.563509607315064,
|
|
"epoch": 2.323131352838771,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044672982772176584,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.22401019036769867,
|
|
"num_tokens": 46157116.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.512927770614624,
|
|
"epoch": 2.323692929746729,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004467038844694227,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.21861641556024553,
|
|
"num_tokens": 46168405.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.525407886505127,
|
|
"epoch": 2.3242545066546865,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004466779357499612,
|
|
"loss": 4.9845,
|
|
"mean_token_accuracy": 0.22031226009130478,
|
|
"num_tokens": 46179907.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.490654182434082,
|
|
"epoch": 2.324816083562644,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044665198156420774,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.214119653403759,
|
|
"num_tokens": 46190750.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.537555742263794,
|
|
"epoch": 2.3253776604706013,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044662602191298856,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.2308503955602646,
|
|
"num_tokens": 46201364.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.508255290985107,
|
|
"epoch": 2.325939237378559,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044660005679713027,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.21568520069122316,
|
|
"num_tokens": 46212341.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.566174173355103,
|
|
"epoch": 2.3265008142865167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044657408621745964,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.2143267035484314,
|
|
"num_tokens": 46223286.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.499310874938965,
|
|
"epoch": 2.327062391194474,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004465481101748036,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.22425410747528077,
|
|
"num_tokens": 46234787.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.533263206481934,
|
|
"epoch": 2.3276239681024316,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044652212866998914,
|
|
"loss": 4.9467,
|
|
"mean_token_accuracy": 0.22225574404001236,
|
|
"num_tokens": 46244845.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.61723051071167,
|
|
"epoch": 2.328185545010389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044649614170384354,
|
|
"loss": 5.058,
|
|
"mean_token_accuracy": 0.22068160623311997,
|
|
"num_tokens": 46256352.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.682117033004761,
|
|
"epoch": 2.328747121918347,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044647014927719436,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.2119855761528015,
|
|
"num_tokens": 46268535.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.535168600082398,
|
|
"epoch": 2.329308698826304,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044644415139086913,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.2223013386130333,
|
|
"num_tokens": 46279164.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.469265508651733,
|
|
"epoch": 2.3298702757342618,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004464181480456955,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.22368853092193602,
|
|
"num_tokens": 46289379.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.509193754196167,
|
|
"epoch": 2.3304318526422194,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004463921392425017,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.22223075330257416,
|
|
"num_tokens": 46301023.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.558109951019287,
|
|
"epoch": 2.330993429550177,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044636612498211566,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.22255484163761138,
|
|
"num_tokens": 46312043.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.468018531799316,
|
|
"epoch": 2.3315550064581343,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044634010526536575,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.2155832827091217,
|
|
"num_tokens": 46322808.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.576207971572876,
|
|
"epoch": 2.332116583366092,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004463140800930804,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20521378070116042,
|
|
"num_tokens": 46334260.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.5808446407318115,
|
|
"epoch": 2.3326781602740496,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004462880494660883,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.21980176419019698,
|
|
"num_tokens": 46344245.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.539191436767578,
|
|
"epoch": 2.333239737182007,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044626201338521834,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.2218586966395378,
|
|
"num_tokens": 46356105.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.418151569366455,
|
|
"epoch": 2.3338013140899645,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004462359718512993,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.2185337781906128,
|
|
"num_tokens": 46367591.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.5117100238800045,
|
|
"epoch": 2.334362890997922,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044620992486516073,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.21553033590316772,
|
|
"num_tokens": 46379022.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.542354440689087,
|
|
"epoch": 2.33492446790588,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004461838724276316,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.22576306760311127,
|
|
"num_tokens": 46390988.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.561664581298828,
|
|
"epoch": 2.3354860448138375,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044615781453954164,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.21842907965183259,
|
|
"num_tokens": 46401576.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.5287188529968265,
|
|
"epoch": 2.3360476217217947,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044613175120172035,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.22184418588876725,
|
|
"num_tokens": 46413114.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.457331752777099,
|
|
"epoch": 2.3366091986297524,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004461056824149979,
|
|
"loss": 4.9477,
|
|
"mean_token_accuracy": 0.22346831113100052,
|
|
"num_tokens": 46424000.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.540341711044311,
|
|
"epoch": 2.33717077553771,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000446079608180204,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.21912174820899963,
|
|
"num_tokens": 46435392.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.476442670822143,
|
|
"epoch": 2.3377323524456672,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004460535284981692,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.21940801292657852,
|
|
"num_tokens": 46445876.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.563913631439209,
|
|
"epoch": 2.338293929353625,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004460274433697235,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.21508759111166,
|
|
"num_tokens": 46457175.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.554486846923828,
|
|
"epoch": 2.3388555062615826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044600135279569784,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.21287397891283036,
|
|
"num_tokens": 46469100.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.50645956993103,
|
|
"epoch": 2.3394170831695402,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044597525677692273,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.22102191001176835,
|
|
"num_tokens": 46481221.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.505612373352051,
|
|
"epoch": 2.3399786600774974,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004459491553142291,
|
|
"loss": 4.9117,
|
|
"mean_token_accuracy": 0.22773180305957794,
|
|
"num_tokens": 46492127.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.516548585891724,
|
|
"epoch": 2.340540236985455,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044592304840844813,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.2095094859600067,
|
|
"num_tokens": 46502880.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.525478887557983,
|
|
"epoch": 2.3411018138934128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000445896936060411,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.22582859694957733,
|
|
"num_tokens": 46513483.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.510151672363281,
|
|
"epoch": 2.3416633908013704,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00044587081827094906,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.2125553920865059,
|
|
"num_tokens": 46526110.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.523391151428223,
|
|
"epoch": 2.3422249677093276,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044584469504089407,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.21782024204730988,
|
|
"num_tokens": 46537832.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.48155779838562,
|
|
"epoch": 2.3427865446172853,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004458185663710777,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.2249519094824791,
|
|
"num_tokens": 46548553.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.584843254089355,
|
|
"epoch": 2.343348121525243,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004457924322623319,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.21825903952121734,
|
|
"num_tokens": 46561095.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.605892562866211,
|
|
"epoch": 2.3439096984332,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044576629271548884,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.21364571750164033,
|
|
"num_tokens": 46572070.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.655474424362183,
|
|
"epoch": 2.344471275341158,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004457401477313808,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.21250015050172805,
|
|
"num_tokens": 46583355.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.514513778686523,
|
|
"epoch": 2.3450328522491155,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004457139973108403,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.21413569003343583,
|
|
"num_tokens": 46594909.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.585882472991943,
|
|
"epoch": 2.345594429157073,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004456878414546998,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.21822667717933655,
|
|
"num_tokens": 46606245.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.47373480796814,
|
|
"epoch": 2.346156006065031,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044566168016379234,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.21907063871622084,
|
|
"num_tokens": 46617761.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.548121356964112,
|
|
"epoch": 2.346717582972988,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004456355134389507,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.21596354842185975,
|
|
"num_tokens": 46628947.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.504271841049194,
|
|
"epoch": 2.3472791598809457,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044560934128100814,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.22426518946886062,
|
|
"num_tokens": 46640243.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.466760921478271,
|
|
"epoch": 2.3478407367889034,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044558316369079805,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.21311718821525574,
|
|
"num_tokens": 46650328.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.456929397583008,
|
|
"epoch": 2.3484023136968606,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044555698066915385,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.21837738305330276,
|
|
"num_tokens": 46661770.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.493517303466797,
|
|
"epoch": 2.3489638906048182,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004455307922169092,
|
|
"loss": 4.9023,
|
|
"mean_token_accuracy": 0.2245308429002762,
|
|
"num_tokens": 46673075.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.51312026977539,
|
|
"epoch": 2.349525467512776,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004455045983348979,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.2141401767730713,
|
|
"num_tokens": 46684040.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.477806138992309,
|
|
"epoch": 2.3500870444207336,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004454783990239542,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.2233012482523918,
|
|
"num_tokens": 46696295.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.508745241165161,
|
|
"epoch": 2.350648621328691,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044545219428491215,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.2180852085351944,
|
|
"num_tokens": 46706399.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.550852251052857,
|
|
"epoch": 2.3512101982366485,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044542598411860605,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.20973829478025435,
|
|
"num_tokens": 46717644.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.640656900405884,
|
|
"epoch": 2.351771775144606,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004453997685258706,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.21761452704668044,
|
|
"num_tokens": 46728556.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.5633306980133055,
|
|
"epoch": 2.3523333520525638,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044537354750754033,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.2242219030857086,
|
|
"num_tokens": 46739730.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.6105064868927,
|
|
"epoch": 2.352894928960521,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004453473210644503,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.21196858435869217,
|
|
"num_tokens": 46752349.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.567393112182617,
|
|
"epoch": 2.3534565058684787,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004453210891974355,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.2106465592980385,
|
|
"num_tokens": 46763771.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.578017377853394,
|
|
"epoch": 2.3540180827764363,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044529485190733113,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.21654513329267502,
|
|
"num_tokens": 46773371.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.504542350769043,
|
|
"epoch": 2.3545796596843935,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004452686091949727,
|
|
"loss": 4.9512,
|
|
"mean_token_accuracy": 0.2269508421421051,
|
|
"num_tokens": 46784244.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.564288759231568,
|
|
"epoch": 2.355141236592351,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044524236106119563,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.21509712040424347,
|
|
"num_tokens": 46795373.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.606797218322754,
|
|
"epoch": 2.355702813500309,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044521610750683586,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.21652642041444778,
|
|
"num_tokens": 46806342.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.50761923789978,
|
|
"epoch": 2.3562643904082665,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004451898485327291,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.22316181808710098,
|
|
"num_tokens": 46817576.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.488369369506836,
|
|
"epoch": 2.356825967316224,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004451635841397116,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.2095343738794327,
|
|
"num_tokens": 46829335.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.564660596847534,
|
|
"epoch": 2.3573875442241814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004451373143286195,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.2060445711016655,
|
|
"num_tokens": 46841334.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.678617334365844,
|
|
"epoch": 2.357949121132139,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044511103910028945,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.2142688125371933,
|
|
"num_tokens": 46852418.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.6049919605255125,
|
|
"epoch": 2.3585106980400967,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004450847584555579,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.21077946275472642,
|
|
"num_tokens": 46863743.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.3585106980400967,
|
|
"eval_entropy": 5.3166733623196665,
|
|
"eval_loss": 5.131991863250732,
|
|
"eval_mean_token_accuracy": 0.21956673764155518,
|
|
"eval_num_tokens": 46863743.0,
|
|
"eval_runtime": 18.5819,
|
|
"eval_samples_per_second": 1668.992,
|
|
"eval_steps_per_second": 208.644,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.4728480815887455,
|
|
"epoch": 2.359072274948054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004450584723952617,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.21824610233306885,
|
|
"num_tokens": 46873628.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.598611831665039,
|
|
"epoch": 2.3596338518560116,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004450321809202377,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.2090076506137848,
|
|
"num_tokens": 46885288.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.553132009506226,
|
|
"epoch": 2.3601954287639693,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004450058840313232,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.21838182657957078,
|
|
"num_tokens": 46897027.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.502333784103394,
|
|
"epoch": 2.360757005671927,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044497958172935536,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.21915906965732573,
|
|
"num_tokens": 46907947.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.543885564804077,
|
|
"epoch": 2.361318582579884,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004449532740151717,
|
|
"loss": 5.0117,
|
|
"mean_token_accuracy": 0.218700835108757,
|
|
"num_tokens": 46918334.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.568187665939331,
|
|
"epoch": 2.361880159487842,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044492696088960985,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.2186417505145073,
|
|
"num_tokens": 46929710.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.526036214828491,
|
|
"epoch": 2.3624417363957995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004449006423535078,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.21543170958757402,
|
|
"num_tokens": 46941436.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.582082605361938,
|
|
"epoch": 2.363003313303757,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044487431840770325,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.21554837077856065,
|
|
"num_tokens": 46953673.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.463430976867675,
|
|
"epoch": 2.3635648902117143,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004448479890530347,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.22241419702768325,
|
|
"num_tokens": 46964412.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.484968566894532,
|
|
"epoch": 2.364126467119672,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044482165429034014,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.2218212902545929,
|
|
"num_tokens": 46975159.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.583731603622437,
|
|
"epoch": 2.3646880440276297,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004447953141204583,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.22347479462623596,
|
|
"num_tokens": 46987165.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.579173994064331,
|
|
"epoch": 2.365249620935587,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00044476896854422785,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.2072166234254837,
|
|
"num_tokens": 46999085.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.5533280849456785,
|
|
"epoch": 2.3658111978435445,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044474261756248745,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.21731692105531691,
|
|
"num_tokens": 47010970.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.576776123046875,
|
|
"epoch": 2.366372774751502,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004447162611760764,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.2213668033480644,
|
|
"num_tokens": 47021396.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.605957555770874,
|
|
"epoch": 2.36693435165946,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004446898993858338,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.21626168340444565,
|
|
"num_tokens": 47033394.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.536564302444458,
|
|
"epoch": 2.3674959285674175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044466353219259884,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.22113928496837615,
|
|
"num_tokens": 47044688.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.6322047233581545,
|
|
"epoch": 2.3680575054753747,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004446371595972114,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.21079250127077104,
|
|
"num_tokens": 47057483.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.554962587356568,
|
|
"epoch": 2.3686190823833324,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004446107816005109,
|
|
"loss": 4.9842,
|
|
"mean_token_accuracy": 0.22407871186733247,
|
|
"num_tokens": 47069031.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.525474405288696,
|
|
"epoch": 2.36918065929129,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004445843982033373,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.22153315246105193,
|
|
"num_tokens": 47080998.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.52097716331482,
|
|
"epoch": 2.3697422361992473,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004445580094065307,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.22196343243122102,
|
|
"num_tokens": 47092065.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.582538080215454,
|
|
"epoch": 2.370303813107205,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004445316152109313,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.21102612912654878,
|
|
"num_tokens": 47102207.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.536190748214722,
|
|
"epoch": 2.3708653900151626,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004445052156173796,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.22026729434728623,
|
|
"num_tokens": 47112675.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.606038808822632,
|
|
"epoch": 2.3714269669231203,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004444788106267161,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.21976112872362136,
|
|
"num_tokens": 47123728.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.537401437759399,
|
|
"epoch": 2.3719885438310775,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004444524002397815,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.21252533793449402,
|
|
"num_tokens": 47136194.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.471619176864624,
|
|
"epoch": 2.372550120739035,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004444259844574167,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.2197939619421959,
|
|
"num_tokens": 47146539.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.567715501785278,
|
|
"epoch": 2.373111697646993,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00044439956328046296,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.21612254977226258,
|
|
"num_tokens": 47158449.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.510401964187622,
|
|
"epoch": 2.3736732745549505,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004443731367097613,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.22437176555395127,
|
|
"num_tokens": 47169687.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.430793571472168,
|
|
"epoch": 2.3742348514629077,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044434670474615334,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.22807710766792297,
|
|
"num_tokens": 47179731.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.493332433700561,
|
|
"epoch": 2.3747964283708654,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044432026739048064,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.2270285189151764,
|
|
"num_tokens": 47189925.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.567548370361328,
|
|
"epoch": 2.375358005278823,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000444293824643585,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.22151532620191575,
|
|
"num_tokens": 47200637.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.512475919723511,
|
|
"epoch": 2.3759195821867802,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004442673765063082,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.21778585910797119,
|
|
"num_tokens": 47211969.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.605420351028442,
|
|
"epoch": 2.376481159094738,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004442409229794925,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.21636663526296615,
|
|
"num_tokens": 47223150.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.6364130020141605,
|
|
"epoch": 2.3770427360026956,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004442144640639803,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.21018742471933366,
|
|
"num_tokens": 47234403.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.532219266891479,
|
|
"epoch": 2.377604312910653,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004441879997606138,
|
|
"loss": 4.9306,
|
|
"mean_token_accuracy": 0.2197708711028099,
|
|
"num_tokens": 47245800.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.5563239574432375,
|
|
"epoch": 2.378165889818611,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004441615300702358,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.21223142743110657,
|
|
"num_tokens": 47256109.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.508763647079467,
|
|
"epoch": 2.378727466726568,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004441350549936891,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.2254544600844383,
|
|
"num_tokens": 47266502.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.528665065765381,
|
|
"epoch": 2.3792890436345258,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004441085745318167,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.22253066599369048,
|
|
"num_tokens": 47278866.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.467287206649781,
|
|
"epoch": 2.3798506205424834,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044408208868546164,
|
|
"loss": 4.9691,
|
|
"mean_token_accuracy": 0.22652524411678315,
|
|
"num_tokens": 47289449.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.538730144500732,
|
|
"epoch": 2.3804121974504406,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004440555974554673,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.2176616981625557,
|
|
"num_tokens": 47301026.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.500134897232056,
|
|
"epoch": 2.3809737743583983,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044402910084267717,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.2230215400457382,
|
|
"num_tokens": 47311579.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.487149047851562,
|
|
"epoch": 2.381535351266356,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004440025988479349,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.21949464380741118,
|
|
"num_tokens": 47322042.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.55103759765625,
|
|
"epoch": 2.3820969281743136,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044397609147208436,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.22424824833869933,
|
|
"num_tokens": 47332821.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.553441286087036,
|
|
"epoch": 2.382658505082271,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004439495787159695,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.21495494544506072,
|
|
"num_tokens": 47344221.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.644854259490967,
|
|
"epoch": 2.3832200819902285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044392306058043453,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.21249861270189285,
|
|
"num_tokens": 47356424.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.546060276031494,
|
|
"epoch": 2.383781658898186,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004438965370663238,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.22182333171367646,
|
|
"num_tokens": 47367546.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.53392333984375,
|
|
"epoch": 2.384343235806144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004438700081744819,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.21625693291425704,
|
|
"num_tokens": 47378281.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.531422472000122,
|
|
"epoch": 2.384904812714101,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044384347390575337,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.22529904991388322,
|
|
"num_tokens": 47389233.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.56420407295227,
|
|
"epoch": 2.3854663896220587,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004438169342609831,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.21440814137458802,
|
|
"num_tokens": 47400114.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.636613845825195,
|
|
"epoch": 2.3860279665300164,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044379038924101627,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.21235498785972595,
|
|
"num_tokens": 47411926.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.620705080032349,
|
|
"epoch": 2.3865895434379736,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004437638388466979,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.2215423807501793,
|
|
"num_tokens": 47424048.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.509614562988281,
|
|
"epoch": 2.3871511203459312,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044373728307887353,
|
|
"loss": 4.9507,
|
|
"mean_token_accuracy": 0.21731945425271987,
|
|
"num_tokens": 47435581.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.545500802993774,
|
|
"epoch": 2.387712697253889,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044371072193838857,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.2206958204507828,
|
|
"num_tokens": 47446831.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.479527187347412,
|
|
"epoch": 2.3882742741618466,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044368415542608874,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.21873867213726045,
|
|
"num_tokens": 47457885.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.5722157001495365,
|
|
"epoch": 2.3888358510698042,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044365758354282005,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.20905736088752747,
|
|
"num_tokens": 47470195.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.532298851013183,
|
|
"epoch": 2.3893974279777614,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004436310062894285,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.22669369876384735,
|
|
"num_tokens": 47481068.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.55592679977417,
|
|
"epoch": 2.389959004885719,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004436044236667603,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.21809228062629699,
|
|
"num_tokens": 47491409.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.485490226745606,
|
|
"epoch": 2.3905205817936768,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004435778356756618,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.21737013459205629,
|
|
"num_tokens": 47504440.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.475134563446045,
|
|
"epoch": 2.391082158701634,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044355124231697967,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.2245649740099907,
|
|
"num_tokens": 47514370.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.558094120025634,
|
|
"epoch": 2.3916437356095916,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004435246435915607,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.22359588891267776,
|
|
"num_tokens": 47525415.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.543868827819824,
|
|
"epoch": 2.3922053125175493,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004434980395002516,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.21471719443798065,
|
|
"num_tokens": 47537029.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.534880495071411,
|
|
"epoch": 2.392766889425507,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044347143004389955,
|
|
"loss": 4.9579,
|
|
"mean_token_accuracy": 0.22084744274616241,
|
|
"num_tokens": 47550434.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.537044525146484,
|
|
"epoch": 2.393328466333464,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004434448152233519,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.22140496969223022,
|
|
"num_tokens": 47560985.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.558386707305909,
|
|
"epoch": 2.393890043241422,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044341819503945594,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.21408640444278718,
|
|
"num_tokens": 47573207.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.499228477478027,
|
|
"epoch": 2.3944516201493795,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004433915694930594,
|
|
"loss": 4.8862,
|
|
"mean_token_accuracy": 0.2303827792406082,
|
|
"num_tokens": 47584666.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.522370481491089,
|
|
"epoch": 2.395013197057337,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004433649385850099,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.21960343420505524,
|
|
"num_tokens": 47598017.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.574892520904541,
|
|
"epoch": 2.3955747739652944,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004433383023161555,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.21126142293214797,
|
|
"num_tokens": 47610947.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.583188009262085,
|
|
"epoch": 2.396136350873252,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004433116606873443,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.20785511732101442,
|
|
"num_tokens": 47621393.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.614343357086182,
|
|
"epoch": 2.3966979277812097,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044328501369942454,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.22038678377866744,
|
|
"num_tokens": 47631615.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.506833028793335,
|
|
"epoch": 2.3972595046891674,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004432583613532446,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.21784006506204606,
|
|
"num_tokens": 47642813.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.686253595352173,
|
|
"epoch": 2.3978210815971246,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004432317036496533,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.21547501683235168,
|
|
"num_tokens": 47654012.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.570473480224609,
|
|
"epoch": 2.3983826585050823,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044320504058949916,
|
|
"loss": 4.9791,
|
|
"mean_token_accuracy": 0.22401940375566481,
|
|
"num_tokens": 47664575.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.528356218338013,
|
|
"epoch": 2.39894423541304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004431783721736314,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.21862082034349442,
|
|
"num_tokens": 47674763.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.54105224609375,
|
|
"epoch": 2.3995058123209976,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044315169840289896,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.2239442989230156,
|
|
"num_tokens": 47685435.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.65291576385498,
|
|
"epoch": 2.400067389228955,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004431250192781513,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.2086026430130005,
|
|
"num_tokens": 47696634.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.534938955307007,
|
|
"epoch": 2.4006289661369125,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004430983348002378,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.21125895231962205,
|
|
"num_tokens": 47707737.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.6109498023986815,
|
|
"epoch": 2.40119054304487,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044307164497000813,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.2127512902021408,
|
|
"num_tokens": 47718131.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.550649261474609,
|
|
"epoch": 2.4017521199528273,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044304494978831204,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.22766806334257125,
|
|
"num_tokens": 47730154.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.563055562973022,
|
|
"epoch": 2.402313696860785,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004430182492559997,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.22248117327690126,
|
|
"num_tokens": 47741893.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.538036823272705,
|
|
"epoch": 2.4028752737687427,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000442991543373921,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.2171744078397751,
|
|
"num_tokens": 47753430.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.478328132629395,
|
|
"epoch": 2.4034368506767003,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004429648321429264,
|
|
"loss": 4.9639,
|
|
"mean_token_accuracy": 0.22029848992824555,
|
|
"num_tokens": 47765181.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.6415657043457035,
|
|
"epoch": 2.4039984275846575,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044293811556386656,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.20478303283452987,
|
|
"num_tokens": 47777211.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.540760278701782,
|
|
"epoch": 2.404560004492615,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004429113936375918,
|
|
"loss": 4.9952,
|
|
"mean_token_accuracy": 0.21467284858226776,
|
|
"num_tokens": 47788397.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.5890221118927,
|
|
"epoch": 2.405121581400573,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044288466636495323,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.21137916892766953,
|
|
"num_tokens": 47799870.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.578742408752442,
|
|
"epoch": 2.4056831583085305,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044285793374680184,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.21733465939760208,
|
|
"num_tokens": 47810696.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.58861608505249,
|
|
"epoch": 2.4062447352164877,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044283119578398866,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.21868714839220046,
|
|
"num_tokens": 47822579.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.539154767990112,
|
|
"epoch": 2.4068063121244454,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004428044524773651,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.22023066580295564,
|
|
"num_tokens": 47832556.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.533116483688355,
|
|
"epoch": 2.407367889032403,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004427777038277827,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.2165318861603737,
|
|
"num_tokens": 47844409.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.51745834350586,
|
|
"epoch": 2.4079294659403607,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044275094983609313,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.2169476941227913,
|
|
"num_tokens": 47855666.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.50396146774292,
|
|
"epoch": 2.408491042848318,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044272419050314833,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.2245641440153122,
|
|
"num_tokens": 47866261.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.553881502151489,
|
|
"epoch": 2.4090526197562756,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044269742582980017,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.2113230973482132,
|
|
"num_tokens": 47878807.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.523854494094849,
|
|
"epoch": 2.4096141966642333,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000442670655816901,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.22196708917617797,
|
|
"num_tokens": 47888935.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.5782805442810055,
|
|
"epoch": 2.410175773572191,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044264388046530304,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.22110257744789125,
|
|
"num_tokens": 47900208.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.65871000289917,
|
|
"epoch": 2.410737350480148,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044261709977585893,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.21914397180080414,
|
|
"num_tokens": 47911131.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.56216721534729,
|
|
"epoch": 2.411298927388106,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004425903137494214,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.21117253303527833,
|
|
"num_tokens": 47922601.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.585661697387695,
|
|
"epoch": 2.4118605042960635,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004425635223868433,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.2183883383870125,
|
|
"num_tokens": 47933168.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.6203748226165775,
|
|
"epoch": 2.4124220812040207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044253672568897754,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.21017939895391463,
|
|
"num_tokens": 47945433.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.57526798248291,
|
|
"epoch": 2.4129836581119783,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004425099236566775,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.21204110980033875,
|
|
"num_tokens": 47957513.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.581760454177856,
|
|
"epoch": 2.413545235019936,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044248311629079657,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.21493119448423387,
|
|
"num_tokens": 47968817.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.608366775512695,
|
|
"epoch": 2.4141068119278937,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004424563035921882,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.22265514135360717,
|
|
"num_tokens": 47979034.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.557721424102783,
|
|
"epoch": 2.414668388835851,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044242948556170634,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.22396552115678786,
|
|
"num_tokens": 47990459.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.525624132156372,
|
|
"epoch": 2.4152299657438085,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044240266220020455,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.21501077860593795,
|
|
"num_tokens": 48000007.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.587209749221802,
|
|
"epoch": 2.415791542651766,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004423758335085371,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.21573759913444518,
|
|
"num_tokens": 48012962.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.537960529327393,
|
|
"epoch": 2.416353119559724,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044234899948755827,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.2154301255941391,
|
|
"num_tokens": 48025916.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.55776047706604,
|
|
"epoch": 2.416914696467681,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044232216013812226,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.2181413382291794,
|
|
"num_tokens": 48036255.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.566539144515991,
|
|
"epoch": 2.4174762733756388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004422953154610838,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.21872445791959763,
|
|
"num_tokens": 48045943.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.460733795166016,
|
|
"epoch": 2.4180378502835964,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004422684654572977,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.22571712285280227,
|
|
"num_tokens": 48056562.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.482293653488159,
|
|
"epoch": 2.418599427191554,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044224161012761874,
|
|
"loss": 4.9579,
|
|
"mean_token_accuracy": 0.21984348744153975,
|
|
"num_tokens": 48066997.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.570831441879273,
|
|
"epoch": 2.4191610040995113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044221474947290205,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.21072416603565217,
|
|
"num_tokens": 48077810.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.617544507980346,
|
|
"epoch": 2.419722581007469,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004421878834940029,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.21212470829486846,
|
|
"num_tokens": 48089422.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.538281679153442,
|
|
"epoch": 2.4202841579154266,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044216101219177667,
|
|
"loss": 4.9771,
|
|
"mean_token_accuracy": 0.21962557286024093,
|
|
"num_tokens": 48101114.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.555485200881958,
|
|
"epoch": 2.4208457348233843,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00044213413556707905,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.22382844239473343,
|
|
"num_tokens": 48110991.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.581249475479126,
|
|
"epoch": 2.4214073117313415,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004421072536207656,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.22342467904090882,
|
|
"num_tokens": 48122889.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.576379728317261,
|
|
"epoch": 2.421968888639299,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044208036635369247,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.21833214312791824,
|
|
"num_tokens": 48133586.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.50508713722229,
|
|
"epoch": 2.422530465547257,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004420534737667157,
|
|
"loss": 4.9644,
|
|
"mean_token_accuracy": 0.21910459846258162,
|
|
"num_tokens": 48144060.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.596248626708984,
|
|
"epoch": 2.423092042455214,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044202657586069153,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.22828783392906188,
|
|
"num_tokens": 48155197.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.611389112472534,
|
|
"epoch": 2.4236536193631717,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044199967263647635,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.21336980313062667,
|
|
"num_tokens": 48166990.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.627614736557007,
|
|
"epoch": 2.4242151962711294,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004419727640949268,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.21566355973482132,
|
|
"num_tokens": 48179454.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.494405269622803,
|
|
"epoch": 2.424776773179087,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004419458502368998,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.2219840332865715,
|
|
"num_tokens": 48192009.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.638784122467041,
|
|
"epoch": 2.4253383500870442,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044191893106325207,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.22114750891923904,
|
|
"num_tokens": 48203111.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.6737504482269285,
|
|
"epoch": 2.425899926995002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004418920065748409,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.21085852533578872,
|
|
"num_tokens": 48214766.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.634136915206909,
|
|
"epoch": 2.4264615039029596,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044186507677252345,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.2217051312327385,
|
|
"num_tokens": 48225061.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.499004793167114,
|
|
"epoch": 2.427023080810917,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004418381416571573,
|
|
"loss": 5.0047,
|
|
"mean_token_accuracy": 0.2182027205824852,
|
|
"num_tokens": 48236101.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.4880900382995605,
|
|
"epoch": 2.4275846577188744,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004418112012296,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.21299759149551392,
|
|
"num_tokens": 48248080.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.512613296508789,
|
|
"epoch": 2.428146234626832,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044178425549070934,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.2208130031824112,
|
|
"num_tokens": 48259177.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.57832670211792,
|
|
"epoch": 2.4287078115347898,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044175730444134326,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.21438329368829728,
|
|
"num_tokens": 48271345.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.577656030654907,
|
|
"epoch": 2.4292693884427474,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00044173034808236,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.21250309348106383,
|
|
"num_tokens": 48284219.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.525196170806884,
|
|
"epoch": 2.4298309653507046,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004417033864146177,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.22022714465856552,
|
|
"num_tokens": 48294626.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.472654199600219,
|
|
"epoch": 2.4303925422586623,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004416764194389751,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.21753796935081482,
|
|
"num_tokens": 48305459.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.545045804977417,
|
|
"epoch": 2.43095411916662,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004416494471562904,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.22274929881095887,
|
|
"num_tokens": 48316232.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.5385518074035645,
|
|
"epoch": 2.4315156960745776,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004416224695674229,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.22060710191726685,
|
|
"num_tokens": 48326711.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.420708703994751,
|
|
"epoch": 2.432077272982535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044159548667323126,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.23928916305303574,
|
|
"num_tokens": 48336860.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.477707147598267,
|
|
"epoch": 2.4326388498904925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004415684984745747,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.21514454931020738,
|
|
"num_tokens": 48348503.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.547321939468384,
|
|
"epoch": 2.43320042679845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004415415049723126,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.21506629288196563,
|
|
"num_tokens": 48359855.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.6125835418701175,
|
|
"epoch": 2.4337620037064074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004415145061673043,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.210033643245697,
|
|
"num_tokens": 48370188.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.532767200469971,
|
|
"epoch": 2.434323580614365,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004414875020604096,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.22840873301029205,
|
|
"num_tokens": 48381152.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.564709138870239,
|
|
"epoch": 2.4348851575223227,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004414604926524882,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.2180789142847061,
|
|
"num_tokens": 48392721.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.527380275726318,
|
|
"epoch": 2.4354467344302804,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004414334779444002,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.21445666402578353,
|
|
"num_tokens": 48404071.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.5229894638061525,
|
|
"epoch": 2.4360083113382376,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044140645793700573,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.20909805744886398,
|
|
"num_tokens": 48416001.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.586248588562012,
|
|
"epoch": 2.4365698882461952,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044137943263116515,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.2170616164803505,
|
|
"num_tokens": 48426880.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.63801121711731,
|
|
"epoch": 2.437131465154153,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004413524020277388,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.21015704870224,
|
|
"num_tokens": 48437147.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.483623886108399,
|
|
"epoch": 2.4376930420621106,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004413253661275875,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.22001013904809952,
|
|
"num_tokens": 48448706.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.496730518341065,
|
|
"epoch": 2.438254618970068,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044129832493157195,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.22480074018239976,
|
|
"num_tokens": 48458873.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.531637573242188,
|
|
"epoch": 2.4388161958780255,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044127127844055335,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.20750064700841903,
|
|
"num_tokens": 48470726.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.532631254196167,
|
|
"epoch": 2.439377772785983,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044124422665539273,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.22326111942529678,
|
|
"num_tokens": 48481912.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.612228918075561,
|
|
"epoch": 2.4399393496939408,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004412171695769515,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.218583445250988,
|
|
"num_tokens": 48492048.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.5597230911254885,
|
|
"epoch": 2.440500926601898,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044119010720609106,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.2209845617413521,
|
|
"num_tokens": 48503190.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.528622722625732,
|
|
"epoch": 2.4410625035098557,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044116303954367314,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.21656447798013687,
|
|
"num_tokens": 48514956.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.649858808517456,
|
|
"epoch": 2.4416240804178133,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004411359665905596,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.21510460376739501,
|
|
"num_tokens": 48526372.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.496010208129883,
|
|
"epoch": 2.442185657325771,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004411088883476125,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.2186761811375618,
|
|
"num_tokens": 48536985.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.521020984649658,
|
|
"epoch": 2.442747234233728,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044108180481569387,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.21845337897539138,
|
|
"num_tokens": 48547505.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.565737867355347,
|
|
"epoch": 2.443308811141686,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044105471599566626,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.21395977288484574,
|
|
"num_tokens": 48560104.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.609021902084351,
|
|
"epoch": 2.4438703880496435,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000441027621888392,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.21737373173236846,
|
|
"num_tokens": 48571203.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.510542392730713,
|
|
"epoch": 2.4444319649576007,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044100052249473393,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.2212828665971756,
|
|
"num_tokens": 48581480.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.540644645690918,
|
|
"epoch": 2.4449935418655584,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004409734178155548,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.2169008657336235,
|
|
"num_tokens": 48592811.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.564657592773438,
|
|
"epoch": 2.445555118773516,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004409463078517178,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.21815027743577958,
|
|
"num_tokens": 48604245.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.584132099151612,
|
|
"epoch": 2.4461166956814737,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044091919260408585,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.22108221799135208,
|
|
"num_tokens": 48615138.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.551406145095825,
|
|
"epoch": 2.446678272589431,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004408920720735225,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.21967096924781798,
|
|
"num_tokens": 48626084.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.528099918365479,
|
|
"epoch": 2.4472398494973886,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044086494626089127,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.21757079064846038,
|
|
"num_tokens": 48636425.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.516553497314453,
|
|
"epoch": 2.4478014264053463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004408378151670558,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.20788152813911437,
|
|
"num_tokens": 48646941.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.505242347717285,
|
|
"epoch": 2.448363003313304,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044081067879288,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.22717584371566774,
|
|
"num_tokens": 48657481.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.5824682235717775,
|
|
"epoch": 2.448924580221261,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004407835371392279,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.21673261672258376,
|
|
"num_tokens": 48669306.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.544094800949097,
|
|
"epoch": 2.449486157129219,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004407563902069636,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.21935464739799498,
|
|
"num_tokens": 48680789.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.590310525894165,
|
|
"epoch": 2.4500477340371765,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004407292379969515,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.21687455326318741,
|
|
"num_tokens": 48691811.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.523129987716675,
|
|
"epoch": 2.450609310945134,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004407020805100563,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.21733230352401733,
|
|
"num_tokens": 48704248.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.52667875289917,
|
|
"epoch": 2.4511708878530913,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004406749177471425,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.22431591898202896,
|
|
"num_tokens": 48714452.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.53293137550354,
|
|
"epoch": 2.451732464761049,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044064774970907516,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.22213433682918549,
|
|
"num_tokens": 48725481.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.626071166992188,
|
|
"epoch": 2.4522940416690067,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004406205763967193,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.21781390607357026,
|
|
"num_tokens": 48737704.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.5852419376373295,
|
|
"epoch": 2.4528556185769643,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004405933978109398,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.21960025727748872,
|
|
"num_tokens": 48749085.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.608274364471436,
|
|
"epoch": 2.4534171954849215,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044056621395260247,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.21499208211898804,
|
|
"num_tokens": 48759432.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.496075296401978,
|
|
"epoch": 2.453978772392879,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044053902482257265,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.21560271680355073,
|
|
"num_tokens": 48769549.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.541296148300171,
|
|
"epoch": 2.454540349300837,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000440511830421716,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.21933341324329375,
|
|
"num_tokens": 48779630.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.600342226028443,
|
|
"epoch": 2.455101926208794,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004404846307508985,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.20777858644723893,
|
|
"num_tokens": 48790489.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.588201379776001,
|
|
"epoch": 2.4556635031167517,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044045742581098624,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.21592924147844314,
|
|
"num_tokens": 48802310.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.5604307651519775,
|
|
"epoch": 2.4562250800247094,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004404302156028453,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.22283110320568084,
|
|
"num_tokens": 48812066.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.622838973999023,
|
|
"epoch": 2.456786656932667,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044040300012734217,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.20811059921979905,
|
|
"num_tokens": 48824477.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.624714708328247,
|
|
"epoch": 2.4573482338406243,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004403757793853434,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21320931613445282,
|
|
"num_tokens": 48835147.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.577275609970092,
|
|
"epoch": 2.457909810748582,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004403485533777157,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.21253500878810883,
|
|
"num_tokens": 48846147.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.64364104270935,
|
|
"epoch": 2.4584713876565396,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004403213221053258,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.2115405887365341,
|
|
"num_tokens": 48857340.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.494124460220337,
|
|
"epoch": 2.4590329645644973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044029408556904093,
|
|
"loss": 4.968,
|
|
"mean_token_accuracy": 0.22081013172864913,
|
|
"num_tokens": 48868256.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.64057297706604,
|
|
"epoch": 2.4595945414724545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004402668437697283,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.2166883260011673,
|
|
"num_tokens": 48879346.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.595098257064819,
|
|
"epoch": 2.460156118380412,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044023959670825533,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20959613025188445,
|
|
"num_tokens": 48890939.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.574087381362915,
|
|
"epoch": 2.46071769528837,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004402123443854894,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.21610628962516784,
|
|
"num_tokens": 48902239.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.610044860839844,
|
|
"epoch": 2.4612792721963275,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004401850868022984,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.21994209736585618,
|
|
"num_tokens": 48913810.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.529143571853638,
|
|
"epoch": 2.4618408491042847,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004401578239595501,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.22830506414175034,
|
|
"num_tokens": 48925180.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.531625175476075,
|
|
"epoch": 2.4624024260122424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044013055585811274,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.21219455897808076,
|
|
"num_tokens": 48937067.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.559192180633545,
|
|
"epoch": 2.4629640029202,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00044010328249885434,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.21141788959503174,
|
|
"num_tokens": 48949220.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.60499939918518,
|
|
"epoch": 2.4635255798281577,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004400760038826434,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.21444390416145326,
|
|
"num_tokens": 48960604.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.525194549560547,
|
|
"epoch": 2.464087156736115,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044004872001034856,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.2230343773961067,
|
|
"num_tokens": 48970561.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.554807949066162,
|
|
"epoch": 2.4646487336440726,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004400214308828384,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.21347619742155075,
|
|
"num_tokens": 48981639.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.656531906127929,
|
|
"epoch": 2.46521031055203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043999413650098193,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.22002118825912476,
|
|
"num_tokens": 48992872.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.587698650360108,
|
|
"epoch": 2.4657718874599874,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004399668368656481,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.21517400741577147,
|
|
"num_tokens": 49004942.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.591521453857422,
|
|
"epoch": 2.466333464367945,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004399395319777062,
|
|
"loss": 5.0023,
|
|
"mean_token_accuracy": 0.22063588201999665,
|
|
"num_tokens": 49016493.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.590505075454712,
|
|
"epoch": 2.4668950412759028,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043991222183802564,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.22150445729494095,
|
|
"num_tokens": 49027780.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.559435224533081,
|
|
"epoch": 2.4674566181838604,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000439884906447476,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.22187412828207015,
|
|
"num_tokens": 49039441.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.566897916793823,
|
|
"epoch": 2.4680181950918176,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000439857585806927,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.21815994381904602,
|
|
"num_tokens": 49050740.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.5444395542144775,
|
|
"epoch": 2.4685797719997753,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043983025991724847,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.21446375995874406,
|
|
"num_tokens": 49062216.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.527111387252807,
|
|
"epoch": 2.469141348907733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004398029287793106,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.21873943656682968,
|
|
"num_tokens": 49072848.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.503522300720215,
|
|
"epoch": 2.4697029258156906,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043977559239398353,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.22482930421829223,
|
|
"num_tokens": 49083382.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.510613679885864,
|
|
"epoch": 2.470264502723648,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004397482507621376,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.21872042566537858,
|
|
"num_tokens": 49095102.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.512297868728638,
|
|
"epoch": 2.4708260796316055,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004397209038846436,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.21971172839403152,
|
|
"num_tokens": 49105964.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.609533739089966,
|
|
"epoch": 2.471387656539563,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043969355176237207,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.2068828597664833,
|
|
"num_tokens": 49117748.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.501383352279663,
|
|
"epoch": 2.471949233447521,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004396661943961941,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.23048588633537292,
|
|
"num_tokens": 49128217.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.614203071594238,
|
|
"epoch": 2.472510810355478,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004396388317869805,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.21290257424116135,
|
|
"num_tokens": 49139272.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.543610334396362,
|
|
"epoch": 2.4730723872634357,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004396114639356027,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.22074592262506484,
|
|
"num_tokens": 49149570.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.4925768852233885,
|
|
"epoch": 2.4736339641713934,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000439584090842932,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.22601675540208815,
|
|
"num_tokens": 49160892.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.529285621643067,
|
|
"epoch": 2.474195541079351,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043955671250984005,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.21862219721078874,
|
|
"num_tokens": 49172476.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.596521234512329,
|
|
"epoch": 2.4747571179873082,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043952932893719847,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.22164974063634874,
|
|
"num_tokens": 49184052.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.554535436630249,
|
|
"epoch": 2.475318694895266,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004395019401258794,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.21259756982326508,
|
|
"num_tokens": 49195441.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.4694586277008055,
|
|
"epoch": 2.4758802718032236,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043947454607675464,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.22147999405860902,
|
|
"num_tokens": 49206395.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.578408527374267,
|
|
"epoch": 2.476441848711181,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004394471467906966,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.21338238567113876,
|
|
"num_tokens": 49217705.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.532431602478027,
|
|
"epoch": 2.4770034256191384,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043941974226857763,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.22884305119514464,
|
|
"num_tokens": 49228348.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.484765291213989,
|
|
"epoch": 2.477565002527096,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004393923325112702,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.21948070228099822,
|
|
"num_tokens": 49239031.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.5636975288391115,
|
|
"epoch": 2.4781265794350538,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004393649175196472,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.2132587820291519,
|
|
"num_tokens": 49250918.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.54942512512207,
|
|
"epoch": 2.478688156343011,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004393374972945815,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.2149665668606758,
|
|
"num_tokens": 49262305.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.520474147796631,
|
|
"epoch": 2.4792497332509686,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043931007183694616,
|
|
"loss": 4.9795,
|
|
"mean_token_accuracy": 0.20945368260145186,
|
|
"num_tokens": 49273106.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.477083158493042,
|
|
"epoch": 2.4798113101589263,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043928264114761437,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.2266913428902626,
|
|
"num_tokens": 49284519.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.49106616973877,
|
|
"epoch": 2.480372887066884,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043925520522745953,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.21971429735422135,
|
|
"num_tokens": 49295753.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.560405540466308,
|
|
"epoch": 2.480934463974841,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004392277640773553,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.22080116868019103,
|
|
"num_tokens": 49307682.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.534575080871582,
|
|
"epoch": 2.481496040882799,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043920031769817543,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.2165607288479805,
|
|
"num_tokens": 49318445.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.572947597503662,
|
|
"epoch": 2.4820576177907565,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043917286609079364,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.20944633781909944,
|
|
"num_tokens": 49328559.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.502476549148559,
|
|
"epoch": 2.482619194698714,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043914540925608426,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.2146335005760193,
|
|
"num_tokens": 49340177.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.557438802719116,
|
|
"epoch": 2.4831807716066714,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004391179471949213,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.22010257691144944,
|
|
"num_tokens": 49351214.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.581044054031372,
|
|
"epoch": 2.483742348514629,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043909047990817917,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.2191672220826149,
|
|
"num_tokens": 49362697.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.532251214981079,
|
|
"epoch": 2.4843039254225867,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043906300739673265,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.2194495379924774,
|
|
"num_tokens": 49374439.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.490808725357056,
|
|
"epoch": 2.4848655023305444,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043903552966145624,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.22121603041887283,
|
|
"num_tokens": 49385834.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.5248185157775875,
|
|
"epoch": 2.4854270792385016,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000439008046703225,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.2221571609377861,
|
|
"num_tokens": 49396562.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.521615076065063,
|
|
"epoch": 2.4859886561464593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000438980558522914,
|
|
"loss": 5.0019,
|
|
"mean_token_accuracy": 0.21405726820230483,
|
|
"num_tokens": 49407339.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.523251152038574,
|
|
"epoch": 2.486550233054417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004389530651213983,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.2225041553378105,
|
|
"num_tokens": 49419190.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.632202053070069,
|
|
"epoch": 2.487111809962374,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043892556649955354,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.21031025052070618,
|
|
"num_tokens": 49430559.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.614979982376099,
|
|
"epoch": 2.487673386870332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004388980626582551,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.21830309331417083,
|
|
"num_tokens": 49441862.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.52970142364502,
|
|
"epoch": 2.4882349637782895,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004388705535983788,
|
|
"loss": 4.9764,
|
|
"mean_token_accuracy": 0.21657631546258926,
|
|
"num_tokens": 49452839.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.512237882614135,
|
|
"epoch": 2.488796540686247,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004388430393208005,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.2214709758758545,
|
|
"num_tokens": 49463683.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.509510946273804,
|
|
"epoch": 2.4893581175942043,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004388155198263963,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.22519282549619674,
|
|
"num_tokens": 49474338.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.516839647293091,
|
|
"epoch": 2.489919694502162,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004387879951160424,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.21573782712221146,
|
|
"num_tokens": 49485888.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.610842943191528,
|
|
"epoch": 2.4904812714101197,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004387604651906152,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.21722840368747712,
|
|
"num_tokens": 49497270.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.65227165222168,
|
|
"epoch": 2.4910428483180773,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004387329300509913,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.2186945915222168,
|
|
"num_tokens": 49509099.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.528162145614624,
|
|
"epoch": 2.4916044252260345,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043870538969804733,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.21776024848222733,
|
|
"num_tokens": 49520110.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.513113641738892,
|
|
"epoch": 2.492166002133992,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004386778441326603,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.2216125413775444,
|
|
"num_tokens": 49531866.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.6150819778442385,
|
|
"epoch": 2.49272757904195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043865029335570725,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.21143260449171067,
|
|
"num_tokens": 49541022.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.571628475189209,
|
|
"epoch": 2.4932891559499075,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004386227373680655,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.21852485537528993,
|
|
"num_tokens": 49551908.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.570519638061524,
|
|
"epoch": 2.4938507328578647,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004385951761706122,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.22085458189249038,
|
|
"num_tokens": 49562475.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.535388422012329,
|
|
"epoch": 2.4944123097658224,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043856760976422506,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.22296399176120757,
|
|
"num_tokens": 49572916.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.569603109359742,
|
|
"epoch": 2.49497388667378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043854003814978174,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.21793714463710784,
|
|
"num_tokens": 49584584.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.483701419830322,
|
|
"epoch": 2.4955354635817377,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043851246132816025,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.21800120919942856,
|
|
"num_tokens": 49595792.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.56827392578125,
|
|
"epoch": 2.496097040489695,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004384848793002385,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.21930606216192244,
|
|
"num_tokens": 49607596.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.589726161956787,
|
|
"epoch": 2.4966586173976526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004384572920668949,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.21339526623487473,
|
|
"num_tokens": 49617990.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.606682252883911,
|
|
"epoch": 2.4972201943056103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004384296996290076,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.21446574181318284,
|
|
"num_tokens": 49629458.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.620165538787842,
|
|
"epoch": 2.4977817712135675,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043840210198745533,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.21858785301446915,
|
|
"num_tokens": 49641227.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.603103542327881,
|
|
"epoch": 2.498343348121525,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043837449914311676,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.2124900832772255,
|
|
"num_tokens": 49652655.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.5356629371643065,
|
|
"epoch": 2.498904925029483,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043834689109687077,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.226297427713871,
|
|
"num_tokens": 49664308.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.5375062942504885,
|
|
"epoch": 2.4994665019374405,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004383192778495964,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.22276538014411926,
|
|
"num_tokens": 49676656.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.5531103134155275,
|
|
"epoch": 2.500028078845398,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000438291659402173,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.22065746784210205,
|
|
"num_tokens": 49687706.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.549444627761841,
|
|
"epoch": 2.5005896557533553,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043826403575547974,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.228230257332325,
|
|
"num_tokens": 49699139.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.449415826797486,
|
|
"epoch": 2.501151232661313,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004382364069103962,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.22547274231910705,
|
|
"num_tokens": 49710690.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.516870927810669,
|
|
"epoch": 2.5017128095692707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043820877286780224,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.2224861204624176,
|
|
"num_tokens": 49721920.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.644588327407837,
|
|
"epoch": 2.502274386477228,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004381811336285776,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.21752933263778687,
|
|
"num_tokens": 49732923.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.485941982269287,
|
|
"epoch": 2.5028359633851855,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004381534891936024,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.2218482807278633,
|
|
"num_tokens": 49744755.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.516797685623169,
|
|
"epoch": 2.503397540293143,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004381258395637568,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.22104183733463287,
|
|
"num_tokens": 49756126.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.561243724822998,
|
|
"epoch": 2.5039591172011004,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004380981847399212,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.22169766575098038,
|
|
"num_tokens": 49767137.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.580629110336304,
|
|
"epoch": 2.504520694109058,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043807052472297626,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.213550928235054,
|
|
"num_tokens": 49778533.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.558511686325073,
|
|
"epoch": 2.5050822710170157,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004380428595138024,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.21728500723838806,
|
|
"num_tokens": 49789494.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.585780954360962,
|
|
"epoch": 2.5056438479249734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043801518911328074,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.2130770653486252,
|
|
"num_tokens": 49799546.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.491135215759277,
|
|
"epoch": 2.506205424832931,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043798751352229227,
|
|
"loss": 4.9177,
|
|
"mean_token_accuracy": 0.22639229595661164,
|
|
"num_tokens": 49810643.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.544972991943359,
|
|
"epoch": 2.5067670017408883,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043795983274171806,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.21402752846479417,
|
|
"num_tokens": 49821410.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.568447828292847,
|
|
"epoch": 2.507328578648846,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043793214677243967,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.21144392788410188,
|
|
"num_tokens": 49832911.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.5967857360839846,
|
|
"epoch": 2.5078901555568036,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004379044556153384,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.2104638934135437,
|
|
"num_tokens": 49845458.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.602751111984253,
|
|
"epoch": 2.508451732464761,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043787675927129625,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.20578212291002274,
|
|
"num_tokens": 49857054.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.538203525543213,
|
|
"epoch": 2.5090133093727185,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043784905774119483,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.22846937477588652,
|
|
"num_tokens": 49867223.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.480139064788818,
|
|
"epoch": 2.509574886280676,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043782135102591626,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.21960829198360443,
|
|
"num_tokens": 49877801.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.5200807571411135,
|
|
"epoch": 2.510136463188634,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004377936391263427,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.21397198140621185,
|
|
"num_tokens": 49888853.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.562374210357666,
|
|
"epoch": 2.5106980400965915,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043776592204335655,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.21970409154891968,
|
|
"num_tokens": 49899989.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.571646404266358,
|
|
"epoch": 2.5112596170045487,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004377381997778403,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.22355668395757675,
|
|
"num_tokens": 49910993.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.599076843261718,
|
|
"epoch": 2.5118211939125064,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004377104723306767,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.21606664806604386,
|
|
"num_tokens": 49922169.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.557157039642334,
|
|
"epoch": 2.512382770820464,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004376827397027485,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.21607503890991211,
|
|
"num_tokens": 49933700.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.600117588043213,
|
|
"epoch": 2.5129443477284212,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004376550018949388,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.21129627972841264,
|
|
"num_tokens": 49944689.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.623361349105835,
|
|
"epoch": 2.513505924636379,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043762725890813083,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.21341352313756942,
|
|
"num_tokens": 49955818.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.512422180175781,
|
|
"epoch": 2.5140675015443366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004375995107432077,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.22385355234146118,
|
|
"num_tokens": 49965799.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.482568359375,
|
|
"epoch": 2.5146290784522938,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043757175740105316,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.21615416258573533,
|
|
"num_tokens": 49977742.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.552643060684204,
|
|
"epoch": 2.5151906553602514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004375439988825508,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.21579795628786086,
|
|
"num_tokens": 49988382.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.619124031066894,
|
|
"epoch": 2.515752232268209,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004375162351885845,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.21582526415586473,
|
|
"num_tokens": 50000190.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.588004064559937,
|
|
"epoch": 2.5163138091761668,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043748846632003823,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.22305434495210646,
|
|
"num_tokens": 50011297.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.548886013031006,
|
|
"epoch": 2.5168753860841244,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043746069227779615,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.21353503912687302,
|
|
"num_tokens": 50023165.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.610385227203369,
|
|
"epoch": 2.5174369629920816,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004374329130627427,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.22064152508974075,
|
|
"num_tokens": 50035803.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.546672582626343,
|
|
"epoch": 2.5179985399000393,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043740512867576224,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.2225762352347374,
|
|
"num_tokens": 50046599.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.551112031936645,
|
|
"epoch": 2.518560116807997,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004373773391177395,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.21202340573072434,
|
|
"num_tokens": 50058170.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.5490889072418215,
|
|
"epoch": 2.519121693715954,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004373495443895593,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.22706874012947081,
|
|
"num_tokens": 50068818.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.602738380432129,
|
|
"epoch": 2.519683270623912,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004373217444921066,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.21045347303152084,
|
|
"num_tokens": 50080533.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.533481502532959,
|
|
"epoch": 2.5202448475318695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043729393942626665,
|
|
"loss": 4.9691,
|
|
"mean_token_accuracy": 0.21968456953763962,
|
|
"num_tokens": 50090897.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.4530292510986325,
|
|
"epoch": 2.520806424439827,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043726612919292476,
|
|
"loss": 4.9196,
|
|
"mean_token_accuracy": 0.22306486815214158,
|
|
"num_tokens": 50101594.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.484946632385254,
|
|
"epoch": 2.521368001347785,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004372383137929663,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.2150701880455017,
|
|
"num_tokens": 50111923.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.569661951065063,
|
|
"epoch": 2.521929578255742,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043721049322727705,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.22039275169372557,
|
|
"num_tokens": 50123295.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.631639194488526,
|
|
"epoch": 2.5224911551636997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004371826674967428,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.21990682780742646,
|
|
"num_tokens": 50133245.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.5404047012329105,
|
|
"epoch": 2.5230527320716574,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043715483660224943,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.22126765698194503,
|
|
"num_tokens": 50144827.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.5998328685760494,
|
|
"epoch": 2.5236143089796146,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004371270005446833,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.21010244339704515,
|
|
"num_tokens": 50156244.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.607388830184936,
|
|
"epoch": 2.5241758858875722,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004370991593249305,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.21505387723445893,
|
|
"num_tokens": 50168363.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.554862833023071,
|
|
"epoch": 2.52473746279553,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043707131294387766,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.21165186464786528,
|
|
"num_tokens": 50179370.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.615903520584107,
|
|
"epoch": 2.525299039703487,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004370434614024113,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.22814715951681136,
|
|
"num_tokens": 50191583.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.624834680557251,
|
|
"epoch": 2.525860616611445,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043701560470141824,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.21351321935653686,
|
|
"num_tokens": 50202008.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.547494554519654,
|
|
"epoch": 2.5264221935194024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004369877428417856,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.2118916019797325,
|
|
"num_tokens": 50212632.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.537798690795898,
|
|
"epoch": 2.52698377042736,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004369598758244003,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.21973357647657393,
|
|
"num_tokens": 50223485.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.598037624359131,
|
|
"epoch": 2.5275453473353178,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043693200365014985,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.21416622251272202,
|
|
"num_tokens": 50235516.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.579493856430053,
|
|
"epoch": 2.528106924243275,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043690412631992154,
|
|
"loss": 4.9597,
|
|
"mean_token_accuracy": 0.22465383857488633,
|
|
"num_tokens": 50246846.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.543366813659668,
|
|
"epoch": 2.5286685011512327,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043687624383460306,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.20700275748968125,
|
|
"num_tokens": 50258433.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.60135407447815,
|
|
"epoch": 2.5292300780591903,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043684835619508215,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.21539919078350067,
|
|
"num_tokens": 50269111.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.609867238998413,
|
|
"epoch": 2.5297916549671475,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004368204634022469,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.21052510142326356,
|
|
"num_tokens": 50280137.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.615333938598633,
|
|
"epoch": 2.530353231875105,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004367925654569852,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.2235727369785309,
|
|
"num_tokens": 50291717.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.585034132003784,
|
|
"epoch": 2.530914808783063,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004367646623601856,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.21523854434490203,
|
|
"num_tokens": 50303107.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.504936599731446,
|
|
"epoch": 2.5314763856910205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004367367541127364,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.2194744572043419,
|
|
"num_tokens": 50313997.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.578470277786255,
|
|
"epoch": 2.532037962598978,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004367088407155261,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.22309055030345917,
|
|
"num_tokens": 50324327.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.505522203445435,
|
|
"epoch": 2.5325995395069354,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004366809221694437,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.22796305269002914,
|
|
"num_tokens": 50334787.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.490261125564575,
|
|
"epoch": 2.533161116414893,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043665299847537805,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.22689362317323686,
|
|
"num_tokens": 50345418.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.529949951171875,
|
|
"epoch": 2.5337226933228507,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043662506963421815,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.21896879822015763,
|
|
"num_tokens": 50357047.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.538169050216675,
|
|
"epoch": 2.534284270230808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004365971356468534,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.22190608382225036,
|
|
"num_tokens": 50368385.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.569509649276734,
|
|
"epoch": 2.5348458471387656,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043656919651417314,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.21234248578548431,
|
|
"num_tokens": 50379389.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.566155529022216,
|
|
"epoch": 2.5354074240467233,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000436541252237067,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.21588984578847886,
|
|
"num_tokens": 50390124.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.5865997791290285,
|
|
"epoch": 2.5359690009546805,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004365133028164248,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.2191238969564438,
|
|
"num_tokens": 50401385.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.540587329864502,
|
|
"epoch": 2.536530577862638,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004364853482531363,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.2085189551115036,
|
|
"num_tokens": 50412890.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.550000953674316,
|
|
"epoch": 2.537092154770596,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043645738854809177,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.21920861303806305,
|
|
"num_tokens": 50424403.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.640579080581665,
|
|
"epoch": 2.5376537316785535,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004364294237021813,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.21410840302705764,
|
|
"num_tokens": 50434598.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.6362710952758786,
|
|
"epoch": 2.538215308586511,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043640145371629544,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.2113214373588562,
|
|
"num_tokens": 50446661.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.637434244155884,
|
|
"epoch": 2.5387768854944683,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004363734785913246,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.21291465163230897,
|
|
"num_tokens": 50458188.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.610230731964111,
|
|
"epoch": 2.539338462402426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004363454983281597,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.2128222480416298,
|
|
"num_tokens": 50469305.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.551889324188233,
|
|
"epoch": 2.5399000393103837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004363175129276915,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.21558892577886582,
|
|
"num_tokens": 50480450.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.540404415130615,
|
|
"epoch": 2.540461616218341,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043628952239081113,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.21602300703525543,
|
|
"num_tokens": 50490397.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.4978930950164795,
|
|
"epoch": 2.5410231931262985,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043626152671840984,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.22429388761520386,
|
|
"num_tokens": 50501068.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.643153238296509,
|
|
"epoch": 2.541584770034256,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000436233525911379,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.20873731821775438,
|
|
"num_tokens": 50513268.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.547293281555175,
|
|
"epoch": 2.542146346942214,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004362055199706101,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.22326887845993043,
|
|
"num_tokens": 50523806.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.556995439529419,
|
|
"epoch": 2.5427079238501715,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043617750889699496,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.2217416599392891,
|
|
"num_tokens": 50535000.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.609346055984497,
|
|
"epoch": 2.5432695007581287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043614949269142546,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.21089616864919664,
|
|
"num_tokens": 50546042.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.678076982498169,
|
|
"epoch": 2.5438310776660864,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043612147135479356,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.21613523811101915,
|
|
"num_tokens": 50556645.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.681654357910157,
|
|
"epoch": 2.544392654574044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004360934448879916,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.2167483538389206,
|
|
"num_tokens": 50567904.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.54044542312622,
|
|
"epoch": 2.5449542314820013,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004360654132919118,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.22040624618530275,
|
|
"num_tokens": 50578280.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.527458238601684,
|
|
"epoch": 2.545515808389959,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004360373765674467,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.22422798573970795,
|
|
"num_tokens": 50590232.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.505819034576416,
|
|
"epoch": 2.5460773852979166,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043600933471548927,
|
|
"loss": 4.9225,
|
|
"mean_token_accuracy": 0.224009145796299,
|
|
"num_tokens": 50601469.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.501074647903442,
|
|
"epoch": 2.546638962205874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004359812877369321,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.21854030340909958,
|
|
"num_tokens": 50612090.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.501127004623413,
|
|
"epoch": 2.5472005391138315,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043595323563266815,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.21293543130159379,
|
|
"num_tokens": 50623834.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.555380201339721,
|
|
"epoch": 2.547762116021789,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043592517840359093,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.2129300355911255,
|
|
"num_tokens": 50633966.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.527233409881592,
|
|
"epoch": 2.548323692929747,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004358971160505936,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.22480797916650772,
|
|
"num_tokens": 50644354.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.524279403686523,
|
|
"epoch": 2.5488852698377045,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043586904857456963,
|
|
"loss": 4.9114,
|
|
"mean_token_accuracy": 0.22117385566234588,
|
|
"num_tokens": 50655525.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.57322359085083,
|
|
"epoch": 2.5494468467456617,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043584097597641275,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.2100875973701477,
|
|
"num_tokens": 50667879.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.509943246841431,
|
|
"epoch": 2.5500084236536193,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043581289825701683,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.22641765773296357,
|
|
"num_tokens": 50679568.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.562136697769165,
|
|
"epoch": 2.550570000561577,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004357848154172759,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.2222215086221695,
|
|
"num_tokens": 50690172.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.510635900497436,
|
|
"epoch": 2.5511315774695342,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043575672745808404,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.21973955482244492,
|
|
"num_tokens": 50701150.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.565816640853882,
|
|
"epoch": 2.551693154377492,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043572863438033556,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.21976277530193328,
|
|
"num_tokens": 50712407.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.507523727416992,
|
|
"epoch": 2.5522547312854496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004357005361849251,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.2146727278828621,
|
|
"num_tokens": 50723122.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.564540863037109,
|
|
"epoch": 2.552816308193407,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043567243287274726,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.2171099916100502,
|
|
"num_tokens": 50734479.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.519728803634644,
|
|
"epoch": 2.553377885101365,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043564432444469686,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.22559794187545776,
|
|
"num_tokens": 50745098.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.584340810775757,
|
|
"epoch": 2.553939462009322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043561621090166885,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.22147706151008606,
|
|
"num_tokens": 50755793.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.541354942321777,
|
|
"epoch": 2.5545010389172798,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004355880922445584,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.21021119952201844,
|
|
"num_tokens": 50767685.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.594926643371582,
|
|
"epoch": 2.5550626158252374,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043555996847426077,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.2064253196120262,
|
|
"num_tokens": 50778583.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.604846334457397,
|
|
"epoch": 2.5556241927331946,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043553183959167154,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.2202865734696388,
|
|
"num_tokens": 50789651.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.666983699798584,
|
|
"epoch": 2.5561857696411523,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043550370559768614,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.21206049025058746,
|
|
"num_tokens": 50800846.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.574242067337036,
|
|
"epoch": 2.55674734654911,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004354755664932006,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.22452501356601715,
|
|
"num_tokens": 50812532.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.581001329421997,
|
|
"epoch": 2.557308923457067,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043544742227911076,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.21348843574523926,
|
|
"num_tokens": 50823592.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.551132583618164,
|
|
"epoch": 2.557870500365025,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043541927295631276,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.21985722631216048,
|
|
"num_tokens": 50834392.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.619601535797119,
|
|
"epoch": 2.5584320772729825,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043539111852570296,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.2140876293182373,
|
|
"num_tokens": 50845371.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.586745262145996,
|
|
"epoch": 2.55899365418094,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043536295898817767,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.21896574646234512,
|
|
"num_tokens": 50857748.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.5192982196807865,
|
|
"epoch": 2.559555231088898,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004353347943446336,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.2236276626586914,
|
|
"num_tokens": 50868646.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.48447961807251,
|
|
"epoch": 2.560116807996855,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043530662459596744,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.22528832107782365,
|
|
"num_tokens": 50880566.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.545956373214722,
|
|
"epoch": 2.5606783849048127,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004352784497430762,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.21939489245414734,
|
|
"num_tokens": 50891487.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.586131954193116,
|
|
"epoch": 2.5612399618127704,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043525026978685706,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.20863131582736968,
|
|
"num_tokens": 50902522.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.706029605865479,
|
|
"epoch": 2.5618015387207276,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043522208472820706,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.20889972299337387,
|
|
"num_tokens": 50913363.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.593763303756714,
|
|
"epoch": 2.5623631156286852,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004351938945680238,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.21895930767059327,
|
|
"num_tokens": 50923724.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.541661262512207,
|
|
"epoch": 2.562924692536643,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004351656993072048,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.21731421947479249,
|
|
"num_tokens": 50933575.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.543890428543091,
|
|
"epoch": 2.5634862694446006,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004351374989466477,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.22146324217319488,
|
|
"num_tokens": 50944619.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.54632534980774,
|
|
"epoch": 2.5640478463525582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043510929348725065,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.22174861282110214,
|
|
"num_tokens": 50955701.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.48409423828125,
|
|
"epoch": 2.5646094232605154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043508108292991156,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.22194865792989732,
|
|
"num_tokens": 50966544.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.551190948486328,
|
|
"epoch": 2.565171000168473,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004350528672755287,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.22015779763460158,
|
|
"num_tokens": 50976648.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.600135803222656,
|
|
"epoch": 2.5657325770764308,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004350246465250005,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.21275390535593033,
|
|
"num_tokens": 50988173.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.549978923797608,
|
|
"epoch": 2.566294153984388,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043499642067922544,
|
|
"loss": 4.9341,
|
|
"mean_token_accuracy": 0.2192499652504921,
|
|
"num_tokens": 50999274.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.493794345855713,
|
|
"epoch": 2.5668557308923456,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043496818973910235,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.22333385199308395,
|
|
"num_tokens": 51010213.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.505479240417481,
|
|
"epoch": 2.5674173078003033,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043493995370553,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.2180625632405281,
|
|
"num_tokens": 51021460.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.640463972091675,
|
|
"epoch": 2.5679788847082605,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043491171257940755,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.217063108086586,
|
|
"num_tokens": 51031713.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.655990123748779,
|
|
"epoch": 2.568540461616218,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043488346636163405,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.21063105762004852,
|
|
"num_tokens": 51043026.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.628523540496826,
|
|
"epoch": 2.569102038524176,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004348552150531091,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.2135657861828804,
|
|
"num_tokens": 51054838.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.539472341537476,
|
|
"epoch": 2.5696636154321335,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043482695865473207,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.2208138421177864,
|
|
"num_tokens": 51065574.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.5037261009216305,
|
|
"epoch": 2.570225192340091,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004347986971674026,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.2235956609249115,
|
|
"num_tokens": 51076814.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.520912218093872,
|
|
"epoch": 2.5707867692480484,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043477043059202077,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.2086984932422638,
|
|
"num_tokens": 51089075.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.603150701522827,
|
|
"epoch": 2.571348346156006,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004347421589294864,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.21212232559919358,
|
|
"num_tokens": 51100148.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.651203966140747,
|
|
"epoch": 2.5719099230639637,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004347138821806997,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.21589789688587188,
|
|
"num_tokens": 51111148.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.6661358833312985,
|
|
"epoch": 2.572471499971921,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000434685600346561,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.21861684769392015,
|
|
"num_tokens": 51122563.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.527582836151123,
|
|
"epoch": 2.5730330768798786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000434657313427971,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.21584047377109528,
|
|
"num_tokens": 51132676.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.544738054275513,
|
|
"epoch": 2.5735946537878363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004346290214258301,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.21463884711265563,
|
|
"num_tokens": 51144317.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.696652603149414,
|
|
"epoch": 2.574156230695794,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043460072434103934,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.20363363921642302,
|
|
"num_tokens": 51156181.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.542945861816406,
|
|
"epoch": 2.5747178076037516,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004345724221744996,
|
|
"loss": 4.9477,
|
|
"mean_token_accuracy": 0.2244648590683937,
|
|
"num_tokens": 51166825.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.621100425720215,
|
|
"epoch": 2.575279384511709,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043454411492711197,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.21736220717430116,
|
|
"num_tokens": 51178839.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.551314878463745,
|
|
"epoch": 2.5758409614196665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043451580259977793,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.21709077209234237,
|
|
"num_tokens": 51190811.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.625671482086181,
|
|
"epoch": 2.576402538327624,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043448748519339875,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.2169414132833481,
|
|
"num_tokens": 51201991.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.5998939037322994,
|
|
"epoch": 2.5769641152355813,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043445916270887626,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.22102876454591752,
|
|
"num_tokens": 51213017.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.582317113876343,
|
|
"epoch": 2.577525692143539,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004344308351471123,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.21882669627666473,
|
|
"num_tokens": 51224412.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.637662315368653,
|
|
"epoch": 2.5780872690514967,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043440250250900854,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.21678484827280045,
|
|
"num_tokens": 51235043.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.583051300048828,
|
|
"epoch": 2.578648845959454,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004343741647954673,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.21320104002952575,
|
|
"num_tokens": 51246182.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.6447920322418215,
|
|
"epoch": 2.5792104228674115,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004343458220073909,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.2133139356970787,
|
|
"num_tokens": 51259791.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.673297262191772,
|
|
"epoch": 2.579771999775369,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004343174741456817,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.21497832834720612,
|
|
"num_tokens": 51270530.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.519698429107666,
|
|
"epoch": 2.580333576683327,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004342891212112423,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.2136576995253563,
|
|
"num_tokens": 51281969.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.515922212600708,
|
|
"epoch": 2.5808951535912845,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043426076320497557,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.22200529128313065,
|
|
"num_tokens": 51292790.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.537673091888427,
|
|
"epoch": 2.5814567304992417,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043423240012778437,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.21154461055994034,
|
|
"num_tokens": 51303949.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.561172676086426,
|
|
"epoch": 2.5820183074071994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004342040319805717,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.21991294920444487,
|
|
"num_tokens": 51314570.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.4681649684906,
|
|
"epoch": 2.582579884315157,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000434175658764241,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.22363439947366714,
|
|
"num_tokens": 51325210.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.490248203277588,
|
|
"epoch": 2.5831414612231143,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043414728047969553,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.22614243477582932,
|
|
"num_tokens": 51335871.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.601178169250488,
|
|
"epoch": 2.583703038131072,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043411889712783897,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.2179405629634857,
|
|
"num_tokens": 51346821.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.577328300476074,
|
|
"epoch": 2.5842646150390296,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043409050870957505,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.2071591928601265,
|
|
"num_tokens": 51358746.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.601737213134766,
|
|
"epoch": 2.5848261919469873,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004340621152258075,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.21209113746881486,
|
|
"num_tokens": 51369628.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.677427625656128,
|
|
"epoch": 2.585387768854945,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043403371667744055,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.22687394469976424,
|
|
"num_tokens": 51382160.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.573103952407837,
|
|
"epoch": 2.585949345762902,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004340053130653785,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.21585660874843599,
|
|
"num_tokens": 51394843.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.543177938461303,
|
|
"epoch": 2.58651092267086,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004339769043905255,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.2211523488163948,
|
|
"num_tokens": 51405714.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.610357093811035,
|
|
"epoch": 2.5870724995788175,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043394849065378624,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.21582823097705842,
|
|
"num_tokens": 51416292.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.579436016082764,
|
|
"epoch": 2.5876340764867747,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043392007185606533,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.2229910150170326,
|
|
"num_tokens": 51426993.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.523529720306397,
|
|
"epoch": 2.5881956533947323,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004338916479982678,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.21342428624629975,
|
|
"num_tokens": 51439493.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.574963092803955,
|
|
"epoch": 2.58875723030269,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043386321908129856,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.2190542295575142,
|
|
"num_tokens": 51451705.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.648854970932007,
|
|
"epoch": 2.589318807210647,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043383478510606276,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.22126546055078505,
|
|
"num_tokens": 51463044.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.508328819274903,
|
|
"epoch": 2.589880384118605,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004338063460734658,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.21700674295425415,
|
|
"num_tokens": 51475009.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.50267391204834,
|
|
"epoch": 2.5904419610265625,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004337779019844132,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.21843096762895584,
|
|
"num_tokens": 51486068.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.600012350082397,
|
|
"epoch": 2.59100353793452,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043374945283981066,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.21449732333421706,
|
|
"num_tokens": 51497642.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.632068157196045,
|
|
"epoch": 2.591565114842478,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004337209986405639,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.21299925744533538,
|
|
"num_tokens": 51511013.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.648039627075195,
|
|
"epoch": 2.592126691750435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000433692539387579,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.2064813494682312,
|
|
"num_tokens": 51521687.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.6208261013031,
|
|
"epoch": 2.5926882686583927,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004336640750817621,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.21434394717216493,
|
|
"num_tokens": 51532288.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.655436420440674,
|
|
"epoch": 2.5932498455663504,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043363560572401953,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.21173933297395706,
|
|
"num_tokens": 51543101.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.555271911621094,
|
|
"epoch": 2.5938114224743076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043360713131525774,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.21710766702890397,
|
|
"num_tokens": 51554729.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.528112697601318,
|
|
"epoch": 2.5943729993822653,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004335786518563834,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.21742669343948365,
|
|
"num_tokens": 51567232.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.637759399414063,
|
|
"epoch": 2.594934576290223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004335501673483033,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.2171348512172699,
|
|
"num_tokens": 51577679.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.59075517654419,
|
|
"epoch": 2.5954961531981806,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043352167779192423,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.22251296490430833,
|
|
"num_tokens": 51588656.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.635020112991333,
|
|
"epoch": 2.5960577301061383,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043349318318815363,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.21598259061574937,
|
|
"num_tokens": 51599016.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.434494256973267,
|
|
"epoch": 2.5966193070140955,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043346468353789853,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.2245782732963562,
|
|
"num_tokens": 51610288.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.566299676895142,
|
|
"epoch": 2.597180883922053,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004334361788420664,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.21472099274396897,
|
|
"num_tokens": 51622450.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.5387269973754885,
|
|
"epoch": 2.597742460830011,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043340766910156497,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.21886856257915496,
|
|
"num_tokens": 51635111.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.5823506832122805,
|
|
"epoch": 2.598304037737968,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043337915431730195,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.2111379936337471,
|
|
"num_tokens": 51646088.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.587726068496704,
|
|
"epoch": 2.5988656146459257,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043335063449018515,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.22186032086610794,
|
|
"num_tokens": 51659337.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.612441778182983,
|
|
"epoch": 2.5994271915538834,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004333221096211227,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.21169385612010955,
|
|
"num_tokens": 51670954.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.531445693969727,
|
|
"epoch": 2.599988768461841,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043329357971102296,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.21522176414728164,
|
|
"num_tokens": 51681104.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.462230396270752,
|
|
"epoch": 2.6005503453697982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043326504476079425,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.22786035537719726,
|
|
"num_tokens": 51691337.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.487305593490601,
|
|
"epoch": 2.601111922277756,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004332365047713451,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.21436865180730819,
|
|
"num_tokens": 51702488.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.615288639068604,
|
|
"epoch": 2.6016734991857136,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004332079597435842,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.22239113450050355,
|
|
"num_tokens": 51714439.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.682943487167359,
|
|
"epoch": 2.602235076093671,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004331794096784206,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.21536314934492112,
|
|
"num_tokens": 51726423.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.6089719295501705,
|
|
"epoch": 2.6027966530016284,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004331508545767633,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.2230703353881836,
|
|
"num_tokens": 51736198.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.489760637283325,
|
|
"epoch": 2.603358229909586,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004331222944395213,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.22321844696998597,
|
|
"num_tokens": 51746993.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.539574480056762,
|
|
"epoch": 2.6039198068175438,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004330937292676042,
|
|
"loss": 4.991,
|
|
"mean_token_accuracy": 0.22326307892799377,
|
|
"num_tokens": 51756981.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.515034246444702,
|
|
"epoch": 2.604481383725501,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004330651590619214,
|
|
"loss": 5.0019,
|
|
"mean_token_accuracy": 0.21755052506923675,
|
|
"num_tokens": 51768192.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.6154913902282715,
|
|
"epoch": 2.6050429606334586,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004330365838233827,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.21758718490600587,
|
|
"num_tokens": 51778996.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.642601108551025,
|
|
"epoch": 2.6056045375414163,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043300800355289786,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.20696892142295836,
|
|
"num_tokens": 51790179.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.566602993011474,
|
|
"epoch": 2.606166114449374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043297941825137684,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.21985449492931367,
|
|
"num_tokens": 51801312.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.539613103866577,
|
|
"epoch": 2.6067276913573316,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043295082791972993,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.22147407978773118,
|
|
"num_tokens": 51811960.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.527957439422607,
|
|
"epoch": 2.607289268265289,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043292223255886737,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.21001969128847123,
|
|
"num_tokens": 51823166.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.555580759048462,
|
|
"epoch": 2.6078508451732465,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043289363216969973,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.2168843314051628,
|
|
"num_tokens": 51835517.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.547658538818359,
|
|
"epoch": 2.608412422081204,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043286502675313757,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.21882623434066772,
|
|
"num_tokens": 51846690.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.5105915546417235,
|
|
"epoch": 2.6089739989891614,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004328364163100917,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.2228497877717018,
|
|
"num_tokens": 51857234.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.573422813415528,
|
|
"epoch": 2.609535575897119,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004328078008414731,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.219734126329422,
|
|
"num_tokens": 51867913.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.506981754302979,
|
|
"epoch": 2.6100971528050767,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000432779180348193,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.22196169048547745,
|
|
"num_tokens": 51878252.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.48753662109375,
|
|
"epoch": 2.6106587297130344,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043275055483116254,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.2182725563645363,
|
|
"num_tokens": 51888407.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.59116153717041,
|
|
"epoch": 2.6112203066209916,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004327219242912933,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.21586089879274367,
|
|
"num_tokens": 51900042.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.588662338256836,
|
|
"epoch": 2.6117818835289492,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004326932887294967,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.21288307756185532,
|
|
"num_tokens": 51909691.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.655903434753418,
|
|
"epoch": 2.612343460436907,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004326646481466848,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.21787814199924468,
|
|
"num_tokens": 51921691.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.561924171447754,
|
|
"epoch": 2.6129050373448646,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004326360025437692,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.21684811860322953,
|
|
"num_tokens": 51934050.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.550407266616821,
|
|
"epoch": 2.613466614252822,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043260735192166217,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.22139995396137238,
|
|
"num_tokens": 51944566.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.517973518371582,
|
|
"epoch": 2.6140281911607794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000432578696281276,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.2239662230014801,
|
|
"num_tokens": 51955485.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.532765245437622,
|
|
"epoch": 2.614589768068737,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000432550035623523,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.2150411680340767,
|
|
"num_tokens": 51965124.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.618502807617188,
|
|
"epoch": 2.6151513449766943,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004325213699493157,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.222160467505455,
|
|
"num_tokens": 51976362.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.518732976913452,
|
|
"epoch": 2.615712921884652,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004324926992595669,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.21798078417778016,
|
|
"num_tokens": 51988068.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.54885687828064,
|
|
"epoch": 2.6162744987926096,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004324640235551895,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.22502567172050475,
|
|
"num_tokens": 51998392.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.487338399887085,
|
|
"epoch": 2.6168360757005673,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004324353428370965,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.21973829865455627,
|
|
"num_tokens": 52009416.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.622116947174073,
|
|
"epoch": 2.617397652608525,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004324066571062012,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.2224043130874634,
|
|
"num_tokens": 52020554.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.549984455108643,
|
|
"epoch": 2.617959229516482,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004323779663634168,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.21777047365903854,
|
|
"num_tokens": 52031301.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.5255049705505375,
|
|
"epoch": 2.61852080642444,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000432349270609657,
|
|
"loss": 4.9958,
|
|
"mean_token_accuracy": 0.2186715066432953,
|
|
"num_tokens": 52041720.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.463754606246948,
|
|
"epoch": 2.6190823833323975,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043232056984583527,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.22599161714315413,
|
|
"num_tokens": 52051911.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.566571187973023,
|
|
"epoch": 2.6196439602403547,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004322918640728656,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.21850325167179108,
|
|
"num_tokens": 52062842.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.570230150222779,
|
|
"epoch": 2.6202055371483124,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043226315329166203,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.21091645658016206,
|
|
"num_tokens": 52075034.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.565611934661865,
|
|
"epoch": 2.62076711405627,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043223443750313873,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.2231694996356964,
|
|
"num_tokens": 52084782.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.491708660125733,
|
|
"epoch": 2.6213286909642277,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004322057167082099,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.21808532178401946,
|
|
"num_tokens": 52095623.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.5372477054595945,
|
|
"epoch": 2.621890267872185,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043217699090779006,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.22173524498939515,
|
|
"num_tokens": 52107240.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.54152193069458,
|
|
"epoch": 2.6224518447801426,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043214826010279383,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.21441062837839125,
|
|
"num_tokens": 52118157.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.652239608764648,
|
|
"epoch": 2.6230134216881003,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004321195242941361,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.20833078920841216,
|
|
"num_tokens": 52130578.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.570171308517456,
|
|
"epoch": 2.623574998596058,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043209078348273175,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.22079967260360717,
|
|
"num_tokens": 52142057.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.624727344512939,
|
|
"epoch": 2.624136575504015,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004320620376694959,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.21060091406106948,
|
|
"num_tokens": 52152370.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.538164472579956,
|
|
"epoch": 2.624698152411973,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043203328685534396,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.22111081331968307,
|
|
"num_tokens": 52162139.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.567763328552246,
|
|
"epoch": 2.6252597293199305,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004320045310411912,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.21296015232801438,
|
|
"num_tokens": 52172820.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.510043478012085,
|
|
"epoch": 2.6258213062278877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043197577022795327,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.22466958910226822,
|
|
"num_tokens": 52183315.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.463102865219116,
|
|
"epoch": 2.6263828831358453,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004319470044165459,
|
|
"loss": 4.9835,
|
|
"mean_token_accuracy": 0.22546387761831282,
|
|
"num_tokens": 52194776.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.638352537155152,
|
|
"epoch": 2.626944460043803,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004319182336078852,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.20687942802906037,
|
|
"num_tokens": 52207370.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.599122190475464,
|
|
"epoch": 2.6275060369517607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000431889457802887,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.2257734939455986,
|
|
"num_tokens": 52218287.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.552238512039184,
|
|
"epoch": 2.6280676138597183,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004318606770024675,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.21333774030208588,
|
|
"num_tokens": 52229418.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.64367823600769,
|
|
"epoch": 2.6286291907676755,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004318318912075433,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.21281637847423554,
|
|
"num_tokens": 52240382.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.622903108596802,
|
|
"epoch": 2.629190767675633,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004318031004190308,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.2143626853823662,
|
|
"num_tokens": 52252608.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.518719100952149,
|
|
"epoch": 2.629752344583591,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043177430463784685,
|
|
"loss": 4.9709,
|
|
"mean_token_accuracy": 0.2281103476881981,
|
|
"num_tokens": 52262940.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.460925817489624,
|
|
"epoch": 2.630313921491548,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043174550386490816,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.22262941151857377,
|
|
"num_tokens": 52273270.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.511773633956909,
|
|
"epoch": 2.6308754983995057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004317166981011319,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.22260909974575044,
|
|
"num_tokens": 52284433.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.604735946655273,
|
|
"epoch": 2.6314370753074634,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043168788734743516,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.2237548992037773,
|
|
"num_tokens": 52296088.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.563038921356201,
|
|
"epoch": 2.631998652215421,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043165907160473525,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.2101515144109726,
|
|
"num_tokens": 52307683.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.546241712570191,
|
|
"epoch": 2.6325602291233783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004316302508739499,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.21393942683935166,
|
|
"num_tokens": 52319845.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.613216590881348,
|
|
"epoch": 2.633121806031336,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004316014251559965,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.220979543030262,
|
|
"num_tokens": 52330196.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.711046171188355,
|
|
"epoch": 2.6336833829392936,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043157259445179304,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.20537890791893004,
|
|
"num_tokens": 52341510.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.550283145904541,
|
|
"epoch": 2.6342449598472513,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004315437587622574,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.21634175926446914,
|
|
"num_tokens": 52351848.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.566129159927368,
|
|
"epoch": 2.6348065367552085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043151491808830777,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.21569227427244186,
|
|
"num_tokens": 52363698.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.560524845123291,
|
|
"epoch": 2.635368113663166,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043148607243086255,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.22090427279472352,
|
|
"num_tokens": 52374433.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.551445150375367,
|
|
"epoch": 2.635929690571124,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004314572217908399,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.22203767001628877,
|
|
"num_tokens": 52385762.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.453604221343994,
|
|
"epoch": 2.636491267479081,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004314283661691587,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.24057159274816514,
|
|
"num_tokens": 52397058.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.624357986450195,
|
|
"epoch": 2.6370528443870387,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004313995055667377,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.20568175464868546,
|
|
"num_tokens": 52407671.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.6014128684997555,
|
|
"epoch": 2.6376144212949963,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004313706399844958,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.2181250274181366,
|
|
"num_tokens": 52419511.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.459224081039428,
|
|
"epoch": 2.638175998202954,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000431341769423352,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.21808459758758544,
|
|
"num_tokens": 52431311.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.549754476547241,
|
|
"epoch": 2.6387375751109117,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004313128938842257,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.21688833236694335,
|
|
"num_tokens": 52442184.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.607006216049195,
|
|
"epoch": 2.639299152018869,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043128401336803616,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.2143138200044632,
|
|
"num_tokens": 52454837.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.579151630401611,
|
|
"epoch": 2.6398607289268265,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043125512787570305,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.21728125512599944,
|
|
"num_tokens": 52465378.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.5668089389801025,
|
|
"epoch": 2.640422305834784,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004312262374081461,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.2150605797767639,
|
|
"num_tokens": 52476025.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.656465530395508,
|
|
"epoch": 2.6409838827427414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043119734196628507,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.21726243942975998,
|
|
"num_tokens": 52487408.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.611485195159912,
|
|
"epoch": 2.641545459650699,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043116844155104025,
|
|
"loss": 4.9643,
|
|
"mean_token_accuracy": 0.2201722115278244,
|
|
"num_tokens": 52497801.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.486942768096924,
|
|
"epoch": 2.6421070365586568,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004311395361633316,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.21692452281713487,
|
|
"num_tokens": 52508918.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.515234327316284,
|
|
"epoch": 2.6426686134666144,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004311106258040795,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.21964964121580124,
|
|
"num_tokens": 52519951.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.458695268630981,
|
|
"epoch": 2.643230190374572,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043108171047420463,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.21469263285398482,
|
|
"num_tokens": 52530710.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.450600433349609,
|
|
"epoch": 2.6437917672825293,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004310527901746275,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.22287482321262359,
|
|
"num_tokens": 52542188.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.565253400802613,
|
|
"epoch": 2.644353344190487,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000431023864906269,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.21562704741954802,
|
|
"num_tokens": 52553848.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.569629430770874,
|
|
"epoch": 2.6449149210984446,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043099493467005015,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.22059585452079772,
|
|
"num_tokens": 52563338.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.609301996231079,
|
|
"epoch": 2.645476498006402,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000430965999466892,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.2103557676076889,
|
|
"num_tokens": 52576369.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.5938667297363285,
|
|
"epoch": 2.6460380749143595,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043093705929771604,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.22299884110689164,
|
|
"num_tokens": 52587409.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.555026531219482,
|
|
"epoch": 2.646599651822317,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004309081141634436,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.22269199639558793,
|
|
"num_tokens": 52599398.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.520162439346313,
|
|
"epoch": 2.6471612287302744,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043087916406499635,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.22397667318582534,
|
|
"num_tokens": 52609565.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.535247755050659,
|
|
"epoch": 2.647722805638232,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043085020900329604,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.21841807812452316,
|
|
"num_tokens": 52621150.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.55713119506836,
|
|
"epoch": 2.6482843825461897,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043082124897926463,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.22170152515172958,
|
|
"num_tokens": 52632030.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.59496841430664,
|
|
"epoch": 2.6488459594541474,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004307922839938242,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.21163937598466873,
|
|
"num_tokens": 52643447.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.590302562713623,
|
|
"epoch": 2.649407536362105,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043076331404789703,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.22133142948150636,
|
|
"num_tokens": 52655017.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.6721782207489015,
|
|
"epoch": 2.6499691132700622,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004307343391424055,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.21467786580324172,
|
|
"num_tokens": 52665674.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.519095611572266,
|
|
"epoch": 2.65053069017802,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004307053592782723,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.21989476531744004,
|
|
"num_tokens": 52678177.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.536273193359375,
|
|
"epoch": 2.6510922670859776,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043067637445642004,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.21184283047914504,
|
|
"num_tokens": 52689326.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.608097219467163,
|
|
"epoch": 2.651653843993935,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043064738467777166,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20859862118959427,
|
|
"num_tokens": 52701686.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.540115213394165,
|
|
"epoch": 2.6522154209018924,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043061838994325007,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.22075248658657073,
|
|
"num_tokens": 52713422.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.611674690246582,
|
|
"epoch": 2.65277699780985,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043058939025377867,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.21506756097078322,
|
|
"num_tokens": 52724438.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.585729312896729,
|
|
"epoch": 2.6533385747178078,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004305603856102808,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.2226301595568657,
|
|
"num_tokens": 52734657.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.559255504608155,
|
|
"epoch": 2.6539001516257654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004305313760136799,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.22225701212882995,
|
|
"num_tokens": 52745832.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.593347358703613,
|
|
"epoch": 2.6544617285337226,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00043050236146489955,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.21271138936281203,
|
|
"num_tokens": 52758795.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.582129430770874,
|
|
"epoch": 2.6550233054416803,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004304733419648638,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.2197338879108429,
|
|
"num_tokens": 52769154.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.564472293853759,
|
|
"epoch": 2.655584882349638,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043044431751449656,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.21921413987874985,
|
|
"num_tokens": 52779189.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.679933023452759,
|
|
"epoch": 2.656146459257595,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004304152881147219,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.21556328535079955,
|
|
"num_tokens": 52789545.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.691593885421753,
|
|
"epoch": 2.656708036165553,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004303862537664642,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.2072175607085228,
|
|
"num_tokens": 52802410.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.528091526031494,
|
|
"epoch": 2.6572696130735105,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000430357214470648,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.2124402791261673,
|
|
"num_tokens": 52814223.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.530760097503662,
|
|
"epoch": 2.6578311899814677,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004303281702281977,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.22196102887392044,
|
|
"num_tokens": 52824554.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.633419990539551,
|
|
"epoch": 2.6583927668894254,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043029912104003827,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.2168179541826248,
|
|
"num_tokens": 52836058.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.579163837432861,
|
|
"epoch": 2.658954343797383,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043027006690709457,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.2120787665247917,
|
|
"num_tokens": 52847220.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.57738356590271,
|
|
"epoch": 2.6595159207053407,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004302410078302918,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.22250157296657563,
|
|
"num_tokens": 52858242.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.510265970230103,
|
|
"epoch": 2.6600774976132984,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043021194381055505,
|
|
"loss": 4.8942,
|
|
"mean_token_accuracy": 0.22220433950424195,
|
|
"num_tokens": 52869439.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.6490987777709964,
|
|
"epoch": 2.6606390745212556,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043018287484880986,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.21071095019578934,
|
|
"num_tokens": 52879893.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.627468824386597,
|
|
"epoch": 2.6612006514292132,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004301538009459817,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.22172343134880065,
|
|
"num_tokens": 52891352.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.5871025085449215,
|
|
"epoch": 2.661762228337171,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004301247221029964,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.21325237303972244,
|
|
"num_tokens": 52904202.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.583196449279785,
|
|
"epoch": 2.662323805245128,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043009563832077977,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.22335248291492463,
|
|
"num_tokens": 52914495.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.540369606018066,
|
|
"epoch": 2.662885382153086,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004300665496002578,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.2104209080338478,
|
|
"num_tokens": 52925930.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.616008710861206,
|
|
"epoch": 2.6634469590610435,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043003745594235687,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.21414703130722046,
|
|
"num_tokens": 52936310.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.622004985809326,
|
|
"epoch": 2.664008535969001,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004300083573480031,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.210498084127903,
|
|
"num_tokens": 52948801.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.609158086776733,
|
|
"epoch": 2.6645701128769588,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042997925381812313,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.2126275658607483,
|
|
"num_tokens": 52960541.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.5655622482299805,
|
|
"epoch": 2.665131689784916,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042995014535364363,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.21792736649513245,
|
|
"num_tokens": 52971973.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.569027423858643,
|
|
"epoch": 2.6656932666928737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004299210319554914,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.23334805816411971,
|
|
"num_tokens": 52983124.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.582093238830566,
|
|
"epoch": 2.6662548436008313,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042989191362459347,
|
|
"loss": 4.9639,
|
|
"mean_token_accuracy": 0.22658378928899764,
|
|
"num_tokens": 52994402.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.58549280166626,
|
|
"epoch": 2.6668164205087885,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004298627903618769,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.2117153748869896,
|
|
"num_tokens": 53005253.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.583654403686523,
|
|
"epoch": 2.667377997416746,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042983366216826907,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.21416014730930327,
|
|
"num_tokens": 53016599.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.592666864395142,
|
|
"epoch": 2.667939574324704,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004298045290446973,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.22050638794898986,
|
|
"num_tokens": 53027412.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.548851823806762,
|
|
"epoch": 2.668501151232661,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042977539099208937,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.21336241513490678,
|
|
"num_tokens": 53039490.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.5841343879699705,
|
|
"epoch": 2.6690627281406187,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042974624801137283,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.21499104499816896,
|
|
"num_tokens": 53049837.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.549221849441528,
|
|
"epoch": 2.6696243050485764,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042971710010347594,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.22599327117204665,
|
|
"num_tokens": 53060187.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.54443621635437,
|
|
"epoch": 2.670185881956534,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042968794726932634,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.21449533551931382,
|
|
"num_tokens": 53072050.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.540900659561157,
|
|
"epoch": 2.6707474588644917,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004296587895098527,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.2143111288547516,
|
|
"num_tokens": 53083235.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.61717381477356,
|
|
"epoch": 2.671309035772449,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042962962682598316,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.21577390730381013,
|
|
"num_tokens": 53093615.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.644925355911255,
|
|
"epoch": 2.6718706126804066,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042960045921864627,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.21291816979646683,
|
|
"num_tokens": 53105611.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.548785066604614,
|
|
"epoch": 2.6724321895883643,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004295712866887709,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.22303890138864518,
|
|
"num_tokens": 53116343.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.615527868270874,
|
|
"epoch": 2.6729937664963215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042954210923728565,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.22928863614797593,
|
|
"num_tokens": 53128754.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.524392700195312,
|
|
"epoch": 2.673555343404279,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004295129268651198,
|
|
"loss": 4.9481,
|
|
"mean_token_accuracy": 0.2301690697669983,
|
|
"num_tokens": 53139508.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.5206374168396,
|
|
"epoch": 2.674116920312237,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004294837395732025,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.22643127888441086,
|
|
"num_tokens": 53149925.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.533429861068726,
|
|
"epoch": 2.6746784972201945,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042945454736246293,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.22216223329305648,
|
|
"num_tokens": 53160053.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.591841316223144,
|
|
"epoch": 2.675240074128152,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042942535023383075,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.21842246353626252,
|
|
"num_tokens": 53170723.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.524808359146118,
|
|
"epoch": 2.6758016510361093,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042939614818823547,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.21424959003925323,
|
|
"num_tokens": 53182120.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.563119745254516,
|
|
"epoch": 2.676363227944067,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004293669412266069,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.2176624447107315,
|
|
"num_tokens": 53192481.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.589255714416504,
|
|
"epoch": 2.6769248048520247,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004293377293498751,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.21449412852525712,
|
|
"num_tokens": 53203710.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.544194173812866,
|
|
"epoch": 2.677486381759982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042930851255897014,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.22476996183395387,
|
|
"num_tokens": 53214051.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.481011962890625,
|
|
"epoch": 2.6780479586679395,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004292792908548223,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.21972022503614425,
|
|
"num_tokens": 53224981.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.416138076782227,
|
|
"epoch": 2.678609535575897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042925006423836197,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.2299204021692276,
|
|
"num_tokens": 53236336.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.575201749801636,
|
|
"epoch": 2.6791711124838544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042922083271051975,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.2151518777012825,
|
|
"num_tokens": 53248212.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.5975884914398195,
|
|
"epoch": 2.679732689391812,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004291915962722265,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.22157537192106247,
|
|
"num_tokens": 53258910.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.596525955200195,
|
|
"epoch": 2.6802942662997697,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004291623549244129,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.21341622620821,
|
|
"num_tokens": 53269445.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.533715677261353,
|
|
"epoch": 2.6808558432077274,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042913310866801024,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.2198767527937889,
|
|
"num_tokens": 53280119.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.616628694534302,
|
|
"epoch": 2.681417420115685,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042910385750394964,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.21987522691488265,
|
|
"num_tokens": 53291496.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.574094676971436,
|
|
"epoch": 2.6819789970236423,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004290746014331623,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.21769677251577377,
|
|
"num_tokens": 53303470.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.631961536407471,
|
|
"epoch": 2.6825405739316,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042904534045658,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.21211613118648528,
|
|
"num_tokens": 53313552.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.589800071716309,
|
|
"epoch": 2.6831021508395576,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004290160745751343,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.21772402077913283,
|
|
"num_tokens": 53325280.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.458279705047607,
|
|
"epoch": 2.683663727747515,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004289868037897571,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.223569855093956,
|
|
"num_tokens": 53334982.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.593946743011474,
|
|
"epoch": 2.6842253046554725,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004289575281013802,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.21609314382076264,
|
|
"num_tokens": 53346367.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.623224878311158,
|
|
"epoch": 2.68478688156343,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000428928247510936,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.21848821491003037,
|
|
"num_tokens": 53356907.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.558687829971314,
|
|
"epoch": 2.685348458471388,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004288989620193567,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.21697301864624025,
|
|
"num_tokens": 53366619.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.553156948089599,
|
|
"epoch": 2.6859100353793455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042886967162757475,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.2189546912908554,
|
|
"num_tokens": 53377578.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.590894556045532,
|
|
"epoch": 2.6864716122873027,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042884037633652276,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.21724062711000441,
|
|
"num_tokens": 53389416.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.548064804077148,
|
|
"epoch": 2.6870331891952604,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042881107614713355,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.23111597448587418,
|
|
"num_tokens": 53399453.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.533367395401001,
|
|
"epoch": 2.687594766103218,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042878177106034,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.21492627412080764,
|
|
"num_tokens": 53409933.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.581508541107178,
|
|
"epoch": 2.6881563430111752,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004287524610770752,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.21146247833967208,
|
|
"num_tokens": 53420943.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.4865772247314455,
|
|
"epoch": 2.688717919919133,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042872314619827234,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.21932219862937927,
|
|
"num_tokens": 53431450.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.50665020942688,
|
|
"epoch": 2.6892794968270906,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000428693826424865,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.2273539811372757,
|
|
"num_tokens": 53442198.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.5151087760925295,
|
|
"epoch": 2.6898410737350478,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004286645017577866,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.2163809671998024,
|
|
"num_tokens": 53452411.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.508965730667114,
|
|
"epoch": 2.6904026506430054,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042863517219797085,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.22573617845773697,
|
|
"num_tokens": 53462644.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.521289920806884,
|
|
"epoch": 2.690964227550963,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00042860583774635165,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.21981215924024583,
|
|
"num_tokens": 53473258.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.551567077636719,
|
|
"epoch": 2.6915258044589208,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000428576498403863,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.2206132873892784,
|
|
"num_tokens": 53484011.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.5922974109649655,
|
|
"epoch": 2.6920873813668784,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000428547154171439,
|
|
"loss": 4.9948,
|
|
"mean_token_accuracy": 0.2312632218003273,
|
|
"num_tokens": 53495549.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.570805072784424,
|
|
"epoch": 2.6926489582748356,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004285178050500142,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.2154817432165146,
|
|
"num_tokens": 53506721.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.664536762237549,
|
|
"epoch": 2.6932105351827933,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004284884510405228,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.20568328499794006,
|
|
"num_tokens": 53518363.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.486470556259155,
|
|
"epoch": 2.693772112090751,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004284590921438997,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.22056799829006196,
|
|
"num_tokens": 53529140.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.491397523880005,
|
|
"epoch": 2.694333688998708,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042842972836107954,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.22073079645633698,
|
|
"num_tokens": 53540707.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.591764640808106,
|
|
"epoch": 2.694895265906666,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004284003596929973,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.21526671051979065,
|
|
"num_tokens": 53551297.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.544229555130005,
|
|
"epoch": 2.6954568428146235,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042837098614058815,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.21908284574747086,
|
|
"num_tokens": 53562207.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.6954568428146235,
|
|
"eval_entropy": 5.3105046128624025,
|
|
"eval_loss": 5.10612678527832,
|
|
"eval_mean_token_accuracy": 0.2231094966656251,
|
|
"eval_num_tokens": 53562207.0,
|
|
"eval_runtime": 18.4542,
|
|
"eval_samples_per_second": 1680.535,
|
|
"eval_steps_per_second": 210.087,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 5.544635820388794,
|
|
"epoch": 2.696018419722581,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042834160770478726,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.2151688426733017,
|
|
"num_tokens": 53573823.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 5.516907215118408,
|
|
"epoch": 2.696579996630539,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042831222438653016,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2287135526537895,
|
|
"num_tokens": 53584724.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 5.632364559173584,
|
|
"epoch": 2.697141573538496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004282828361867524,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.21913208961486816,
|
|
"num_tokens": 53596212.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 5.5931037902832035,
|
|
"epoch": 2.6977031504464537,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042825344310638966,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.22129443287849426,
|
|
"num_tokens": 53608341.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.589526987075805,
|
|
"epoch": 2.6982647273544114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042822404514637785,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.22291859090328217,
|
|
"num_tokens": 53619598.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 5.529772615432739,
|
|
"epoch": 2.6988263042623686,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000428194642307653,
|
|
"loss": 4.9802,
|
|
"mean_token_accuracy": 0.21959089487791061,
|
|
"num_tokens": 53630174.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 5.630548572540283,
|
|
"epoch": 2.6993878811703262,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004281652345911513,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21340149343013765,
|
|
"num_tokens": 53641929.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.571681833267212,
|
|
"epoch": 2.699949458078284,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042813582199780913,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.22430293411016464,
|
|
"num_tokens": 53652262.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 5.637401151657104,
|
|
"epoch": 2.700511034986241,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004281064045285631,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.2184930771589279,
|
|
"num_tokens": 53663351.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.501698732376099,
|
|
"epoch": 2.701072611894199,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042807698218434964,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.2270791843533516,
|
|
"num_tokens": 53674632.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 5.492489147186279,
|
|
"epoch": 2.7016341888021564,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042804755496610576,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.2191448226571083,
|
|
"num_tokens": 53686346.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 5.600733518600464,
|
|
"epoch": 2.702195765710114,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042801812287476836,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.21388763338327407,
|
|
"num_tokens": 53697519.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 5.602367687225342,
|
|
"epoch": 2.7027573426180718,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004279886859112746,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.21362039893865586,
|
|
"num_tokens": 53707858.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 5.5312947750091555,
|
|
"epoch": 2.703318919526029,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042795924407656175,
|
|
"loss": 4.9574,
|
|
"mean_token_accuracy": 0.2211656913161278,
|
|
"num_tokens": 53719168.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 5.586428689956665,
|
|
"epoch": 2.7038804964339866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042792979737156717,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.22266509532928466,
|
|
"num_tokens": 53730601.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.5165135860443115,
|
|
"epoch": 2.7044420733419443,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004279003457972286,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.21919665187597276,
|
|
"num_tokens": 53741410.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 5.499764728546142,
|
|
"epoch": 2.7050036502499015,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004278708893544837,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.2259981945157051,
|
|
"num_tokens": 53752585.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 5.558006048202515,
|
|
"epoch": 2.705565227157859,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004278414280442704,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.21771454215049743,
|
|
"num_tokens": 53762604.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 5.517166996002198,
|
|
"epoch": 2.706126804065817,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042781196186752676,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.20772805362939833,
|
|
"num_tokens": 53773938.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 5.683482217788696,
|
|
"epoch": 2.7066883809737745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004277824908251909,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.21830846816301347,
|
|
"num_tokens": 53785142.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 5.705449390411377,
|
|
"epoch": 2.707249957881732,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004277530149182014,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.21444797217845918,
|
|
"num_tokens": 53797352.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 5.607677745819092,
|
|
"epoch": 2.7078115347896894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042772353414749655,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.2129104971885681,
|
|
"num_tokens": 53808027.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.451170301437378,
|
|
"epoch": 2.708373111697647,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042769404851401524,
|
|
"loss": 4.9275,
|
|
"mean_token_accuracy": 0.22241841107606888,
|
|
"num_tokens": 53818520.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 5.537364053726196,
|
|
"epoch": 2.7089346886056047,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004276645580186961,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.22288234233856202,
|
|
"num_tokens": 53829234.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 5.571797895431518,
|
|
"epoch": 2.709496265513562,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042763506266247834,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.22768196016550063,
|
|
"num_tokens": 53839097.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 5.5192718505859375,
|
|
"epoch": 2.7100578424215196,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004276055624463009,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.21334451138973237,
|
|
"num_tokens": 53850375.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 5.509925317764282,
|
|
"epoch": 2.7106194193294773,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042757605737110324,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.23576504439115525,
|
|
"num_tokens": 53861711.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 5.565814781188965,
|
|
"epoch": 2.7111809962374345,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004275465474378246,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.21972900331020356,
|
|
"num_tokens": 53872081.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 5.556499290466308,
|
|
"epoch": 2.711742573145392,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004275170326474049,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.21599068343639374,
|
|
"num_tokens": 53882591.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 5.560353422164917,
|
|
"epoch": 2.71230415005335,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042748751300078367,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.2311661124229431,
|
|
"num_tokens": 53893246.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 5.507780408859253,
|
|
"epoch": 2.7128657269613075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004274579884989008,
|
|
"loss": 4.9152,
|
|
"mean_token_accuracy": 0.23194238394498826,
|
|
"num_tokens": 53904579.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 5.428848552703857,
|
|
"epoch": 2.713427303869265,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042742845914269645,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.22007752805948258,
|
|
"num_tokens": 53916342.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 5.530459022521972,
|
|
"epoch": 2.7139888807772223,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042739892493311095,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.22191207408905028,
|
|
"num_tokens": 53927414.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 5.574505615234375,
|
|
"epoch": 2.71455045768518,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042736938587108447,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.22048151791095733,
|
|
"num_tokens": 53938679.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 5.577069473266602,
|
|
"epoch": 2.7151120345931377,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004273398419575577,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.21298779398202897,
|
|
"num_tokens": 53951364.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 5.628380393981933,
|
|
"epoch": 2.715673611501095,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004273102931934713,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.21173987835645675,
|
|
"num_tokens": 53963590.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 5.677175903320313,
|
|
"epoch": 2.7162351884090525,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000427280739579766,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.21769947707653045,
|
|
"num_tokens": 53974315.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.583457326889038,
|
|
"epoch": 2.71679676531701,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042725118111738305,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.21212602257728577,
|
|
"num_tokens": 53985058.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 5.554093217849731,
|
|
"epoch": 2.717358342224968,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004272216178072633,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.22454863637685776,
|
|
"num_tokens": 53994876.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 5.598874759674072,
|
|
"epoch": 2.7179199191329255,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004271920496503483,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.2101570561528206,
|
|
"num_tokens": 54005705.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.607243776321411,
|
|
"epoch": 2.7184814960408827,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042716247664757934,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.22021563798189164,
|
|
"num_tokens": 54015787.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 5.590617513656616,
|
|
"epoch": 2.7190430729488404,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042713289879989816,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.2145649492740631,
|
|
"num_tokens": 54027545.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 5.574843549728394,
|
|
"epoch": 2.719604649856798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004271033161082464,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.22024666517972946,
|
|
"num_tokens": 54038560.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.646217775344849,
|
|
"epoch": 2.7201662267647553,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042707372857356615,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.21420280486345292,
|
|
"num_tokens": 54049286.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 5.518394660949707,
|
|
"epoch": 2.720727803672713,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004270441361967994,
|
|
"loss": 4.9454,
|
|
"mean_token_accuracy": 0.22476993054151534,
|
|
"num_tokens": 54059894.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 5.5569994926452635,
|
|
"epoch": 2.7212893805806706,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004270145389788883,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.22141834646463393,
|
|
"num_tokens": 54070084.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 5.5050702571868895,
|
|
"epoch": 2.721850957488628,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042698493692077533,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.22715820372104645,
|
|
"num_tokens": 54081607.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 5.5751618385314945,
|
|
"epoch": 2.7224125343965855,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004269553300234031,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.21217825561761855,
|
|
"num_tokens": 54093364.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.578548431396484,
|
|
"epoch": 2.722974111304543,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042692571828771423,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.22387901544570923,
|
|
"num_tokens": 54105199.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 5.519577312469482,
|
|
"epoch": 2.723535688212501,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042689610171465147,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.2310764029622078,
|
|
"num_tokens": 54116013.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 5.592418527603149,
|
|
"epoch": 2.7240972651204585,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000426866480305158,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21720847636461257,
|
|
"num_tokens": 54128457.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.5267438888549805,
|
|
"epoch": 2.7246588420284157,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004268368540601769,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.2171653538942337,
|
|
"num_tokens": 54139865.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 5.661649370193482,
|
|
"epoch": 2.7252204189363733,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004268072229806514,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.2195376858115196,
|
|
"num_tokens": 54152264.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.664064931869507,
|
|
"epoch": 2.725781995844331,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004267775870675251,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.2274167701601982,
|
|
"num_tokens": 54164339.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 5.4914178371429445,
|
|
"epoch": 2.7263435727522882,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004267479463217415,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.22495653182268144,
|
|
"num_tokens": 54174041.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 5.51395845413208,
|
|
"epoch": 2.726905149660246,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042671830074424453,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.2258743792772293,
|
|
"num_tokens": 54186457.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.549795055389405,
|
|
"epoch": 2.7274667265682035,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000426688650335978,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.2211918443441391,
|
|
"num_tokens": 54197217.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 5.613171482086182,
|
|
"epoch": 2.728028303476161,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042665899509788593,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.22093276232481002,
|
|
"num_tokens": 54209773.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.5137670040130615,
|
|
"epoch": 2.728589880384119,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004266293350309128,
|
|
"loss": 4.9766,
|
|
"mean_token_accuracy": 0.21691375970840454,
|
|
"num_tokens": 54219772.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.4940893173217775,
|
|
"epoch": 2.729151457292076,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004265996701360026,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.2148838609457016,
|
|
"num_tokens": 54231222.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 5.598021841049194,
|
|
"epoch": 2.7297130342000337,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042657000041410026,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.22610272616147994,
|
|
"num_tokens": 54242113.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 5.602778673171997,
|
|
"epoch": 2.7302746111079914,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004265403258661503,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.22088048756122589,
|
|
"num_tokens": 54252073.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 5.572432374954223,
|
|
"epoch": 2.7308361880159486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004265106464930976,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.2125305414199829,
|
|
"num_tokens": 54262920.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 5.612000274658203,
|
|
"epoch": 2.7313977649239063,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042648096229588715,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.21904549598693848,
|
|
"num_tokens": 54274525.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 5.589860296249389,
|
|
"epoch": 2.731959341831864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042645127327546405,
|
|
"loss": 4.9623,
|
|
"mean_token_accuracy": 0.22295622825622557,
|
|
"num_tokens": 54284312.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 5.505074787139892,
|
|
"epoch": 2.732520918739821,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042642157943277375,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.2246400982141495,
|
|
"num_tokens": 54295735.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 5.502002239227295,
|
|
"epoch": 2.733082495647779,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004263918807687616,
|
|
"loss": 4.9436,
|
|
"mean_token_accuracy": 0.22359382957220078,
|
|
"num_tokens": 54306435.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 5.514667510986328,
|
|
"epoch": 2.7336440725557365,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004263621772843733,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.22747963666915894,
|
|
"num_tokens": 54316454.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 5.640577793121338,
|
|
"epoch": 2.734205649463694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004263324689805545,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.22378503978252412,
|
|
"num_tokens": 54327270.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 5.5991720199584964,
|
|
"epoch": 2.734767226371652,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004263027558582512,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.21667415052652358,
|
|
"num_tokens": 54338788.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 5.660614824295044,
|
|
"epoch": 2.735328803279609,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004262730379184095,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.2114749252796173,
|
|
"num_tokens": 54350568.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 5.563668298721313,
|
|
"epoch": 2.7358903801875667,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042624331516197554,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.2216835305094719,
|
|
"num_tokens": 54361318.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 5.5490552425384525,
|
|
"epoch": 2.7364519570955244,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042621358758989584,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.2221916899085045,
|
|
"num_tokens": 54371548.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.623265027999878,
|
|
"epoch": 2.7370135340034816,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004261838552031169,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.21096192598342894,
|
|
"num_tokens": 54384485.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.652944421768188,
|
|
"epoch": 2.7375751109114392,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042615411800258523,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.2170294925570488,
|
|
"num_tokens": 54396155.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 5.558684825897217,
|
|
"epoch": 2.738136687819397,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042612437598924793,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.21891277581453322,
|
|
"num_tokens": 54406222.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 5.71791706085205,
|
|
"epoch": 2.7386982647273546,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004260946291640519,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.2185111477971077,
|
|
"num_tokens": 54419271.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.573440361022949,
|
|
"epoch": 2.739259841635312,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042606487752794417,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.21805084496736526,
|
|
"num_tokens": 54430517.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 5.612448072433471,
|
|
"epoch": 2.7398214185432694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042603512108187224,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.20982653349637986,
|
|
"num_tokens": 54442273.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 5.5216014862060545,
|
|
"epoch": 2.740382995451227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042600535982678347,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.22384606450796127,
|
|
"num_tokens": 54452727.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.611261558532715,
|
|
"epoch": 2.7409445723591848,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042597559376362544,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.22246812880039216,
|
|
"num_tokens": 54463133.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.610063600540161,
|
|
"epoch": 2.741506149267142,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004259458228933459,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.2139550656080246,
|
|
"num_tokens": 54475525.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 5.612029027938843,
|
|
"epoch": 2.7420677261750996,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042591604721689297,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.22754261046648025,
|
|
"num_tokens": 54488012.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 5.541912364959717,
|
|
"epoch": 2.7426293030830573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004258862667352145,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.22735538631677626,
|
|
"num_tokens": 54499485.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 5.639661836624145,
|
|
"epoch": 2.7431908799910145,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004258564814492587,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.21500169038772582,
|
|
"num_tokens": 54509883.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 5.617622423171997,
|
|
"epoch": 2.743752456898972,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000425826691359974,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.2120448961853981,
|
|
"num_tokens": 54521320.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 5.614077186584472,
|
|
"epoch": 2.74431403380693,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004257968964683091,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.21707042008638383,
|
|
"num_tokens": 54532537.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 5.584558534622192,
|
|
"epoch": 2.7448756107148875,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004257670967752125,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.21783716082572938,
|
|
"num_tokens": 54542494.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 5.6383038520812985,
|
|
"epoch": 2.745437187622845,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000425737292281633,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.21060753166675567,
|
|
"num_tokens": 54553583.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 5.588726663589478,
|
|
"epoch": 2.7459987645308024,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004257074829885196,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.2249542683362961,
|
|
"num_tokens": 54565655.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.5068494319915775,
|
|
"epoch": 2.74656034143876,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004256776688968216,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.21883491724729537,
|
|
"num_tokens": 54578615.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 5.6273187637329105,
|
|
"epoch": 2.7471219183467177,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042564785000748814,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.22129494547843934,
|
|
"num_tokens": 54590645.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 5.650982141494751,
|
|
"epoch": 2.747683495254675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004256180263214687,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.218598772585392,
|
|
"num_tokens": 54602326.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 5.6791668891906735,
|
|
"epoch": 2.7482450721626326,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042558819783971295,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.20856716930866243,
|
|
"num_tokens": 54614008.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 5.616146993637085,
|
|
"epoch": 2.7488066490705902,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004255583645631705,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.22271402329206466,
|
|
"num_tokens": 54625482.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 5.693532943725586,
|
|
"epoch": 2.749368225978548,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004255285264927913,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.21355687826871872,
|
|
"num_tokens": 54636423.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 5.629725503921509,
|
|
"epoch": 2.7499298028865056,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042549868362952556,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.2149553045630455,
|
|
"num_tokens": 54648152.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.5416429996490475,
|
|
"epoch": 2.750491379794463,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042546883597432327,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.2261292368173599,
|
|
"num_tokens": 54661141.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.632721948623657,
|
|
"epoch": 2.7510529567024204,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042543898352813485,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.21437397599220276,
|
|
"num_tokens": 54671180.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 5.491722345352173,
|
|
"epoch": 2.751614533610378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000425409126291911,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.22715606391429902,
|
|
"num_tokens": 54681451.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 5.5261153221130375,
|
|
"epoch": 2.7521761105183353,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004253792642666021,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.22382416427135468,
|
|
"num_tokens": 54691760.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 5.5517534732818605,
|
|
"epoch": 2.752737687426293,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042534939745315914,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.21514102965593337,
|
|
"num_tokens": 54703761.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 5.602504634857178,
|
|
"epoch": 2.7532992643342507,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000425319525852533,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.21493685394525527,
|
|
"num_tokens": 54715495.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 5.566152715682984,
|
|
"epoch": 2.753860841242208,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004252896494656749,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.2192312404513359,
|
|
"num_tokens": 54727061.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 5.587003898620606,
|
|
"epoch": 2.7544224181501655,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004252597682935362,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.21754622757434844,
|
|
"num_tokens": 54738368.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 5.566675662994385,
|
|
"epoch": 2.754983995058123,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000425229882337068,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.21475308984518052,
|
|
"num_tokens": 54749372.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 5.60365514755249,
|
|
"epoch": 2.755545571966081,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042519999159722216,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20833380073308944,
|
|
"num_tokens": 54761309.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 5.612498044967651,
|
|
"epoch": 2.7561071488740385,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042517009607495035,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21164119392633438,
|
|
"num_tokens": 54773072.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 5.589128208160401,
|
|
"epoch": 2.7566687257819957,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042514019577120444,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.2175447851419449,
|
|
"num_tokens": 54783603.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 5.5800975322723385,
|
|
"epoch": 2.7572303026899534,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004251102906869364,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.21490543633699416,
|
|
"num_tokens": 54794706.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 5.625557708740234,
|
|
"epoch": 2.757791879597911,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004250803808230986,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.21279107332229613,
|
|
"num_tokens": 54804023.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.55083384513855,
|
|
"epoch": 2.7583534565058683,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042505046618064314,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.2256367549300194,
|
|
"num_tokens": 54813616.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 5.601083993911743,
|
|
"epoch": 2.758915033413826,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042502054676052273,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.2203081175684929,
|
|
"num_tokens": 54825876.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 5.689446592330933,
|
|
"epoch": 2.7594766103217836,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042499062256368987,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.2169337809085846,
|
|
"num_tokens": 54837207.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 5.59466061592102,
|
|
"epoch": 2.7600381872297413,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004249606935910975,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.2187360167503357,
|
|
"num_tokens": 54849155.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 5.592064905166626,
|
|
"epoch": 2.760599764137699,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004249307598436984,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.21958846598863602,
|
|
"num_tokens": 54860345.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 5.53883810043335,
|
|
"epoch": 2.761161341045656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004249008213224458,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.21966609358787537,
|
|
"num_tokens": 54871676.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 5.547421073913574,
|
|
"epoch": 2.761722917953614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042487087802829275,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.21987203657627105,
|
|
"num_tokens": 54882352.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.658636665344238,
|
|
"epoch": 2.7622844948615715,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004248409299621931,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.22315721362829208,
|
|
"num_tokens": 54893862.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 5.5933526992797855,
|
|
"epoch": 2.7628460717695287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004248109771251,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.22097033113241196,
|
|
"num_tokens": 54904851.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 5.643644142150879,
|
|
"epoch": 2.7634076486774863,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042478101951796716,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.21780983209609986,
|
|
"num_tokens": 54916472.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 5.582379388809204,
|
|
"epoch": 2.763969225585444,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004247510571417487,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.22177616953849794,
|
|
"num_tokens": 54927383.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 5.608755683898925,
|
|
"epoch": 2.764530802493401,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004247210899973985,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.2202654927968979,
|
|
"num_tokens": 54938157.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 5.634595727920532,
|
|
"epoch": 2.765092379401359,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004246911180858707,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.22345135658979415,
|
|
"num_tokens": 54949812.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 5.636399269104004,
|
|
"epoch": 2.7656539563093165,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004246611414081197,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20676581263542176,
|
|
"num_tokens": 54961201.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 5.611662340164185,
|
|
"epoch": 2.766215533217274,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042463115996509984,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.22162859439849852,
|
|
"num_tokens": 54971071.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 5.61544280052185,
|
|
"epoch": 2.766777110125232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004246011737577658,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.2158202737569809,
|
|
"num_tokens": 54981294.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.626071119308472,
|
|
"epoch": 2.767338687033189,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004245711827870724,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.21849923133850097,
|
|
"num_tokens": 54994071.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 5.639868831634521,
|
|
"epoch": 2.7679002639411467,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042454118705397454,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.21918870210647584,
|
|
"num_tokens": 55005087.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 5.5640827178955075,
|
|
"epoch": 2.7684618408491044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004245111865594273,
|
|
"loss": 4.9532,
|
|
"mean_token_accuracy": 0.22642153054475783,
|
|
"num_tokens": 55016103.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.6164774894714355,
|
|
"epoch": 2.7690234177570616,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042448118130438583,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.2136676162481308,
|
|
"num_tokens": 55028656.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 5.6489166736602785,
|
|
"epoch": 2.7695849946650193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042445117128980553,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.2168092295527458,
|
|
"num_tokens": 55038957.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 5.589179039001465,
|
|
"epoch": 2.770146571572977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042442115651664217,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.22629621177911757,
|
|
"num_tokens": 55050407.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 5.6163280487060545,
|
|
"epoch": 2.7707081484809346,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042439113698585103,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.21637962013483047,
|
|
"num_tokens": 55060119.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 5.61150050163269,
|
|
"epoch": 2.7712697253888923,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004243611126983882,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.2211490750312805,
|
|
"num_tokens": 55072059.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 5.533651399612427,
|
|
"epoch": 2.7718313022968495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042433108365520967,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.21819489002227782,
|
|
"num_tokens": 55083640.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 5.576551151275635,
|
|
"epoch": 2.772392879204807,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042430104985727155,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.21939810067415239,
|
|
"num_tokens": 55093014.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.61958532333374,
|
|
"epoch": 2.772954456112765,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042427101130553,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.22353479117155076,
|
|
"num_tokens": 55102795.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.612531232833862,
|
|
"epoch": 2.773516033020722,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004242409680009416,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.21285583823919296,
|
|
"num_tokens": 55114389.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 5.646224737167358,
|
|
"epoch": 2.7740776099286797,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004242109199444629,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.2165633872151375,
|
|
"num_tokens": 55125078.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 5.613523197174072,
|
|
"epoch": 2.7746391868366374,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004241808671370506,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.21897988319396972,
|
|
"num_tokens": 55135151.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 5.570691967010498,
|
|
"epoch": 2.7752007637445946,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042415080957966176,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.21986111402511596,
|
|
"num_tokens": 55146330.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 5.553201341629029,
|
|
"epoch": 2.7757623406525522,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004241207472732531,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.22506178617477418,
|
|
"num_tokens": 55156636.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 5.627899122238159,
|
|
"epoch": 2.77632391756051,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004240906802187821,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.21474718153476716,
|
|
"num_tokens": 55168761.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 5.576206922531128,
|
|
"epoch": 2.7768854944684676,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004240606084172061,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.2215985029935837,
|
|
"num_tokens": 55180747.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 5.653404664993286,
|
|
"epoch": 2.777447071376425,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042403053186948237,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.2087620824575424,
|
|
"num_tokens": 55191645.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 5.56553282737732,
|
|
"epoch": 2.7780086482843824,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004240004505765688,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.21187689006328583,
|
|
"num_tokens": 55203623.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 5.616534757614136,
|
|
"epoch": 2.77857022519234,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004239703645394231,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.21366011202335358,
|
|
"num_tokens": 55214635.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 5.5404528141021725,
|
|
"epoch": 2.7791318021002978,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004239402737590032,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.2171587571501732,
|
|
"num_tokens": 55225524.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 5.505533742904663,
|
|
"epoch": 2.779693379008255,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042391017823626716,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.22355866879224778,
|
|
"num_tokens": 55238360.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 5.697990226745605,
|
|
"epoch": 2.7802549559162126,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004238800779721734,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.20726322680711745,
|
|
"num_tokens": 55248524.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 5.697133255004883,
|
|
"epoch": 2.7808165328241703,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042384997296768007,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.21429698318243026,
|
|
"num_tokens": 55260283.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 5.651599597930908,
|
|
"epoch": 2.781378109732128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000423819863223746,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.22127679288387297,
|
|
"num_tokens": 55271928.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.615195226669312,
|
|
"epoch": 2.7819396866400856,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042378974874132967,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.21925686597824096,
|
|
"num_tokens": 55283015.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 5.567049598693847,
|
|
"epoch": 2.782501263548043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004237596295213901,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.2232092186808586,
|
|
"num_tokens": 55293918.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 5.496550226211548,
|
|
"epoch": 2.7830628404560005,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004237295055648862,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.21526937782764435,
|
|
"num_tokens": 55305808.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.5662178039550785,
|
|
"epoch": 2.783624417363958,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042369937687277716,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.21711852699518203,
|
|
"num_tokens": 55318128.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 5.6404852867126465,
|
|
"epoch": 2.7841859942719154,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004236692434460223,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.21978225260972978,
|
|
"num_tokens": 55329934.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 5.720998096466064,
|
|
"epoch": 2.784747571179873,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004236391052855811,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.21627382785081864,
|
|
"num_tokens": 55340971.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 5.605195426940918,
|
|
"epoch": 2.7853091480878307,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042360896239241306,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.21438998132944107,
|
|
"num_tokens": 55352243.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 5.634967184066772,
|
|
"epoch": 2.785870724995788,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042357881476747807,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.22047195434570313,
|
|
"num_tokens": 55363694.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 5.617276668548584,
|
|
"epoch": 2.7864323019037456,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000423548662411736,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.21638458967208862,
|
|
"num_tokens": 55375720.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 5.598473167419433,
|
|
"epoch": 2.7869938788117032,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004235185053261469,
|
|
"loss": 4.9952,
|
|
"mean_token_accuracy": 0.22519772201776506,
|
|
"num_tokens": 55387493.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 5.672822904586792,
|
|
"epoch": 2.787555455719661,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000423488343511671,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.20349788963794707,
|
|
"num_tokens": 55399468.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.604741191864013,
|
|
"epoch": 2.7881170326276186,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004234581769692686,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.21332421898841858,
|
|
"num_tokens": 55411526.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 5.611629390716553,
|
|
"epoch": 2.788678609535576,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004234280056999003,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.2224307671189308,
|
|
"num_tokens": 55422550.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 5.5610949993133545,
|
|
"epoch": 2.7892401864435334,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004233978297045267,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.22901219874620438,
|
|
"num_tokens": 55433433.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 5.552649211883545,
|
|
"epoch": 2.789801763351491,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004233676489841087,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.22923493385314941,
|
|
"num_tokens": 55444225.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 5.614105129241944,
|
|
"epoch": 2.7903633402594483,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042333746353960723,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.22101957499980926,
|
|
"num_tokens": 55456117.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 5.546189451217652,
|
|
"epoch": 2.790924917167406,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004233072733719833,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.21858023554086686,
|
|
"num_tokens": 55467267.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 5.630628347396851,
|
|
"epoch": 2.7914864940753636,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004232770784821984,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.21942986249923707,
|
|
"num_tokens": 55478520.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 5.632269048690796,
|
|
"epoch": 2.7920480709833213,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042324687887121366,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.21222303658723832,
|
|
"num_tokens": 55489704.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.569357109069824,
|
|
"epoch": 2.792609647891279,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004232166745399909,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.2248135909438133,
|
|
"num_tokens": 55500942.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.628040504455567,
|
|
"epoch": 2.793171224799236,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042318646548949177,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.20071526020765304,
|
|
"num_tokens": 55512691.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 5.597206926345825,
|
|
"epoch": 2.793732801707194,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042315625172067794,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.2301034539937973,
|
|
"num_tokens": 55523827.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 5.637387752532959,
|
|
"epoch": 2.7942943786151515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042312603323451173,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.21762217432260514,
|
|
"num_tokens": 55534674.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 5.578826904296875,
|
|
"epoch": 2.7948559555231087,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004230958100319551,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.2252967119216919,
|
|
"num_tokens": 55545504.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 5.624304008483887,
|
|
"epoch": 2.7954175324310664,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004230655821139705,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.2055450886487961,
|
|
"num_tokens": 55557818.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 5.6314921379089355,
|
|
"epoch": 2.795979109339024,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004230353494815203,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.22097052186727523,
|
|
"num_tokens": 55568143.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 5.6623317241668705,
|
|
"epoch": 2.7965406862469813,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004230051121355672,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.21232933849096297,
|
|
"num_tokens": 55579358.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 5.608452367782593,
|
|
"epoch": 2.797102263154939,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042297487007707387,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.20934192687273026,
|
|
"num_tokens": 55590430.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 5.582632970809937,
|
|
"epoch": 2.7976638400628966,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042294462330700336,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.22190260887145996,
|
|
"num_tokens": 55602377.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 5.601512384414673,
|
|
"epoch": 2.7982254169708543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004229143718263186,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.21553928703069686,
|
|
"num_tokens": 55613261.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 5.488930082321167,
|
|
"epoch": 2.798786993878812,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004228841156359829,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.22007523626089096,
|
|
"num_tokens": 55624514.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 5.591027879714966,
|
|
"epoch": 2.799348570786769,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004228538547369596,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.21814448833465577,
|
|
"num_tokens": 55635899.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 5.617343139648438,
|
|
"epoch": 2.799910147694727,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042282358913021224,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.22072907388210297,
|
|
"num_tokens": 55646807.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 5.651160621643067,
|
|
"epoch": 2.8004717246026845,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042279331881670446,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.22227088063955308,
|
|
"num_tokens": 55658937.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 5.5538359642028805,
|
|
"epoch": 2.8010333015106417,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004227630437974,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.2219369351863861,
|
|
"num_tokens": 55670216.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.656847715377808,
|
|
"epoch": 2.8015948784185993,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042273276407326304,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.22021135836839675,
|
|
"num_tokens": 55682743.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.546968984603882,
|
|
"epoch": 2.802156455326557,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042270247964525755,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.21341633349657058,
|
|
"num_tokens": 55694338.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 5.622180652618408,
|
|
"epoch": 2.8027180322345147,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004226721905143477,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.2152806267142296,
|
|
"num_tokens": 55704224.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.531118679046631,
|
|
"epoch": 2.8032796091424723,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042264189668149817,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.21417306214571,
|
|
"num_tokens": 55714901.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 5.648329448699951,
|
|
"epoch": 2.8038411860504295,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004226115981476733,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.20825002938508988,
|
|
"num_tokens": 55725020.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 5.536133337020874,
|
|
"epoch": 2.804402762958387,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000422581294913838,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.21989802420139312,
|
|
"num_tokens": 55735643.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.551947546005249,
|
|
"epoch": 2.804964339866345,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000422550986980957,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.21446762830018998,
|
|
"num_tokens": 55745778.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 5.527707767486572,
|
|
"epoch": 2.805525916774302,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042252067434999524,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.21430004388093948,
|
|
"num_tokens": 55757055.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 5.544073867797851,
|
|
"epoch": 2.8060874936822597,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004224903570219181,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.21548645794391633,
|
|
"num_tokens": 55768193.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 5.545985364913941,
|
|
"epoch": 2.8066490705902174,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042246003499769077,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.2239174321293831,
|
|
"num_tokens": 55779382.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 5.543783235549927,
|
|
"epoch": 2.8072106474981746,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042242970827827874,
|
|
"loss": 4.9485,
|
|
"mean_token_accuracy": 0.22828053086996078,
|
|
"num_tokens": 55790933.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.520154905319214,
|
|
"epoch": 2.8077722244061323,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004223993768646476,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.2215719848871231,
|
|
"num_tokens": 55803101.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.5459935665130615,
|
|
"epoch": 2.80833380131409,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004223690407577631,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.22632056921720506,
|
|
"num_tokens": 55814651.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 5.604466152191162,
|
|
"epoch": 2.8088953782220476,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042233869995859127,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.2173448085784912,
|
|
"num_tokens": 55825696.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.551787233352661,
|
|
"epoch": 2.8094569551300053,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042230835446809803,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.22348258942365645,
|
|
"num_tokens": 55836679.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 5.562099409103394,
|
|
"epoch": 2.8100185320379625,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004222780042872496,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.21157509982585906,
|
|
"num_tokens": 55848013.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 5.497231721878052,
|
|
"epoch": 2.81058010894592,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004222476494170125,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.22729654908180236,
|
|
"num_tokens": 55859310.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 5.597151041030884,
|
|
"epoch": 2.811141685853878,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004222172898583531,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.20485784113407135,
|
|
"num_tokens": 55870484.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.662850189208984,
|
|
"epoch": 2.811703262761835,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004221869256122381,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.21494369208812714,
|
|
"num_tokens": 55881279.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 5.590051221847534,
|
|
"epoch": 2.8122648396697927,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004221565566796343,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.2165265291929245,
|
|
"num_tokens": 55893029.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.4660204410552975,
|
|
"epoch": 2.8128264165777503,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004221261830615086,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.2302219018340111,
|
|
"num_tokens": 55904171.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 5.516700315475464,
|
|
"epoch": 2.813387993485708,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004220958047588282,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.22349219024181366,
|
|
"num_tokens": 55916121.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 5.591952991485596,
|
|
"epoch": 2.8139495703936657,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004220654217725603,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.2101338416337967,
|
|
"num_tokens": 55925982.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.592261266708374,
|
|
"epoch": 2.814511147301623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042203503410367244,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.22079451531171798,
|
|
"num_tokens": 55935768.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.625176095962525,
|
|
"epoch": 2.8150727242095805,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000422004641753132,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.2258559837937355,
|
|
"num_tokens": 55946742.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 5.5510008335113525,
|
|
"epoch": 2.815634301117538,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004219742447219068,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.2256132110953331,
|
|
"num_tokens": 55957133.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 5.5698424816131595,
|
|
"epoch": 2.8161958780254954,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042194384301096457,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.22091479748487472,
|
|
"num_tokens": 55967179.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 5.4881181716918945,
|
|
"epoch": 2.816757454933453,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042191343662127337,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.22647910863161086,
|
|
"num_tokens": 55977713.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.608286190032959,
|
|
"epoch": 2.8173190318414107,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042188302555380144,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.21693834215402602,
|
|
"num_tokens": 55988650.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 5.555837774276734,
|
|
"epoch": 2.817880608749368,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000421852609809517,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.21836603283882142,
|
|
"num_tokens": 55999745.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 5.535125494003296,
|
|
"epoch": 2.8184421856573256,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004218221893893884,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.22247155755758286,
|
|
"num_tokens": 56011171.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 5.5078123092651365,
|
|
"epoch": 2.8190037625652833,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042179176429438454,
|
|
"loss": 4.9908,
|
|
"mean_token_accuracy": 0.2272492378950119,
|
|
"num_tokens": 56022121.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 5.5384063720703125,
|
|
"epoch": 2.819565339473241,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004217613345254739,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.22011999487876893,
|
|
"num_tokens": 56033769.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.545672798156739,
|
|
"epoch": 2.8201269163811986,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042173090008362535,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.22202559262514115,
|
|
"num_tokens": 56044691.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.504302597045898,
|
|
"epoch": 2.820688493289156,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042170046096980807,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.22252642810344697,
|
|
"num_tokens": 56055639.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.656686878204345,
|
|
"epoch": 2.8212500701971135,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042167001718499124,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.2176651045680046,
|
|
"num_tokens": 56066579.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 5.637359189987182,
|
|
"epoch": 2.821811647105071,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004216395687301442,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.21362511217594146,
|
|
"num_tokens": 56076871.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 5.623414993286133,
|
|
"epoch": 2.8223732240130284,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004216091156062364,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.2145496726036072,
|
|
"num_tokens": 56090022.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 5.452678442001343,
|
|
"epoch": 2.822934800920986,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004215786578142375,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.23220874816179277,
|
|
"num_tokens": 56100545.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 5.572584390640259,
|
|
"epoch": 2.8234963778289437,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042154819535511733,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20995839983224868,
|
|
"num_tokens": 56112059.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 5.589248943328857,
|
|
"epoch": 2.8240579547369014,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042151772822984567,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.22118968665599822,
|
|
"num_tokens": 56123162.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 5.747325086593628,
|
|
"epoch": 2.824619531644859,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004214872564393928,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.2172114595770836,
|
|
"num_tokens": 56136008.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.619822072982788,
|
|
"epoch": 2.8251811085528162,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004214567799847289,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.2245807483792305,
|
|
"num_tokens": 56147169.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.547734355926513,
|
|
"epoch": 2.825742685460774,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004214262988668242,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.2187368780374527,
|
|
"num_tokens": 56157644.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 5.614610481262207,
|
|
"epoch": 2.8263042623687316,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004213958130866494,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.21630357056856156,
|
|
"num_tokens": 56168248.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.666193532943725,
|
|
"epoch": 2.8268658392766888,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042136532264517527,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.21701632291078568,
|
|
"num_tokens": 56179140.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.624569940567016,
|
|
"epoch": 2.8274274161846464,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042133482754337236,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.21418482810258865,
|
|
"num_tokens": 56190184.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 5.636811542510986,
|
|
"epoch": 2.827988993092604,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042130432778221186,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.22389225661754608,
|
|
"num_tokens": 56201619.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 5.529171514511108,
|
|
"epoch": 2.8285505700005613,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042127382336266467,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.2135986328125,
|
|
"num_tokens": 56212339.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.647890090942383,
|
|
"epoch": 2.829112146908519,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004212433142857024,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.22764317095279693,
|
|
"num_tokens": 56224734.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 5.599243593215943,
|
|
"epoch": 2.8296737238164766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042121280055229624,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.2194100558757782,
|
|
"num_tokens": 56235594.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 5.520002746582032,
|
|
"epoch": 2.8302353007244343,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004211822821634177,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.22107012569904327,
|
|
"num_tokens": 56246932.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 5.505723237991333,
|
|
"epoch": 2.830796877632392,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004211517591200387,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.22343918681144714,
|
|
"num_tokens": 56258217.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 5.632580089569092,
|
|
"epoch": 2.831358454540349,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004211212314231309,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.21510278880596162,
|
|
"num_tokens": 56269226.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 5.585519695281983,
|
|
"epoch": 2.831920031448307,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042109069907366646,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.21452156007289885,
|
|
"num_tokens": 56280411.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 5.612366008758545,
|
|
"epoch": 2.8324816083562645,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042106016207261754,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.21425868421792985,
|
|
"num_tokens": 56292048.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 5.550600194931031,
|
|
"epoch": 2.8330431852642217,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042102962042095643,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.21906120628118514,
|
|
"num_tokens": 56302470.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 5.587191247940064,
|
|
"epoch": 2.8336047621721794,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042099907411965553,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.21981210112571717,
|
|
"num_tokens": 56313871.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 5.499729013442993,
|
|
"epoch": 2.834166339080137,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042096852316968756,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.2242471918463707,
|
|
"num_tokens": 56325455.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.617038154602051,
|
|
"epoch": 2.8347279159880947,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042093796757202513,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.22257792800664902,
|
|
"num_tokens": 56336187.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.683760643005371,
|
|
"epoch": 2.8352894928960524,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004209074073276412,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.21053181141614913,
|
|
"num_tokens": 56348175.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.602967357635498,
|
|
"epoch": 2.8358510698040096,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004208768424375089,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.21564120650291443,
|
|
"num_tokens": 56359668.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.60188045501709,
|
|
"epoch": 2.8364126467119672,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042084627290260124,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.2215082451701164,
|
|
"num_tokens": 56371160.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 5.532908725738525,
|
|
"epoch": 2.836974223619925,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004208156987238918,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.2215232267975807,
|
|
"num_tokens": 56382873.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 5.5972696304321286,
|
|
"epoch": 2.837535800527882,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004207851199023539,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.22182929068803786,
|
|
"num_tokens": 56393562.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 5.605169630050659,
|
|
"epoch": 2.83809737743584,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042075453643896125,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.2161230832338333,
|
|
"num_tokens": 56405789.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 5.562541055679321,
|
|
"epoch": 2.8386589543437974,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042072394833468765,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.22654656171798707,
|
|
"num_tokens": 56417621.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 5.620244741439819,
|
|
"epoch": 2.8392205312517547,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000420693355590507,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.21427745074033738,
|
|
"num_tokens": 56430167.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 5.592439222335815,
|
|
"epoch": 2.8397821081597123,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042066275820739333,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.213396418094635,
|
|
"num_tokens": 56441853.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.483617925643921,
|
|
"epoch": 2.84034368506767,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000420632156186321,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.22101952284574508,
|
|
"num_tokens": 56454504.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 5.601282405853271,
|
|
"epoch": 2.8409052619756276,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004206015495282644,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.22482540756464003,
|
|
"num_tokens": 56465503.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 5.6149476051330565,
|
|
"epoch": 2.8414668388835853,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042057093823419795,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.2148782342672348,
|
|
"num_tokens": 56475310.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 5.570071268081665,
|
|
"epoch": 2.8420284157915425,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042054032230509636,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.22249614000320433,
|
|
"num_tokens": 56486575.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.677678966522217,
|
|
"epoch": 2.8425899926995,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042050970174193437,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.21606945395469665,
|
|
"num_tokens": 56496542.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 5.682838726043701,
|
|
"epoch": 2.843151569607458,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042047907654568724,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.2193937838077545,
|
|
"num_tokens": 56507124.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.611813735961914,
|
|
"epoch": 2.843713146515415,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004204484467173297,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.21647137254476548,
|
|
"num_tokens": 56518635.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 5.548235273361206,
|
|
"epoch": 2.8442747234233727,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004204178122578373,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.2296797513961792,
|
|
"num_tokens": 56529499.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 5.595295143127442,
|
|
"epoch": 2.8448363003313304,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042038717316818534,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.2186821550130844,
|
|
"num_tokens": 56542432.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.6039834976196286,
|
|
"epoch": 2.845397877239288,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004203565294493494,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.21384170800447463,
|
|
"num_tokens": 56552783.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 5.578670263290405,
|
|
"epoch": 2.8459594541472457,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042032588110230525,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.2193298265337944,
|
|
"num_tokens": 56563654.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 5.624504470825196,
|
|
"epoch": 2.846521031055203,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004202952281280286,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21905057728290558,
|
|
"num_tokens": 56575541.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 5.665398120880127,
|
|
"epoch": 2.8470826079631606,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004202645705274956,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.2144771173596382,
|
|
"num_tokens": 56588397.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 5.610690116882324,
|
|
"epoch": 2.8476441848711183,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042023390830168224,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.2167350471019745,
|
|
"num_tokens": 56599858.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 5.6298754692077635,
|
|
"epoch": 2.8482057617790755,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000420203241451565,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.22255731225013733,
|
|
"num_tokens": 56610972.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 5.570920419692993,
|
|
"epoch": 2.848767338687033,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042017256997812016,
|
|
"loss": 4.9431,
|
|
"mean_token_accuracy": 0.22578550428152083,
|
|
"num_tokens": 56621619.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 5.555037021636963,
|
|
"epoch": 2.849328915594991,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042014189388232446,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.2185448080301285,
|
|
"num_tokens": 56632955.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 5.6541999816894535,
|
|
"epoch": 2.849890492502948,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004201112131651545,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.21847341060638428,
|
|
"num_tokens": 56645896.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.545515871047973,
|
|
"epoch": 2.8504520694109057,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004200805278275873,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.22004535049200058,
|
|
"num_tokens": 56656974.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.679248809814453,
|
|
"epoch": 2.8510136463188633,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004200498378705997,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.213205486536026,
|
|
"num_tokens": 56669251.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 5.628998327255249,
|
|
"epoch": 2.851575223226821,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004200191432951692,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.23081331104040145,
|
|
"num_tokens": 56679526.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 5.5765221118927,
|
|
"epoch": 2.8521368001347787,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004199884441022728,
|
|
"loss": 4.9802,
|
|
"mean_token_accuracy": 0.21962834745645524,
|
|
"num_tokens": 56690276.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 5.483601522445679,
|
|
"epoch": 2.852698377042736,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00041995774029288807,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.22877176254987716,
|
|
"num_tokens": 56702509.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 5.592777490615845,
|
|
"epoch": 2.8532599539506935,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041992703186799273,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.21983936578035354,
|
|
"num_tokens": 56713562.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 5.560223340988159,
|
|
"epoch": 2.853821530858651,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041989631882856447,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.21689575612545015,
|
|
"num_tokens": 56724793.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.582694959640503,
|
|
"epoch": 2.8543831077666084,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004198656011755812,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.21342141777276993,
|
|
"num_tokens": 56736842.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 5.626321315765381,
|
|
"epoch": 2.854944684674566,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004198348789100211,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.21372145116329194,
|
|
"num_tokens": 56748220.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 5.496590995788575,
|
|
"epoch": 2.8555062615825237,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041980415203286223,
|
|
"loss": 4.917,
|
|
"mean_token_accuracy": 0.22714268714189528,
|
|
"num_tokens": 56758420.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 5.502436971664428,
|
|
"epoch": 2.8560678384904814,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000419773420545083,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.2290786013007164,
|
|
"num_tokens": 56768801.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 5.66392674446106,
|
|
"epoch": 2.856629415398439,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041974268444766187,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.2118438869714737,
|
|
"num_tokens": 56780756.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.558347225189209,
|
|
"epoch": 2.8571909923063963,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004197119437415776,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.22431382685899734,
|
|
"num_tokens": 56790679.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 5.573500442504883,
|
|
"epoch": 2.857752569214354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004196811984278089,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.2203909710049629,
|
|
"num_tokens": 56802513.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 5.586177635192871,
|
|
"epoch": 2.8583141461223116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004196504485073347,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.2201363429427147,
|
|
"num_tokens": 56813213.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 5.61485595703125,
|
|
"epoch": 2.858875723030269,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041961969398113404,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.21364909261465073,
|
|
"num_tokens": 56825097.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.595111989974976,
|
|
"epoch": 2.8594372999382265,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041958893485018634,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.21799872666597367,
|
|
"num_tokens": 56837185.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 5.534339904785156,
|
|
"epoch": 2.859998876846184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004195581711154709,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.21605376601219178,
|
|
"num_tokens": 56848696.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.571237516403198,
|
|
"epoch": 2.8605604537541414,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041952740277796717,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.21382589340209962,
|
|
"num_tokens": 56860955.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.641934156417847,
|
|
"epoch": 2.861122030662099,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041949662983865486,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.22525737434625626,
|
|
"num_tokens": 56872375.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.6342205047607425,
|
|
"epoch": 2.8616836075700567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004194658522985139,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.21301176398992538,
|
|
"num_tokens": 56883644.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.586756229400635,
|
|
"epoch": 2.8622451844780143,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004194350701585241,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.21257018595933913,
|
|
"num_tokens": 56894803.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 5.6222553730010985,
|
|
"epoch": 2.862806761385972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004194042834196656,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.21669812947511674,
|
|
"num_tokens": 56906475.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 5.6371039867401125,
|
|
"epoch": 2.8633683382939292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004193734920829188,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.21696168035268784,
|
|
"num_tokens": 56918086.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 5.55425271987915,
|
|
"epoch": 2.863929915201887,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000419342696149264,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.23110055178403854,
|
|
"num_tokens": 56929300.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.633211851119995,
|
|
"epoch": 2.8644914921098446,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004193118956196818,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.22795605808496475,
|
|
"num_tokens": 56941858.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 5.616082334518433,
|
|
"epoch": 2.8650530690178018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004192810904951528,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.21582840383052826,
|
|
"num_tokens": 56953214.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 5.568009233474731,
|
|
"epoch": 2.8656146459257594,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000419250280776658,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.21862360835075378,
|
|
"num_tokens": 56963437.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 5.631611919403076,
|
|
"epoch": 2.866176222833717,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004192194664651783,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.22637753933668137,
|
|
"num_tokens": 56975771.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 5.54576473236084,
|
|
"epoch": 2.8667377997416748,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004191886475616947,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.22778481394052505,
|
|
"num_tokens": 56986084.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 5.460924863815308,
|
|
"epoch": 2.8672993766496324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041915782406718875,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.22985132336616515,
|
|
"num_tokens": 56996616.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.499322175979614,
|
|
"epoch": 2.8678609535575896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004191269959826418,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.2220218911767006,
|
|
"num_tokens": 57008431.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 5.539438533782959,
|
|
"epoch": 2.8684225304655473,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041909616330903544,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.21979374438524246,
|
|
"num_tokens": 57019265.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 5.60076494216919,
|
|
"epoch": 2.868984107373505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041906532604735127,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.22223494797945023,
|
|
"num_tokens": 57029869.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.623810243606568,
|
|
"epoch": 2.869545684281462,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004190344841985713,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.22648789882659912,
|
|
"num_tokens": 57041168.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.500378799438477,
|
|
"epoch": 2.87010726118942,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041900363776367747,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.23076533526182175,
|
|
"num_tokens": 57052190.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 5.6062055110931395,
|
|
"epoch": 2.8706688380973775,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004189727867436519,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.21113839596509934,
|
|
"num_tokens": 57063817.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 5.654064798355103,
|
|
"epoch": 2.8712304150053347,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041894193113947703,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.21746568381786346,
|
|
"num_tokens": 57074998.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 5.554781532287597,
|
|
"epoch": 2.8717919919132924,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041891107095213523,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.22703617364168166,
|
|
"num_tokens": 57085377.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.525472974777221,
|
|
"epoch": 2.87235356882125,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041888020618260913,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.2222997471690178,
|
|
"num_tokens": 57096698.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 5.453274822235107,
|
|
"epoch": 2.8729151457292077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004188493368318814,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.23559003919363022,
|
|
"num_tokens": 57107559.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.600018072128296,
|
|
"epoch": 2.8734767226371654,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000418818462900935,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.2213119626045227,
|
|
"num_tokens": 57118252.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 5.663866853713989,
|
|
"epoch": 2.8740382995451226,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004187875843907531,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.20774328857660293,
|
|
"num_tokens": 57128635.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.579119348526001,
|
|
"epoch": 2.8745998764530802,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041875670130231857,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.21427127867937087,
|
|
"num_tokens": 57138139.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 5.640179538726807,
|
|
"epoch": 2.875161453361038,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000418725813636615,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.22114354074001313,
|
|
"num_tokens": 57149456.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 5.693110561370849,
|
|
"epoch": 2.875723030268995,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041869492139462585,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.2198270305991173,
|
|
"num_tokens": 57160710.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 5.5945288181304935,
|
|
"epoch": 2.876284607176953,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041866402457733454,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.21979276835918427,
|
|
"num_tokens": 57172006.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 5.57083101272583,
|
|
"epoch": 2.8768461840849104,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041863312318572504,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21841199398040773,
|
|
"num_tokens": 57183665.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 5.564107418060303,
|
|
"epoch": 2.877407760992868,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004186022172207812,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.21109368652105331,
|
|
"num_tokens": 57195711.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.587660408020019,
|
|
"epoch": 2.8779693379008258,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041857130668348705,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.22217325866222382,
|
|
"num_tokens": 57206664.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 5.587422847747803,
|
|
"epoch": 2.878530914808783,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004185403915748268,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.20906299650669097,
|
|
"num_tokens": 57217407.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.5482477188110355,
|
|
"epoch": 2.8790924917167406,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004185094718957848,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.2242898926138878,
|
|
"num_tokens": 57228707.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 5.523576259613037,
|
|
"epoch": 2.8796540686246983,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041847854764734556,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.2240604043006897,
|
|
"num_tokens": 57240802.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 5.584910535812378,
|
|
"epoch": 2.8802156455326555,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004184476188304937,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.21112448126077651,
|
|
"num_tokens": 57251999.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 5.721147775650024,
|
|
"epoch": 2.880777222440613,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041841668544621396,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.21009841859340667,
|
|
"num_tokens": 57264199.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 5.564109849929809,
|
|
"epoch": 2.881338799348571,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004183857474954915,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.21615907400846482,
|
|
"num_tokens": 57275234.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 5.635121154785156,
|
|
"epoch": 2.881900376256528,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041835480497931114,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.2142004445195198,
|
|
"num_tokens": 57286920.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 5.651198959350586,
|
|
"epoch": 2.8824619531644857,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004183238578986582,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.21833174526691437,
|
|
"num_tokens": 57298148.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 5.569286966323853,
|
|
"epoch": 2.8830235300724434,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041829290625451806,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.22026716470718383,
|
|
"num_tokens": 57308717.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 5.54247727394104,
|
|
"epoch": 2.883585106980401,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041826195004787616,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.21268752217292786,
|
|
"num_tokens": 57319308.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 5.664852952957153,
|
|
"epoch": 2.8841466838883587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041823098927971827,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.20864370912313462,
|
|
"num_tokens": 57330911.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 5.625681781768799,
|
|
"epoch": 2.884708260796316,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004182000239510301,
|
|
"loss": 5.0438,
|
|
"mean_token_accuracy": 0.21077817678451538,
|
|
"num_tokens": 57341624.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 5.599301052093506,
|
|
"epoch": 2.8852698377042736,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041816905406279756,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.22161109894514083,
|
|
"num_tokens": 57353399.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 5.676513195037842,
|
|
"epoch": 2.8858314146122312,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041813807961600685,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.21541933417320253,
|
|
"num_tokens": 57364481.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 5.564233207702637,
|
|
"epoch": 2.8863929915201885,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004181071006116442,
|
|
"loss": 4.9448,
|
|
"mean_token_accuracy": 0.22597839683294296,
|
|
"num_tokens": 57375588.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 5.4937660694122314,
|
|
"epoch": 2.886954568428146,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041807611705069593,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.2205230787396431,
|
|
"num_tokens": 57387048.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.535889196395874,
|
|
"epoch": 2.887516145336104,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041804512893414865,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.2300904855132103,
|
|
"num_tokens": 57397946.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 5.623824214935302,
|
|
"epoch": 2.8880777222440615,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041801413626298893,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.2212996229529381,
|
|
"num_tokens": 57409505.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.533370399475098,
|
|
"epoch": 2.888639299152019,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004179831390382037,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.21612535566091537,
|
|
"num_tokens": 57420745.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 5.611901807785034,
|
|
"epoch": 2.8892008760599763,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004179521372607798,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.2170137494802475,
|
|
"num_tokens": 57431557.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 5.554759407043457,
|
|
"epoch": 2.889762452967934,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041792113093170447,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.21813760250806807,
|
|
"num_tokens": 57442029.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 5.713116264343261,
|
|
"epoch": 2.8903240298758917,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004178901200519649,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.21058197617530822,
|
|
"num_tokens": 57452921.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.537770223617554,
|
|
"epoch": 2.890885606783849,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004178591046225485,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.2225617364048958,
|
|
"num_tokens": 57463068.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 5.598526334762573,
|
|
"epoch": 2.8914471836918065,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041782808464444274,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.22234574109315872,
|
|
"num_tokens": 57474064.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 5.5382448673248295,
|
|
"epoch": 2.892008760599764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041779706011863546,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.22327730506658555,
|
|
"num_tokens": 57485473.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 5.500561666488648,
|
|
"epoch": 2.8925703375077214,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041776603104611427,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.2290210410952568,
|
|
"num_tokens": 57495562.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 5.565589189529419,
|
|
"epoch": 2.893131914415679,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041773499742786736,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.22601421028375626,
|
|
"num_tokens": 57506322.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.592988729476929,
|
|
"epoch": 2.8936934913236367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041770395926488276,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.2185847729444504,
|
|
"num_tokens": 57517353.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 5.657332801818848,
|
|
"epoch": 2.8942550682315944,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004176729165581488,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.22609457969665528,
|
|
"num_tokens": 57527273.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 5.53686671257019,
|
|
"epoch": 2.894816645139552,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041764186930865377,
|
|
"loss": 4.9509,
|
|
"mean_token_accuracy": 0.22293547987937928,
|
|
"num_tokens": 57538486.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.583703231811524,
|
|
"epoch": 2.8953782220475093,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004176108175173863,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.21665232479572297,
|
|
"num_tokens": 57549682.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 5.62061071395874,
|
|
"epoch": 2.895939798955467,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004175797611853351,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.21234313547611236,
|
|
"num_tokens": 57559397.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 5.6338952541351315,
|
|
"epoch": 2.8965013758634246,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000417548700313489,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.21985413134098053,
|
|
"num_tokens": 57570568.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.561668586730957,
|
|
"epoch": 2.897062952771382,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000417517634902837,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.21826740801334382,
|
|
"num_tokens": 57581152.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.610563707351685,
|
|
"epoch": 2.8976245296793395,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041748656495436834,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.21663812696933746,
|
|
"num_tokens": 57592227.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 5.618358469009399,
|
|
"epoch": 2.898186106587297,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041745549046907205,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.21550197154283524,
|
|
"num_tokens": 57604037.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 5.665638875961304,
|
|
"epoch": 2.898747683495255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041742441144793774,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.2212419703602791,
|
|
"num_tokens": 57613937.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 5.574352979660034,
|
|
"epoch": 2.8993092604032125,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004173933278919549,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.2131936863064766,
|
|
"num_tokens": 57624287.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 5.656936454772949,
|
|
"epoch": 2.8998708373111697,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004173622398021133,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.2140283465385437,
|
|
"num_tokens": 57636677.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.4852124691009525,
|
|
"epoch": 2.9004324142191273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041733114717940273,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.22693321406841277,
|
|
"num_tokens": 57647848.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 5.506951236724854,
|
|
"epoch": 2.900993991127085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004173000500248133,
|
|
"loss": 4.875,
|
|
"mean_token_accuracy": 0.22183370143175124,
|
|
"num_tokens": 57658946.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 5.603242874145508,
|
|
"epoch": 2.901555568035042,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004172689483393351,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.2190452992916107,
|
|
"num_tokens": 57670690.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 5.718130302429199,
|
|
"epoch": 2.902117144943,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041723784212395834,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.21574632823467255,
|
|
"num_tokens": 57682309.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 5.616652154922486,
|
|
"epoch": 2.9026787218509575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041720673137967356,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.21810843497514726,
|
|
"num_tokens": 57692804.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 5.710249280929565,
|
|
"epoch": 2.9032402987589148,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041717561610747124,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.21294964253902435,
|
|
"num_tokens": 57705824.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 5.6275430679321286,
|
|
"epoch": 2.9038018756668724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041714449630834223,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.21879950910806656,
|
|
"num_tokens": 57718983.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 5.612572860717774,
|
|
"epoch": 2.90436345257483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004171133719832774,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.22187898308038712,
|
|
"num_tokens": 57730727.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.6061601638793945,
|
|
"epoch": 2.9049250294827877,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041708224313326747,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.20999071896076202,
|
|
"num_tokens": 57742474.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 5.702406024932861,
|
|
"epoch": 2.9054866063907454,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000417051109759304,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.2232889026403427,
|
|
"num_tokens": 57755094.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 5.643236494064331,
|
|
"epoch": 2.9060481832987026,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000417019971862378,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.21230996698141097,
|
|
"num_tokens": 57765820.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 5.619383907318115,
|
|
"epoch": 2.9066097602066603,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041698882944348105,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.21842698454856874,
|
|
"num_tokens": 57776749.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.601936769485474,
|
|
"epoch": 2.907171337114618,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041695768250360466,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.2168375164270401,
|
|
"num_tokens": 57787734.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 5.574479007720948,
|
|
"epoch": 2.907732914022575,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004169265310437407,
|
|
"loss": 5.0554,
|
|
"mean_token_accuracy": 0.21586465388536452,
|
|
"num_tokens": 57799799.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 5.496630048751831,
|
|
"epoch": 2.908294490930533,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004168953750648809,
|
|
"loss": 4.9315,
|
|
"mean_token_accuracy": 0.2193639472126961,
|
|
"num_tokens": 57810446.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 5.630498838424683,
|
|
"epoch": 2.9088560678384905,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041686421456801724,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.21604665368795395,
|
|
"num_tokens": 57822931.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 5.641361713409424,
|
|
"epoch": 2.909417644746448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004168330495541421,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.21157032251358032,
|
|
"num_tokens": 57835250.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.614517307281494,
|
|
"epoch": 2.909979221654406,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041680188002424755,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.21710609048604965,
|
|
"num_tokens": 57847726.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 5.5594147682189945,
|
|
"epoch": 2.910540798562363,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004167707059793262,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.21698143631219863,
|
|
"num_tokens": 57858484.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.53210334777832,
|
|
"epoch": 2.9111023754703207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041673952742037057,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.2283505454659462,
|
|
"num_tokens": 57870469.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.648314094543457,
|
|
"epoch": 2.9116639523782784,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004167083443483734,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.21679263263940812,
|
|
"num_tokens": 57880088.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 5.601202487945557,
|
|
"epoch": 2.9122255292862356,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004166771567643276,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.2089635208249092,
|
|
"num_tokens": 57890521.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 5.667679929733277,
|
|
"epoch": 2.9127871061941932,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004166459646692262,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.21260135620832443,
|
|
"num_tokens": 57904111.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.68510627746582,
|
|
"epoch": 2.913348683102151,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004166147680640623,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.21412087827920914,
|
|
"num_tokens": 57915854.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 5.543605995178223,
|
|
"epoch": 2.913910260010108,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041658356694982936,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.22885756194591522,
|
|
"num_tokens": 57926822.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.595948886871338,
|
|
"epoch": 2.9144718369180658,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004165523613275207,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.22199762016534805,
|
|
"num_tokens": 57939029.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 5.5520439624786375,
|
|
"epoch": 2.9150334138260234,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004165211511981299,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.21819553822278975,
|
|
"num_tokens": 57950053.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.568528413772583,
|
|
"epoch": 2.915594990733981,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004164899365626507,
|
|
"loss": 4.9362,
|
|
"mean_token_accuracy": 0.22587220072746278,
|
|
"num_tokens": 57960925.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.555482578277588,
|
|
"epoch": 2.9161565676419388,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004164587174220771,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.21716040521860122,
|
|
"num_tokens": 57971948.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 5.5790307998657225,
|
|
"epoch": 2.916718144549896,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041642749377740316,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.21013092547655104,
|
|
"num_tokens": 57984310.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 5.592931079864502,
|
|
"epoch": 2.9172797214578536,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041639626562962293,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.22583333849906922,
|
|
"num_tokens": 57995194.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 5.644208288192749,
|
|
"epoch": 2.9178412983658113,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00041636503297973074,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.2191808983683586,
|
|
"num_tokens": 58006370.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 5.605284023284912,
|
|
"epoch": 2.9184028752737685,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000416333795828721,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.22652453780174256,
|
|
"num_tokens": 58017635.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 5.633948421478271,
|
|
"epoch": 2.918964452181726,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004163025541775885,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.22624033093452453,
|
|
"num_tokens": 58028110.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.591439485549927,
|
|
"epoch": 2.919526029089684,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004162713080273278,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.2108023151755333,
|
|
"num_tokens": 58039715.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.660518789291382,
|
|
"epoch": 2.9200876059976415,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041624005737893387,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.2241167813539505,
|
|
"num_tokens": 58051052.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 5.578507137298584,
|
|
"epoch": 2.920649182905599,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004162088022334018,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.2247178226709366,
|
|
"num_tokens": 58062789.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 5.500988864898682,
|
|
"epoch": 2.9212107598135564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041617754259172665,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.22189042568206788,
|
|
"num_tokens": 58073896.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 5.706841087341308,
|
|
"epoch": 2.921772336721514,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041614627845490377,
|
|
"loss": 5.2047,
|
|
"mean_token_accuracy": 0.21089344769716262,
|
|
"num_tokens": 58084529.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.621143960952759,
|
|
"epoch": 2.9223339136294717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041611500982392867,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.2144147962331772,
|
|
"num_tokens": 58095989.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 5.5562886714935305,
|
|
"epoch": 2.922895490537429,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041608373669979696,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.23353600203990937,
|
|
"num_tokens": 58107001.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 5.568478631973266,
|
|
"epoch": 2.9234570674453866,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004160524590835042,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.22066669762134553,
|
|
"num_tokens": 58118224.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 5.575009822845459,
|
|
"epoch": 2.9240186443533442,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041602117697604664,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.22678082883358003,
|
|
"num_tokens": 58129675.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.577386569976807,
|
|
"epoch": 2.9245802212613015,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041598989037842,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.22001363337039948,
|
|
"num_tokens": 58140409.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 5.598912382125855,
|
|
"epoch": 2.925141798169259,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004159585992916206,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.22628665417432786,
|
|
"num_tokens": 58151139.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 5.651967525482178,
|
|
"epoch": 2.925703375077217,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004159273037166447,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.21162593364715576,
|
|
"num_tokens": 58162953.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 5.602564859390259,
|
|
"epoch": 2.9262649519851744,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041589600365448884,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.219600348174572,
|
|
"num_tokens": 58173480.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 5.643392705917359,
|
|
"epoch": 2.926826528893132,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004158646991061495,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.21681753396987916,
|
|
"num_tokens": 58185392.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 5.571819639205932,
|
|
"epoch": 2.9273881058010893,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004158333900726235,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.22926130294799804,
|
|
"num_tokens": 58195984.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 5.634227561950683,
|
|
"epoch": 2.927949682709047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041580207655490776,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.22101980298757554,
|
|
"num_tokens": 58207529.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 5.630969715118408,
|
|
"epoch": 2.9285112596170046,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004157707585539994,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.22079076915979384,
|
|
"num_tokens": 58217936.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 5.619207429885864,
|
|
"epoch": 2.929072836524962,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041573943607089536,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.2257535934448242,
|
|
"num_tokens": 58228144.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 5.558273553848267,
|
|
"epoch": 2.9296344134329195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004157081091065932,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.21984717398881912,
|
|
"num_tokens": 58239130.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 5.551471090316772,
|
|
"epoch": 2.930195990340877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004156767776620902,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.2203984960913658,
|
|
"num_tokens": 58253119.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 5.678849506378174,
|
|
"epoch": 2.930757567248835,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000415645441738384,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.21664858758449554,
|
|
"num_tokens": 58265549.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.597069787979126,
|
|
"epoch": 2.9313191441567925,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041561410133647244,
|
|
"loss": 4.9465,
|
|
"mean_token_accuracy": 0.23273052275180817,
|
|
"num_tokens": 58275021.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.579960107803345,
|
|
"epoch": 2.9318807210647497,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041558275645735336,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.21994332671165467,
|
|
"num_tokens": 58286191.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.510994529724121,
|
|
"epoch": 2.9324422979727074,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041555140710202484,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.23022146970033647,
|
|
"num_tokens": 58297066.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 5.59955358505249,
|
|
"epoch": 2.933003874880665,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041552005327148494,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.22445250749588014,
|
|
"num_tokens": 58308008.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 5.618601989746094,
|
|
"epoch": 2.9335654517886223,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004154886949667321,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.21552089899778365,
|
|
"num_tokens": 58319584.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.60830864906311,
|
|
"epoch": 2.93412702869658,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041545733218876466,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.2178304210305214,
|
|
"num_tokens": 58328964.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.662229871749878,
|
|
"epoch": 2.9346886056045376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004154259649385813,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.22466324120759965,
|
|
"num_tokens": 58339673.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.637851810455322,
|
|
"epoch": 2.935250182512495,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041539459321718076,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.2178229108452797,
|
|
"num_tokens": 58351453.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 5.610768175125122,
|
|
"epoch": 2.9358117594204525,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004153632170255619,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.21244012117385863,
|
|
"num_tokens": 58362792.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 5.600987768173217,
|
|
"epoch": 2.93637333632841,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041533183636472385,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.22293654680252076,
|
|
"num_tokens": 58372628.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 5.510374116897583,
|
|
"epoch": 2.936934913236368,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004153004512356656,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.22574298679828644,
|
|
"num_tokens": 58383723.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 5.5313849449157715,
|
|
"epoch": 2.9374964901443255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004152690616393866,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.221626977622509,
|
|
"num_tokens": 58394547.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 5.559050130844116,
|
|
"epoch": 2.9380580670522827,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041523766757688634,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.2219364732503891,
|
|
"num_tokens": 58405460.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 5.636883401870728,
|
|
"epoch": 2.9386196439602403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004152062690491643,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.22280002981424332,
|
|
"num_tokens": 58416436.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.608496475219726,
|
|
"epoch": 2.939181220868198,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004151748660572203,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.2284125104546547,
|
|
"num_tokens": 58426920.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 5.5391199588775635,
|
|
"epoch": 2.939742797776155,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004151434586020541,
|
|
"loss": 4.8883,
|
|
"mean_token_accuracy": 0.22992363572120667,
|
|
"num_tokens": 58437525.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 5.614537096023559,
|
|
"epoch": 2.940304374684113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041511204668466593,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.22051404565572738,
|
|
"num_tokens": 58448955.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.48357367515564,
|
|
"epoch": 2.9408659515920705,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041508063030605585,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.22482797205448152,
|
|
"num_tokens": 58459941.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 5.600832748413086,
|
|
"epoch": 2.941427528500028,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041504920946722413,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.2195356696844101,
|
|
"num_tokens": 58470499.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 5.594505643844604,
|
|
"epoch": 2.941989105407986,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004150177841691713,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.22155385613441467,
|
|
"num_tokens": 58482969.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 5.634841346740723,
|
|
"epoch": 2.942550682315943,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004149863544128979,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.21820665448904036,
|
|
"num_tokens": 58492929.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.549111938476562,
|
|
"epoch": 2.9431122592239007,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041495492019940467,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.2211384192109108,
|
|
"num_tokens": 58503932.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.504226398468018,
|
|
"epoch": 2.9436738361318584,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004149234815296925,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.22743856012821198,
|
|
"num_tokens": 58515282.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 5.62899227142334,
|
|
"epoch": 2.9442354130398156,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041489203840476243,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.21633688360452652,
|
|
"num_tokens": 58527218.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 5.637971115112305,
|
|
"epoch": 2.9447969899477733,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041486059082561556,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.21961130946874619,
|
|
"num_tokens": 58538622.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 5.60837607383728,
|
|
"epoch": 2.945358566855731,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004148291387932533,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.22258053869009017,
|
|
"num_tokens": 58549747.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 5.572348117828369,
|
|
"epoch": 2.9459201437636886,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041479768230867696,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.21775744408369063,
|
|
"num_tokens": 58560771.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 5.5707612991333,
|
|
"epoch": 2.946481720671646,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041476622137288823,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.21913426816463472,
|
|
"num_tokens": 58571184.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.633505392074585,
|
|
"epoch": 2.9470432975796035,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041473475598688886,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21455072313547136,
|
|
"num_tokens": 58583075.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 5.651118373870849,
|
|
"epoch": 2.947604874487561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004147032861516805,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.22358528077602385,
|
|
"num_tokens": 58593978.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 5.586923456192016,
|
|
"epoch": 2.948166451395519,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041467181186826546,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.21794222444295883,
|
|
"num_tokens": 58604525.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.546811962127686,
|
|
"epoch": 2.948728028303476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041464033313764575,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.2222319081425667,
|
|
"num_tokens": 58614965.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.612073755264282,
|
|
"epoch": 2.9492896052114337,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041460884996082363,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.21657573878765107,
|
|
"num_tokens": 58626254.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 5.600900888442993,
|
|
"epoch": 2.9498511821193913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041457736233880166,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.22112308591604232,
|
|
"num_tokens": 58637474.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.612212657928467,
|
|
"epoch": 2.9504127590273486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004145458702725823,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.2152599349617958,
|
|
"num_tokens": 58649560.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.526739883422851,
|
|
"epoch": 2.9509743359353062,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041451437376316825,
|
|
"loss": 4.986,
|
|
"mean_token_accuracy": 0.2162500038743019,
|
|
"num_tokens": 58659944.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 5.668224334716797,
|
|
"epoch": 2.951535912843264,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004144828728115624,
|
|
"loss": 5.0166,
|
|
"mean_token_accuracy": 0.21550311148166656,
|
|
"num_tokens": 58670636.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 5.596641540527344,
|
|
"epoch": 2.9520974897512215,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004144513674187679,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.21579279750585556,
|
|
"num_tokens": 58682832.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.571224021911621,
|
|
"epoch": 2.952659066659179,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004144198575857878,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.217382575571537,
|
|
"num_tokens": 58694675.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.538844299316406,
|
|
"epoch": 2.9532206435671364,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004143883433136252,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.22334482967853547,
|
|
"num_tokens": 58705613.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 5.661744403839111,
|
|
"epoch": 2.953782220475094,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004143568246032838,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.2139691472053528,
|
|
"num_tokens": 58716951.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.617868041992187,
|
|
"epoch": 2.9543437973830518,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004143253014557671,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.2122076243162155,
|
|
"num_tokens": 58727730.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.571199512481689,
|
|
"epoch": 2.954905374291009,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041429377387207865,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.22090323865413666,
|
|
"num_tokens": 58739183.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.635788822174073,
|
|
"epoch": 2.9554669511989666,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041426224185322255,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.21842235773801805,
|
|
"num_tokens": 58750031.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 5.650490427017212,
|
|
"epoch": 2.9560285281069243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004142307054002025,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.21939669996500016,
|
|
"num_tokens": 58760488.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 5.666536664962768,
|
|
"epoch": 2.956590105014882,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004141991645140228,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.21088163554668427,
|
|
"num_tokens": 58771484.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.533496904373169,
|
|
"epoch": 2.957151681922839,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041416761919568784,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.21633679866790773,
|
|
"num_tokens": 58782208.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.615951251983643,
|
|
"epoch": 2.957713258830797,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041413606944620183,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.21860676854848862,
|
|
"num_tokens": 58792556.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 5.53474907875061,
|
|
"epoch": 2.9582748357387545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004141045152665695,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.2230062171816826,
|
|
"num_tokens": 58803531.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 5.607926893234253,
|
|
"epoch": 2.958836412646712,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041407295665779533,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.22123559713363647,
|
|
"num_tokens": 58813639.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 5.666520071029663,
|
|
"epoch": 2.9593979895546694,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041404139362088434,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.21848286539316178,
|
|
"num_tokens": 58824830.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 5.59608678817749,
|
|
"epoch": 2.959959566462627,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004140098261568414,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.21748420000076293,
|
|
"num_tokens": 58835664.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.587133741378784,
|
|
"epoch": 2.9605211433705847,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041397825426667175,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.2206347554922104,
|
|
"num_tokens": 58845872.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 5.526347827911377,
|
|
"epoch": 2.961082720278542,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004139466779513805,
|
|
"loss": 4.8498,
|
|
"mean_token_accuracy": 0.23413795083761216,
|
|
"num_tokens": 58857090.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 5.634381246566773,
|
|
"epoch": 2.9616442971864996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004139150972119732,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.219214728474617,
|
|
"num_tokens": 58868814.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 5.4929839134216305,
|
|
"epoch": 2.9622058740944572,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041388351204945534,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.2203420504927635,
|
|
"num_tokens": 58879270.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.641345071792602,
|
|
"epoch": 2.962767451002415,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041385192246483257,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.21958244144916533,
|
|
"num_tokens": 58891861.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.64852294921875,
|
|
"epoch": 2.9633290279103726,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041382032845911073,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.2210833951830864,
|
|
"num_tokens": 58903779.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 5.675687408447265,
|
|
"epoch": 2.9638906048183298,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041378873003329575,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.22037521451711656,
|
|
"num_tokens": 58915773.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.5513111591339115,
|
|
"epoch": 2.9644521817262874,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004137571271883938,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.2179988980293274,
|
|
"num_tokens": 58926701.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 5.534038734436035,
|
|
"epoch": 2.965013758634245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004137255199254112,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.2258329138159752,
|
|
"num_tokens": 58937606.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 5.602986001968384,
|
|
"epoch": 2.9655753355422023,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041369390824535417,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.2231776386499405,
|
|
"num_tokens": 58948982.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 5.599208736419678,
|
|
"epoch": 2.96613691245016,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041366229214922926,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.22695890814065933,
|
|
"num_tokens": 58961607.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 5.566433477401733,
|
|
"epoch": 2.9666984893581176,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004136306716380432,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.2244621440768242,
|
|
"num_tokens": 58973072.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 5.610176849365234,
|
|
"epoch": 2.9672600662660753,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041359904671280285,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.22607431262731553,
|
|
"num_tokens": 58983330.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 5.669292020797729,
|
|
"epoch": 2.9678216431740325,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004135674173745151,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.21109250336885452,
|
|
"num_tokens": 58995912.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 5.659941244125366,
|
|
"epoch": 2.96838322008199,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041353578362418695,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.21872776448726655,
|
|
"num_tokens": 59005964.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 5.698803186416626,
|
|
"epoch": 2.968944796989948,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004135041454628258,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.21069853454828263,
|
|
"num_tokens": 59017285.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 5.508225536346435,
|
|
"epoch": 2.9695063738979055,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004134725028914389,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.22802856266498567,
|
|
"num_tokens": 59027751.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.579375743865967,
|
|
"epoch": 2.9700679508058627,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041344085591103383,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.2164480358362198,
|
|
"num_tokens": 59039568.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 5.616402816772461,
|
|
"epoch": 2.9706295277138204,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004134092045226182,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.2181648150086403,
|
|
"num_tokens": 59051162.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 5.575061273574829,
|
|
"epoch": 2.971191104621778,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041337754872719984,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.22277375757694245,
|
|
"num_tokens": 59061381.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 5.545869827270508,
|
|
"epoch": 2.9717526815297353,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004133458885257866,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.22256572544574738,
|
|
"num_tokens": 59071026.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 5.501360559463501,
|
|
"epoch": 2.972314258437693,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041331422391938663,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.2142934411764145,
|
|
"num_tokens": 59082793.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.714851713180542,
|
|
"epoch": 2.9728758353456506,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004132825549090082,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.21535486429929734,
|
|
"num_tokens": 59094247.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.528332090377807,
|
|
"epoch": 2.9734374122536082,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004132508814956595,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.2191714271903038,
|
|
"num_tokens": 59104936.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 5.622325325012207,
|
|
"epoch": 2.973998989161566,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004132192036803491,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.22253736555576326,
|
|
"num_tokens": 59116181.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 5.5036866664886475,
|
|
"epoch": 2.974560566069523,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041318752146408575,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.22272662520408631,
|
|
"num_tokens": 59126953.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 5.6002874851226805,
|
|
"epoch": 2.975122142977481,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004131558348478781,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.21699765771627427,
|
|
"num_tokens": 59138460.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 5.66509428024292,
|
|
"epoch": 2.9756837198854384,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041312414383273507,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.22336007356643678,
|
|
"num_tokens": 59149003.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 5.626164340972901,
|
|
"epoch": 2.9762452967933957,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041309244841966565,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.21752355992794037,
|
|
"num_tokens": 59160582.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 5.597275638580323,
|
|
"epoch": 2.9768068737013533,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041306074860967916,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.21244291812181473,
|
|
"num_tokens": 59172115.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 5.571255111694336,
|
|
"epoch": 2.977368450609311,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041302904440378494,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.21846363693475723,
|
|
"num_tokens": 59183044.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 5.672640037536621,
|
|
"epoch": 2.9779300275172687,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041299733580299236,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20768973231315613,
|
|
"num_tokens": 59194791.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.530934143066406,
|
|
"epoch": 2.978491604425226,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041296562280831106,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.2131525993347168,
|
|
"num_tokens": 59206285.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.61741271018982,
|
|
"epoch": 2.9790531813331835,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041293390542075095,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.21599126905202864,
|
|
"num_tokens": 59217906.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.617485380172729,
|
|
"epoch": 2.979614758241141,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004129021836413217,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.21503397673368455,
|
|
"num_tokens": 59228163.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.548622274398804,
|
|
"epoch": 2.980176335149099,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004128704574710334,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.21659666895866395,
|
|
"num_tokens": 59238633.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.653303766250611,
|
|
"epoch": 2.980737912057056,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004128387269108963,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.2131243646144867,
|
|
"num_tokens": 59249523.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.695711612701416,
|
|
"epoch": 2.9812994889650137,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041280699196192074,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.21380117386579514,
|
|
"num_tokens": 59259636.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.604764366149903,
|
|
"epoch": 2.9818610658729714,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041277525262511705,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.21954265981912613,
|
|
"num_tokens": 59270963.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 5.685041522979736,
|
|
"epoch": 2.9824226427809286,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041274350890149584,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.21476903408765793,
|
|
"num_tokens": 59282085.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 5.666931200027466,
|
|
"epoch": 2.9829842196888863,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000412711760792068,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.2158407375216484,
|
|
"num_tokens": 59292210.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.587758350372314,
|
|
"epoch": 2.983545796596844,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004126800082978442,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.22109282463788987,
|
|
"num_tokens": 59303727.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 5.577067899703979,
|
|
"epoch": 2.9841073735048016,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041264825141983547,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.22230175882577896,
|
|
"num_tokens": 59313922.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.562071180343628,
|
|
"epoch": 2.9846689504127593,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041261649015905314,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.2226293295621872,
|
|
"num_tokens": 59324974.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 5.65451078414917,
|
|
"epoch": 2.9852305273207165,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004125847245165084,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.21487370282411575,
|
|
"num_tokens": 59335538.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 5.671197938919067,
|
|
"epoch": 2.985792104228674,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004125529544932126,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.2190108612179756,
|
|
"num_tokens": 59347116.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 5.6342737674713135,
|
|
"epoch": 2.986353681136632,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004125211800901774,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.22166917771100997,
|
|
"num_tokens": 59358505.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.561140775680542,
|
|
"epoch": 2.986915258044589,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004124894013084145,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.22465308308601378,
|
|
"num_tokens": 59369897.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 5.565539407730102,
|
|
"epoch": 2.9874768349525467,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041245761814893576,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.22121806293725968,
|
|
"num_tokens": 59381372.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 5.600912475585938,
|
|
"epoch": 2.9880384118605043,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004124258306127531,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.22060222923755646,
|
|
"num_tokens": 59391543.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 5.661279201507568,
|
|
"epoch": 2.988599988768462,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004123940387008787,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.22177618592977524,
|
|
"num_tokens": 59402474.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 5.589154767990112,
|
|
"epoch": 2.9891615656764197,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004123622424143248,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.2212647721171379,
|
|
"num_tokens": 59413970.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 5.528221273422242,
|
|
"epoch": 2.989723142584377,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041233044175410387,
|
|
"loss": 4.9775,
|
|
"mean_token_accuracy": 0.22525646090507506,
|
|
"num_tokens": 59424958.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.593805742263794,
|
|
"epoch": 2.9902847194923345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041229863672122844,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.2222837597131729,
|
|
"num_tokens": 59436226.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 5.68821439743042,
|
|
"epoch": 2.990846296400292,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004122668273167111,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.21499409675598144,
|
|
"num_tokens": 59447607.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 5.506497859954834,
|
|
"epoch": 2.9914078733082494,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004122350135415648,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.22258247137069703,
|
|
"num_tokens": 59458120.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 5.634333896636963,
|
|
"epoch": 2.991969450216207,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004122031953968024,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.2198478788137436,
|
|
"num_tokens": 59468646.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 5.628108978271484,
|
|
"epoch": 2.9925310271241647,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041217137288343704,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.2185439184308052,
|
|
"num_tokens": 59478887.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 5.623139810562134,
|
|
"epoch": 2.993092604032122,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000412139546002482,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.21818922013044356,
|
|
"num_tokens": 59490501.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.643443584442139,
|
|
"epoch": 2.9936541809400796,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041210771475495064,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.21556769460439681,
|
|
"num_tokens": 59500873.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 5.529023790359497,
|
|
"epoch": 2.9942157578480373,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004120758791418564,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.22116817086935042,
|
|
"num_tokens": 59511793.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 5.60467939376831,
|
|
"epoch": 2.994777334755995,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004120440391642131,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.2162816718220711,
|
|
"num_tokens": 59523978.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 5.635572481155395,
|
|
"epoch": 2.9953389116639526,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004120121948230343,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.22099651396274567,
|
|
"num_tokens": 59534575.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.5965369701385494,
|
|
"epoch": 2.99590048857191,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004119803461193342,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.2096935972571373,
|
|
"num_tokens": 59545542.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.636129665374756,
|
|
"epoch": 2.9964620654798675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004119484930541267,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.22173017710447313,
|
|
"num_tokens": 59556482.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 5.618430328369141,
|
|
"epoch": 2.997023642387825,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041191663562842605,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.2205251559615135,
|
|
"num_tokens": 59568941.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 5.589690017700195,
|
|
"epoch": 2.9975852192957824,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004118847738432467,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.2160871535539627,
|
|
"num_tokens": 59579690.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 5.603187179565429,
|
|
"epoch": 2.99814679620374,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004118529076996029,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.21755025684833526,
|
|
"num_tokens": 59589831.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 5.586891746520996,
|
|
"epoch": 2.9987083731116977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041182103719850967,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.2142437145113945,
|
|
"num_tokens": 59600939.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 5.49670557975769,
|
|
"epoch": 2.9992699500196554,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041178916234098134,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.22747726142406463,
|
|
"num_tokens": 59612084.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 5.5654003620147705,
|
|
"epoch": 2.999831526927613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004117572831280332,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.21565888673067093,
|
|
"num_tokens": 59624359.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 5.708814938863118,
|
|
"epoch": 3.0003369461447744,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041172539956068,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.2256504628393385,
|
|
"num_tokens": 59633030.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 5.557371664047241,
|
|
"epoch": 3.000898523052732,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041169351163993705,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.22609374821186065,
|
|
"num_tokens": 59644107.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.510533142089844,
|
|
"epoch": 3.0014600999606897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041166161936681973,
|
|
"loss": 4.8418,
|
|
"mean_token_accuracy": 0.2321416139602661,
|
|
"num_tokens": 59654166.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.546385049819946,
|
|
"epoch": 3.002021676868647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004116297227423435,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.22372154295444488,
|
|
"num_tokens": 59664785.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 5.519131088256836,
|
|
"epoch": 3.0025832537766046,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041159782176752375,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.23805160373449324,
|
|
"num_tokens": 59675634.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 5.613343048095703,
|
|
"epoch": 3.0031448306845623,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004115659164433765,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.22848716825246812,
|
|
"num_tokens": 59687636.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.590230464935303,
|
|
"epoch": 3.00370640759252,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041153400677091745,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.22088900506496428,
|
|
"num_tokens": 59700389.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 5.565920162200928,
|
|
"epoch": 3.004267984500477,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041150209275116266,
|
|
"loss": 4.8957,
|
|
"mean_token_accuracy": 0.22856015861034393,
|
|
"num_tokens": 59710898.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 5.6286545753479,
|
|
"epoch": 3.004829561408435,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041147017438512834,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.22162396907806398,
|
|
"num_tokens": 59722398.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 5.567217445373535,
|
|
"epoch": 3.0053911383163925,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041143825167383073,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.2286151573061943,
|
|
"num_tokens": 59732504.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.586511135101318,
|
|
"epoch": 3.00595271522435,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004114063246182863,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.22306661158800126,
|
|
"num_tokens": 59742919.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 5.557434797286987,
|
|
"epoch": 3.0065142921323074,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041137439321951147,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.2221282660961151,
|
|
"num_tokens": 59754316.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.650656700134277,
|
|
"epoch": 3.007075869040265,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041134245747852314,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.21448576152324678,
|
|
"num_tokens": 59765031.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.624220657348633,
|
|
"epoch": 3.0076374459482227,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004113105173963382,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.22047698646783828,
|
|
"num_tokens": 59776338.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 5.597538328170776,
|
|
"epoch": 3.0081990228561803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004112785729739733,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.22831390351057052,
|
|
"num_tokens": 59788544.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 5.572019577026367,
|
|
"epoch": 3.0087605997641376,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041124662421244593,
|
|
"loss": 4.9315,
|
|
"mean_token_accuracy": 0.22100671827793122,
|
|
"num_tokens": 59800131.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.624274063110351,
|
|
"epoch": 3.0093221766720952,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004112146711127732,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.2244979679584503,
|
|
"num_tokens": 59811986.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 5.620622730255127,
|
|
"epoch": 3.009883753580053,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004111827136759725,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.22448165565729142,
|
|
"num_tokens": 59824758.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.525171613693237,
|
|
"epoch": 3.0104453304880106,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004111507519030613,
|
|
"loss": 4.9532,
|
|
"mean_token_accuracy": 0.22100224792957307,
|
|
"num_tokens": 59836317.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.5775196075439455,
|
|
"epoch": 3.0110069073959678,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004111187857950574,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.22560350447893143,
|
|
"num_tokens": 59847743.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 5.6016380310058596,
|
|
"epoch": 3.0115684843039254,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004110868153529786,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.22939324826002122,
|
|
"num_tokens": 59859442.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 5.559607696533203,
|
|
"epoch": 3.012130061211883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004110548405778428,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.2291795626282692,
|
|
"num_tokens": 59869949.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.5046473979949955,
|
|
"epoch": 3.0126916381198403,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004110228614706681,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.22418624311685562,
|
|
"num_tokens": 59881818.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.576461553573608,
|
|
"epoch": 3.013253215027798,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041099087803247276,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.22609559893608094,
|
|
"num_tokens": 59893152.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 5.688030529022217,
|
|
"epoch": 3.0138147919357556,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004109588902642751,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21245867609977723,
|
|
"num_tokens": 59904082.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 5.595840930938721,
|
|
"epoch": 3.0143763688437133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004109268981670936,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.2243754595518112,
|
|
"num_tokens": 59916116.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 5.490266466140747,
|
|
"epoch": 3.0149379457516705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000410894901741947,
|
|
"loss": 4.8527,
|
|
"mean_token_accuracy": 0.2275776594877243,
|
|
"num_tokens": 59926399.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.545608043670654,
|
|
"epoch": 3.015499522659628,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000410862900989854,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.2291798248887062,
|
|
"num_tokens": 59936986.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.6806854724884035,
|
|
"epoch": 3.016061099567586,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004108308959118336,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.2155949741601944,
|
|
"num_tokens": 59948926.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 5.519014453887939,
|
|
"epoch": 3.0166226764755435,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004107988865089047,
|
|
"loss": 4.8883,
|
|
"mean_token_accuracy": 0.22921250015497208,
|
|
"num_tokens": 59960468.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 5.563865804672242,
|
|
"epoch": 3.0171842533835007,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041076687278208664,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.22252197116613387,
|
|
"num_tokens": 59971151.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.586475658416748,
|
|
"epoch": 3.0177458302914584,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004107348547323987,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.22716388553380967,
|
|
"num_tokens": 59982205.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 5.5411091327667235,
|
|
"epoch": 3.018307407199416,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041070283236086024,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.23318922370672227,
|
|
"num_tokens": 59993612.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 5.658241701126099,
|
|
"epoch": 3.0188689841073737,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004106708056684911,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.21513381004333496,
|
|
"num_tokens": 60004284.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 5.671487808227539,
|
|
"epoch": 3.019430561015331,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041063877465631084,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.21611254960298537,
|
|
"num_tokens": 60016276.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.563733863830566,
|
|
"epoch": 3.0199921379232886,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004106067393253394,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.22970511317253112,
|
|
"num_tokens": 60029155.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 5.548474216461182,
|
|
"epoch": 3.0205537148312462,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004105746996765968,
|
|
"loss": 4.9451,
|
|
"mean_token_accuracy": 0.21942289173603058,
|
|
"num_tokens": 60041042.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 5.640822124481201,
|
|
"epoch": 3.021115291739204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004105426557111031,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.22505772411823272,
|
|
"num_tokens": 60052025.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 5.5889997482299805,
|
|
"epoch": 3.021676868647161,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004105106074298787,
|
|
"loss": 4.9614,
|
|
"mean_token_accuracy": 0.2243972048163414,
|
|
"num_tokens": 60063260.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 5.556883430480957,
|
|
"epoch": 3.022238445555119,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000410478554833944,
|
|
"loss": 4.9959,
|
|
"mean_token_accuracy": 0.22114973962306977,
|
|
"num_tokens": 60074721.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.557315063476563,
|
|
"epoch": 3.0228000224630764,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041044649792431963,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.22680170983076095,
|
|
"num_tokens": 60085028.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.537068271636963,
|
|
"epoch": 3.0233615993710337,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041041443670202616,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.2296934336423874,
|
|
"num_tokens": 60095587.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 5.521029090881347,
|
|
"epoch": 3.0239231762789913,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004103823711680846,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.23327098935842513,
|
|
"num_tokens": 60106574.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 5.496912288665771,
|
|
"epoch": 3.024484753186949,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041035030132351575,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.2286642611026764,
|
|
"num_tokens": 60116821.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.5649689674377445,
|
|
"epoch": 3.0250463300949066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041031822716934086,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.21918057799339294,
|
|
"num_tokens": 60128229.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.605934476852417,
|
|
"epoch": 3.025607907002864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041028614870658106,
|
|
"loss": 4.923,
|
|
"mean_token_accuracy": 0.21941576302051544,
|
|
"num_tokens": 60139416.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 5.591204071044922,
|
|
"epoch": 3.0261694839108215,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004102540659362579,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.2235393524169922,
|
|
"num_tokens": 60150225.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 5.561678647994995,
|
|
"epoch": 3.026731060818779,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041022197885939285,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.22065623849630356,
|
|
"num_tokens": 60160065.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 5.588074636459351,
|
|
"epoch": 3.027292637726737,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041018988747700745,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.23837000280618667,
|
|
"num_tokens": 60170396.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.523979949951172,
|
|
"epoch": 3.027854214634694,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004101577917901236,
|
|
"loss": 4.9419,
|
|
"mean_token_accuracy": 0.2237023577094078,
|
|
"num_tokens": 60181938.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.595704221725464,
|
|
"epoch": 3.0284157915426517,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041012569179976326,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.22399763017892838,
|
|
"num_tokens": 60192388.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 5.671125745773315,
|
|
"epoch": 3.0289773684506094,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004100935875069485,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.21967650949954987,
|
|
"num_tokens": 60203195.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 5.598564529418946,
|
|
"epoch": 3.029538945358567,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004100614789127015,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.22699477821588515,
|
|
"num_tokens": 60213659.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 5.491554117202758,
|
|
"epoch": 3.0301005222665243,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004100293660180447,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.22301185727119446,
|
|
"num_tokens": 60224795.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 5.512055969238281,
|
|
"epoch": 3.030662099174482,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040999724882400046,
|
|
"loss": 4.8431,
|
|
"mean_token_accuracy": 0.22858722358942032,
|
|
"num_tokens": 60236188.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.621142625808716,
|
|
"epoch": 3.0312236760824396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004099651273315915,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.2263819009065628,
|
|
"num_tokens": 60247003.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 5.55358395576477,
|
|
"epoch": 3.0317852529903973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004099330015418405,
|
|
"loss": 4.9498,
|
|
"mean_token_accuracy": 0.21866278052330018,
|
|
"num_tokens": 60258317.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 5.594918155670166,
|
|
"epoch": 3.0323468298983545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040990087145577044,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.22607746124267578,
|
|
"num_tokens": 60269000.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 3.0323468298983545,
|
|
"eval_entropy": 5.363691991157128,
|
|
"eval_loss": 5.094874382019043,
|
|
"eval_mean_token_accuracy": 0.2249208676340748,
|
|
"eval_num_tokens": 60269000.0,
|
|
"eval_runtime": 18.6026,
|
|
"eval_samples_per_second": 1667.136,
|
|
"eval_steps_per_second": 208.412,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 5.558486413955689,
|
|
"epoch": 3.032908406806312,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004098687370744042,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.23307243138551711,
|
|
"num_tokens": 60280411.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 5.63655948638916,
|
|
"epoch": 3.03346998371427,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004098365983987652,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.21562781184911728,
|
|
"num_tokens": 60290197.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 5.635416650772095,
|
|
"epoch": 3.034031560622227,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040980445542987653,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.22533439248800277,
|
|
"num_tokens": 60300927.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 5.557941150665283,
|
|
"epoch": 3.0345931375301847,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040977230816876176,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.2295539692044258,
|
|
"num_tokens": 60312697.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 5.486485815048217,
|
|
"epoch": 3.0351547144381423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040974015661644433,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.23654679954051971,
|
|
"num_tokens": 60323779.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 5.601055574417114,
|
|
"epoch": 3.0357162913461,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004097080007739481,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.22536797672510148,
|
|
"num_tokens": 60335036.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 5.562702703475952,
|
|
"epoch": 3.036277868254057,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040967584064229695,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.2156827673316002,
|
|
"num_tokens": 60345600.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 5.63621678352356,
|
|
"epoch": 3.036839445162015,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040964367622251473,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.22252043783664704,
|
|
"num_tokens": 60357241.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 5.577012968063355,
|
|
"epoch": 3.0374010220699725,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004096115075156257,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.22577587366104127,
|
|
"num_tokens": 60369036.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 5.6808857917785645,
|
|
"epoch": 3.03796259897793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004095793345226541,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.21666744202375413,
|
|
"num_tokens": 60380310.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 5.57183427810669,
|
|
"epoch": 3.0385241758858874,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004095471572446242,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.2313407689332962,
|
|
"num_tokens": 60390962.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 5.688633966445923,
|
|
"epoch": 3.039085752793845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004095149756825606,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.21910676509141921,
|
|
"num_tokens": 60400342.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 5.502812385559082,
|
|
"epoch": 3.0396473297018027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004094827898374881,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.22730057090520858,
|
|
"num_tokens": 60411921.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 5.686021375656128,
|
|
"epoch": 3.0402089066097604,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004094505997104314,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.22019569873809813,
|
|
"num_tokens": 60424185.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 5.477052783966064,
|
|
"epoch": 3.0407704835177176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040941840530241537,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.22203737497329712,
|
|
"num_tokens": 60433729.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 5.656256818771363,
|
|
"epoch": 3.0413320604256753,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040938620661446526,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.22028948366641998,
|
|
"num_tokens": 60443846.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 5.597944879531861,
|
|
"epoch": 3.041893637333633,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004093540036476062,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.2238491505384445,
|
|
"num_tokens": 60455183.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 5.546351957321167,
|
|
"epoch": 3.0424552142415906,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040932179640286356,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.21708359718322753,
|
|
"num_tokens": 60465769.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 5.493973684310913,
|
|
"epoch": 3.043016791149548,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004092895848812628,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.2287045180797577,
|
|
"num_tokens": 60476252.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 5.598827171325683,
|
|
"epoch": 3.0435783680575055,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040925736908382953,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.2275824725627899,
|
|
"num_tokens": 60485939.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 5.551936626434326,
|
|
"epoch": 3.044139944965463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004092251490115896,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.224759241938591,
|
|
"num_tokens": 60497994.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 5.715364599227906,
|
|
"epoch": 3.0447015218734204,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040919292466556895,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.22014500945806503,
|
|
"num_tokens": 60508944.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 5.654387140274048,
|
|
"epoch": 3.045263098781378,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004091606960467934,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.2298287719488144,
|
|
"num_tokens": 60519928.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 5.560505390167236,
|
|
"epoch": 3.0458246756893357,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040912846315628934,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.22980407029390335,
|
|
"num_tokens": 60530417.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 5.514606189727783,
|
|
"epoch": 3.0463862525972933,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000409096225995083,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.21758127510547637,
|
|
"num_tokens": 60542140.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 5.5537135124206545,
|
|
"epoch": 3.0469478295052506,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040906398456420077,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.23028424084186555,
|
|
"num_tokens": 60553032.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 5.651614427566528,
|
|
"epoch": 3.047509406413208,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040903173886466934,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.22842672616243362,
|
|
"num_tokens": 60563773.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 5.517093801498413,
|
|
"epoch": 3.048070983321166,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040899948889751525,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.23000732958316802,
|
|
"num_tokens": 60574354.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 5.571668243408203,
|
|
"epoch": 3.0486325602291235,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040896723466376557,
|
|
"loss": 4.9509,
|
|
"mean_token_accuracy": 0.22544005811214446,
|
|
"num_tokens": 60584760.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 5.448996305465698,
|
|
"epoch": 3.0491941371370808,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040893497616444714,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.23239941745996476,
|
|
"num_tokens": 60595322.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 5.66293888092041,
|
|
"epoch": 3.0497557140450384,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004089027134005871,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.21055228263139725,
|
|
"num_tokens": 60607897.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 5.569510364532471,
|
|
"epoch": 3.050317290952996,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004088704463732127,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.22420456260442734,
|
|
"num_tokens": 60618882.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 5.596968412399292,
|
|
"epoch": 3.0508788678609537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004088381750833514,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.22474605441093445,
|
|
"num_tokens": 60630431.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 5.665701961517334,
|
|
"epoch": 3.051440444768911,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004088058995320307,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.21727689802646638,
|
|
"num_tokens": 60642479.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 5.53288722038269,
|
|
"epoch": 3.0520020216768686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004087736197202784,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.22389906793832778,
|
|
"num_tokens": 60652922.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 5.573962020874023,
|
|
"epoch": 3.0525635985848263,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040874133564912195,
|
|
"loss": 4.9463,
|
|
"mean_token_accuracy": 0.22480494678020477,
|
|
"num_tokens": 60665125.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 5.711909914016724,
|
|
"epoch": 3.053125175492784,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040870904731958965,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.2174843043088913,
|
|
"num_tokens": 60675807.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 5.590922927856445,
|
|
"epoch": 3.053686752400741,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004086767547327094,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.22445883303880693,
|
|
"num_tokens": 60686841.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 5.602829933166504,
|
|
"epoch": 3.054248329308699,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040864445788950935,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.22158134281635283,
|
|
"num_tokens": 60698965.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 5.630339002609253,
|
|
"epoch": 3.0548099062166565,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000408612156791018,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.2232961818575859,
|
|
"num_tokens": 60709962.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 5.562480401992798,
|
|
"epoch": 3.0553714831246137,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004085798514382637,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.2273497462272644,
|
|
"num_tokens": 60721267.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 5.556097745895386,
|
|
"epoch": 3.0559330600325714,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040854754183227516,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.2321533277630806,
|
|
"num_tokens": 60731892.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 5.558875226974488,
|
|
"epoch": 3.056494636940529,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004085152279740811,
|
|
"loss": 4.9427,
|
|
"mean_token_accuracy": 0.2173493266105652,
|
|
"num_tokens": 60742875.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 5.657172012329101,
|
|
"epoch": 3.0570562138484867,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040848290986471037,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.22380901277065277,
|
|
"num_tokens": 60752716.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 5.585988759994507,
|
|
"epoch": 3.057617790756444,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040845058750519205,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.21485718935728074,
|
|
"num_tokens": 60765466.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 5.586630582809448,
|
|
"epoch": 3.0581793676644016,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040841826089655525,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.21510081887245178,
|
|
"num_tokens": 60776488.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 5.633428907394409,
|
|
"epoch": 3.0587409445723592,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040838593003982926,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.21921625584363938,
|
|
"num_tokens": 60786510.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 5.55984206199646,
|
|
"epoch": 3.059302521480317,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004083535949360436,
|
|
"loss": 4.908,
|
|
"mean_token_accuracy": 0.2335616797208786,
|
|
"num_tokens": 60798300.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 5.456761026382447,
|
|
"epoch": 3.059864098388274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004083212555862277,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.21970295757055283,
|
|
"num_tokens": 60809949.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 5.578208303451538,
|
|
"epoch": 3.0604256752962318,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004082889119914113,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.2251430094242096,
|
|
"num_tokens": 60819960.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 5.669431352615357,
|
|
"epoch": 3.0609872522041894,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004082565641526242,
|
|
"loss": 4.9451,
|
|
"mean_token_accuracy": 0.230980084836483,
|
|
"num_tokens": 60830934.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 5.513065433502197,
|
|
"epoch": 3.061548829112147,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040822421207089654,
|
|
"loss": 4.9431,
|
|
"mean_token_accuracy": 0.22104135453701018,
|
|
"num_tokens": 60842161.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 5.611032962799072,
|
|
"epoch": 3.0621104060201043,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004081918557472582,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.2235030487179756,
|
|
"num_tokens": 60854220.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 5.597393369674682,
|
|
"epoch": 3.062671982928062,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004081594951827396,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.22864819765090943,
|
|
"num_tokens": 60864769.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 5.561152935028076,
|
|
"epoch": 3.0632335598360196,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040812713037837096,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.2292250409722328,
|
|
"num_tokens": 60874865.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 5.5817169666290285,
|
|
"epoch": 3.0637951367439773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040809476133518284,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.2173627644777298,
|
|
"num_tokens": 60885099.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 5.648992252349854,
|
|
"epoch": 3.0643567136519345,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040806238805420595,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.22085327804088592,
|
|
"num_tokens": 60896071.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 5.6786926746368405,
|
|
"epoch": 3.064918290559892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000408030010536471,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.22156515270471572,
|
|
"num_tokens": 60907255.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 5.5399878978729244,
|
|
"epoch": 3.06547986746785,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040799762878300895,
|
|
"loss": 4.8581,
|
|
"mean_token_accuracy": 0.2331258162856102,
|
|
"num_tokens": 60918740.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 5.544711875915527,
|
|
"epoch": 3.066041444375807,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040796524279485084,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.2307876914739609,
|
|
"num_tokens": 60929327.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 5.5497571468353275,
|
|
"epoch": 3.0666030212837647,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040793285257302776,
|
|
"loss": 4.913,
|
|
"mean_token_accuracy": 0.22399263381958007,
|
|
"num_tokens": 60939987.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 5.677018737792968,
|
|
"epoch": 3.0671645981917224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000407900458118571,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.22529786378145217,
|
|
"num_tokens": 60951924.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 5.638948822021485,
|
|
"epoch": 3.06772617509968,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004078680594325123,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.22023938447237015,
|
|
"num_tokens": 60963706.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 5.605771160125732,
|
|
"epoch": 3.0682877520076373,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000407835656515883,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.2281312420964241,
|
|
"num_tokens": 60974842.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 5.546226835250854,
|
|
"epoch": 3.068849328915595,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040780324936971486,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.2313540145754814,
|
|
"num_tokens": 60984921.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 5.601503515243531,
|
|
"epoch": 3.0694109058235526,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004077708379950397,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.22090831100940705,
|
|
"num_tokens": 60995648.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 5.565261888504028,
|
|
"epoch": 3.0699724827315102,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004077384223928896,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.21964947134256363,
|
|
"num_tokens": 61008020.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 5.591892194747925,
|
|
"epoch": 3.0705340596394675,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004077060025642967,
|
|
"loss": 4.8719,
|
|
"mean_token_accuracy": 0.2295897364616394,
|
|
"num_tokens": 61017735.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 5.57374119758606,
|
|
"epoch": 3.071095636547425,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004076735785102931,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.21753766685724257,
|
|
"num_tokens": 61029111.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 5.601520252227783,
|
|
"epoch": 3.071657213455383,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004076411502319114,
|
|
"loss": 4.946,
|
|
"mean_token_accuracy": 0.22416476309299468,
|
|
"num_tokens": 61039392.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 5.554129886627197,
|
|
"epoch": 3.0722187903633404,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040760871773018405,
|
|
"loss": 4.9315,
|
|
"mean_token_accuracy": 0.23245068937540053,
|
|
"num_tokens": 61049681.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 5.592700052261352,
|
|
"epoch": 3.0727803672712977,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004075762810061437,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.2254200682044029,
|
|
"num_tokens": 61059910.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 5.634598207473755,
|
|
"epoch": 3.0733419441792553,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000407543840060823,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.22702838182449342,
|
|
"num_tokens": 61071074.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 5.559741401672364,
|
|
"epoch": 3.073903521087213,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004075113948952551,
|
|
"loss": 4.9061,
|
|
"mean_token_accuracy": 0.22817442417144776,
|
|
"num_tokens": 61082051.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 5.621154165267944,
|
|
"epoch": 3.0744650979951706,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004074789455104731,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.22695875465869902,
|
|
"num_tokens": 61093578.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 5.568066549301148,
|
|
"epoch": 3.075026674903128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040744649190750995,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.22573281824588776,
|
|
"num_tokens": 61105192.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 5.572705888748169,
|
|
"epoch": 3.0755882518110855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004074140340873992,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.22133377492427825,
|
|
"num_tokens": 61116659.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 5.608372402191162,
|
|
"epoch": 3.076149828719043,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004073815720511743,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.2240496188402176,
|
|
"num_tokens": 61127761.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 5.575599956512451,
|
|
"epoch": 3.0767114056270004,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040734910579986875,
|
|
"loss": 4.8611,
|
|
"mean_token_accuracy": 0.2426621809601784,
|
|
"num_tokens": 61139039.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 5.573233222961425,
|
|
"epoch": 3.077272982534958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040731663533451624,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.22212466597557068,
|
|
"num_tokens": 61149877.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 5.632668352127075,
|
|
"epoch": 3.0778345594429157,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040728416065615087,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.22379509210586548,
|
|
"num_tokens": 61160806.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 5.613773345947266,
|
|
"epoch": 3.0783961363508734,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004072516817658065,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.21418614387512208,
|
|
"num_tokens": 61171471.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 5.585139513015747,
|
|
"epoch": 3.0789577132588306,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040721919866451724,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.22203302383422852,
|
|
"num_tokens": 61182140.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 5.547602558135987,
|
|
"epoch": 3.0795192901667883,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004071867113533174,
|
|
"loss": 4.917,
|
|
"mean_token_accuracy": 0.22529924511909485,
|
|
"num_tokens": 61192532.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 5.640742063522339,
|
|
"epoch": 3.080080867074746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040715421983324147,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.22193865180015565,
|
|
"num_tokens": 61205207.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 5.722278690338134,
|
|
"epoch": 3.0806424439827036,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040712172410532397,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.21932635605335235,
|
|
"num_tokens": 61218039.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 5.649944591522217,
|
|
"epoch": 3.081204020890661,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004070892241705994,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.22498717457056044,
|
|
"num_tokens": 61230343.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 5.494122743606567,
|
|
"epoch": 3.0817655977986185,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040705672003010275,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.22621229141950608,
|
|
"num_tokens": 61240781.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 5.545804882049561,
|
|
"epoch": 3.082327174706576,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000407024211684869,
|
|
"loss": 4.9646,
|
|
"mean_token_accuracy": 0.22552465945482253,
|
|
"num_tokens": 61250638.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 5.671315765380859,
|
|
"epoch": 3.082888751614534,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040699169913593306,
|
|
"loss": 4.9661,
|
|
"mean_token_accuracy": 0.2233765482902527,
|
|
"num_tokens": 61261431.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 5.6553126811981205,
|
|
"epoch": 3.083450328522491,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004069591823843302,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.2157829836010933,
|
|
"num_tokens": 61272726.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 5.637541437149048,
|
|
"epoch": 3.0840119054304487,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004069266614310959,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.2244120106101036,
|
|
"num_tokens": 61283779.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 5.615284252166748,
|
|
"epoch": 3.0845734823384063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040689413627726544,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.22493742555379867,
|
|
"num_tokens": 61294477.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 5.6914393424987795,
|
|
"epoch": 3.085135059246364,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040686160692387455,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.21247234791517258,
|
|
"num_tokens": 61305302.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 5.630256175994873,
|
|
"epoch": 3.085696636154321,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040682907337195894,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.22402355670928956,
|
|
"num_tokens": 61315499.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 5.63127589225769,
|
|
"epoch": 3.086258213062279,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004067965356225545,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.2171141982078552,
|
|
"num_tokens": 61326654.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 5.573463344573975,
|
|
"epoch": 3.0868197899702365,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040676399367669733,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.22105314284563066,
|
|
"num_tokens": 61338475.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 5.580693912506104,
|
|
"epoch": 3.0873813668781938,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004067314475354234,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.22053759545087814,
|
|
"num_tokens": 61348748.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 5.58357801437378,
|
|
"epoch": 3.0879429437861514,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040669889719976916,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.2295169711112976,
|
|
"num_tokens": 61359466.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 5.559934616088867,
|
|
"epoch": 3.088504520694109,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004066663426707709,
|
|
"loss": 4.8789,
|
|
"mean_token_accuracy": 0.23761471807956697,
|
|
"num_tokens": 61370136.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 5.55004768371582,
|
|
"epoch": 3.0890660976020667,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040663378394946534,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.217906254529953,
|
|
"num_tokens": 61381012.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 5.560540390014649,
|
|
"epoch": 3.089627674510024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004066012210368889,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.22672462612390518,
|
|
"num_tokens": 61393530.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 5.6092630386352536,
|
|
"epoch": 3.0901892514179816,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004065686539340786,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.22075356394052506,
|
|
"num_tokens": 61405753.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 5.5725194931030275,
|
|
"epoch": 3.0907508283259393,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040653608264207134,
|
|
"loss": 4.9022,
|
|
"mean_token_accuracy": 0.2242591291666031,
|
|
"num_tokens": 61416688.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 5.6714136600494385,
|
|
"epoch": 3.091312405233897,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040650350716190417,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.2236556053161621,
|
|
"num_tokens": 61427377.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 5.589133930206299,
|
|
"epoch": 3.091873982141854,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004064709274946143,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.22709283828735352,
|
|
"num_tokens": 61438457.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 5.5138819217681885,
|
|
"epoch": 3.092435559049812,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004064383436412392,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.22419706732034683,
|
|
"num_tokens": 61449380.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 5.548916673660278,
|
|
"epoch": 3.0929971359577695,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004064057556028162,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.22535633742809297,
|
|
"num_tokens": 61460846.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 5.61983470916748,
|
|
"epoch": 3.093558712865727,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000406373163380383,
|
|
"loss": 4.9598,
|
|
"mean_token_accuracy": 0.2237158015370369,
|
|
"num_tokens": 61471593.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 5.589644289016723,
|
|
"epoch": 3.0941202897736844,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040634056697497726,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.22137218564748765,
|
|
"num_tokens": 61483643.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 5.563120555877686,
|
|
"epoch": 3.094681866681642,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000406307966387637,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.22403628677129744,
|
|
"num_tokens": 61493220.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 5.561548042297363,
|
|
"epoch": 3.0952434435895997,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040627536161940016,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.2258682519197464,
|
|
"num_tokens": 61504372.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 5.503778028488159,
|
|
"epoch": 3.0958050204975573,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004062427526713049,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.22515564560890197,
|
|
"num_tokens": 61515335.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 5.573483276367187,
|
|
"epoch": 3.0963665974055146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004062101395443894,
|
|
"loss": 4.9114,
|
|
"mean_token_accuracy": 0.22263796031475067,
|
|
"num_tokens": 61526265.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 5.64127893447876,
|
|
"epoch": 3.0969281743134722,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004061775222396922,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.21362631618976594,
|
|
"num_tokens": 61538075.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 5.544527292251587,
|
|
"epoch": 3.09748975122143,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004061449007582519,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.22200874239206314,
|
|
"num_tokens": 61548612.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 5.514366531372071,
|
|
"epoch": 3.098051328129387,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000406112275101107,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.22773876041173935,
|
|
"num_tokens": 61559702.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 5.600785160064698,
|
|
"epoch": 3.0986129050373448,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040607964526929655,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.2276442140340805,
|
|
"num_tokens": 61569815.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 5.592655658721924,
|
|
"epoch": 3.0991744819453024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040604701126385924,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.22727261632680892,
|
|
"num_tokens": 61580050.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 5.632911205291748,
|
|
"epoch": 3.09973605885326,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004060143730858342,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.22215938419103623,
|
|
"num_tokens": 61590885.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 5.578213167190552,
|
|
"epoch": 3.1002976357612173,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040598173073626086,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.22555753737688064,
|
|
"num_tokens": 61601633.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 5.6698235988616945,
|
|
"epoch": 3.100859212669175,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004059490842161783,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.208466799557209,
|
|
"num_tokens": 61613244.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 5.635281324386597,
|
|
"epoch": 3.1014207895771326,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040591643352662615,
|
|
"loss": 4.9178,
|
|
"mean_token_accuracy": 0.23888467103242875,
|
|
"num_tokens": 61624939.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 5.526462268829346,
|
|
"epoch": 3.1019823664850903,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000405883778668644,
|
|
"loss": 4.8297,
|
|
"mean_token_accuracy": 0.2250433713197708,
|
|
"num_tokens": 61635480.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 5.56867356300354,
|
|
"epoch": 3.1025439433930475,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040585111964327157,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.22454623281955718,
|
|
"num_tokens": 61645500.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 5.505336618423462,
|
|
"epoch": 3.103105520301005,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040581845645154877,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.22822339683771134,
|
|
"num_tokens": 61656880.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 5.645993280410766,
|
|
"epoch": 3.103667097208963,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004057857890945155,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.22456287890672683,
|
|
"num_tokens": 61667451.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 5.666503095626831,
|
|
"epoch": 3.1042286741169205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040575311757321203,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.21725614815950395,
|
|
"num_tokens": 61679356.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 5.6136058330535885,
|
|
"epoch": 3.1047902510248777,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040572044188867863,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.21950583457946776,
|
|
"num_tokens": 61690154.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 5.621434020996094,
|
|
"epoch": 3.1053518279328354,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004056877620419556,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.22487679719924927,
|
|
"num_tokens": 61702321.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 5.599789953231811,
|
|
"epoch": 3.105913404840793,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004056550780340835,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.21997095495462418,
|
|
"num_tokens": 61713498.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 5.696123027801514,
|
|
"epoch": 3.1064749817487507,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004056223898661031,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.21557250320911409,
|
|
"num_tokens": 61725009.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 5.6352862358093265,
|
|
"epoch": 3.107036558656708,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040558969753905514,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.23166171014308928,
|
|
"num_tokens": 61735652.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 5.457483148574829,
|
|
"epoch": 3.1075981355646656,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004055570010539806,
|
|
"loss": 4.8404,
|
|
"mean_token_accuracy": 0.23383834660053254,
|
|
"num_tokens": 61746435.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 5.4883991241455075,
|
|
"epoch": 3.1081597124726232,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004055243004119204,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.23060853481292726,
|
|
"num_tokens": 61757523.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 5.71703143119812,
|
|
"epoch": 3.108721289380581,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040549159561391595,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.2195887967944145,
|
|
"num_tokens": 61769309.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 5.620844984054566,
|
|
"epoch": 3.109282866288538,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004054588866610085,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.22052332162857055,
|
|
"num_tokens": 61781093.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 5.596531009674072,
|
|
"epoch": 3.1098444431964958,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040542617355423947,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.23341619223356247,
|
|
"num_tokens": 61792837.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 5.649868488311768,
|
|
"epoch": 3.1104060201044534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040539345629465043,
|
|
"loss": 5.0023,
|
|
"mean_token_accuracy": 0.22726088166236877,
|
|
"num_tokens": 61804212.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 5.632020807266235,
|
|
"epoch": 3.1109675970124107,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040536073488328325,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.21697750240564345,
|
|
"num_tokens": 61815436.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 5.650684452056884,
|
|
"epoch": 3.1115291739203683,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004053280093211796,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.22085783928632735,
|
|
"num_tokens": 61829292.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 5.706311273574829,
|
|
"epoch": 3.112090750828326,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004052952796093817,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.23005418628454208,
|
|
"num_tokens": 61841440.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 5.5740132331848145,
|
|
"epoch": 3.1126523277362836,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040526254574893154,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.22830920070409774,
|
|
"num_tokens": 61853864.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 5.614470386505127,
|
|
"epoch": 3.113213904644241,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040522980774087143,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.22703793346881868,
|
|
"num_tokens": 61864739.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 5.548041677474975,
|
|
"epoch": 3.1137754815521985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004051970655862437,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.223625348508358,
|
|
"num_tokens": 61875940.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 5.598105430603027,
|
|
"epoch": 3.114337058460156,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004051643192860908,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.22745892107486726,
|
|
"num_tokens": 61887650.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 5.668389892578125,
|
|
"epoch": 3.114898635368114,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040513156884145564,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.21740048825740815,
|
|
"num_tokens": 61898624.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 5.57290210723877,
|
|
"epoch": 3.115460212276071,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004050988142533808,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.21458253264427185,
|
|
"num_tokens": 61911017.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 5.583318614959717,
|
|
"epoch": 3.1160217891840287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004050660555229093,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.2151665970683098,
|
|
"num_tokens": 61922381.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 5.691133213043213,
|
|
"epoch": 3.1165833660919864,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004050332926510841,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21812008768320085,
|
|
"num_tokens": 61932876.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 5.5446301937103275,
|
|
"epoch": 3.117144942999944,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004050005256389484,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.22809818238019944,
|
|
"num_tokens": 61943121.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 5.5478928565979,
|
|
"epoch": 3.1177065199079013,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004049677544875456,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.22225356549024583,
|
|
"num_tokens": 61953988.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 5.644856262207031,
|
|
"epoch": 3.118268096815859,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040493497919791906,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.22798736691474913,
|
|
"num_tokens": 61965111.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 5.6782220840454105,
|
|
"epoch": 3.1188296737238166,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040490219977111237,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.22663998007774352,
|
|
"num_tokens": 61976193.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 5.666691684722901,
|
|
"epoch": 3.1193912506317742,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004048694162081693,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.21886671036481858,
|
|
"num_tokens": 61987554.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 5.689150285720825,
|
|
"epoch": 3.1199528275397315,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004048366285101336,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.2126305654644966,
|
|
"num_tokens": 61998472.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 5.570993804931641,
|
|
"epoch": 3.120514404447689,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004048038366780494,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.22306917309761048,
|
|
"num_tokens": 62009368.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 5.546466302871704,
|
|
"epoch": 3.121075981355647,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004047710407129606,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.22991593629121782,
|
|
"num_tokens": 62021510.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 5.640787744522095,
|
|
"epoch": 3.121637558263604,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004047382406159115,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.2225070431828499,
|
|
"num_tokens": 62032057.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 5.580123233795166,
|
|
"epoch": 3.1221991351715617,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004047054363879466,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.23149583041667937,
|
|
"num_tokens": 62043185.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 5.68489260673523,
|
|
"epoch": 3.1227607120795193,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040467262803011025,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.21837891787290573,
|
|
"num_tokens": 62053483.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 5.657906436920166,
|
|
"epoch": 3.123322288987477,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040463981554344716,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.21096821427345275,
|
|
"num_tokens": 62065721.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 5.623401117324829,
|
|
"epoch": 3.123883865895434,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040460699892900197,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.22988318651914597,
|
|
"num_tokens": 62076251.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 5.596304988861084,
|
|
"epoch": 3.124445442803392,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004045741781878198,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.22625997215509414,
|
|
"num_tokens": 62086791.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 5.546246576309204,
|
|
"epoch": 3.1250070197113495,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040454135332094543,
|
|
"loss": 4.8345,
|
|
"mean_token_accuracy": 0.2328280985355377,
|
|
"num_tokens": 62097054.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 5.577165269851685,
|
|
"epoch": 3.125568596619307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004045085243294242,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.23235608786344528,
|
|
"num_tokens": 62108304.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 5.598659896850586,
|
|
"epoch": 3.1261301735272644,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004044756912143013,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.21928934752941132,
|
|
"num_tokens": 62119724.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 5.559492015838623,
|
|
"epoch": 3.126691750435222,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040444285397662225,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.2341329723596573,
|
|
"num_tokens": 62131021.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 5.679141712188721,
|
|
"epoch": 3.1272533273431797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004044100126174324,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.21583354026079177,
|
|
"num_tokens": 62141846.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 5.672500371932983,
|
|
"epoch": 3.1278149042511374,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040437716713777756,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21473847031593324,
|
|
"num_tokens": 62152922.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 5.679659652709961,
|
|
"epoch": 3.1283764811590946,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004043443175387036,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.21505232155323029,
|
|
"num_tokens": 62164645.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 5.583871078491211,
|
|
"epoch": 3.1289380580670523,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040431146382125644,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.21819087117910385,
|
|
"num_tokens": 62175910.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 5.517398881912231,
|
|
"epoch": 3.12949963497501,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000404278605986482,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.22941214740276336,
|
|
"num_tokens": 62187411.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 5.53351058959961,
|
|
"epoch": 3.1300612118829676,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004042457440354267,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.23500000089406967,
|
|
"num_tokens": 62199316.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 5.708405351638794,
|
|
"epoch": 3.130622788790925,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004042128779691368,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.2237364962697029,
|
|
"num_tokens": 62211864.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 5.606237411499023,
|
|
"epoch": 3.1311843656988825,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004041800077886587,
|
|
"loss": 4.8886,
|
|
"mean_token_accuracy": 0.2335718169808388,
|
|
"num_tokens": 62221715.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 5.608114957809448,
|
|
"epoch": 3.13174594260684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040414713349503907,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.22822613418102264,
|
|
"num_tokens": 62233198.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 5.576194715499878,
|
|
"epoch": 3.1323075195147974,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040411425508932457,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.22734561264514924,
|
|
"num_tokens": 62244149.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 5.657273387908935,
|
|
"epoch": 3.132869096422755,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040408137257256225,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.22101794928312302,
|
|
"num_tokens": 62254994.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 5.654990339279175,
|
|
"epoch": 3.1334306733307127,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004040484859457988,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.21375194936990738,
|
|
"num_tokens": 62265685.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 5.55957145690918,
|
|
"epoch": 3.1339922502386703,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040401559521008155,
|
|
"loss": 4.942,
|
|
"mean_token_accuracy": 0.230035762488842,
|
|
"num_tokens": 62275765.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 5.51606764793396,
|
|
"epoch": 3.1345538271466276,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040398270036645775,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.2198595553636551,
|
|
"num_tokens": 62286020.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 5.6264642715454105,
|
|
"epoch": 3.135115404054585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004039498014159748,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.2215246379375458,
|
|
"num_tokens": 62296231.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 5.616795349121094,
|
|
"epoch": 3.135676980962543,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040391689835968004,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.2205485448241234,
|
|
"num_tokens": 62307243.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 5.598483228683472,
|
|
"epoch": 3.1362385578705005,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004038839911986213,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.2240550175309181,
|
|
"num_tokens": 62319061.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 5.645838785171509,
|
|
"epoch": 3.1368001347784578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004038510799338462,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.22065349370241166,
|
|
"num_tokens": 62329477.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 5.615762376785279,
|
|
"epoch": 3.1373617116864154,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004038181645664029,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.232073549926281,
|
|
"num_tokens": 62339170.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 5.690928554534912,
|
|
"epoch": 3.137923288594373,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040378524509733916,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.2182541847229004,
|
|
"num_tokens": 62350548.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 5.5630041599273685,
|
|
"epoch": 3.1384848655023307,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004037523215277033,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.22435346245765686,
|
|
"num_tokens": 62361105.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 5.589398527145386,
|
|
"epoch": 3.139046442410288,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004037193938585436,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.22615769356489182,
|
|
"num_tokens": 62372048.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 5.576702642440796,
|
|
"epoch": 3.1396080193182456,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004036864620909085,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.216849485039711,
|
|
"num_tokens": 62382936.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 5.59371600151062,
|
|
"epoch": 3.1401695962262033,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004036535262258465,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.2246306747198105,
|
|
"num_tokens": 62393656.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 5.619045352935791,
|
|
"epoch": 3.140731173134161,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040362058626440637,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.2227358788251877,
|
|
"num_tokens": 62404234.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 5.621191596984863,
|
|
"epoch": 3.141292750042118,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040358764220763685,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.22192031741142274,
|
|
"num_tokens": 62416694.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 5.627512788772583,
|
|
"epoch": 3.141854326950076,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040355469405658687,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.22449714690446854,
|
|
"num_tokens": 62429437.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 5.639588928222656,
|
|
"epoch": 3.1424159038580335,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004035217418123056,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.2276619479060173,
|
|
"num_tokens": 62440085.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 5.652481985092163,
|
|
"epoch": 3.1429774807659907,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040348878547584227,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.22264629006385803,
|
|
"num_tokens": 62451285.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 5.555470609664917,
|
|
"epoch": 3.1435390576739484,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040345582504824624,
|
|
"loss": 4.9455,
|
|
"mean_token_accuracy": 0.22719353288412095,
|
|
"num_tokens": 62461777.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 5.611395692825317,
|
|
"epoch": 3.144100634581906,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004034228605305668,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.22931823432445525,
|
|
"num_tokens": 62472463.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 5.519044017791748,
|
|
"epoch": 3.1446622114898637,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040338989192385377,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.2225746288895607,
|
|
"num_tokens": 62484168.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 5.688692378997803,
|
|
"epoch": 3.145223788397821,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004033569192291567,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.22328701317310334,
|
|
"num_tokens": 62495187.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 5.640716028213501,
|
|
"epoch": 3.1457853653057786,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004033239424475256,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.21195005774497985,
|
|
"num_tokens": 62505936.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 5.696809720993042,
|
|
"epoch": 3.1463469422137362,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040329096158001033,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.2199963241815567,
|
|
"num_tokens": 62516486.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 5.620268487930298,
|
|
"epoch": 3.146908519121694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004032579766276612,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.2293887585401535,
|
|
"num_tokens": 62528349.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 5.495006656646728,
|
|
"epoch": 3.147470096029651,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040322498759152824,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.21923377960920334,
|
|
"num_tokens": 62538698.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 5.659903812408447,
|
|
"epoch": 3.1480316729376088,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040319199447266205,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.21442670226097107,
|
|
"num_tokens": 62550891.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 5.704310417175293,
|
|
"epoch": 3.1485932498455664,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004031589972721129,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.21713108122348784,
|
|
"num_tokens": 62560553.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 5.709572887420654,
|
|
"epoch": 3.149154826753524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004031259959909317,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.22173553705215454,
|
|
"num_tokens": 62571281.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 5.520815515518189,
|
|
"epoch": 3.1497164036614813,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000403092990630169,
|
|
"loss": 4.9427,
|
|
"mean_token_accuracy": 0.22334519475698472,
|
|
"num_tokens": 62583489.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 5.528823137283325,
|
|
"epoch": 3.150277980569439,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004030599811908758,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.2342058777809143,
|
|
"num_tokens": 62594155.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 5.575923252105713,
|
|
"epoch": 3.1508395574773966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004030269676741032,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.2288086161017418,
|
|
"num_tokens": 62605464.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 5.59696626663208,
|
|
"epoch": 3.1514011343853543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004029939500809023,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.22414637058973313,
|
|
"num_tokens": 62617343.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 5.625635576248169,
|
|
"epoch": 3.1519627112933115,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004029609284123243,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.23136115521192552,
|
|
"num_tokens": 62628461.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 5.593613862991333,
|
|
"epoch": 3.152524288201269,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040292790266942074,
|
|
"loss": 4.948,
|
|
"mean_token_accuracy": 0.22467086166143418,
|
|
"num_tokens": 62638947.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 5.492580270767212,
|
|
"epoch": 3.153085865109227,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040289487285324324,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.2365974083542824,
|
|
"num_tokens": 62648840.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 5.674798250198364,
|
|
"epoch": 3.153647442017184,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004028618389648433,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.2167844980955124,
|
|
"num_tokens": 62659491.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 5.686497402191162,
|
|
"epoch": 3.1542090189251417,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004028288010052728,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.2200331211090088,
|
|
"num_tokens": 62669038.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 5.564283943176269,
|
|
"epoch": 3.1547705958330994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004027957589755837,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.23523188084363938,
|
|
"num_tokens": 62680280.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 5.597380065917969,
|
|
"epoch": 3.155332172741057,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040276271287682813,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.2267753079533577,
|
|
"num_tokens": 62691767.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 5.663282203674316,
|
|
"epoch": 3.1558937496490143,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040272966271005816,
|
|
"loss": 4.9801,
|
|
"mean_token_accuracy": 0.22500652223825454,
|
|
"num_tokens": 62701721.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 5.660431814193726,
|
|
"epoch": 3.156455326556972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040269660847632626,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.22658491581678392,
|
|
"num_tokens": 62713238.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 5.540104532241822,
|
|
"epoch": 3.1570169034649296,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040266355017668475,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.23023918718099595,
|
|
"num_tokens": 62724457.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 5.6167796611785885,
|
|
"epoch": 3.1575784803728872,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004026304878121864,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.2282220885157585,
|
|
"num_tokens": 62735178.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 5.634019804000855,
|
|
"epoch": 3.1581400572808445,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040259742138388366,
|
|
"loss": 4.9646,
|
|
"mean_token_accuracy": 0.22580485045909882,
|
|
"num_tokens": 62746767.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 5.615706491470337,
|
|
"epoch": 3.158701634188802,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040256435089282966,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.22743033319711686,
|
|
"num_tokens": 62757963.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 5.645140886306763,
|
|
"epoch": 3.15926321109676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004025312763400772,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.21428212225437165,
|
|
"num_tokens": 62769763.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 5.509347772598266,
|
|
"epoch": 3.1598247880047174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004024981977266794,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.23655095249414443,
|
|
"num_tokens": 62780947.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 5.627530574798584,
|
|
"epoch": 3.1603863649126747,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004024651150536896,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.21395987123250962,
|
|
"num_tokens": 62793003.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 5.598092174530029,
|
|
"epoch": 3.1609479418206323,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004024320283221611,
|
|
"loss": 4.9691,
|
|
"mean_token_accuracy": 0.21721746474504472,
|
|
"num_tokens": 62804467.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 5.590987730026245,
|
|
"epoch": 3.16150951872859,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040239893753314735,
|
|
"loss": 4.9333,
|
|
"mean_token_accuracy": 0.22746841311454774,
|
|
"num_tokens": 62815834.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 5.607584762573242,
|
|
"epoch": 3.1620710956365476,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004023658426877021,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.21550233662128448,
|
|
"num_tokens": 62827277.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 5.613339567184449,
|
|
"epoch": 3.162632672544505,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040233274378687897,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.23264726251363754,
|
|
"num_tokens": 62838652.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 5.650116205215454,
|
|
"epoch": 3.1631942494524625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040229964083173187,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.21528787910938263,
|
|
"num_tokens": 62849448.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 5.626809167861938,
|
|
"epoch": 3.16375582636042,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040226653382331484,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.2308835044503212,
|
|
"num_tokens": 62860840.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 5.639439725875855,
|
|
"epoch": 3.1643174032683774,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000402233422762682,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.23053320050239562,
|
|
"num_tokens": 62871321.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 5.541574001312256,
|
|
"epoch": 3.164878980176335,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040220030765088764,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.2297578290104866,
|
|
"num_tokens": 62882865.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 5.601031494140625,
|
|
"epoch": 3.1654405570842927,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004021671884889862,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.22014516294002534,
|
|
"num_tokens": 62894122.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 5.607012605667114,
|
|
"epoch": 3.1660021339922504,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004021340652780321,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.21380530446767806,
|
|
"num_tokens": 62904797.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 5.6487390995025635,
|
|
"epoch": 3.1665637109002076,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004021009380190801,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.2248694881796837,
|
|
"num_tokens": 62914739.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 5.642565298080444,
|
|
"epoch": 3.1671252878081653,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040206780671318495,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.22209043204784393,
|
|
"num_tokens": 62925183.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 5.5819539546966555,
|
|
"epoch": 3.167686864716123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004020346713614015,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.22480290830135347,
|
|
"num_tokens": 62936197.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 5.57702054977417,
|
|
"epoch": 3.1682484416240806,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040200153196478486,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.22232259064912796,
|
|
"num_tokens": 62947571.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 5.604915809631348,
|
|
"epoch": 3.168810018532038,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004019683885243902,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.22094154804944993,
|
|
"num_tokens": 62957614.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 5.595571231842041,
|
|
"epoch": 3.1693715954399955,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004019352410412728,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.22746020257472993,
|
|
"num_tokens": 62968840.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 5.620762300491333,
|
|
"epoch": 3.169933172347953,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040190208951648807,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.22472333461046218,
|
|
"num_tokens": 62979956.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 5.586041641235352,
|
|
"epoch": 3.170494749255911,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004018689339510916,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.2356567680835724,
|
|
"num_tokens": 62991352.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 5.750027370452881,
|
|
"epoch": 3.171056326163868,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040183577434613904,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.21556919515132905,
|
|
"num_tokens": 63002738.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 5.646267700195312,
|
|
"epoch": 3.1716179030718257,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004018026107026863,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.22068951427936553,
|
|
"num_tokens": 63013989.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 5.553122091293335,
|
|
"epoch": 3.1721794799797833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004017694430217892,
|
|
"loss": 4.9111,
|
|
"mean_token_accuracy": 0.222635355591774,
|
|
"num_tokens": 63026158.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 5.543333292007446,
|
|
"epoch": 3.172741056887741,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004017362713045039,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.22551799416542054,
|
|
"num_tokens": 63036432.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 5.665471363067627,
|
|
"epoch": 3.173302633795698,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040170309555188655,
|
|
"loss": 4.9745,
|
|
"mean_token_accuracy": 0.22300178706645965,
|
|
"num_tokens": 63047151.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 5.599868488311768,
|
|
"epoch": 3.173864210703656,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004016699157649936,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.2243029937148094,
|
|
"num_tokens": 63059514.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 5.711123514175415,
|
|
"epoch": 3.1744257876116135,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004016367319448812,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.21803859621286392,
|
|
"num_tokens": 63071037.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 5.645338153839111,
|
|
"epoch": 3.1749873645195708,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040160354409260625,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.22489237338304519,
|
|
"num_tokens": 63083615.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 5.582065773010254,
|
|
"epoch": 3.1755489414275284,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004015703522092254,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.2223475009202957,
|
|
"num_tokens": 63094377.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 5.53400502204895,
|
|
"epoch": 3.176110518335486,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004015371562957954,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.22478598803281785,
|
|
"num_tokens": 63105108.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 5.719071722030639,
|
|
"epoch": 3.1766720952434437,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004015039563533732,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.2152826964855194,
|
|
"num_tokens": 63116576.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 5.676792240142822,
|
|
"epoch": 3.177233672151401,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004014707523830161,
|
|
"loss": 5.0234,
|
|
"mean_token_accuracy": 0.22692816257476806,
|
|
"num_tokens": 63128343.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 5.728842735290527,
|
|
"epoch": 3.1777952490593586,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004014375443857811,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.21146599054336548,
|
|
"num_tokens": 63140309.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 5.687521123886109,
|
|
"epoch": 3.1783568259673163,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004014043323627257,
|
|
"loss": 5.0268,
|
|
"mean_token_accuracy": 0.21995241940021515,
|
|
"num_tokens": 63150825.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 5.603007555007935,
|
|
"epoch": 3.178918402875274,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004013711163149072,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.23019881546497345,
|
|
"num_tokens": 63161296.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 5.593397188186645,
|
|
"epoch": 3.179479979783231,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040133789624338353,
|
|
"loss": 4.8995,
|
|
"mean_token_accuracy": 0.2303716540336609,
|
|
"num_tokens": 63171447.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 5.561095285415649,
|
|
"epoch": 3.180041556691189,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040130467214921216,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.21394664347171782,
|
|
"num_tokens": 63182860.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 5.683769941329956,
|
|
"epoch": 3.1806031335991465,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000401271444033451,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.22363089323043822,
|
|
"num_tokens": 63192894.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 5.671697044372559,
|
|
"epoch": 3.181164710507104,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004012382118971582,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.21789546459913253,
|
|
"num_tokens": 63204013.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 5.592043876647949,
|
|
"epoch": 3.1817262874150614,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004012049757413917,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.22924842238426207,
|
|
"num_tokens": 63215079.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 5.567132663726807,
|
|
"epoch": 3.182287864323019,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040117173556720976,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.2212101325392723,
|
|
"num_tokens": 63225185.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 5.701519107818603,
|
|
"epoch": 3.1828494412309767,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040113849137567094,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.22365955114364625,
|
|
"num_tokens": 63237490.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 5.620514822006226,
|
|
"epoch": 3.1834110181389343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004011052431678336,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.23210598528385162,
|
|
"num_tokens": 63247774.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 5.599667930603028,
|
|
"epoch": 3.1839725950468916,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004010719909447564,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.22572488486766815,
|
|
"num_tokens": 63258953.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 5.578725099563599,
|
|
"epoch": 3.1845341719548492,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004010387347074981,
|
|
"loss": 4.9513,
|
|
"mean_token_accuracy": 0.22603930979967118,
|
|
"num_tokens": 63269670.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 5.581488370895386,
|
|
"epoch": 3.185095748862807,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040100547445711765,
|
|
"loss": 4.9679,
|
|
"mean_token_accuracy": 0.23008579909801483,
|
|
"num_tokens": 63280644.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 5.627592897415161,
|
|
"epoch": 3.185657325770764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040097221019467393,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.22343634814023972,
|
|
"num_tokens": 63292328.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 5.505062580108643,
|
|
"epoch": 3.1862189026787218,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004009389419212262,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.2324822261929512,
|
|
"num_tokens": 63302849.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 5.536277341842651,
|
|
"epoch": 3.1867804795866794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040090566963783375,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.22081674188375472,
|
|
"num_tokens": 63314460.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 5.610166788101196,
|
|
"epoch": 3.187342056494637,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040087239334555603,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.2264371395111084,
|
|
"num_tokens": 63325713.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 5.648744440078735,
|
|
"epoch": 3.1879036334025943,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040083911304545234,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.21988650560379028,
|
|
"num_tokens": 63338287.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 5.630614328384399,
|
|
"epoch": 3.188465210310552,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040080582873858254,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.22815661877393723,
|
|
"num_tokens": 63349592.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 5.607546329498291,
|
|
"epoch": 3.1890267872185096,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004007725404260064,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.23346428871154784,
|
|
"num_tokens": 63359913.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 5.634452962875367,
|
|
"epoch": 3.1895883641264673,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004007392481087837,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.22086248993873597,
|
|
"num_tokens": 63370677.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 5.647119808197021,
|
|
"epoch": 3.1901499410344245,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004007059517879747,
|
|
"loss": 4.9196,
|
|
"mean_token_accuracy": 0.23623029738664628,
|
|
"num_tokens": 63381467.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 5.623531007766724,
|
|
"epoch": 3.190711517942382,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004006726514646393,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.22387082278728485,
|
|
"num_tokens": 63392808.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 5.55219988822937,
|
|
"epoch": 3.19127309485034,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040063934713983803,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.22332260757684708,
|
|
"num_tokens": 63405206.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 5.4819502353668215,
|
|
"epoch": 3.1918346717582975,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040060603881463127,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.2297041669487953,
|
|
"num_tokens": 63416923.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 5.605182790756226,
|
|
"epoch": 3.1923962486662547,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040057272649007944,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.22530280351638793,
|
|
"num_tokens": 63426681.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 5.662752771377564,
|
|
"epoch": 3.1929578255742124,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00040053941016724326,
|
|
"loss": 4.9423,
|
|
"mean_token_accuracy": 0.2234150767326355,
|
|
"num_tokens": 63437299.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 5.631463670730591,
|
|
"epoch": 3.19351940248217,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040050608984718364,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.22425127774477005,
|
|
"num_tokens": 63449075.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 5.583202266693116,
|
|
"epoch": 3.1940809793901277,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004004727655309614,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.225144162774086,
|
|
"num_tokens": 63460592.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 5.658104467391968,
|
|
"epoch": 3.194642556298085,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040043943721963766,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.22377624064683915,
|
|
"num_tokens": 63471043.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 5.686793851852417,
|
|
"epoch": 3.1952041332060426,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040040610491427357,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.21680007874965668,
|
|
"num_tokens": 63482556.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 5.7502038955688475,
|
|
"epoch": 3.1957657101140002,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004003727686159305,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.21160504817962647,
|
|
"num_tokens": 63493973.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 5.659843397140503,
|
|
"epoch": 3.1963272870219575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040033942832566984,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.21579598188400267,
|
|
"num_tokens": 63504489.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 5.647422933578492,
|
|
"epoch": 3.196888863929915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004003060840445531,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.22027967125177383,
|
|
"num_tokens": 63516688.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 5.736678838729858,
|
|
"epoch": 3.1974504408378728,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004002727357736422,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.2157798871397972,
|
|
"num_tokens": 63528680.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 5.626579666137696,
|
|
"epoch": 3.1980120177458304,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040023938351399865,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.22218971848487853,
|
|
"num_tokens": 63540489.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 5.620211553573609,
|
|
"epoch": 3.1985735946537877,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004002060272666846,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.21842532753944396,
|
|
"num_tokens": 63551974.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 5.670551109313965,
|
|
"epoch": 3.1991351715617453,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004001726670327621,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.21671505719423295,
|
|
"num_tokens": 63564437.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 5.6582976341247555,
|
|
"epoch": 3.199696748469703,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004001393028132933,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.23306961953639985,
|
|
"num_tokens": 63575041.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 5.61745548248291,
|
|
"epoch": 3.2002583253776606,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040010593460934065,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.22745491415262223,
|
|
"num_tokens": 63587381.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 5.645371532440185,
|
|
"epoch": 3.200819902285618,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040007256242196644,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.22352198809385299,
|
|
"num_tokens": 63599206.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 5.663104438781739,
|
|
"epoch": 3.2013814791935755,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040003918625223335,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.2161872059106827,
|
|
"num_tokens": 63609557.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 5.615341281890869,
|
|
"epoch": 3.201943056101533,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040000580610120406,
|
|
"loss": 4.9795,
|
|
"mean_token_accuracy": 0.21958695501089096,
|
|
"num_tokens": 63620423.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 5.712139368057251,
|
|
"epoch": 3.202504633009491,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003999724219699415,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.22141887098550797,
|
|
"num_tokens": 63632222.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 5.594260120391846,
|
|
"epoch": 3.203066209917448,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003999390338595085,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.224665866792202,
|
|
"num_tokens": 63643077.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 5.548943424224854,
|
|
"epoch": 3.2036277868254057,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039990564177096817,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.2330853074789047,
|
|
"num_tokens": 63653642.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 5.579360389709473,
|
|
"epoch": 3.2041893637333634,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003998722457053838,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.2170818865299225,
|
|
"num_tokens": 63665646.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 5.733917474746704,
|
|
"epoch": 3.204750940641321,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039983884566381866,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.21715219616889953,
|
|
"num_tokens": 63677928.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 5.681574440002441,
|
|
"epoch": 3.2053125175492783,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003998054416473363,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.2210349142551422,
|
|
"num_tokens": 63688670.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 5.685310697555542,
|
|
"epoch": 3.205874094457236,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039977203365700026,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.2224513530731201,
|
|
"num_tokens": 63699963.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 5.611152219772339,
|
|
"epoch": 3.2064356713651936,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003997386216938743,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.20903612971305846,
|
|
"num_tokens": 63711333.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 5.643983936309814,
|
|
"epoch": 3.206997248273151,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039970520575902216,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.22614717185497285,
|
|
"num_tokens": 63721916.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 5.594388866424561,
|
|
"epoch": 3.2075588251811085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000399671785853508,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.2226802110671997,
|
|
"num_tokens": 63733313.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 5.626555442810059,
|
|
"epoch": 3.208120402089066,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039963836197839584,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.2225699707865715,
|
|
"num_tokens": 63743249.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 5.621691703796387,
|
|
"epoch": 3.208681978997024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039960493413474977,
|
|
"loss": 5.0098,
|
|
"mean_token_accuracy": 0.21902186572551727,
|
|
"num_tokens": 63754355.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 5.795539903640747,
|
|
"epoch": 3.209243555904981,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039957150232363433,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.21956883519887924,
|
|
"num_tokens": 63766620.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 5.649285840988159,
|
|
"epoch": 3.2098051328129387,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000399538066546114,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.22591305822134017,
|
|
"num_tokens": 63777195.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 5.53043794631958,
|
|
"epoch": 3.2103667097208963,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039950462680325336,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.22404814511537552,
|
|
"num_tokens": 63787653.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 5.611427879333496,
|
|
"epoch": 3.210928286628854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000399471183096117,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.22068421989679338,
|
|
"num_tokens": 63799371.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 5.5553487777709964,
|
|
"epoch": 3.211489863536811,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003994377354257698,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.2349778965115547,
|
|
"num_tokens": 63809791.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 5.648146152496338,
|
|
"epoch": 3.212051440444769,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039940428379327703,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.2267472267150879,
|
|
"num_tokens": 63819972.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 5.49125394821167,
|
|
"epoch": 3.2126130173527265,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003993708281997036,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.22454729825258254,
|
|
"num_tokens": 63830144.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 5.6125038146972654,
|
|
"epoch": 3.213174594260684,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003993373686461147,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.2178807720541954,
|
|
"num_tokens": 63842393.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 5.627258586883545,
|
|
"epoch": 3.2137361711686414,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003993039051335758,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.21924506723880768,
|
|
"num_tokens": 63853392.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 5.603962707519531,
|
|
"epoch": 3.214297748076599,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003992704376631523,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.22116690874099731,
|
|
"num_tokens": 63866037.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 5.618041944503784,
|
|
"epoch": 3.2148593249845567,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003992369662359099,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.2265725165605545,
|
|
"num_tokens": 63876264.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 5.565889358520508,
|
|
"epoch": 3.2154209018925144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003992034908529143,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.2310175135731697,
|
|
"num_tokens": 63887545.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 5.584534358978272,
|
|
"epoch": 3.2159824788004716,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039917001151523144,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.2180737227201462,
|
|
"num_tokens": 63897689.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 5.651491403579712,
|
|
"epoch": 3.2165440557084293,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003991365282239272,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.22292573302984237,
|
|
"num_tokens": 63908884.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 5.625011682510376,
|
|
"epoch": 3.217105632616387,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039910304098006775,
|
|
"loss": 4.9373,
|
|
"mean_token_accuracy": 0.22243258208036423,
|
|
"num_tokens": 63918515.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 5.575724649429321,
|
|
"epoch": 3.217667209524344,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003990695497847193,
|
|
"loss": 4.9501,
|
|
"mean_token_accuracy": 0.22924645245075226,
|
|
"num_tokens": 63928802.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 5.605947780609131,
|
|
"epoch": 3.218228786432302,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003990360546389484,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.23326669931411742,
|
|
"num_tokens": 63940770.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 5.702812385559082,
|
|
"epoch": 3.2187903633402595,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039900255554382126,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.22550639063119887,
|
|
"num_tokens": 63951851.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 5.603956985473633,
|
|
"epoch": 3.219351940248217,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039896905250040473,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.2193770781159401,
|
|
"num_tokens": 63962768.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 5.607453203201294,
|
|
"epoch": 3.2199135171561744,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039893554550976545,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21117885559797286,
|
|
"num_tokens": 63973855.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 5.698689699172974,
|
|
"epoch": 3.220475094064132,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003989020345729705,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.21951902508735657,
|
|
"num_tokens": 63986342.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 5.595315885543823,
|
|
"epoch": 3.2210366709720897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039886851969108653,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.22717487961053848,
|
|
"num_tokens": 63997080.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 5.552761268615723,
|
|
"epoch": 3.2215982478800473,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039883500086518086,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.2240300565958023,
|
|
"num_tokens": 64007373.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 5.626544046401977,
|
|
"epoch": 3.2221598247880046,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039880147809632084,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.22316653579473494,
|
|
"num_tokens": 64018429.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 5.621206903457642,
|
|
"epoch": 3.222721401695962,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039876795138557363,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.2271012544631958,
|
|
"num_tokens": 64028633.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 5.695056390762329,
|
|
"epoch": 3.22328297860392,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003987344207340069,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.22144312411546707,
|
|
"num_tokens": 64040860.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 5.6856475353240965,
|
|
"epoch": 3.2238445555118775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039870088614268824,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.21385203003883363,
|
|
"num_tokens": 64053141.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 5.549976062774658,
|
|
"epoch": 3.2244061324198348,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039866734761268534,
|
|
"loss": 4.9192,
|
|
"mean_token_accuracy": 0.2305079370737076,
|
|
"num_tokens": 64064583.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 5.720214319229126,
|
|
"epoch": 3.2249677093277924,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039863380514506614,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.21617454737424852,
|
|
"num_tokens": 64075368.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 5.6710512161254885,
|
|
"epoch": 3.22552928623575,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039860025874089865,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.22218833565711976,
|
|
"num_tokens": 64085815.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 5.6086067199707035,
|
|
"epoch": 3.2260908631437077,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000398566708401251,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.2323991686105728,
|
|
"num_tokens": 64096825.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 5.586061286926269,
|
|
"epoch": 3.226652440051665,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039853315412719144,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.2305946409702301,
|
|
"num_tokens": 64108010.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 5.6647796630859375,
|
|
"epoch": 3.2272140169596226,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003984995959197883,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.2221042737364769,
|
|
"num_tokens": 64119829.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 5.636851119995117,
|
|
"epoch": 3.2277755938675803,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003984660337801101,
|
|
"loss": 4.9366,
|
|
"mean_token_accuracy": 0.2235192283987999,
|
|
"num_tokens": 64130138.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 5.636291074752807,
|
|
"epoch": 3.2283371707755375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039843246770922557,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.22106845676898956,
|
|
"num_tokens": 64141651.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 5.677275609970093,
|
|
"epoch": 3.228898747683495,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003983988977082033,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.21703296154737473,
|
|
"num_tokens": 64152718.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 5.618657732009888,
|
|
"epoch": 3.229460324591453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039836532377811237,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.22281094938516616,
|
|
"num_tokens": 64163977.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 5.585703420639038,
|
|
"epoch": 3.2300219014994105,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003983317459200217,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.2238154798746109,
|
|
"num_tokens": 64175298.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 5.61435604095459,
|
|
"epoch": 3.2305834784073677,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039829816413500035,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.22376581877470017,
|
|
"num_tokens": 64186746.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 5.629458618164063,
|
|
"epoch": 3.2311450553153254,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003982645784241176,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.2188843831419945,
|
|
"num_tokens": 64198682.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 5.667328262329102,
|
|
"epoch": 3.231706632223283,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003982309887884429,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.22733115553855895,
|
|
"num_tokens": 64210425.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 5.593331050872803,
|
|
"epoch": 3.2322682091312407,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039819739522904576,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.23105984479188918,
|
|
"num_tokens": 64222839.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 5.53798475265503,
|
|
"epoch": 3.232829786039198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039816379774699573,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.2255244717001915,
|
|
"num_tokens": 64234235.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 5.635688304901123,
|
|
"epoch": 3.2333913629471556,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039813019634336264,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.22515739053487777,
|
|
"num_tokens": 64244607.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 5.61917896270752,
|
|
"epoch": 3.2339529398551132,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003980965910192163,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.22240060865879058,
|
|
"num_tokens": 64254434.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 5.539731502532959,
|
|
"epoch": 3.234514516763071,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039806298177562675,
|
|
"loss": 4.9579,
|
|
"mean_token_accuracy": 0.22198902070522308,
|
|
"num_tokens": 64266693.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 5.5998095035552975,
|
|
"epoch": 3.235076093671028,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039802936861366416,
|
|
"loss": 4.9817,
|
|
"mean_token_accuracy": 0.22675332874059678,
|
|
"num_tokens": 64277901.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 5.663611602783203,
|
|
"epoch": 3.2356376705789858,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003979957515343988,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.22274363934993743,
|
|
"num_tokens": 64288583.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 5.620576810836792,
|
|
"epoch": 3.2361992474869434,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000397962130538901,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.22480532228946687,
|
|
"num_tokens": 64299688.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 5.584033250808716,
|
|
"epoch": 3.236760824394901,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039792850562824124,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.22674895972013473,
|
|
"num_tokens": 64311150.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 5.592848062515259,
|
|
"epoch": 3.2373224013028583,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003978948768034902,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.22668081074953078,
|
|
"num_tokens": 64322658.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 5.588323783874512,
|
|
"epoch": 3.237883978210816,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039786124406571854,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.22377798706293106,
|
|
"num_tokens": 64333350.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 5.658504629135132,
|
|
"epoch": 3.2384455551187736,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039782760741599734,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.22426819950342178,
|
|
"num_tokens": 64344689.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 5.560111618041992,
|
|
"epoch": 3.239007132026731,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003977939668553973,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.22333277761936188,
|
|
"num_tokens": 64356602.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 5.584130907058716,
|
|
"epoch": 3.2395687089346885,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039776032238498995,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.22475631833076476,
|
|
"num_tokens": 64368496.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 5.6583386898040775,
|
|
"epoch": 3.240130285842646,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003977266740058462,
|
|
"loss": 4.9802,
|
|
"mean_token_accuracy": 0.21868252456188203,
|
|
"num_tokens": 64379374.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 5.681223583221436,
|
|
"epoch": 3.240691862750604,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003976930217190376,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.2287382885813713,
|
|
"num_tokens": 64391006.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 5.584674406051636,
|
|
"epoch": 3.241253439658561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003976593655256356,
|
|
"loss": 4.9622,
|
|
"mean_token_accuracy": 0.2221319168806076,
|
|
"num_tokens": 64403100.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 5.533655071258545,
|
|
"epoch": 3.2418150165665187,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039762570542671176,
|
|
"loss": 4.9081,
|
|
"mean_token_accuracy": 0.2288163810968399,
|
|
"num_tokens": 64413763.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 5.546851778030396,
|
|
"epoch": 3.2423765934744764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000397592041423338,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.22541419118642808,
|
|
"num_tokens": 64425289.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 5.663061714172363,
|
|
"epoch": 3.242938170382434,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039755837351658605,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.22416529059410095,
|
|
"num_tokens": 64436080.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 5.620600271224975,
|
|
"epoch": 3.2434997472903913,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003975247017075279,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.22164130508899688,
|
|
"num_tokens": 64447036.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 5.689269208908081,
|
|
"epoch": 3.244061324198349,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003974910259972358,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.2166299656033516,
|
|
"num_tokens": 64458173.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 5.636039733886719,
|
|
"epoch": 3.2446229011063066,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003974573463867819,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.22040609121322632,
|
|
"num_tokens": 64468985.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 5.622228765487671,
|
|
"epoch": 3.2451844780142642,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039742366287723855,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.221105195581913,
|
|
"num_tokens": 64479802.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 5.570299911499023,
|
|
"epoch": 3.2457460549222215,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039738997546967834,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.21234782934188842,
|
|
"num_tokens": 64490072.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 5.583495473861694,
|
|
"epoch": 3.246307631830179,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039735628416517394,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.2233000561594963,
|
|
"num_tokens": 64501096.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 5.605816841125488,
|
|
"epoch": 3.246869208738137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039732258896479786,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.22557010650634765,
|
|
"num_tokens": 64512562.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 5.554577970504761,
|
|
"epoch": 3.2474307856460944,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003972888898696231,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.22449371665716172,
|
|
"num_tokens": 64522955.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 5.638792419433594,
|
|
"epoch": 3.2479923625540517,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039725518688072276,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.2236968457698822,
|
|
"num_tokens": 64533805.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 5.59912486076355,
|
|
"epoch": 3.2485539394620093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039722147999916976,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.21271185725927352,
|
|
"num_tokens": 64545543.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 5.620989370346069,
|
|
"epoch": 3.249115516369967,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003971877692260375,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.2184781551361084,
|
|
"num_tokens": 64557109.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 5.649204683303833,
|
|
"epoch": 3.249677093277924,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039715405456239924,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.22277338206768035,
|
|
"num_tokens": 64568880.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 5.651802587509155,
|
|
"epoch": 3.250238670185882,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003971203360093286,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.2290601760149002,
|
|
"num_tokens": 64579859.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 5.581382989883423,
|
|
"epoch": 3.2508002470938395,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039708661356789896,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.23802388459444046,
|
|
"num_tokens": 64589133.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 5.5575682640075685,
|
|
"epoch": 3.251361824001797,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039705288723918415,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.22594044655561446,
|
|
"num_tokens": 64600040.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 5.513377046585083,
|
|
"epoch": 3.2519234009097544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003970191570242582,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.23177869617938995,
|
|
"num_tokens": 64611756.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 5.6025275707244875,
|
|
"epoch": 3.252484977817712,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000396985422924195,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.21893276423215866,
|
|
"num_tokens": 64622994.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 5.621108770370483,
|
|
"epoch": 3.2530465547256697,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039695168494006857,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.22493505775928496,
|
|
"num_tokens": 64633200.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 5.600263261795044,
|
|
"epoch": 3.2536081316336274,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003969179430729531,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.21945893466472627,
|
|
"num_tokens": 64644412.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 5.547242927551269,
|
|
"epoch": 3.2541697085415846,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003968841973239231,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.22422965317964555,
|
|
"num_tokens": 64655986.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 5.518402719497681,
|
|
"epoch": 3.2547312854495423,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000396850447694053,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.22508468776941298,
|
|
"num_tokens": 64667770.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 5.713359022140503,
|
|
"epoch": 3.2552928623575,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003968166941844174,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.2115077406167984,
|
|
"num_tokens": 64679239.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 5.639494371414185,
|
|
"epoch": 3.2558544392654576,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000396782936796091,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.22732115387916565,
|
|
"num_tokens": 64690192.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 5.5794628143310545,
|
|
"epoch": 3.256416016173415,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003967491755301487,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.2243642419576645,
|
|
"num_tokens": 64700692.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 5.615986108779907,
|
|
"epoch": 3.2569775930813725,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003967154103876654,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.21847174167633057,
|
|
"num_tokens": 64711753.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 5.704402017593384,
|
|
"epoch": 3.25753916998933,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039668164136971615,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.21638649255037307,
|
|
"num_tokens": 64722145.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 5.579876708984375,
|
|
"epoch": 3.258100746897288,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003966478684773763,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.22425017207860948,
|
|
"num_tokens": 64732059.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 5.622774314880371,
|
|
"epoch": 3.258662323805245,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039661409171172117,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.2205080971121788,
|
|
"num_tokens": 64742811.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 5.516185855865478,
|
|
"epoch": 3.2592239007132027,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039658031107382615,
|
|
"loss": 4.9061,
|
|
"mean_token_accuracy": 0.229988931119442,
|
|
"num_tokens": 64753287.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 5.6982808113098145,
|
|
"epoch": 3.2597854776211603,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039654652656476695,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.21627851724624633,
|
|
"num_tokens": 64767739.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 5.637081336975098,
|
|
"epoch": 3.2603470545291175,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003965127381856191,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.21957307308912277,
|
|
"num_tokens": 64779217.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 5.6398640155792235,
|
|
"epoch": 3.260908631437075,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039647894593745865,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.22788986712694168,
|
|
"num_tokens": 64790613.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 5.5220667839050295,
|
|
"epoch": 3.261470208345033,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039644514982136136,
|
|
"loss": 4.8977,
|
|
"mean_token_accuracy": 0.22341181486845016,
|
|
"num_tokens": 64801256.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 5.560265970230103,
|
|
"epoch": 3.2620317852529905,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039641134983840336,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.2311493381857872,
|
|
"num_tokens": 64812938.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 5.650543689727783,
|
|
"epoch": 3.2625933621609478,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000396377545989661,
|
|
"loss": 4.9643,
|
|
"mean_token_accuracy": 0.22110091894865036,
|
|
"num_tokens": 64824041.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 5.559698677062988,
|
|
"epoch": 3.2631549390689054,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039634373827621047,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.23182594180107116,
|
|
"num_tokens": 64833837.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 5.488413143157959,
|
|
"epoch": 3.263716515976863,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003963099266991282,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.22819430083036424,
|
|
"num_tokens": 64843937.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 5.5773108959197994,
|
|
"epoch": 3.2642780928848207,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039627611125949086,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.2204499512910843,
|
|
"num_tokens": 64855955.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 5.739634609222412,
|
|
"epoch": 3.264839669792778,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039624229195837506,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.22181614637374877,
|
|
"num_tokens": 64867505.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 5.528939962387085,
|
|
"epoch": 3.2654012467007356,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039620846879685767,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.23188625872135163,
|
|
"num_tokens": 64878746.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 5.603091669082642,
|
|
"epoch": 3.2659628236086933,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039617464177601564,
|
|
"loss": 5.0438,
|
|
"mean_token_accuracy": 0.2262365147471428,
|
|
"num_tokens": 64889520.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 5.653062152862549,
|
|
"epoch": 3.266524400516651,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039614081089692606,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.22266669422388077,
|
|
"num_tokens": 64900380.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 5.632506656646728,
|
|
"epoch": 3.267085977424608,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039610697616066604,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.22433314621448516,
|
|
"num_tokens": 64910480.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 5.5448933124542235,
|
|
"epoch": 3.267647554332566,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039607313756831296,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.22830421030521392,
|
|
"num_tokens": 64920911.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 5.554177379608154,
|
|
"epoch": 3.2682091312405235,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039603929512094417,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.22558909207582473,
|
|
"num_tokens": 64930687.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 5.481979274749756,
|
|
"epoch": 3.268770708148481,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003960054488196373,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.22558794915676117,
|
|
"num_tokens": 64942143.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 5.567085313796997,
|
|
"epoch": 3.2693322850564384,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039597159866546996,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.22452132552862167,
|
|
"num_tokens": 64952440.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 5.642243480682373,
|
|
"epoch": 3.269893861964396,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003959377446595201,
|
|
"loss": 4.942,
|
|
"mean_token_accuracy": 0.22662267386913298,
|
|
"num_tokens": 64962752.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 5.555770301818848,
|
|
"epoch": 3.2704554388723537,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039590388680286543,
|
|
"loss": 4.9345,
|
|
"mean_token_accuracy": 0.22830827981233598,
|
|
"num_tokens": 64975413.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 5.58867130279541,
|
|
"epoch": 3.271017015780311,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003958700250965842,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.22434492111206056,
|
|
"num_tokens": 64987922.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 5.5406177043914795,
|
|
"epoch": 3.2715785926882686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003958361595417544,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.21842263340950013,
|
|
"num_tokens": 64999448.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 5.634398508071899,
|
|
"epoch": 3.2721401695962262,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003958022901394545,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.21465549021959304,
|
|
"num_tokens": 65010771.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 5.691718530654907,
|
|
"epoch": 3.272701746504184,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003957684168907628,
|
|
"loss": 5.025,
|
|
"mean_token_accuracy": 0.22132568955421447,
|
|
"num_tokens": 65021368.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 5.592639780044555,
|
|
"epoch": 3.273263323412141,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039573453979675793,
|
|
"loss": 4.8808,
|
|
"mean_token_accuracy": 0.2429708644747734,
|
|
"num_tokens": 65032622.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 5.488206291198731,
|
|
"epoch": 3.2738249003200988,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039570065885851844,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.2306182563304901,
|
|
"num_tokens": 65043655.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 5.578858709335327,
|
|
"epoch": 3.2743864772280564,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003956667740771231,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.21670502573251724,
|
|
"num_tokens": 65055846.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 5.682757997512818,
|
|
"epoch": 3.274948054136014,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003956328854536509,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.21198037415742874,
|
|
"num_tokens": 65067617.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 5.760885286331177,
|
|
"epoch": 3.2755096310439713,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039559899298918094,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.23553928583860398,
|
|
"num_tokens": 65080111.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 5.581401920318603,
|
|
"epoch": 3.276071207951929,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003955650966847922,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.2334904596209526,
|
|
"num_tokens": 65092284.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 5.590202903747558,
|
|
"epoch": 3.2766327848598866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000395531196541564,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.2268014892935753,
|
|
"num_tokens": 65104133.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 5.527865600585938,
|
|
"epoch": 3.2771943617678443,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039549729256057583,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.22273971438407897,
|
|
"num_tokens": 65116065.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 5.565624666213989,
|
|
"epoch": 3.2777559386758015,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000395463384742907,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.2278800666332245,
|
|
"num_tokens": 65127235.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 5.667405319213867,
|
|
"epoch": 3.278317515583759,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039542947308963733,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.21417480558156968,
|
|
"num_tokens": 65138186.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 5.586130666732788,
|
|
"epoch": 3.278879092491717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003953955576018466,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.22253081053495408,
|
|
"num_tokens": 65149222.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 5.5688783645629885,
|
|
"epoch": 3.2794406693996745,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003953616382806145,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.22795179933309556,
|
|
"num_tokens": 65160404.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 5.626569557189941,
|
|
"epoch": 3.2800022463076317,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039532771512702124,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.21938242763280869,
|
|
"num_tokens": 65171395.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 5.604249906539917,
|
|
"epoch": 3.2805638232155894,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003952937881421468,
|
|
"loss": 5.0055,
|
|
"mean_token_accuracy": 0.21867889165878296,
|
|
"num_tokens": 65183752.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 5.552662992477417,
|
|
"epoch": 3.281125400123547,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003952598573270716,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.22674647718667984,
|
|
"num_tokens": 65193807.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 5.598779010772705,
|
|
"epoch": 3.2816869770315042,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003952259226828759,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.22041567116975785,
|
|
"num_tokens": 65203482.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 5.65418496131897,
|
|
"epoch": 3.282248553939462,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039519198421064005,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.21273995637893678,
|
|
"num_tokens": 65214965.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 5.613926553726197,
|
|
"epoch": 3.2828101308474196,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039515804191144496,
|
|
"loss": 4.8882,
|
|
"mean_token_accuracy": 0.22405080646276473,
|
|
"num_tokens": 65227791.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 5.70930814743042,
|
|
"epoch": 3.2833717077553772,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039512409578637114,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.22126224935054778,
|
|
"num_tokens": 65238937.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 5.619851541519165,
|
|
"epoch": 3.2839332846633345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039509014583649947,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.21573661565780639,
|
|
"num_tokens": 65250912.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 5.5950452327728275,
|
|
"epoch": 3.284494861571292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039505619206291106,
|
|
"loss": 4.9795,
|
|
"mean_token_accuracy": 0.22129611372947694,
|
|
"num_tokens": 65262094.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 5.549280786514283,
|
|
"epoch": 3.2850564384792498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039502223446668687,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.23611785471439362,
|
|
"num_tokens": 65271860.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 5.636439275741577,
|
|
"epoch": 3.2856180153872074,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003949882730489082,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.21593456119298934,
|
|
"num_tokens": 65282341.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 5.613181447982788,
|
|
"epoch": 3.2861795922951647,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039495430781065645,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.22451214641332626,
|
|
"num_tokens": 65293570.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 5.531803607940674,
|
|
"epoch": 3.2867411692031223,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000394920338753013,
|
|
"loss": 4.9366,
|
|
"mean_token_accuracy": 0.22777618020772933,
|
|
"num_tokens": 65305226.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 5.559498310089111,
|
|
"epoch": 3.28730274611108,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003948863658770594,
|
|
"loss": 4.8418,
|
|
"mean_token_accuracy": 0.22553104311227798,
|
|
"num_tokens": 65316309.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 5.600387382507324,
|
|
"epoch": 3.2878643230190376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003948523891838774,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.23289123624563218,
|
|
"num_tokens": 65327491.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 5.53121280670166,
|
|
"epoch": 3.288425899926995,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039481840867454886,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.23056156039237977,
|
|
"num_tokens": 65337908.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 5.470587110519409,
|
|
"epoch": 3.2889874768349525,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003947844243501558,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.23341647982597352,
|
|
"num_tokens": 65348209.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 5.560776329040527,
|
|
"epoch": 3.28954905374291,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039475043621178005,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.22360182851552962,
|
|
"num_tokens": 65358648.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 5.563247156143189,
|
|
"epoch": 3.290110630650868,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003947164442605041,
|
|
"loss": 4.948,
|
|
"mean_token_accuracy": 0.22615625560283661,
|
|
"num_tokens": 65369132.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 5.61669888496399,
|
|
"epoch": 3.290672207558825,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003946824484974101,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.22330738753080367,
|
|
"num_tokens": 65380334.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 5.75339412689209,
|
|
"epoch": 3.2912337844667827,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003946484489235805,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.211371511220932,
|
|
"num_tokens": 65394680.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 5.67488923072815,
|
|
"epoch": 3.2917953613747404,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039461444554009787,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.22769994139671326,
|
|
"num_tokens": 65406029.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 5.568291521072387,
|
|
"epoch": 3.2923569382826976,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000394580438348045,
|
|
"loss": 4.9507,
|
|
"mean_token_accuracy": 0.2286419689655304,
|
|
"num_tokens": 65416626.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 5.626316356658935,
|
|
"epoch": 3.2929185151906553,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039454642734850447,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.23000646084547044,
|
|
"num_tokens": 65427579.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 5.6130129337310795,
|
|
"epoch": 3.293480092098613,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003945124125425594,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.21711541712284088,
|
|
"num_tokens": 65439893.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 5.738810110092163,
|
|
"epoch": 3.2940416690065706,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003944783939312928,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.2187036707997322,
|
|
"num_tokens": 65451861.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 5.550241851806641,
|
|
"epoch": 3.294603245914528,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003944443715157877,
|
|
"loss": 4.9217,
|
|
"mean_token_accuracy": 0.2223477080464363,
|
|
"num_tokens": 65463764.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 5.503076362609863,
|
|
"epoch": 3.2951648228224855,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003944103452971275,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.21922703683376313,
|
|
"num_tokens": 65474367.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 5.596628427505493,
|
|
"epoch": 3.295726399730443,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039437631527639553,
|
|
"loss": 4.88,
|
|
"mean_token_accuracy": 0.2309821754693985,
|
|
"num_tokens": 65485347.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 5.635243463516235,
|
|
"epoch": 3.296287976638401,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039434228145467554,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.23041861206293107,
|
|
"num_tokens": 65495858.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 5.516305351257325,
|
|
"epoch": 3.296849553546358,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000394308243833051,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.23208544105291368,
|
|
"num_tokens": 65505649.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 5.595996475219726,
|
|
"epoch": 3.2974111304543157,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039427420241260557,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.23151884973049164,
|
|
"num_tokens": 65516437.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 5.509012460708618,
|
|
"epoch": 3.2979727073622733,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039424015719442335,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.23005390763282776,
|
|
"num_tokens": 65528854.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 5.688011312484742,
|
|
"epoch": 3.298534284270231,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039420610817958836,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.22091888189315795,
|
|
"num_tokens": 65539459.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 5.672497892379761,
|
|
"epoch": 3.299095861178188,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003941720553691846,
|
|
"loss": 5.0028,
|
|
"mean_token_accuracy": 0.21610130965709687,
|
|
"num_tokens": 65550818.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 5.652425622940063,
|
|
"epoch": 3.299657438086146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003941379987642963,
|
|
"loss": 4.9233,
|
|
"mean_token_accuracy": 0.22144919633865356,
|
|
"num_tokens": 65562572.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 5.582521677017212,
|
|
"epoch": 3.3002190149941035,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000394103938366008,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.2260396435856819,
|
|
"num_tokens": 65573764.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 5.656918716430664,
|
|
"epoch": 3.300780591902061,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003940698741754041,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.22675496488809585,
|
|
"num_tokens": 65585628.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 5.617207145690918,
|
|
"epoch": 3.3013421688100184,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003940358061935692,
|
|
"loss": 4.9523,
|
|
"mean_token_accuracy": 0.22517151683568953,
|
|
"num_tokens": 65596142.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 5.702070474624634,
|
|
"epoch": 3.301903745717976,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003940017344215881,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.21968696266412735,
|
|
"num_tokens": 65607824.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 5.598457336425781,
|
|
"epoch": 3.3024653226259337,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039396765886054555,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.22423498034477235,
|
|
"num_tokens": 65617862.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 5.602728462219238,
|
|
"epoch": 3.303026899533891,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039393357951152667,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.22281179279088975,
|
|
"num_tokens": 65629224.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 5.54803581237793,
|
|
"epoch": 3.3035884764418486,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039389949637561646,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.22487375289201736,
|
|
"num_tokens": 65640419.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 5.608315753936767,
|
|
"epoch": 3.3041500533498063,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039386540945390017,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.2166498512029648,
|
|
"num_tokens": 65651305.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 5.638318157196045,
|
|
"epoch": 3.304711630257764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003938313187474631,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.21081383675336837,
|
|
"num_tokens": 65662702.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 5.599985408782959,
|
|
"epoch": 3.3052732071657216,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003937972242573908,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.223843914270401,
|
|
"num_tokens": 65673981.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 5.637802600860596,
|
|
"epoch": 3.305834784073679,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003937631259847688,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.2313285142183304,
|
|
"num_tokens": 65684633.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 5.623660278320313,
|
|
"epoch": 3.3063963609816365,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003937290239306828,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.214102204144001,
|
|
"num_tokens": 65696890.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 5.564179801940918,
|
|
"epoch": 3.306957937889594,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039369491809621867,
|
|
"loss": 4.9244,
|
|
"mean_token_accuracy": 0.2238264873623848,
|
|
"num_tokens": 65708620.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 5.635856437683105,
|
|
"epoch": 3.3075195147975514,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003936608084824623,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.22663332223892213,
|
|
"num_tokens": 65720182.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 5.644085836410523,
|
|
"epoch": 3.308081091705509,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039362669509049975,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.21696722656488418,
|
|
"num_tokens": 65731376.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 5.668196153640747,
|
|
"epoch": 3.3086426686134667,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039359257792141717,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.22621786892414092,
|
|
"num_tokens": 65743303.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 5.7632981300354,
|
|
"epoch": 3.3092042455214243,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000393558456976301,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.21259842813014984,
|
|
"num_tokens": 65755486.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 5.563900327682495,
|
|
"epoch": 3.3097658224293816,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003935243322562375,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.22141591012477874,
|
|
"num_tokens": 65766855.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 5.588717460632324,
|
|
"epoch": 3.310327399337339,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003934902037623133,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.22379037439823152,
|
|
"num_tokens": 65778077.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 5.563067865371704,
|
|
"epoch": 3.310888976245297,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039345607149561513,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.221240234375,
|
|
"num_tokens": 65791051.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 5.6837427616119385,
|
|
"epoch": 3.3114505531532545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039342193545722966,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.22030096352100373,
|
|
"num_tokens": 65802769.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 5.6370233535766605,
|
|
"epoch": 3.3120121300612118,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003933877956482438,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.22808735817670822,
|
|
"num_tokens": 65813602.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 5.633676242828369,
|
|
"epoch": 3.3125737069691694,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039335365206974465,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.22062040865421295,
|
|
"num_tokens": 65826675.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 5.591550683975219,
|
|
"epoch": 3.313135283877127,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003933195047228193,
|
|
"loss": 4.9201,
|
|
"mean_token_accuracy": 0.23327559977769852,
|
|
"num_tokens": 65837643.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 5.667750978469849,
|
|
"epoch": 3.3136968607850843,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039328535360855503,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.22914017587900162,
|
|
"num_tokens": 65850184.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 5.608892726898193,
|
|
"epoch": 3.314258437693042,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039325119872803924,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.2222956731915474,
|
|
"num_tokens": 65861178.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 5.59312949180603,
|
|
"epoch": 3.3148200146009996,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039321704008235943,
|
|
"loss": 4.8794,
|
|
"mean_token_accuracy": 0.23230232149362565,
|
|
"num_tokens": 65872458.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 5.589869642257691,
|
|
"epoch": 3.3153815915089573,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039318287767260316,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.22675976455211638,
|
|
"num_tokens": 65883152.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 5.555652379989624,
|
|
"epoch": 3.315943168416915,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039314871149985834,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.22781698405742645,
|
|
"num_tokens": 65894220.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 5.6145796298980715,
|
|
"epoch": 3.316504745324872,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003931145415652126,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.21698874682188035,
|
|
"num_tokens": 65904159.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 5.683998060226441,
|
|
"epoch": 3.31706632223283,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039308036786975416,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.21672240793704986,
|
|
"num_tokens": 65915599.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 5.611990213394165,
|
|
"epoch": 3.3176278991407875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003930461904145709,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.2257765933871269,
|
|
"num_tokens": 65926518.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 5.581943082809448,
|
|
"epoch": 3.3181894760487447,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003930120092007512,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.22265743762254714,
|
|
"num_tokens": 65938901.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 5.622525787353515,
|
|
"epoch": 3.3187510529567024,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003929778242293834,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.2190771758556366,
|
|
"num_tokens": 65949798.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 5.634861946105957,
|
|
"epoch": 3.31931262986466,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003929436355015558,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.2354223132133484,
|
|
"num_tokens": 65961222.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 5.66882553100586,
|
|
"epoch": 3.3198742067726177,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039290944301835723,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.2124689057469368,
|
|
"num_tokens": 65972373.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 5.557436561584472,
|
|
"epoch": 3.320435783680575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039287524678087617,
|
|
"loss": 4.9244,
|
|
"mean_token_accuracy": 0.22783544063568115,
|
|
"num_tokens": 65983716.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 5.697549629211426,
|
|
"epoch": 3.3209973605885326,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039284104679020154,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.22414888590574264,
|
|
"num_tokens": 65994827.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 5.613718795776367,
|
|
"epoch": 3.3215589374964902,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003928068430474224,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.2337096557021141,
|
|
"num_tokens": 66006249.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 5.625052118301392,
|
|
"epoch": 3.322120514404448,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003927726355536275,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.22366324216127395,
|
|
"num_tokens": 66017175.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 5.575991487503051,
|
|
"epoch": 3.322682091312405,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039273842430990634,
|
|
"loss": 4.9207,
|
|
"mean_token_accuracy": 0.2254957839846611,
|
|
"num_tokens": 66028518.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 5.635163593292236,
|
|
"epoch": 3.3232436682203628,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003927042093173481,
|
|
"loss": 4.9594,
|
|
"mean_token_accuracy": 0.21791379004716874,
|
|
"num_tokens": 66038927.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 5.641508340835571,
|
|
"epoch": 3.3238052451283204,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003926699905770421,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.2296861007809639,
|
|
"num_tokens": 66050649.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 5.632432365417481,
|
|
"epoch": 3.3243668220362776,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000392635768090078,
|
|
"loss": 4.9742,
|
|
"mean_token_accuracy": 0.22827840745449066,
|
|
"num_tokens": 66061585.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 5.625937128067017,
|
|
"epoch": 3.3249283989442353,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039260154185754545,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.2298382356762886,
|
|
"num_tokens": 66071312.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 5.623424053192139,
|
|
"epoch": 3.325489975852193,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003925673118805341,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.22680336982011795,
|
|
"num_tokens": 66082643.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 5.5718029022216795,
|
|
"epoch": 3.3260515527601506,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000392533078160134,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.22988757342100144,
|
|
"num_tokens": 66094094.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 5.585574150085449,
|
|
"epoch": 3.3266131296681083,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039249884069743514,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.22520186454057695,
|
|
"num_tokens": 66105365.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 5.644037199020386,
|
|
"epoch": 3.3271747065760655,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003924645994935276,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.22082462310791015,
|
|
"num_tokens": 66115440.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 5.610313892364502,
|
|
"epoch": 3.327736283484023,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003924303545495017,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.21679486483335494,
|
|
"num_tokens": 66127213.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 5.603411483764648,
|
|
"epoch": 3.328297860391981,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039239610586644765,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.2253841057419777,
|
|
"num_tokens": 66138016.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 5.524543046951294,
|
|
"epoch": 3.328859437299938,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003923618534454561,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.2321717619895935,
|
|
"num_tokens": 66149981.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 5.578205347061157,
|
|
"epoch": 3.3294210142078957,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003923275972876176,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.2321137398481369,
|
|
"num_tokens": 66161609.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 5.538463163375854,
|
|
"epoch": 3.3299825911158534,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039229333739402303,
|
|
"loss": 4.8901,
|
|
"mean_token_accuracy": 0.22226026356220246,
|
|
"num_tokens": 66171665.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 5.5389093399047855,
|
|
"epoch": 3.330544168023811,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000392259073765763,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.2238623932003975,
|
|
"num_tokens": 66181773.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 5.6573412895202635,
|
|
"epoch": 3.3311057449317683,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039222480640392854,
|
|
"loss": 4.9735,
|
|
"mean_token_accuracy": 0.2290860593318939,
|
|
"num_tokens": 66193578.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 5.662036466598511,
|
|
"epoch": 3.331667321839726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039219053530961087,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.21854458302259444,
|
|
"num_tokens": 66205185.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 5.526615810394287,
|
|
"epoch": 3.3322288987476836,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039215626048390105,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.22718935310840607,
|
|
"num_tokens": 66217143.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 5.595347261428833,
|
|
"epoch": 3.3327904756556412,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003921219819278905,
|
|
"loss": 4.9711,
|
|
"mean_token_accuracy": 0.23123189955949783,
|
|
"num_tokens": 66229022.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 5.612782287597656,
|
|
"epoch": 3.3333520525635985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003920876996426706,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.21619020104408265,
|
|
"num_tokens": 66240028.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 5.619263410568237,
|
|
"epoch": 3.333913629471556,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039205341362933294,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.22793985158205032,
|
|
"num_tokens": 66251656.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 5.579437923431397,
|
|
"epoch": 3.334475206379514,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003920191238889691,
|
|
"loss": 4.937,
|
|
"mean_token_accuracy": 0.2300856366753578,
|
|
"num_tokens": 66262644.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 5.5091390132904055,
|
|
"epoch": 3.335036783287471,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003919848304226711,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.222806116938591,
|
|
"num_tokens": 66273374.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 5.569142436981201,
|
|
"epoch": 3.3355983601954287,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003919505332315307,
|
|
"loss": 4.937,
|
|
"mean_token_accuracy": 0.22788834124803542,
|
|
"num_tokens": 66284490.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 5.6923534870147705,
|
|
"epoch": 3.3361599371033863,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039191623231663985,
|
|
"loss": 4.9454,
|
|
"mean_token_accuracy": 0.22931817471981047,
|
|
"num_tokens": 66295555.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 5.61996374130249,
|
|
"epoch": 3.336721514011344,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000391881927679091,
|
|
"loss": 4.9343,
|
|
"mean_token_accuracy": 0.224620820581913,
|
|
"num_tokens": 66307234.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 5.696124505996704,
|
|
"epoch": 3.3372830909193016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039184761931997607,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.21845099627971648,
|
|
"num_tokens": 66319239.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 5.673655605316162,
|
|
"epoch": 3.337844667827259,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003918133072403878,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.22607903480529784,
|
|
"num_tokens": 66332260.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 5.649950551986694,
|
|
"epoch": 3.3384062447352165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039177899144141835,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.21831774413585664,
|
|
"num_tokens": 66343817.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 5.668838882446289,
|
|
"epoch": 3.338967821643174,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003917446719241606,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.21548139303922653,
|
|
"num_tokens": 66355724.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 5.5913787364959715,
|
|
"epoch": 3.3395293985511314,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039171034868970724,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.22590429484844207,
|
|
"num_tokens": 66365994.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 5.649165678024292,
|
|
"epoch": 3.340090975459089,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039167602173915104,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.21146737933158874,
|
|
"num_tokens": 66377929.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 5.569516944885254,
|
|
"epoch": 3.3406525523670467,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003916416910735851,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.22606093138456346,
|
|
"num_tokens": 66389292.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 5.628697156906128,
|
|
"epoch": 3.3412141292750044,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039160735669410246,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.22354757338762282,
|
|
"num_tokens": 66399266.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 5.573943042755127,
|
|
"epoch": 3.3417757061829616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003915730186017964,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.22413557767868042,
|
|
"num_tokens": 66410718.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 5.565828847885132,
|
|
"epoch": 3.3423372830909193,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039153867679776023,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.22196794003248216,
|
|
"num_tokens": 66420982.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 5.653739356994629,
|
|
"epoch": 3.342898859998877,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003915043312830873,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.22797484397888185,
|
|
"num_tokens": 66431378.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 5.66716160774231,
|
|
"epoch": 3.3434604369068346,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003914699820588714,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.22695696502923965,
|
|
"num_tokens": 66442033.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 5.546166896820068,
|
|
"epoch": 3.344022013814792,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039143562912620603,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.22590834349393846,
|
|
"num_tokens": 66453486.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 5.6332286357879635,
|
|
"epoch": 3.3445835907227495,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000391401272486185,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.2161085531115532,
|
|
"num_tokens": 66464931.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 5.7921449661254885,
|
|
"epoch": 3.345145167630707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003913669121399024,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.21639847457408906,
|
|
"num_tokens": 66477187.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 5.6464385986328125,
|
|
"epoch": 3.3457067445386643,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039133254808845216,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.2257029742002487,
|
|
"num_tokens": 66488777.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 5.615569829940796,
|
|
"epoch": 3.346268321446622,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039129818033292843,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.23031931817531587,
|
|
"num_tokens": 66499576.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 5.5009729862213135,
|
|
"epoch": 3.3468298983545797,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003912638088744256,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.24341761469841003,
|
|
"num_tokens": 66510824.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 5.62365312576294,
|
|
"epoch": 3.3473914752625373,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000391229433714038,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.22164506316184998,
|
|
"num_tokens": 66523151.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 5.557165193557739,
|
|
"epoch": 3.347953052170495,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003911950548528601,
|
|
"loss": 4.8996,
|
|
"mean_token_accuracy": 0.22774474024772645,
|
|
"num_tokens": 66533921.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 5.557341480255127,
|
|
"epoch": 3.348514629078452,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003911606722919866,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.22940873950719834,
|
|
"num_tokens": 66545867.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 5.596244955062867,
|
|
"epoch": 3.34907620598641,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003911262860325123,
|
|
"loss": 4.9348,
|
|
"mean_token_accuracy": 0.22831295132637025,
|
|
"num_tokens": 66557522.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 5.61635570526123,
|
|
"epoch": 3.3496377828943675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003910918960755319,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.2286524713039398,
|
|
"num_tokens": 66568792.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 5.649629211425781,
|
|
"epoch": 3.3501993598023248,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003910575024221406,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.22513770014047624,
|
|
"num_tokens": 66580231.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 5.5305705070495605,
|
|
"epoch": 3.3507609367102824,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039102310507343335,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.23049129098653792,
|
|
"num_tokens": 66591171.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 5.616701745986939,
|
|
"epoch": 3.35132251361824,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003909887040305055,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.21653061211109162,
|
|
"num_tokens": 66602676.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 5.606766128540039,
|
|
"epoch": 3.3518840905261977,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003909542992944523,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.2250973880290985,
|
|
"num_tokens": 66613526.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 5.549674606323242,
|
|
"epoch": 3.352445667434155,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003909198908663692,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.22619426846504212,
|
|
"num_tokens": 66624279.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 5.619165515899658,
|
|
"epoch": 3.3530072443421126,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039088547874735187,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.2359496608376503,
|
|
"num_tokens": 66636908.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 5.706976747512817,
|
|
"epoch": 3.3535688212500703,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039085106293849594,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.21220379173755646,
|
|
"num_tokens": 66648545.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 5.60441222190857,
|
|
"epoch": 3.354130398158028,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039081664344089724,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.22105880379676818,
|
|
"num_tokens": 66659245.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 5.544858455657959,
|
|
"epoch": 3.354691975065985,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003907822202556516,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.23168789893388747,
|
|
"num_tokens": 66670866.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 5.667668294906616,
|
|
"epoch": 3.355253551973943,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003907477933838553,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.2202111080288887,
|
|
"num_tokens": 66681970.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 5.698285961151123,
|
|
"epoch": 3.3558151288819005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039071336282660437,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.22758581340312958,
|
|
"num_tokens": 66693252.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 5.633811569213867,
|
|
"epoch": 3.3563767057898577,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039067892858499496,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.22320382297039032,
|
|
"num_tokens": 66703821.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 5.522962856292724,
|
|
"epoch": 3.3569382826978154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003906444906601237,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.2258063495159149,
|
|
"num_tokens": 66715945.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 5.629836702346802,
|
|
"epoch": 3.357499859605773,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000390610049053087,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.22219389528036118,
|
|
"num_tokens": 66727551.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 5.632623958587646,
|
|
"epoch": 3.3580614365137307,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039057560376498147,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.22849724739789962,
|
|
"num_tokens": 66738257.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 5.717036199569702,
|
|
"epoch": 3.3586230134216883,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003905411547969038,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.20839426964521407,
|
|
"num_tokens": 66750305.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 5.663428783416748,
|
|
"epoch": 3.3591845903296456,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003905067021499511,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.2165266305208206,
|
|
"num_tokens": 66761659.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 5.640324497222901,
|
|
"epoch": 3.359746167237603,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039047224582522015,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.23228950649499894,
|
|
"num_tokens": 66771981.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 5.634357929229736,
|
|
"epoch": 3.360307744145561,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003904377858238081,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.21704142689704894,
|
|
"num_tokens": 66783915.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 5.5644148826599125,
|
|
"epoch": 3.360869321053518,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003904033221468122,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.22494590133428574,
|
|
"num_tokens": 66795691.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 5.61035795211792,
|
|
"epoch": 3.3614308979614758,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003903688547953297,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.22018447667360305,
|
|
"num_tokens": 66805792.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 5.593730306625366,
|
|
"epoch": 3.3619924748694334,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003903343837704582,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.2312409460544586,
|
|
"num_tokens": 66817657.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 5.577921056747437,
|
|
"epoch": 3.362554051777391,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003902999090732951,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.23244166672229766,
|
|
"num_tokens": 66828593.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 5.542215490341187,
|
|
"epoch": 3.3631156286853483,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039026543070493823,
|
|
"loss": 4.9618,
|
|
"mean_token_accuracy": 0.22664941251277923,
|
|
"num_tokens": 66839405.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 5.522049903869629,
|
|
"epoch": 3.363677205593306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003902309486664854,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.22373108118772506,
|
|
"num_tokens": 66849938.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 5.616359663009644,
|
|
"epoch": 3.3642387825012636,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003901964629590344,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.2240708976984024,
|
|
"num_tokens": 66861105.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 5.585463333129883,
|
|
"epoch": 3.3648003594092213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003901619735836833,
|
|
"loss": 4.9403,
|
|
"mean_token_accuracy": 0.22575917840003967,
|
|
"num_tokens": 66873065.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 5.720394563674927,
|
|
"epoch": 3.3653619363171785,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039012748054153044,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.21627963334321976,
|
|
"num_tokens": 66885639.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 5.649977540969848,
|
|
"epoch": 3.365923513225136,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003900929838336738,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.2216775581240654,
|
|
"num_tokens": 66896576.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 5.591810607910157,
|
|
"epoch": 3.366485090133094,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003900584834612119,
|
|
"loss": 4.9178,
|
|
"mean_token_accuracy": 0.22338406145572662,
|
|
"num_tokens": 66907595.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 5.644698143005371,
|
|
"epoch": 3.367046667041051,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003900239794252434,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.2217564955353737,
|
|
"num_tokens": 66918231.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 5.689141082763672,
|
|
"epoch": 3.3676082439490087,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003899894717268667,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.21183950453996658,
|
|
"num_tokens": 66930929.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 5.644493198394775,
|
|
"epoch": 3.3681698208569664,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003899549603671807,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.22521693110466004,
|
|
"num_tokens": 66941714.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 5.6211583614349365,
|
|
"epoch": 3.368731397764924,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038992044534728404,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.21968078911304473,
|
|
"num_tokens": 66951732.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 5.682870817184448,
|
|
"epoch": 3.3692929746728817,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038988592666827594,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.22418947517871857,
|
|
"num_tokens": 66962941.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 3.3692929746728817,
|
|
"eval_entropy": 5.399628516475903,
|
|
"eval_loss": 5.084558486938477,
|
|
"eval_mean_token_accuracy": 0.22630211478783846,
|
|
"eval_num_tokens": 66962941.0,
|
|
"eval_runtime": 18.4362,
|
|
"eval_samples_per_second": 1682.181,
|
|
"eval_steps_per_second": 210.293,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"entropy": 5.695588397979736,
|
|
"epoch": 3.369854551580839,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003898514043312553,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.21628064513206482,
|
|
"num_tokens": 66975096.0,
|
|
"step": 30005
|
|
},
|
|
{
|
|
"entropy": 5.6607238292694095,
|
|
"epoch": 3.3704161284887966,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00038981687833732146,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.23126367330551148,
|
|
"num_tokens": 66987621.0,
|
|
"step": 30010
|
|
},
|
|
{
|
|
"entropy": 5.655307054519653,
|
|
"epoch": 3.3709777053967542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003897823486875737,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.22212796956300734,
|
|
"num_tokens": 66998801.0,
|
|
"step": 30015
|
|
},
|
|
{
|
|
"entropy": 5.634281301498413,
|
|
"epoch": 3.3715392823047114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003897478153831114,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.21678673177957536,
|
|
"num_tokens": 67010698.0,
|
|
"step": 30020
|
|
},
|
|
{
|
|
"entropy": 5.5986956596374515,
|
|
"epoch": 3.372100859212669,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038971327842503414,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.2310822382569313,
|
|
"num_tokens": 67022487.0,
|
|
"step": 30025
|
|
},
|
|
{
|
|
"entropy": 5.593844795227051,
|
|
"epoch": 3.3726624361206268,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038967873781444167,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.22471238672733307,
|
|
"num_tokens": 67032517.0,
|
|
"step": 30030
|
|
},
|
|
{
|
|
"entropy": 5.579101276397705,
|
|
"epoch": 3.3732240130285844,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038964419355243365,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.22966323494911195,
|
|
"num_tokens": 67042466.0,
|
|
"step": 30035
|
|
},
|
|
{
|
|
"entropy": 5.636154413223267,
|
|
"epoch": 3.3737855899365417,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003896096456401101,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.22345336228609086,
|
|
"num_tokens": 67053090.0,
|
|
"step": 30040
|
|
},
|
|
{
|
|
"entropy": 5.635897779464722,
|
|
"epoch": 3.3743471668444993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038957509407857097,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.22621527463197708,
|
|
"num_tokens": 67064332.0,
|
|
"step": 30045
|
|
},
|
|
{
|
|
"entropy": 5.615554618835449,
|
|
"epoch": 3.374908743752457,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038954053886891635,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.2242666468024254,
|
|
"num_tokens": 67074788.0,
|
|
"step": 30050
|
|
},
|
|
{
|
|
"entropy": 5.574945735931396,
|
|
"epoch": 3.3754703206604146,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003895059800122466,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.2237071454524994,
|
|
"num_tokens": 67086510.0,
|
|
"step": 30055
|
|
},
|
|
{
|
|
"entropy": 5.585254812240601,
|
|
"epoch": 3.376031897568372,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000389471417509662,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.2217086970806122,
|
|
"num_tokens": 67096561.0,
|
|
"step": 30060
|
|
},
|
|
{
|
|
"entropy": 5.591224002838135,
|
|
"epoch": 3.3765934744763295,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000389436851362263,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.22595889419317244,
|
|
"num_tokens": 67107897.0,
|
|
"step": 30065
|
|
},
|
|
{
|
|
"entropy": 5.6158651351928714,
|
|
"epoch": 3.377155051384287,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038940228157115036,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.21025949865579605,
|
|
"num_tokens": 67119686.0,
|
|
"step": 30070
|
|
},
|
|
{
|
|
"entropy": 5.666406774520874,
|
|
"epoch": 3.3777166282922444,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038936770813742473,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.22296384871006011,
|
|
"num_tokens": 67131041.0,
|
|
"step": 30075
|
|
},
|
|
{
|
|
"entropy": 5.698159313201904,
|
|
"epoch": 3.378278205200202,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038933313106218694,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.22343514561653138,
|
|
"num_tokens": 67143065.0,
|
|
"step": 30080
|
|
},
|
|
{
|
|
"entropy": 5.6483542919158936,
|
|
"epoch": 3.3788397821081597,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038929855034653776,
|
|
"loss": 4.9001,
|
|
"mean_token_accuracy": 0.2271954044699669,
|
|
"num_tokens": 67154173.0,
|
|
"step": 30085
|
|
},
|
|
{
|
|
"entropy": 5.594772386550903,
|
|
"epoch": 3.3794013590161174,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038926396599157855,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.22065323144197463,
|
|
"num_tokens": 67165909.0,
|
|
"step": 30090
|
|
},
|
|
{
|
|
"entropy": 5.585291481018066,
|
|
"epoch": 3.379962935924075,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003892293779984103,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.2304204821586609,
|
|
"num_tokens": 67177474.0,
|
|
"step": 30095
|
|
},
|
|
{
|
|
"entropy": 5.698488569259643,
|
|
"epoch": 3.3805245128320323,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003891947863681344,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.21958156675100327,
|
|
"num_tokens": 67187590.0,
|
|
"step": 30100
|
|
},
|
|
{
|
|
"entropy": 5.561813831329346,
|
|
"epoch": 3.38108608973999,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003891601911018521,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.2244551032781601,
|
|
"num_tokens": 67198579.0,
|
|
"step": 30105
|
|
},
|
|
{
|
|
"entropy": 5.584885311126709,
|
|
"epoch": 3.3816476666479476,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003891255922006652,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.22932556569576262,
|
|
"num_tokens": 67208503.0,
|
|
"step": 30110
|
|
},
|
|
{
|
|
"entropy": 5.577893829345703,
|
|
"epoch": 3.382209243555905,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000389090989665675,
|
|
"loss": 4.9099,
|
|
"mean_token_accuracy": 0.22648553550243378,
|
|
"num_tokens": 67219363.0,
|
|
"step": 30115
|
|
},
|
|
{
|
|
"entropy": 5.517968702316284,
|
|
"epoch": 3.3827708204638625,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003890563834979835,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.21743973195552826,
|
|
"num_tokens": 67231030.0,
|
|
"step": 30120
|
|
},
|
|
{
|
|
"entropy": 5.665895748138428,
|
|
"epoch": 3.38333239737182,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003890217736986926,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.22376058995723724,
|
|
"num_tokens": 67242962.0,
|
|
"step": 30125
|
|
},
|
|
{
|
|
"entropy": 5.684974241256714,
|
|
"epoch": 3.383893974279778,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038898716026890414,
|
|
"loss": 4.986,
|
|
"mean_token_accuracy": 0.21845709830522536,
|
|
"num_tokens": 67253871.0,
|
|
"step": 30130
|
|
},
|
|
{
|
|
"entropy": 5.621030950546265,
|
|
"epoch": 3.384455551187735,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003889525432097203,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.21812014132738114,
|
|
"num_tokens": 67265875.0,
|
|
"step": 30135
|
|
},
|
|
{
|
|
"entropy": 5.573254919052124,
|
|
"epoch": 3.3850171280956927,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003889179225222432,
|
|
"loss": 4.9399,
|
|
"mean_token_accuracy": 0.22739183902740479,
|
|
"num_tokens": 67274920.0,
|
|
"step": 30140
|
|
},
|
|
{
|
|
"entropy": 5.55876898765564,
|
|
"epoch": 3.3855787050036503,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038888329820757536,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.22654686719179154,
|
|
"num_tokens": 67286440.0,
|
|
"step": 30145
|
|
},
|
|
{
|
|
"entropy": 5.5855326652526855,
|
|
"epoch": 3.386140281911608,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00038884867026681906,
|
|
"loss": 4.9183,
|
|
"mean_token_accuracy": 0.2318769484758377,
|
|
"num_tokens": 67297803.0,
|
|
"step": 30150
|
|
},
|
|
{
|
|
"entropy": 5.517073249816894,
|
|
"epoch": 3.386701858819565,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003888140387010771,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.23603840470314025,
|
|
"num_tokens": 67309153.0,
|
|
"step": 30155
|
|
},
|
|
{
|
|
"entropy": 5.531494522094727,
|
|
"epoch": 3.387263435727523,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038877940351145186,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.22195524871349334,
|
|
"num_tokens": 67319695.0,
|
|
"step": 30160
|
|
},
|
|
{
|
|
"entropy": 5.553009986877441,
|
|
"epoch": 3.3878250126354805,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038874476469904633,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.22860146313905716,
|
|
"num_tokens": 67331615.0,
|
|
"step": 30165
|
|
},
|
|
{
|
|
"entropy": 5.519521284103393,
|
|
"epoch": 3.3883865895434377,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003887101222649634,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.23377367556095124,
|
|
"num_tokens": 67341898.0,
|
|
"step": 30170
|
|
},
|
|
{
|
|
"entropy": 5.645916414260864,
|
|
"epoch": 3.3889481664513954,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000388675476210306,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.22163360863924025,
|
|
"num_tokens": 67352677.0,
|
|
"step": 30175
|
|
},
|
|
{
|
|
"entropy": 5.60285120010376,
|
|
"epoch": 3.389509743359353,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038864082653617744,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.2230159670114517,
|
|
"num_tokens": 67363215.0,
|
|
"step": 30180
|
|
},
|
|
{
|
|
"entropy": 5.594004821777344,
|
|
"epoch": 3.3900713202673107,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038860617324368085,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.22872202843427658,
|
|
"num_tokens": 67374489.0,
|
|
"step": 30185
|
|
},
|
|
{
|
|
"entropy": 5.654152679443359,
|
|
"epoch": 3.3906328971752684,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003885715163339196,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.22653746753931045,
|
|
"num_tokens": 67384890.0,
|
|
"step": 30190
|
|
},
|
|
{
|
|
"entropy": 5.586863327026367,
|
|
"epoch": 3.3911944740832256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038853685580799726,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.22550730258226395,
|
|
"num_tokens": 67395811.0,
|
|
"step": 30195
|
|
},
|
|
{
|
|
"entropy": 5.575191640853882,
|
|
"epoch": 3.3917560509911833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003885021916670174,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.23533074855804442,
|
|
"num_tokens": 67407056.0,
|
|
"step": 30200
|
|
},
|
|
{
|
|
"entropy": 5.598905181884765,
|
|
"epoch": 3.392317627899141,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003884675239120838,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.22499606460332872,
|
|
"num_tokens": 67418371.0,
|
|
"step": 30205
|
|
},
|
|
{
|
|
"entropy": 5.593638181686401,
|
|
"epoch": 3.392879204807098,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038843285254430005,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.21907222270965576,
|
|
"num_tokens": 67429165.0,
|
|
"step": 30210
|
|
},
|
|
{
|
|
"entropy": 5.7613811016082765,
|
|
"epoch": 3.393440781715056,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003883981775647705,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.2190519765019417,
|
|
"num_tokens": 67442317.0,
|
|
"step": 30215
|
|
},
|
|
{
|
|
"entropy": 5.714413785934449,
|
|
"epoch": 3.3940023586230135,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003883634989745988,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.22958104014396669,
|
|
"num_tokens": 67454086.0,
|
|
"step": 30220
|
|
},
|
|
{
|
|
"entropy": 5.670026636123657,
|
|
"epoch": 3.394563935530971,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038832881677488944,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.2215357393026352,
|
|
"num_tokens": 67465066.0,
|
|
"step": 30225
|
|
},
|
|
{
|
|
"entropy": 5.575761890411377,
|
|
"epoch": 3.3951255124389284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038829413096674653,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.22905391305685044,
|
|
"num_tokens": 67475456.0,
|
|
"step": 30230
|
|
},
|
|
{
|
|
"entropy": 5.6038086891174315,
|
|
"epoch": 3.395687089346886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003882594415512746,
|
|
"loss": 4.9495,
|
|
"mean_token_accuracy": 0.2245165377855301,
|
|
"num_tokens": 67486315.0,
|
|
"step": 30235
|
|
},
|
|
{
|
|
"entropy": 5.5411583423614506,
|
|
"epoch": 3.3962486662548437,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038822474852957817,
|
|
"loss": 4.8928,
|
|
"mean_token_accuracy": 0.22465853691101073,
|
|
"num_tokens": 67497431.0,
|
|
"step": 30240
|
|
},
|
|
{
|
|
"entropy": 5.607159805297852,
|
|
"epoch": 3.3968102431628013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003881900519027618,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.22944845706224443,
|
|
"num_tokens": 67508054.0,
|
|
"step": 30245
|
|
},
|
|
{
|
|
"entropy": 5.648603773117065,
|
|
"epoch": 3.3973718200707586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003881553516719303,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.21988645195960999,
|
|
"num_tokens": 67519083.0,
|
|
"step": 30250
|
|
},
|
|
{
|
|
"entropy": 5.670793056488037,
|
|
"epoch": 3.397933396978716,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038812064783818847,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.2177373394370079,
|
|
"num_tokens": 67528909.0,
|
|
"step": 30255
|
|
},
|
|
{
|
|
"entropy": 5.533089590072632,
|
|
"epoch": 3.398494973886674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038808594040264127,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.23817309439182283,
|
|
"num_tokens": 67540069.0,
|
|
"step": 30260
|
|
},
|
|
{
|
|
"entropy": 5.545989370346069,
|
|
"epoch": 3.399056550794631,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000388051229366394,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.23169338405132295,
|
|
"num_tokens": 67550733.0,
|
|
"step": 30265
|
|
},
|
|
{
|
|
"entropy": 5.665881729125976,
|
|
"epoch": 3.3996181277025888,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038801651473055167,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.2223559334874153,
|
|
"num_tokens": 67562118.0,
|
|
"step": 30270
|
|
},
|
|
{
|
|
"entropy": 5.591964864730835,
|
|
"epoch": 3.4001797046105464,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003879817964962197,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.22948747724294663,
|
|
"num_tokens": 67572408.0,
|
|
"step": 30275
|
|
},
|
|
{
|
|
"entropy": 5.67496542930603,
|
|
"epoch": 3.400741281518504,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003879470746645035,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.21941790878772735,
|
|
"num_tokens": 67584125.0,
|
|
"step": 30280
|
|
},
|
|
{
|
|
"entropy": 5.620260334014892,
|
|
"epoch": 3.4013028584264617,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038791234923650866,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.2229629322886467,
|
|
"num_tokens": 67595093.0,
|
|
"step": 30285
|
|
},
|
|
{
|
|
"entropy": 5.6366486072540285,
|
|
"epoch": 3.401864435334419,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038787762021334077,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.21764893978834152,
|
|
"num_tokens": 67606794.0,
|
|
"step": 30290
|
|
},
|
|
{
|
|
"entropy": 5.509547328948974,
|
|
"epoch": 3.4024260122423766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003878428875961057,
|
|
"loss": 4.7631,
|
|
"mean_token_accuracy": 0.237938092648983,
|
|
"num_tokens": 67617207.0,
|
|
"step": 30295
|
|
},
|
|
{
|
|
"entropy": 5.507755470275879,
|
|
"epoch": 3.4029875891503343,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038780815138590935,
|
|
"loss": 4.8995,
|
|
"mean_token_accuracy": 0.22490244805812837,
|
|
"num_tokens": 67628301.0,
|
|
"step": 30300
|
|
},
|
|
{
|
|
"entropy": 5.628145408630371,
|
|
"epoch": 3.4035491660582915,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003877734115838577,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.22221696823835374,
|
|
"num_tokens": 67640363.0,
|
|
"step": 30305
|
|
},
|
|
{
|
|
"entropy": 5.644474506378174,
|
|
"epoch": 3.404110742966249,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038773866819105684,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.22330857217311859,
|
|
"num_tokens": 67651515.0,
|
|
"step": 30310
|
|
},
|
|
{
|
|
"entropy": 5.579376220703125,
|
|
"epoch": 3.404672319874207,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003877039212086131,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.22439851611852646,
|
|
"num_tokens": 67661669.0,
|
|
"step": 30315
|
|
},
|
|
{
|
|
"entropy": 5.562666130065918,
|
|
"epoch": 3.4052338967821645,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038766917063763287,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.22513179928064347,
|
|
"num_tokens": 67671945.0,
|
|
"step": 30320
|
|
},
|
|
{
|
|
"entropy": 5.575850248336792,
|
|
"epoch": 3.4057954736901217,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038763441647922246,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.22464766949415207,
|
|
"num_tokens": 67683090.0,
|
|
"step": 30325
|
|
},
|
|
{
|
|
"entropy": 5.611435985565185,
|
|
"epoch": 3.4063570505980794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003875996587344885,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.2297675997018814,
|
|
"num_tokens": 67694036.0,
|
|
"step": 30330
|
|
},
|
|
{
|
|
"entropy": 5.625906467437744,
|
|
"epoch": 3.406918627506037,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038756489740453785,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.23059436976909636,
|
|
"num_tokens": 67704677.0,
|
|
"step": 30335
|
|
},
|
|
{
|
|
"entropy": 5.630937671661377,
|
|
"epoch": 3.4074802044139947,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038753013249047706,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.22784361839294434,
|
|
"num_tokens": 67715165.0,
|
|
"step": 30340
|
|
},
|
|
{
|
|
"entropy": 5.620278596878052,
|
|
"epoch": 3.408041781321952,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003874953639934134,
|
|
"loss": 4.9217,
|
|
"mean_token_accuracy": 0.23640780597925187,
|
|
"num_tokens": 67726226.0,
|
|
"step": 30345
|
|
},
|
|
{
|
|
"entropy": 5.58723669052124,
|
|
"epoch": 3.4086033582299096,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003874605919144536,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.2326648250222206,
|
|
"num_tokens": 67739564.0,
|
|
"step": 30350
|
|
},
|
|
{
|
|
"entropy": 5.592278289794922,
|
|
"epoch": 3.4091649351378672,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003874258162547049,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.22431472241878508,
|
|
"num_tokens": 67751683.0,
|
|
"step": 30355
|
|
},
|
|
{
|
|
"entropy": 5.691811656951904,
|
|
"epoch": 3.4097265120458244,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003873910370152747,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.22577064782381057,
|
|
"num_tokens": 67762782.0,
|
|
"step": 30360
|
|
},
|
|
{
|
|
"entropy": 5.6275646686553955,
|
|
"epoch": 3.410288088953782,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003873562541972702,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.2200116902589798,
|
|
"num_tokens": 67773583.0,
|
|
"step": 30365
|
|
},
|
|
{
|
|
"entropy": 5.6145227432250975,
|
|
"epoch": 3.4108496658617398,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003873214678017991,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.22344059497117996,
|
|
"num_tokens": 67785428.0,
|
|
"step": 30370
|
|
},
|
|
{
|
|
"entropy": 5.65561695098877,
|
|
"epoch": 3.4114112427696974,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003872866778299688,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.21717340797185897,
|
|
"num_tokens": 67797678.0,
|
|
"step": 30375
|
|
},
|
|
{
|
|
"entropy": 5.673375225067138,
|
|
"epoch": 3.411972819677655,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003872518842828872,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.2298155188560486,
|
|
"num_tokens": 67809314.0,
|
|
"step": 30380
|
|
},
|
|
{
|
|
"entropy": 5.57480149269104,
|
|
"epoch": 3.4125343965856123,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038721708716166203,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.22673002034425735,
|
|
"num_tokens": 67820591.0,
|
|
"step": 30385
|
|
},
|
|
{
|
|
"entropy": 5.5687095642089846,
|
|
"epoch": 3.41309597349357,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003871822864674013,
|
|
"loss": 4.9196,
|
|
"mean_token_accuracy": 0.23152067363262177,
|
|
"num_tokens": 67831436.0,
|
|
"step": 30390
|
|
},
|
|
{
|
|
"entropy": 5.610189819335938,
|
|
"epoch": 3.4136575504015276,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038714748220121305,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.22457361817359925,
|
|
"num_tokens": 67842813.0,
|
|
"step": 30395
|
|
},
|
|
{
|
|
"entropy": 5.605137062072754,
|
|
"epoch": 3.414219127309485,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003871126743642055,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.22219155430793763,
|
|
"num_tokens": 67853899.0,
|
|
"step": 30400
|
|
},
|
|
{
|
|
"entropy": 5.617282915115356,
|
|
"epoch": 3.4147807042174425,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038707786295748693,
|
|
"loss": 4.9301,
|
|
"mean_token_accuracy": 0.2244442030787468,
|
|
"num_tokens": 67864237.0,
|
|
"step": 30405
|
|
},
|
|
{
|
|
"entropy": 5.603562879562378,
|
|
"epoch": 3.4153422811254,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038704304798216566,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.2195644870400429,
|
|
"num_tokens": 67876109.0,
|
|
"step": 30410
|
|
},
|
|
{
|
|
"entropy": 5.502943706512451,
|
|
"epoch": 3.415903858033358,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003870082294393503,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.22652095556259155,
|
|
"num_tokens": 67888461.0,
|
|
"step": 30415
|
|
},
|
|
{
|
|
"entropy": 5.585151958465576,
|
|
"epoch": 3.416465434941315,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003869734073301495,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.2302572548389435,
|
|
"num_tokens": 67899543.0,
|
|
"step": 30420
|
|
},
|
|
{
|
|
"entropy": 5.658939266204834,
|
|
"epoch": 3.4170270118492727,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038693858165567195,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.22264360785484313,
|
|
"num_tokens": 67910606.0,
|
|
"step": 30425
|
|
},
|
|
{
|
|
"entropy": 5.61535611152649,
|
|
"epoch": 3.4175885887572304,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003869037524170266,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.22902851849794387,
|
|
"num_tokens": 67921240.0,
|
|
"step": 30430
|
|
},
|
|
{
|
|
"entropy": 5.6573738098144535,
|
|
"epoch": 3.418150165665188,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038686891961532227,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.2101387083530426,
|
|
"num_tokens": 67935178.0,
|
|
"step": 30435
|
|
},
|
|
{
|
|
"entropy": 5.501389694213867,
|
|
"epoch": 3.4187117425731453,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003868340832516683,
|
|
"loss": 4.8413,
|
|
"mean_token_accuracy": 0.23308784812688826,
|
|
"num_tokens": 67947260.0,
|
|
"step": 30440
|
|
},
|
|
{
|
|
"entropy": 5.630807685852051,
|
|
"epoch": 3.419273319481103,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038679924332717363,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.2269672840833664,
|
|
"num_tokens": 67956665.0,
|
|
"step": 30445
|
|
},
|
|
{
|
|
"entropy": 5.626975440979004,
|
|
"epoch": 3.4198348963890606,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038676439984294776,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.22066444009542466,
|
|
"num_tokens": 67967927.0,
|
|
"step": 30450
|
|
},
|
|
{
|
|
"entropy": 5.605084228515625,
|
|
"epoch": 3.420396473297018,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038672955280009996,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.2278073325753212,
|
|
"num_tokens": 67979574.0,
|
|
"step": 30455
|
|
},
|
|
{
|
|
"entropy": 5.568082284927368,
|
|
"epoch": 3.4209580502049755,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038669470219973996,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.218979212641716,
|
|
"num_tokens": 67991671.0,
|
|
"step": 30460
|
|
},
|
|
{
|
|
"entropy": 5.691042041778564,
|
|
"epoch": 3.421519627112933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038665984804297734,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.21657371371984482,
|
|
"num_tokens": 68002443.0,
|
|
"step": 30465
|
|
},
|
|
{
|
|
"entropy": 5.643999433517456,
|
|
"epoch": 3.4220812040208908,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003866249903309218,
|
|
"loss": 4.9547,
|
|
"mean_token_accuracy": 0.21994713246822356,
|
|
"num_tokens": 68013681.0,
|
|
"step": 30470
|
|
},
|
|
{
|
|
"entropy": 5.628871631622315,
|
|
"epoch": 3.4226427809288484,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003865901290646833,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.22824249416589737,
|
|
"num_tokens": 68023757.0,
|
|
"step": 30475
|
|
},
|
|
{
|
|
"entropy": 5.545018434524536,
|
|
"epoch": 3.4232043578368057,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038655526424537175,
|
|
"loss": 4.9267,
|
|
"mean_token_accuracy": 0.2262836903333664,
|
|
"num_tokens": 68035491.0,
|
|
"step": 30480
|
|
},
|
|
{
|
|
"entropy": 5.51676869392395,
|
|
"epoch": 3.4237659347447633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038652039587409734,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.22542443871498108,
|
|
"num_tokens": 68047581.0,
|
|
"step": 30485
|
|
},
|
|
{
|
|
"entropy": 5.650005578994751,
|
|
"epoch": 3.424327511652721,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003864855239519703,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.2160930261015892,
|
|
"num_tokens": 68058232.0,
|
|
"step": 30490
|
|
},
|
|
{
|
|
"entropy": 5.795702362060547,
|
|
"epoch": 3.424889088560678,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038645064848010093,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.21742963045835495,
|
|
"num_tokens": 68071602.0,
|
|
"step": 30495
|
|
},
|
|
{
|
|
"entropy": 5.611180543899536,
|
|
"epoch": 3.425450665468636,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038641576945959964,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.22505564093589783,
|
|
"num_tokens": 68083169.0,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"entropy": 5.60994520187378,
|
|
"epoch": 3.4260122423765935,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038638088689157713,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.2112673968076706,
|
|
"num_tokens": 68093951.0,
|
|
"step": 30505
|
|
},
|
|
{
|
|
"entropy": 5.677316808700562,
|
|
"epoch": 3.426573819284551,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038634600077714395,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.21537300795316697,
|
|
"num_tokens": 68105398.0,
|
|
"step": 30510
|
|
},
|
|
{
|
|
"entropy": 5.665712451934814,
|
|
"epoch": 3.4271353961925084,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003863111111174109,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.22858485579490662,
|
|
"num_tokens": 68116544.0,
|
|
"step": 30515
|
|
},
|
|
{
|
|
"entropy": 5.629970121383667,
|
|
"epoch": 3.427696973100466,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038627621791348886,
|
|
"loss": 4.8818,
|
|
"mean_token_accuracy": 0.24030185788869857,
|
|
"num_tokens": 68126977.0,
|
|
"step": 30520
|
|
},
|
|
{
|
|
"entropy": 5.655009317398071,
|
|
"epoch": 3.4282585500084237,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038624132116648897,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.21516470462083817,
|
|
"num_tokens": 68137884.0,
|
|
"step": 30525
|
|
},
|
|
{
|
|
"entropy": 5.674043226242065,
|
|
"epoch": 3.4288201269163814,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003862064208775223,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.2229892149567604,
|
|
"num_tokens": 68149026.0,
|
|
"step": 30530
|
|
},
|
|
{
|
|
"entropy": 5.616882228851319,
|
|
"epoch": 3.4293817038243386,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038617151704769994,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.221979059278965,
|
|
"num_tokens": 68159962.0,
|
|
"step": 30535
|
|
},
|
|
{
|
|
"entropy": 5.5884795665740965,
|
|
"epoch": 3.4299432807322963,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003861366096781334,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.22505539953708648,
|
|
"num_tokens": 68170849.0,
|
|
"step": 30540
|
|
},
|
|
{
|
|
"entropy": 5.566911888122559,
|
|
"epoch": 3.430504857640254,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003861016987699342,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.2299817755818367,
|
|
"num_tokens": 68181623.0,
|
|
"step": 30545
|
|
},
|
|
{
|
|
"entropy": 5.589145374298096,
|
|
"epoch": 3.431066434548211,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038606678432421366,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.2398008167743683,
|
|
"num_tokens": 68191943.0,
|
|
"step": 30550
|
|
},
|
|
{
|
|
"entropy": 5.558414363861084,
|
|
"epoch": 3.431628011456169,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003860318663420837,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.22246327251195908,
|
|
"num_tokens": 68203833.0,
|
|
"step": 30555
|
|
},
|
|
{
|
|
"entropy": 5.54455599784851,
|
|
"epoch": 3.4321895883641265,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038599694482465606,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.21951879411935807,
|
|
"num_tokens": 68213992.0,
|
|
"step": 30560
|
|
},
|
|
{
|
|
"entropy": 5.598366069793701,
|
|
"epoch": 3.432751165272084,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038596201977304263,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.22997366338968278,
|
|
"num_tokens": 68224575.0,
|
|
"step": 30565
|
|
},
|
|
{
|
|
"entropy": 5.602128791809082,
|
|
"epoch": 3.433312742180042,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038592709118835547,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.22197000235319136,
|
|
"num_tokens": 68235513.0,
|
|
"step": 30570
|
|
},
|
|
{
|
|
"entropy": 5.698203420639038,
|
|
"epoch": 3.433874319087999,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038589215907170664,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.225494484603405,
|
|
"num_tokens": 68246560.0,
|
|
"step": 30575
|
|
},
|
|
{
|
|
"entropy": 5.545177364349366,
|
|
"epoch": 3.4344358959959567,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003858572234242086,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.23405828773975373,
|
|
"num_tokens": 68257760.0,
|
|
"step": 30580
|
|
},
|
|
{
|
|
"entropy": 5.530983018875122,
|
|
"epoch": 3.4349974729039143,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038582228424697347,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.24124003499746322,
|
|
"num_tokens": 68269631.0,
|
|
"step": 30585
|
|
},
|
|
{
|
|
"entropy": 5.602777528762817,
|
|
"epoch": 3.4355590498118715,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003857873415411138,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.23047890663146972,
|
|
"num_tokens": 68280198.0,
|
|
"step": 30590
|
|
},
|
|
{
|
|
"entropy": 5.603708648681641,
|
|
"epoch": 3.436120626719829,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003857523953077423,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.21836123168468474,
|
|
"num_tokens": 68291812.0,
|
|
"step": 30595
|
|
},
|
|
{
|
|
"entropy": 5.658810043334961,
|
|
"epoch": 3.436682203627787,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038571744554797156,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.21888261735439302,
|
|
"num_tokens": 68303202.0,
|
|
"step": 30600
|
|
},
|
|
{
|
|
"entropy": 5.60409517288208,
|
|
"epoch": 3.4372437805357445,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038568249226291433,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.2231913074851036,
|
|
"num_tokens": 68313768.0,
|
|
"step": 30605
|
|
},
|
|
{
|
|
"entropy": 5.6093645095825195,
|
|
"epoch": 3.4378053574437017,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038564753545368375,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.2247022420167923,
|
|
"num_tokens": 68325325.0,
|
|
"step": 30610
|
|
},
|
|
{
|
|
"entropy": 5.601677799224854,
|
|
"epoch": 3.4383669343516594,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038561257512139264,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.22143895477056502,
|
|
"num_tokens": 68337166.0,
|
|
"step": 30615
|
|
},
|
|
{
|
|
"entropy": 5.645495319366455,
|
|
"epoch": 3.438928511259617,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038557761126715426,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.2317008927464485,
|
|
"num_tokens": 68348898.0,
|
|
"step": 30620
|
|
},
|
|
{
|
|
"entropy": 5.6403450012207035,
|
|
"epoch": 3.4394900881675747,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003855426438920818,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.2240382730960846,
|
|
"num_tokens": 68360589.0,
|
|
"step": 30625
|
|
},
|
|
{
|
|
"entropy": 5.487015008926392,
|
|
"epoch": 3.440051665075532,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038550767299728875,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.2384212076663971,
|
|
"num_tokens": 68371813.0,
|
|
"step": 30630
|
|
},
|
|
{
|
|
"entropy": 5.617304086685181,
|
|
"epoch": 3.4406132419834896,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038547269858388853,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.2183618500828743,
|
|
"num_tokens": 68382060.0,
|
|
"step": 30635
|
|
},
|
|
{
|
|
"entropy": 5.682156610488891,
|
|
"epoch": 3.4411748188914473,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003854377206529947,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.22922839522361754,
|
|
"num_tokens": 68395603.0,
|
|
"step": 30640
|
|
},
|
|
{
|
|
"entropy": 5.571892833709716,
|
|
"epoch": 3.4417363957994045,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000385402739205721,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.2335370346903801,
|
|
"num_tokens": 68406725.0,
|
|
"step": 30645
|
|
},
|
|
{
|
|
"entropy": 5.617381763458252,
|
|
"epoch": 3.442297972707362,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003853677542431813,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.21746852695941926,
|
|
"num_tokens": 68418577.0,
|
|
"step": 30650
|
|
},
|
|
{
|
|
"entropy": 5.5899497985839846,
|
|
"epoch": 3.44285954961532,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003853327657664895,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.22328908741474152,
|
|
"num_tokens": 68429708.0,
|
|
"step": 30655
|
|
},
|
|
{
|
|
"entropy": 5.65862627029419,
|
|
"epoch": 3.4434211265232775,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003852977737767596,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.22211045622825623,
|
|
"num_tokens": 68442115.0,
|
|
"step": 30660
|
|
},
|
|
{
|
|
"entropy": 5.614062881469726,
|
|
"epoch": 3.443982703431235,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003852627782751059,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.22897686213254928,
|
|
"num_tokens": 68453555.0,
|
|
"step": 30665
|
|
},
|
|
{
|
|
"entropy": 5.5696734428405765,
|
|
"epoch": 3.4445442803391924,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003852277792626425,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.23406410217285156,
|
|
"num_tokens": 68466859.0,
|
|
"step": 30670
|
|
},
|
|
{
|
|
"entropy": 5.5930492877960205,
|
|
"epoch": 3.44510585724715,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003851927767404839,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.2216804400086403,
|
|
"num_tokens": 68477628.0,
|
|
"step": 30675
|
|
},
|
|
{
|
|
"entropy": 5.642091083526611,
|
|
"epoch": 3.4456674341551077,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003851577707097445,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.22821634113788605,
|
|
"num_tokens": 68488764.0,
|
|
"step": 30680
|
|
},
|
|
{
|
|
"entropy": 5.665640115737915,
|
|
"epoch": 3.446229011063065,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000385122761171539,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.22071099281311035,
|
|
"num_tokens": 68499433.0,
|
|
"step": 30685
|
|
},
|
|
{
|
|
"entropy": 5.636741209030151,
|
|
"epoch": 3.4467905879710226,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038508774812698207,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.22196804732084274,
|
|
"num_tokens": 68510832.0,
|
|
"step": 30690
|
|
},
|
|
{
|
|
"entropy": 5.534621715545654,
|
|
"epoch": 3.44735216487898,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003850527315771885,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.22504502832889556,
|
|
"num_tokens": 68520946.0,
|
|
"step": 30695
|
|
},
|
|
{
|
|
"entropy": 5.653549528121948,
|
|
"epoch": 3.447913741786938,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038501771152327333,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.2185288742184639,
|
|
"num_tokens": 68531769.0,
|
|
"step": 30700
|
|
},
|
|
{
|
|
"entropy": 5.662854909896851,
|
|
"epoch": 3.448475318694895,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038498268796635155,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.21592954695224761,
|
|
"num_tokens": 68543172.0,
|
|
"step": 30705
|
|
},
|
|
{
|
|
"entropy": 5.549572896957398,
|
|
"epoch": 3.4490368956028528,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038494766090753824,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.22722936570644378,
|
|
"num_tokens": 68554078.0,
|
|
"step": 30710
|
|
},
|
|
{
|
|
"entropy": 5.585100555419922,
|
|
"epoch": 3.4495984725108104,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038491263034794886,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.22861261516809464,
|
|
"num_tokens": 68564705.0,
|
|
"step": 30715
|
|
},
|
|
{
|
|
"entropy": 5.685156440734863,
|
|
"epoch": 3.450160049418768,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003848775962886987,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.2136169582605362,
|
|
"num_tokens": 68577010.0,
|
|
"step": 30720
|
|
},
|
|
{
|
|
"entropy": 5.670284175872803,
|
|
"epoch": 3.4507216263267253,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003848425587309032,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.2248897820711136,
|
|
"num_tokens": 68588465.0,
|
|
"step": 30725
|
|
},
|
|
{
|
|
"entropy": 5.643072414398193,
|
|
"epoch": 3.451283203234683,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038480751767567807,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.22895626425743104,
|
|
"num_tokens": 68599666.0,
|
|
"step": 30730
|
|
},
|
|
{
|
|
"entropy": 5.571522808074951,
|
|
"epoch": 3.4518447801426406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000384772473124139,
|
|
"loss": 4.9377,
|
|
"mean_token_accuracy": 0.23245566636323928,
|
|
"num_tokens": 68610530.0,
|
|
"step": 30735
|
|
},
|
|
{
|
|
"entropy": 5.510235023498535,
|
|
"epoch": 3.452406357050598,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003847374250774018,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.2279008746147156,
|
|
"num_tokens": 68621360.0,
|
|
"step": 30740
|
|
},
|
|
{
|
|
"entropy": 5.652305984497071,
|
|
"epoch": 3.4529679339585555,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038470237353658237,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.222293983399868,
|
|
"num_tokens": 68632874.0,
|
|
"step": 30745
|
|
},
|
|
{
|
|
"entropy": 5.618166399002075,
|
|
"epoch": 3.453529510866513,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038466731850279683,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.22358962148427963,
|
|
"num_tokens": 68643715.0,
|
|
"step": 30750
|
|
},
|
|
{
|
|
"entropy": 5.564495420455932,
|
|
"epoch": 3.454091087774471,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038463225997716137,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.22255211025476457,
|
|
"num_tokens": 68655433.0,
|
|
"step": 30755
|
|
},
|
|
{
|
|
"entropy": 5.6487181186676025,
|
|
"epoch": 3.4546526646824285,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038459719796079227,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.2257697194814682,
|
|
"num_tokens": 68667321.0,
|
|
"step": 30760
|
|
},
|
|
{
|
|
"entropy": 5.645577239990234,
|
|
"epoch": 3.4552142415903857,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003845621324548059,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.22060278058052063,
|
|
"num_tokens": 68677314.0,
|
|
"step": 30765
|
|
},
|
|
{
|
|
"entropy": 5.626969957351685,
|
|
"epoch": 3.4557758184983434,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003845270634603186,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.2187577322125435,
|
|
"num_tokens": 68688871.0,
|
|
"step": 30770
|
|
},
|
|
{
|
|
"entropy": 5.635045385360717,
|
|
"epoch": 3.456337395406301,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038449199097844724,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.2267114520072937,
|
|
"num_tokens": 68699760.0,
|
|
"step": 30775
|
|
},
|
|
{
|
|
"entropy": 5.6993739128112795,
|
|
"epoch": 3.4568989723142582,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003844569150103084,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.21374503076076506,
|
|
"num_tokens": 68711113.0,
|
|
"step": 30780
|
|
},
|
|
{
|
|
"entropy": 5.684715843200683,
|
|
"epoch": 3.457460549222216,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003844218355570189,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.22359290421009065,
|
|
"num_tokens": 68722904.0,
|
|
"step": 30785
|
|
},
|
|
{
|
|
"entropy": 5.583766937255859,
|
|
"epoch": 3.4580221261301736,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003843867526196957,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.22427257895469666,
|
|
"num_tokens": 68733753.0,
|
|
"step": 30790
|
|
},
|
|
{
|
|
"entropy": 5.577167415618897,
|
|
"epoch": 3.4585837030381312,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003843516661994559,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.21433907747268677,
|
|
"num_tokens": 68744477.0,
|
|
"step": 30795
|
|
},
|
|
{
|
|
"entropy": 5.726285982131958,
|
|
"epoch": 3.4591452799460884,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003843165762974167,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.21834613531827926,
|
|
"num_tokens": 68755607.0,
|
|
"step": 30800
|
|
},
|
|
{
|
|
"entropy": 5.70891227722168,
|
|
"epoch": 3.459706856854046,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038428148291469515,
|
|
"loss": 5.0117,
|
|
"mean_token_accuracy": 0.22129384726285933,
|
|
"num_tokens": 68766477.0,
|
|
"step": 30805
|
|
},
|
|
{
|
|
"entropy": 5.569132375717163,
|
|
"epoch": 3.4602684337620038,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000384246386052409,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.231479649245739,
|
|
"num_tokens": 68776806.0,
|
|
"step": 30810
|
|
},
|
|
{
|
|
"entropy": 5.576468467712402,
|
|
"epoch": 3.4608300106699614,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003842112857116754,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.2298204332590103,
|
|
"num_tokens": 68788011.0,
|
|
"step": 30815
|
|
},
|
|
{
|
|
"entropy": 5.575132608413696,
|
|
"epoch": 3.4613915875779186,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003841761818936122,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.22747757136821747,
|
|
"num_tokens": 68800370.0,
|
|
"step": 30820
|
|
},
|
|
{
|
|
"entropy": 5.668542957305908,
|
|
"epoch": 3.4619531644858763,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000384141074599337,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.21945376098155975,
|
|
"num_tokens": 68811644.0,
|
|
"step": 30825
|
|
},
|
|
{
|
|
"entropy": 5.6099936962127686,
|
|
"epoch": 3.462514741393834,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038410596382996764,
|
|
"loss": 4.9303,
|
|
"mean_token_accuracy": 0.2121934026479721,
|
|
"num_tokens": 68823672.0,
|
|
"step": 30830
|
|
},
|
|
{
|
|
"entropy": 5.599378681182861,
|
|
"epoch": 3.463076318301791,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003840708495866221,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.22199391573667526,
|
|
"num_tokens": 68835340.0,
|
|
"step": 30835
|
|
},
|
|
{
|
|
"entropy": 5.632833194732666,
|
|
"epoch": 3.463637895209749,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003840357318704183,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.22802898585796355,
|
|
"num_tokens": 68845903.0,
|
|
"step": 30840
|
|
},
|
|
{
|
|
"entropy": 5.630199670791626,
|
|
"epoch": 3.4641994721177065,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003840006106824746,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.22440036237239838,
|
|
"num_tokens": 68857287.0,
|
|
"step": 30845
|
|
},
|
|
{
|
|
"entropy": 5.646532440185547,
|
|
"epoch": 3.464761049025664,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003839654860239091,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.21863283663988115,
|
|
"num_tokens": 68868961.0,
|
|
"step": 30850
|
|
},
|
|
{
|
|
"entropy": 5.66611270904541,
|
|
"epoch": 3.465322625933622,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003839303578958404,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.224497452378273,
|
|
"num_tokens": 68880275.0,
|
|
"step": 30855
|
|
},
|
|
{
|
|
"entropy": 5.642799282073975,
|
|
"epoch": 3.465884202841579,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038389522629938676,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.23793625980615615,
|
|
"num_tokens": 68891445.0,
|
|
"step": 30860
|
|
},
|
|
{
|
|
"entropy": 5.564932727813721,
|
|
"epoch": 3.4664457797495367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003838600912356669,
|
|
"loss": 4.9097,
|
|
"mean_token_accuracy": 0.22719421088695527,
|
|
"num_tokens": 68903591.0,
|
|
"step": 30865
|
|
},
|
|
{
|
|
"entropy": 5.619049215316773,
|
|
"epoch": 3.4670073566574944,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003838249527057995,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.22910211384296417,
|
|
"num_tokens": 68914094.0,
|
|
"step": 30870
|
|
},
|
|
{
|
|
"entropy": 5.648839330673217,
|
|
"epoch": 3.4675689335654516,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038378981071090346,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.22862350642681123,
|
|
"num_tokens": 68925929.0,
|
|
"step": 30875
|
|
},
|
|
{
|
|
"entropy": 5.598537969589233,
|
|
"epoch": 3.4681305104734093,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038375466525209764,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.2303771421313286,
|
|
"num_tokens": 68936087.0,
|
|
"step": 30880
|
|
},
|
|
{
|
|
"entropy": 5.567670726776123,
|
|
"epoch": 3.468692087381367,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038371951633050106,
|
|
"loss": 4.9448,
|
|
"mean_token_accuracy": 0.2324620768427849,
|
|
"num_tokens": 68946878.0,
|
|
"step": 30885
|
|
},
|
|
{
|
|
"entropy": 5.6476922035217285,
|
|
"epoch": 3.4692536642893246,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038368436394723294,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.22553730905056,
|
|
"num_tokens": 68957896.0,
|
|
"step": 30890
|
|
},
|
|
{
|
|
"entropy": 5.661101341247559,
|
|
"epoch": 3.469815241197282,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038364920810341255,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.2247934103012085,
|
|
"num_tokens": 68969173.0,
|
|
"step": 30895
|
|
},
|
|
{
|
|
"entropy": 5.677996826171875,
|
|
"epoch": 3.4703768181052395,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003836140488001592,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.22644104957580566,
|
|
"num_tokens": 68980537.0,
|
|
"step": 30900
|
|
},
|
|
{
|
|
"entropy": 5.608390235900879,
|
|
"epoch": 3.470938395013197,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038357888603859236,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.2254740208387375,
|
|
"num_tokens": 68991736.0,
|
|
"step": 30905
|
|
},
|
|
{
|
|
"entropy": 5.596353387832641,
|
|
"epoch": 3.471499971921155,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038354371981983175,
|
|
"loss": 4.922,
|
|
"mean_token_accuracy": 0.22648791521787642,
|
|
"num_tokens": 69002316.0,
|
|
"step": 30910
|
|
},
|
|
{
|
|
"entropy": 5.552998399734497,
|
|
"epoch": 3.472061548829112,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003835085501449969,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.22322353720664978,
|
|
"num_tokens": 69014204.0,
|
|
"step": 30915
|
|
},
|
|
{
|
|
"entropy": 5.605351400375366,
|
|
"epoch": 3.4726231257370697,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038347337701520785,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.22266777455806733,
|
|
"num_tokens": 69026482.0,
|
|
"step": 30920
|
|
},
|
|
{
|
|
"entropy": 5.6745100021362305,
|
|
"epoch": 3.4731847026450273,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038343820043158436,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.22016577422618866,
|
|
"num_tokens": 69036527.0,
|
|
"step": 30925
|
|
},
|
|
{
|
|
"entropy": 5.625564908981323,
|
|
"epoch": 3.4737462795529845,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003834030203952465,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.225662524998188,
|
|
"num_tokens": 69047684.0,
|
|
"step": 30930
|
|
},
|
|
{
|
|
"entropy": 5.582140970230102,
|
|
"epoch": 3.474307856460942,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003833678369073144,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.2210787534713745,
|
|
"num_tokens": 69059236.0,
|
|
"step": 30935
|
|
},
|
|
{
|
|
"entropy": 5.559390258789063,
|
|
"epoch": 3.4748694333689,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003833326499689084,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.2253415673971176,
|
|
"num_tokens": 69069713.0,
|
|
"step": 30940
|
|
},
|
|
{
|
|
"entropy": 5.634436798095703,
|
|
"epoch": 3.4754310102768575,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003832974595811488,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.21467609703540802,
|
|
"num_tokens": 69079046.0,
|
|
"step": 30945
|
|
},
|
|
{
|
|
"entropy": 5.682177209854126,
|
|
"epoch": 3.475992587184815,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000383262265745156,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.223556749522686,
|
|
"num_tokens": 69090080.0,
|
|
"step": 30950
|
|
},
|
|
{
|
|
"entropy": 5.645875549316406,
|
|
"epoch": 3.4765541640927724,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038322706846205073,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.21839417815208434,
|
|
"num_tokens": 69102374.0,
|
|
"step": 30955
|
|
},
|
|
{
|
|
"entropy": 5.643726253509522,
|
|
"epoch": 3.47711574100073,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038319186773295364,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.22790421694517135,
|
|
"num_tokens": 69112688.0,
|
|
"step": 30960
|
|
},
|
|
{
|
|
"entropy": 5.668537330627442,
|
|
"epoch": 3.4776773179086877,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003831566635589856,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.22655625343322755,
|
|
"num_tokens": 69124861.0,
|
|
"step": 30965
|
|
},
|
|
{
|
|
"entropy": 5.638547086715699,
|
|
"epoch": 3.478238894816645,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003831214559412674,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.2221964493393898,
|
|
"num_tokens": 69135898.0,
|
|
"step": 30970
|
|
},
|
|
{
|
|
"entropy": 5.731487083435058,
|
|
"epoch": 3.4788004717246026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038308624488092005,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.21874358355998993,
|
|
"num_tokens": 69146692.0,
|
|
"step": 30975
|
|
},
|
|
{
|
|
"entropy": 5.628411483764649,
|
|
"epoch": 3.4793620486325603,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003830510303790647,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.22313846349716188,
|
|
"num_tokens": 69157908.0,
|
|
"step": 30980
|
|
},
|
|
{
|
|
"entropy": 5.594046401977539,
|
|
"epoch": 3.479923625540518,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038301581243682263,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.2198239505290985,
|
|
"num_tokens": 69168596.0,
|
|
"step": 30985
|
|
},
|
|
{
|
|
"entropy": 5.559089326858521,
|
|
"epoch": 3.480485202448475,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003829805910553153,
|
|
"loss": 4.9195,
|
|
"mean_token_accuracy": 0.22340953797101976,
|
|
"num_tokens": 69179261.0,
|
|
"step": 30990
|
|
},
|
|
{
|
|
"entropy": 5.627126264572143,
|
|
"epoch": 3.481046779356433,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038294536623566407,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.2222731038928032,
|
|
"num_tokens": 69190410.0,
|
|
"step": 30995
|
|
},
|
|
{
|
|
"entropy": 5.635567903518677,
|
|
"epoch": 3.4816083562643905,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003829101379789905,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.22158874720335006,
|
|
"num_tokens": 69201114.0,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"entropy": 5.614851188659668,
|
|
"epoch": 3.482169933172348,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003828749062864162,
|
|
"loss": 4.9233,
|
|
"mean_token_accuracy": 0.22843078523874283,
|
|
"num_tokens": 69212240.0,
|
|
"step": 31005
|
|
},
|
|
{
|
|
"entropy": 5.63623366355896,
|
|
"epoch": 3.4827315100803053,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003828396711590631,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.2152373120188713,
|
|
"num_tokens": 69223714.0,
|
|
"step": 31010
|
|
},
|
|
{
|
|
"entropy": 5.657439231872559,
|
|
"epoch": 3.483293086988263,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038280443259805307,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.21979161053895951,
|
|
"num_tokens": 69234364.0,
|
|
"step": 31015
|
|
},
|
|
{
|
|
"entropy": 5.571760606765747,
|
|
"epoch": 3.4838546638962207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003827691906045081,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.2263505905866623,
|
|
"num_tokens": 69245584.0,
|
|
"step": 31020
|
|
},
|
|
{
|
|
"entropy": 5.601265525817871,
|
|
"epoch": 3.484416240804178,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003827339451795503,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.22036703824996948,
|
|
"num_tokens": 69256891.0,
|
|
"step": 31025
|
|
},
|
|
{
|
|
"entropy": 5.646401977539062,
|
|
"epoch": 3.4849778177121356,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003826986963243018,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.22931007891893387,
|
|
"num_tokens": 69266972.0,
|
|
"step": 31030
|
|
},
|
|
{
|
|
"entropy": 5.6487603187561035,
|
|
"epoch": 3.485539394620093,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003826634440398852,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.2307904601097107,
|
|
"num_tokens": 69277993.0,
|
|
"step": 31035
|
|
},
|
|
{
|
|
"entropy": 5.581854820251465,
|
|
"epoch": 3.486100971528051,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038262818832742276,
|
|
"loss": 4.9267,
|
|
"mean_token_accuracy": 0.22529180496931075,
|
|
"num_tokens": 69289720.0,
|
|
"step": 31040
|
|
},
|
|
{
|
|
"entropy": 5.677014780044556,
|
|
"epoch": 3.4866625484360085,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038259292918803696,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.21467891037464143,
|
|
"num_tokens": 69301169.0,
|
|
"step": 31045
|
|
},
|
|
{
|
|
"entropy": 5.587120294570923,
|
|
"epoch": 3.4872241253439658,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003825576666228506,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.22226338982582092,
|
|
"num_tokens": 69311443.0,
|
|
"step": 31050
|
|
},
|
|
{
|
|
"entropy": 5.631369018554688,
|
|
"epoch": 3.4877857022519234,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003825224006329864,
|
|
"loss": 4.9756,
|
|
"mean_token_accuracy": 0.22414859682321547,
|
|
"num_tokens": 69322035.0,
|
|
"step": 31055
|
|
},
|
|
{
|
|
"entropy": 5.573304891586304,
|
|
"epoch": 3.488347279159881,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003824871312195673,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.23900145888328553,
|
|
"num_tokens": 69331955.0,
|
|
"step": 31060
|
|
},
|
|
{
|
|
"entropy": 5.596124935150146,
|
|
"epoch": 3.4889088560678383,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003824518583837163,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.22788560539484023,
|
|
"num_tokens": 69343897.0,
|
|
"step": 31065
|
|
},
|
|
{
|
|
"entropy": 5.556146430969238,
|
|
"epoch": 3.489470432975796,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003824165821265564,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.23212257474660875,
|
|
"num_tokens": 69353886.0,
|
|
"step": 31070
|
|
},
|
|
{
|
|
"entropy": 5.552418661117554,
|
|
"epoch": 3.4900320098837536,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003823813024492108,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.23067676872015,
|
|
"num_tokens": 69365328.0,
|
|
"step": 31075
|
|
},
|
|
{
|
|
"entropy": 5.659568643569946,
|
|
"epoch": 3.4905935867917113,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000382346019352803,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.21584972143173217,
|
|
"num_tokens": 69376007.0,
|
|
"step": 31080
|
|
},
|
|
{
|
|
"entropy": 5.6325647830963135,
|
|
"epoch": 3.4911551636996685,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003823107328384562,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.21539446860551834,
|
|
"num_tokens": 69386668.0,
|
|
"step": 31085
|
|
},
|
|
{
|
|
"entropy": 5.628579902648926,
|
|
"epoch": 3.491716740607626,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003822754429072942,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.24219659566879273,
|
|
"num_tokens": 69397827.0,
|
|
"step": 31090
|
|
},
|
|
{
|
|
"entropy": 5.655579280853272,
|
|
"epoch": 3.492278317515584,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003822401495604403,
|
|
"loss": 4.9817,
|
|
"mean_token_accuracy": 0.23129326105117798,
|
|
"num_tokens": 69409268.0,
|
|
"step": 31095
|
|
},
|
|
{
|
|
"entropy": 5.6095147132873535,
|
|
"epoch": 3.4928398944235415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038220485279901855,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.2292480245232582,
|
|
"num_tokens": 69420995.0,
|
|
"step": 31100
|
|
},
|
|
{
|
|
"entropy": 5.613202619552612,
|
|
"epoch": 3.4934014713314987,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038216955262415273,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.23008969724178313,
|
|
"num_tokens": 69432919.0,
|
|
"step": 31105
|
|
},
|
|
{
|
|
"entropy": 5.614201068878174,
|
|
"epoch": 3.4939630482394564,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038213424903696673,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.22827843874692916,
|
|
"num_tokens": 69443321.0,
|
|
"step": 31110
|
|
},
|
|
{
|
|
"entropy": 5.598361492156982,
|
|
"epoch": 3.494524625147414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038209894203858477,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.231070639193058,
|
|
"num_tokens": 69454695.0,
|
|
"step": 31115
|
|
},
|
|
{
|
|
"entropy": 5.6511698246002195,
|
|
"epoch": 3.4950862020553712,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038206363163013093,
|
|
"loss": 4.9021,
|
|
"mean_token_accuracy": 0.2252427637577057,
|
|
"num_tokens": 69465617.0,
|
|
"step": 31120
|
|
},
|
|
{
|
|
"entropy": 5.569686698913574,
|
|
"epoch": 3.495647778963329,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038202831781272944,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.22769572734832763,
|
|
"num_tokens": 69476730.0,
|
|
"step": 31125
|
|
},
|
|
{
|
|
"entropy": 5.56137866973877,
|
|
"epoch": 3.4962093558712866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038199300058750494,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.22593751698732376,
|
|
"num_tokens": 69488488.0,
|
|
"step": 31130
|
|
},
|
|
{
|
|
"entropy": 5.673739099502564,
|
|
"epoch": 3.4967709327792442,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038195767995558174,
|
|
"loss": 5.0055,
|
|
"mean_token_accuracy": 0.22169163823127747,
|
|
"num_tokens": 69498718.0,
|
|
"step": 31135
|
|
},
|
|
{
|
|
"entropy": 5.649611520767212,
|
|
"epoch": 3.497332509687202,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003819223559180845,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.22568783909082413,
|
|
"num_tokens": 69509567.0,
|
|
"step": 31140
|
|
},
|
|
{
|
|
"entropy": 5.6024564743042,
|
|
"epoch": 3.497894086595159,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000381887028476138,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.2223321869969368,
|
|
"num_tokens": 69519392.0,
|
|
"step": 31145
|
|
},
|
|
{
|
|
"entropy": 5.691204833984375,
|
|
"epoch": 3.4984556635031168,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038185169763086703,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.21555382907390594,
|
|
"num_tokens": 69531228.0,
|
|
"step": 31150
|
|
},
|
|
{
|
|
"entropy": 5.701887226104736,
|
|
"epoch": 3.4990172404110744,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003818163633833966,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.22965107858181,
|
|
"num_tokens": 69542888.0,
|
|
"step": 31155
|
|
},
|
|
{
|
|
"entropy": 5.631932544708252,
|
|
"epoch": 3.4995788173190316,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038178102573485173,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.2238784283399582,
|
|
"num_tokens": 69553481.0,
|
|
"step": 31160
|
|
},
|
|
{
|
|
"entropy": 5.5904396057128904,
|
|
"epoch": 3.5001403942269893,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003817456846863575,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.22754694968461991,
|
|
"num_tokens": 69565314.0,
|
|
"step": 31165
|
|
},
|
|
{
|
|
"entropy": 5.58748197555542,
|
|
"epoch": 3.500701971134947,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038171034023903937,
|
|
"loss": 4.949,
|
|
"mean_token_accuracy": 0.217664934694767,
|
|
"num_tokens": 69575807.0,
|
|
"step": 31170
|
|
},
|
|
{
|
|
"entropy": 5.665528964996338,
|
|
"epoch": 3.5012635480429046,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003816749923940226,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.227462275326252,
|
|
"num_tokens": 69587873.0,
|
|
"step": 31175
|
|
},
|
|
{
|
|
"entropy": 5.6578452587127686,
|
|
"epoch": 3.5018251249508623,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038163964115243276,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.22025266885757447,
|
|
"num_tokens": 69598015.0,
|
|
"step": 31180
|
|
},
|
|
{
|
|
"entropy": 5.657416439056396,
|
|
"epoch": 3.5023867018588195,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038160428651539535,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.22167667150497436,
|
|
"num_tokens": 69609345.0,
|
|
"step": 31185
|
|
},
|
|
{
|
|
"entropy": 5.654294157028199,
|
|
"epoch": 3.502948278766777,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038156892848403606,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.2146736904978752,
|
|
"num_tokens": 69620075.0,
|
|
"step": 31190
|
|
},
|
|
{
|
|
"entropy": 5.657861995697021,
|
|
"epoch": 3.503509855674735,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003815335670594808,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.22726310938596725,
|
|
"num_tokens": 69630825.0,
|
|
"step": 31195
|
|
},
|
|
{
|
|
"entropy": 5.694580030441284,
|
|
"epoch": 3.504071432582692,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038149820224285546,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.2218390941619873,
|
|
"num_tokens": 69642415.0,
|
|
"step": 31200
|
|
},
|
|
{
|
|
"entropy": 5.5423377513885494,
|
|
"epoch": 3.5046330094906497,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000381462834035286,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.22709050625562668,
|
|
"num_tokens": 69652735.0,
|
|
"step": 31205
|
|
},
|
|
{
|
|
"entropy": 5.579527521133423,
|
|
"epoch": 3.5051945863986074,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003814274624378986,
|
|
"loss": 4.9557,
|
|
"mean_token_accuracy": 0.23342255353927613,
|
|
"num_tokens": 69664312.0,
|
|
"step": 31210
|
|
},
|
|
{
|
|
"entropy": 5.606108570098877,
|
|
"epoch": 3.5057561633065646,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003813920874518196,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.22566757202148438,
|
|
"num_tokens": 69674570.0,
|
|
"step": 31215
|
|
},
|
|
{
|
|
"entropy": 5.610865736007691,
|
|
"epoch": 3.5063177402145222,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003813567090781752,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.22185004204511644,
|
|
"num_tokens": 69686591.0,
|
|
"step": 31220
|
|
},
|
|
{
|
|
"entropy": 5.672500848770142,
|
|
"epoch": 3.50687931712248,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000381321327318092,
|
|
"loss": 4.9948,
|
|
"mean_token_accuracy": 0.22577270567417146,
|
|
"num_tokens": 69697104.0,
|
|
"step": 31225
|
|
},
|
|
{
|
|
"entropy": 5.643404388427735,
|
|
"epoch": 3.5074408940304376,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003812859421726964,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.22735425978899002,
|
|
"num_tokens": 69708827.0,
|
|
"step": 31230
|
|
},
|
|
{
|
|
"entropy": 5.613665914535522,
|
|
"epoch": 3.5080024709383952,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038125055364311526,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.22803750038146972,
|
|
"num_tokens": 69720426.0,
|
|
"step": 31235
|
|
},
|
|
{
|
|
"entropy": 5.749856233596802,
|
|
"epoch": 3.5085640478463525,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003812151617304753,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.21431656032800675,
|
|
"num_tokens": 69733199.0,
|
|
"step": 31240
|
|
},
|
|
{
|
|
"entropy": 5.568854808807373,
|
|
"epoch": 3.50912562475431,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003811797664359033,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.232829686999321,
|
|
"num_tokens": 69744322.0,
|
|
"step": 31245
|
|
},
|
|
{
|
|
"entropy": 5.5728717803955075,
|
|
"epoch": 3.5096872016622678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038114436776052644,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.225986048579216,
|
|
"num_tokens": 69755662.0,
|
|
"step": 31250
|
|
},
|
|
{
|
|
"entropy": 5.50123028755188,
|
|
"epoch": 3.510248778570225,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003811089657054717,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.23238087594509124,
|
|
"num_tokens": 69765663.0,
|
|
"step": 31255
|
|
},
|
|
{
|
|
"entropy": 5.614222431182862,
|
|
"epoch": 3.5108103554781827,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003810735602718664,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.2224779263138771,
|
|
"num_tokens": 69777483.0,
|
|
"step": 31260
|
|
},
|
|
{
|
|
"entropy": 5.695147848129272,
|
|
"epoch": 3.5113719323861403,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003810381514608378,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.2237599238753319,
|
|
"num_tokens": 69789034.0,
|
|
"step": 31265
|
|
},
|
|
{
|
|
"entropy": 5.675678300857544,
|
|
"epoch": 3.511933509294098,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003810027392735133,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.22305118143558503,
|
|
"num_tokens": 69801288.0,
|
|
"step": 31270
|
|
},
|
|
{
|
|
"entropy": 5.601374292373658,
|
|
"epoch": 3.5124950862020556,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003809673237110204,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.22410505563020705,
|
|
"num_tokens": 69811063.0,
|
|
"step": 31275
|
|
},
|
|
{
|
|
"entropy": 5.56068058013916,
|
|
"epoch": 3.513056663110013,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003809319047744869,
|
|
"loss": 4.9469,
|
|
"mean_token_accuracy": 0.2248974159359932,
|
|
"num_tokens": 69822572.0,
|
|
"step": 31280
|
|
},
|
|
{
|
|
"entropy": 5.500233364105225,
|
|
"epoch": 3.5136182400179705,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038089648246504045,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.23002798110246658,
|
|
"num_tokens": 69834082.0,
|
|
"step": 31285
|
|
},
|
|
{
|
|
"entropy": 5.6169336318969725,
|
|
"epoch": 3.514179816925928,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038086105678380896,
|
|
"loss": 4.942,
|
|
"mean_token_accuracy": 0.23066042959690095,
|
|
"num_tokens": 69844560.0,
|
|
"step": 31290
|
|
},
|
|
{
|
|
"entropy": 5.6110998630523685,
|
|
"epoch": 3.5147413938338854,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038082562773192026,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.22343335598707198,
|
|
"num_tokens": 69854993.0,
|
|
"step": 31295
|
|
},
|
|
{
|
|
"entropy": 5.59699559211731,
|
|
"epoch": 3.515302970741843,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038079019531050257,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.22892549633979797,
|
|
"num_tokens": 69866074.0,
|
|
"step": 31300
|
|
},
|
|
{
|
|
"entropy": 5.636641263961792,
|
|
"epoch": 3.5158645476498007,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038075475952068405,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.2182900130748749,
|
|
"num_tokens": 69877101.0,
|
|
"step": 31305
|
|
},
|
|
{
|
|
"entropy": 5.508067893981933,
|
|
"epoch": 3.516426124557758,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000380719320363593,
|
|
"loss": 4.868,
|
|
"mean_token_accuracy": 0.23586657792329788,
|
|
"num_tokens": 69887388.0,
|
|
"step": 31310
|
|
},
|
|
{
|
|
"entropy": 5.655311727523804,
|
|
"epoch": 3.5169877014657156,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038068387784035774,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.22361396998167038,
|
|
"num_tokens": 69898242.0,
|
|
"step": 31315
|
|
},
|
|
{
|
|
"entropy": 5.644119215011597,
|
|
"epoch": 3.5175492783736733,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003806484319521069,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.22629733234643937,
|
|
"num_tokens": 69909645.0,
|
|
"step": 31320
|
|
},
|
|
{
|
|
"entropy": 5.635271978378296,
|
|
"epoch": 3.518110855281631,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038061298269996893,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.22579518854618072,
|
|
"num_tokens": 69920862.0,
|
|
"step": 31325
|
|
},
|
|
{
|
|
"entropy": 5.623143196105957,
|
|
"epoch": 3.5186724321895886,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003805775300850727,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.23157859295606614,
|
|
"num_tokens": 69932219.0,
|
|
"step": 31330
|
|
},
|
|
{
|
|
"entropy": 5.657098722457886,
|
|
"epoch": 3.519234009097546,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003805420741085469,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.22814429253339769,
|
|
"num_tokens": 69942642.0,
|
|
"step": 31335
|
|
},
|
|
{
|
|
"entropy": 5.698792314529419,
|
|
"epoch": 3.5197955860055035,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003805066147715205,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.20751005113124849,
|
|
"num_tokens": 69954336.0,
|
|
"step": 31340
|
|
},
|
|
{
|
|
"entropy": 5.63145694732666,
|
|
"epoch": 3.520357162913461,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003804711520751226,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.22586465775966644,
|
|
"num_tokens": 69965716.0,
|
|
"step": 31345
|
|
},
|
|
{
|
|
"entropy": 5.59663143157959,
|
|
"epoch": 3.5209187398214183,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038043568602048227,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.2196234792470932,
|
|
"num_tokens": 69976545.0,
|
|
"step": 31350
|
|
},
|
|
{
|
|
"entropy": 5.639213275909424,
|
|
"epoch": 3.521480316729376,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003804002166087289,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.22634847462177277,
|
|
"num_tokens": 69987846.0,
|
|
"step": 31355
|
|
},
|
|
{
|
|
"entropy": 5.637618970870972,
|
|
"epoch": 3.5220418936373337,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038036474384099174,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.22938409596681594,
|
|
"num_tokens": 69998089.0,
|
|
"step": 31360
|
|
},
|
|
{
|
|
"entropy": 5.654968786239624,
|
|
"epoch": 3.5226034705452913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003803292677184002,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.22037222981452942,
|
|
"num_tokens": 70008900.0,
|
|
"step": 31365
|
|
},
|
|
{
|
|
"entropy": 5.673267650604248,
|
|
"epoch": 3.523165047453249,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038029378824208394,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.22584838271141053,
|
|
"num_tokens": 70019675.0,
|
|
"step": 31370
|
|
},
|
|
{
|
|
"entropy": 5.6810691356658936,
|
|
"epoch": 3.523726624361206,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003802583054131727,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.22074116468429567,
|
|
"num_tokens": 70031077.0,
|
|
"step": 31375
|
|
},
|
|
{
|
|
"entropy": 5.6620643615722654,
|
|
"epoch": 3.524288201269164,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003802228192327961,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.2130663961172104,
|
|
"num_tokens": 70044569.0,
|
|
"step": 31380
|
|
},
|
|
{
|
|
"entropy": 5.647518253326416,
|
|
"epoch": 3.5248497781771215,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038018732970208414,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.2318346083164215,
|
|
"num_tokens": 70056396.0,
|
|
"step": 31385
|
|
},
|
|
{
|
|
"entropy": 5.7231690883636475,
|
|
"epoch": 3.5254113550850787,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003801518368221668,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.2182469353079796,
|
|
"num_tokens": 70068341.0,
|
|
"step": 31390
|
|
},
|
|
{
|
|
"entropy": 5.585336017608642,
|
|
"epoch": 3.5259729319930364,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003801163405941743,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.22950218468904496,
|
|
"num_tokens": 70079069.0,
|
|
"step": 31395
|
|
},
|
|
{
|
|
"entropy": 5.676183986663818,
|
|
"epoch": 3.526534508900994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038008084101923665,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.2192911222577095,
|
|
"num_tokens": 70090274.0,
|
|
"step": 31400
|
|
},
|
|
{
|
|
"entropy": 5.577758169174194,
|
|
"epoch": 3.5270960858089513,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038004533809848435,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.2216128945350647,
|
|
"num_tokens": 70101144.0,
|
|
"step": 31405
|
|
},
|
|
{
|
|
"entropy": 5.609874200820923,
|
|
"epoch": 3.527657662716909,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038000983183304765,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.22463015019893645,
|
|
"num_tokens": 70112210.0,
|
|
"step": 31410
|
|
},
|
|
{
|
|
"entropy": 5.700867700576782,
|
|
"epoch": 3.5282192396248666,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003799743222240572,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.22109546214342118,
|
|
"num_tokens": 70124302.0,
|
|
"step": 31415
|
|
},
|
|
{
|
|
"entropy": 5.698978328704834,
|
|
"epoch": 3.5287808165328243,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003799388092726436,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.227472747862339,
|
|
"num_tokens": 70136026.0,
|
|
"step": 31420
|
|
},
|
|
{
|
|
"entropy": 5.673033618927002,
|
|
"epoch": 3.529342393440782,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037990329297993763,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.2238374650478363,
|
|
"num_tokens": 70147439.0,
|
|
"step": 31425
|
|
},
|
|
{
|
|
"entropy": 5.541409969329834,
|
|
"epoch": 3.529903970348739,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003798677733470701,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.23745138794183732,
|
|
"num_tokens": 70158367.0,
|
|
"step": 31430
|
|
},
|
|
{
|
|
"entropy": 5.630693149566651,
|
|
"epoch": 3.530465547256697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037983225037517207,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21869808733463286,
|
|
"num_tokens": 70169226.0,
|
|
"step": 31435
|
|
},
|
|
{
|
|
"entropy": 5.648898267745972,
|
|
"epoch": 3.5310271241646545,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037979672406537445,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.2266835778951645,
|
|
"num_tokens": 70179440.0,
|
|
"step": 31440
|
|
},
|
|
{
|
|
"entropy": 5.639286279678345,
|
|
"epoch": 3.5315887010726117,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003797611944188086,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.22010063678026198,
|
|
"num_tokens": 70191160.0,
|
|
"step": 31445
|
|
},
|
|
{
|
|
"entropy": 5.64278769493103,
|
|
"epoch": 3.5321502779805694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037972566143660566,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.22181763947010041,
|
|
"num_tokens": 70202143.0,
|
|
"step": 31450
|
|
},
|
|
{
|
|
"entropy": 5.636749219894409,
|
|
"epoch": 3.532711854888527,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003796901251198969,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.22537980377674102,
|
|
"num_tokens": 70213957.0,
|
|
"step": 31455
|
|
},
|
|
{
|
|
"entropy": 5.647455501556396,
|
|
"epoch": 3.5332734317964847,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000379654585469814,
|
|
"loss": 4.9639,
|
|
"mean_token_accuracy": 0.2263486474752426,
|
|
"num_tokens": 70224153.0,
|
|
"step": 31460
|
|
},
|
|
{
|
|
"entropy": 5.612217998504638,
|
|
"epoch": 3.5338350087044423,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003796190424874886,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.21861798018217088,
|
|
"num_tokens": 70236093.0,
|
|
"step": 31465
|
|
},
|
|
{
|
|
"entropy": 5.610202503204346,
|
|
"epoch": 3.5343965856123996,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003795834961740523,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.22009911239147187,
|
|
"num_tokens": 70246865.0,
|
|
"step": 31470
|
|
},
|
|
{
|
|
"entropy": 5.63806529045105,
|
|
"epoch": 3.534958162520357,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037954794653063695,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.21626954823732375,
|
|
"num_tokens": 70258601.0,
|
|
"step": 31475
|
|
},
|
|
{
|
|
"entropy": 5.62465124130249,
|
|
"epoch": 3.535519739428315,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003795123935583743,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.22178590297698975,
|
|
"num_tokens": 70269020.0,
|
|
"step": 31480
|
|
},
|
|
{
|
|
"entropy": 5.655442476272583,
|
|
"epoch": 3.536081316336272,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003794768372583966,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.21959098428487778,
|
|
"num_tokens": 70280582.0,
|
|
"step": 31485
|
|
},
|
|
{
|
|
"entropy": 5.759591770172119,
|
|
"epoch": 3.5366428932442298,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037944127763183587,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.22675618827342986,
|
|
"num_tokens": 70292848.0,
|
|
"step": 31490
|
|
},
|
|
{
|
|
"entropy": 5.72399320602417,
|
|
"epoch": 3.5372044701521874,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037940571467982436,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.22367611676454544,
|
|
"num_tokens": 70304892.0,
|
|
"step": 31495
|
|
},
|
|
{
|
|
"entropy": 5.552187061309814,
|
|
"epoch": 3.5377660470601446,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003793701484034944,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.2322118878364563,
|
|
"num_tokens": 70316244.0,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"entropy": 5.6397380352020265,
|
|
"epoch": 3.5383276239681023,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037933457880397843,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.22456417679786683,
|
|
"num_tokens": 70327037.0,
|
|
"step": 31505
|
|
},
|
|
{
|
|
"entropy": 5.603342342376709,
|
|
"epoch": 3.53888920087606,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037929900588240897,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.23175566792488098,
|
|
"num_tokens": 70338587.0,
|
|
"step": 31510
|
|
},
|
|
{
|
|
"entropy": 5.559327793121338,
|
|
"epoch": 3.5394507777840176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003792634296399187,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.22451532483100892,
|
|
"num_tokens": 70349930.0,
|
|
"step": 31515
|
|
},
|
|
{
|
|
"entropy": 5.498275327682495,
|
|
"epoch": 3.5400123546919753,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037922785007764043,
|
|
"loss": 4.8309,
|
|
"mean_token_accuracy": 0.23178461492061614,
|
|
"num_tokens": 70360880.0,
|
|
"step": 31520
|
|
},
|
|
{
|
|
"entropy": 5.725407695770263,
|
|
"epoch": 3.5405739315999325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000379192267196707,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.21918500661849977,
|
|
"num_tokens": 70372508.0,
|
|
"step": 31525
|
|
},
|
|
{
|
|
"entropy": 5.662397766113282,
|
|
"epoch": 3.54113550850789,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037915668099825135,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.22409658282995223,
|
|
"num_tokens": 70383960.0,
|
|
"step": 31530
|
|
},
|
|
{
|
|
"entropy": 5.668739080429077,
|
|
"epoch": 3.541697085415848,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037912109148340663,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.22442958652973174,
|
|
"num_tokens": 70395881.0,
|
|
"step": 31535
|
|
},
|
|
{
|
|
"entropy": 5.653093576431274,
|
|
"epoch": 3.542258662323805,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037908549865330596,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.22145021557807923,
|
|
"num_tokens": 70407590.0,
|
|
"step": 31540
|
|
},
|
|
{
|
|
"entropy": 5.659515810012818,
|
|
"epoch": 3.5428202392317627,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037904990250908256,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.23649535477161407,
|
|
"num_tokens": 70418078.0,
|
|
"step": 31545
|
|
},
|
|
{
|
|
"entropy": 5.599126195907592,
|
|
"epoch": 3.5433818161397204,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037901430305187,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.2220785915851593,
|
|
"num_tokens": 70428292.0,
|
|
"step": 31550
|
|
},
|
|
{
|
|
"entropy": 5.546735620498657,
|
|
"epoch": 3.543943393047678,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037897870028280167,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.23098516315221787,
|
|
"num_tokens": 70438481.0,
|
|
"step": 31555
|
|
},
|
|
{
|
|
"entropy": 5.612603282928466,
|
|
"epoch": 3.5445049699556357,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003789430942030112,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.21826253235340118,
|
|
"num_tokens": 70449949.0,
|
|
"step": 31560
|
|
},
|
|
{
|
|
"entropy": 5.720025491714478,
|
|
"epoch": 3.545066546863593,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037890748481363216,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.22329754680395125,
|
|
"num_tokens": 70461159.0,
|
|
"step": 31565
|
|
},
|
|
{
|
|
"entropy": 5.635644912719727,
|
|
"epoch": 3.5456281237715506,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003788718721157987,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.2289634808897972,
|
|
"num_tokens": 70471212.0,
|
|
"step": 31570
|
|
},
|
|
{
|
|
"entropy": 5.617584848403931,
|
|
"epoch": 3.5461897006795082,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003788362561106445,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.2283087819814682,
|
|
"num_tokens": 70481587.0,
|
|
"step": 31575
|
|
},
|
|
{
|
|
"entropy": 5.69949893951416,
|
|
"epoch": 3.5467512775874654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037880063679930355,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.22097103744745256,
|
|
"num_tokens": 70491952.0,
|
|
"step": 31580
|
|
},
|
|
{
|
|
"entropy": 5.647241258621216,
|
|
"epoch": 3.547312854495423,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037876501418291015,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.22080730646848679,
|
|
"num_tokens": 70503279.0,
|
|
"step": 31585
|
|
},
|
|
{
|
|
"entropy": 5.602861547470093,
|
|
"epoch": 3.5478744314033808,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003787293882625984,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.2241335019469261,
|
|
"num_tokens": 70514779.0,
|
|
"step": 31590
|
|
},
|
|
{
|
|
"entropy": 5.588173294067383,
|
|
"epoch": 3.548436008311338,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003786937590395027,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.22702885568141937,
|
|
"num_tokens": 70526478.0,
|
|
"step": 31595
|
|
},
|
|
{
|
|
"entropy": 5.605623197555542,
|
|
"epoch": 3.5489975852192956,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003786581265147575,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.21664549708366393,
|
|
"num_tokens": 70537293.0,
|
|
"step": 31600
|
|
},
|
|
{
|
|
"entropy": 5.679314041137696,
|
|
"epoch": 3.5495591621272533,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003786224906894974,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.22727784067392348,
|
|
"num_tokens": 70547357.0,
|
|
"step": 31605
|
|
},
|
|
{
|
|
"entropy": 5.630980014801025,
|
|
"epoch": 3.550120739035211,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000378586851564857,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.21864532828330993,
|
|
"num_tokens": 70558102.0,
|
|
"step": 31610
|
|
},
|
|
{
|
|
"entropy": 5.686899614334107,
|
|
"epoch": 3.5506823159431686,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000378551209141971,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.22910067588090896,
|
|
"num_tokens": 70569454.0,
|
|
"step": 31615
|
|
},
|
|
{
|
|
"entropy": 5.648395156860351,
|
|
"epoch": 3.551243892851126,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003785155634219744,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.22203535586595535,
|
|
"num_tokens": 70580590.0,
|
|
"step": 31620
|
|
},
|
|
{
|
|
"entropy": 5.566197061538697,
|
|
"epoch": 3.5518054697590835,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003784799144060021,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.22596345990896224,
|
|
"num_tokens": 70591233.0,
|
|
"step": 31625
|
|
},
|
|
{
|
|
"entropy": 5.6287181854248045,
|
|
"epoch": 3.552367046667041,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037844426209518916,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.23009438961744308,
|
|
"num_tokens": 70603029.0,
|
|
"step": 31630
|
|
},
|
|
{
|
|
"entropy": 5.743393278121948,
|
|
"epoch": 3.5529286235749984,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037840860649067084,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.21827963143587112,
|
|
"num_tokens": 70616021.0,
|
|
"step": 31635
|
|
},
|
|
{
|
|
"entropy": 5.664538908004761,
|
|
"epoch": 3.553490200482956,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037837294759358235,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.23274715542793273,
|
|
"num_tokens": 70627044.0,
|
|
"step": 31640
|
|
},
|
|
{
|
|
"entropy": 5.545947265625,
|
|
"epoch": 3.5540517773909137,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037833728540505914,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.2257361888885498,
|
|
"num_tokens": 70637435.0,
|
|
"step": 31645
|
|
},
|
|
{
|
|
"entropy": 5.637209558486939,
|
|
"epoch": 3.5546133542988714,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003783016199262367,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.22246545255184175,
|
|
"num_tokens": 70648106.0,
|
|
"step": 31650
|
|
},
|
|
{
|
|
"entropy": 5.612761449813843,
|
|
"epoch": 3.555174931206829,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003782659511582505,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.22612168341875077,
|
|
"num_tokens": 70661242.0,
|
|
"step": 31655
|
|
},
|
|
{
|
|
"entropy": 5.6149749755859375,
|
|
"epoch": 3.5557365081147863,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003782302791022365,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.2216070145368576,
|
|
"num_tokens": 70672758.0,
|
|
"step": 31660
|
|
},
|
|
{
|
|
"entropy": 5.684432411193848,
|
|
"epoch": 3.556298085022744,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037819460375933034,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.22075514048337935,
|
|
"num_tokens": 70683365.0,
|
|
"step": 31665
|
|
},
|
|
{
|
|
"entropy": 5.554342269897461,
|
|
"epoch": 3.5568596619307016,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003781589251306679,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.23156138509511948,
|
|
"num_tokens": 70693984.0,
|
|
"step": 31670
|
|
},
|
|
{
|
|
"entropy": 5.615491056442261,
|
|
"epoch": 3.557421238838659,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003781232432173853,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.21688568890094756,
|
|
"num_tokens": 70704748.0,
|
|
"step": 31675
|
|
},
|
|
{
|
|
"entropy": 5.570781230926514,
|
|
"epoch": 3.5579828157466165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037808755802061874,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.2260505199432373,
|
|
"num_tokens": 70715415.0,
|
|
"step": 31680
|
|
},
|
|
{
|
|
"entropy": 5.592070913314819,
|
|
"epoch": 3.558544392654574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003780518695415043,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.22834405899047852,
|
|
"num_tokens": 70726646.0,
|
|
"step": 31685
|
|
},
|
|
{
|
|
"entropy": 5.722567701339722,
|
|
"epoch": 3.5591059695625313,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037801617778117835,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.2118683338165283,
|
|
"num_tokens": 70737515.0,
|
|
"step": 31690
|
|
},
|
|
{
|
|
"entropy": 5.696927452087403,
|
|
"epoch": 3.559667546470489,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037798048274077735,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.22345094829797746,
|
|
"num_tokens": 70747751.0,
|
|
"step": 31695
|
|
},
|
|
{
|
|
"entropy": 5.665301418304443,
|
|
"epoch": 3.5602291233784467,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037794478442143786,
|
|
"loss": 4.8977,
|
|
"mean_token_accuracy": 0.23268759548664092,
|
|
"num_tokens": 70757951.0,
|
|
"step": 31700
|
|
},
|
|
{
|
|
"entropy": 5.626680850982666,
|
|
"epoch": 3.5607907002864043,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037790908282429647,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.20994700640439987,
|
|
"num_tokens": 70769515.0,
|
|
"step": 31705
|
|
},
|
|
{
|
|
"entropy": 5.61968412399292,
|
|
"epoch": 3.561352277194362,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037787337795049,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.2249227285385132,
|
|
"num_tokens": 70780567.0,
|
|
"step": 31710
|
|
},
|
|
{
|
|
"entropy": 5.665572690963745,
|
|
"epoch": 3.561913854102319,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037783766980115525,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.22257055789232255,
|
|
"num_tokens": 70793250.0,
|
|
"step": 31715
|
|
},
|
|
{
|
|
"entropy": 5.7308351516723635,
|
|
"epoch": 3.562475431010277,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037780195837742927,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.22264975905418397,
|
|
"num_tokens": 70804579.0,
|
|
"step": 31720
|
|
},
|
|
{
|
|
"entropy": 5.637225389480591,
|
|
"epoch": 3.5630370079182345,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037776624368044895,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.224591201543808,
|
|
"num_tokens": 70815931.0,
|
|
"step": 31725
|
|
},
|
|
{
|
|
"entropy": 5.699103450775146,
|
|
"epoch": 3.5635985848261917,
|
|
"grad_norm": 6.0,
|
|
"learning_rate": 0.00037773052571135157,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21815710067749022,
|
|
"num_tokens": 70828058.0,
|
|
"step": 31730
|
|
},
|
|
{
|
|
"entropy": 5.675920486450195,
|
|
"epoch": 3.5641601617341494,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003776948044712745,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.22197217494249344,
|
|
"num_tokens": 70838177.0,
|
|
"step": 31735
|
|
},
|
|
{
|
|
"entropy": 5.627750539779663,
|
|
"epoch": 3.564721738642107,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000377659079961355,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.22289901077747346,
|
|
"num_tokens": 70849888.0,
|
|
"step": 31740
|
|
},
|
|
{
|
|
"entropy": 5.6300136089324955,
|
|
"epoch": 3.5652833155500647,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037762335218273057,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.22686788737773894,
|
|
"num_tokens": 70859754.0,
|
|
"step": 31745
|
|
},
|
|
{
|
|
"entropy": 5.6864378452301025,
|
|
"epoch": 3.5658448924580224,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003775876211365388,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.2203614741563797,
|
|
"num_tokens": 70870166.0,
|
|
"step": 31750
|
|
},
|
|
{
|
|
"entropy": 5.66638150215149,
|
|
"epoch": 3.5664064693659796,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003775518868239174,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.2264384463429451,
|
|
"num_tokens": 70882204.0,
|
|
"step": 31755
|
|
},
|
|
{
|
|
"entropy": 5.546868419647216,
|
|
"epoch": 3.5669680462739373,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037751614924600417,
|
|
"loss": 4.977,
|
|
"mean_token_accuracy": 0.22235599607229234,
|
|
"num_tokens": 70894317.0,
|
|
"step": 31760
|
|
},
|
|
{
|
|
"entropy": 5.647011232376099,
|
|
"epoch": 3.567529623181895,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000377480408403937,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.2258722484111786,
|
|
"num_tokens": 70906224.0,
|
|
"step": 31765
|
|
},
|
|
{
|
|
"entropy": 5.706483364105225,
|
|
"epoch": 3.568091200089852,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003774446642988538,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.2183710366487503,
|
|
"num_tokens": 70918134.0,
|
|
"step": 31770
|
|
},
|
|
{
|
|
"entropy": 5.606899213790894,
|
|
"epoch": 3.56865277699781,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037740891693189286,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.22141058444976808,
|
|
"num_tokens": 70929695.0,
|
|
"step": 31775
|
|
},
|
|
{
|
|
"entropy": 5.672659397125244,
|
|
"epoch": 3.5692143539057675,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003773731663041922,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.21426038146018983,
|
|
"num_tokens": 70941204.0,
|
|
"step": 31780
|
|
},
|
|
{
|
|
"entropy": 5.658635568618775,
|
|
"epoch": 3.5697759308137247,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037733741241689024,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.22983028888702392,
|
|
"num_tokens": 70953221.0,
|
|
"step": 31785
|
|
},
|
|
{
|
|
"entropy": 5.665912246704101,
|
|
"epoch": 3.5703375077216823,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003773016552711254,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.22406790107488633,
|
|
"num_tokens": 70967081.0,
|
|
"step": 31790
|
|
},
|
|
{
|
|
"entropy": 5.629627370834351,
|
|
"epoch": 3.57089908462964,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037726589486803617,
|
|
"loss": 4.902,
|
|
"mean_token_accuracy": 0.22792659997940062,
|
|
"num_tokens": 70977911.0,
|
|
"step": 31795
|
|
},
|
|
{
|
|
"entropy": 5.66916790008545,
|
|
"epoch": 3.5714606615375977,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037723013120876113,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.2302204579114914,
|
|
"num_tokens": 70989001.0,
|
|
"step": 31800
|
|
},
|
|
{
|
|
"entropy": 5.6544427394866945,
|
|
"epoch": 3.5720222384455553,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037719436429443915,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.2145455777645111,
|
|
"num_tokens": 70999698.0,
|
|
"step": 31805
|
|
},
|
|
{
|
|
"entropy": 5.502149295806885,
|
|
"epoch": 3.5725838153535125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037715859412620895,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.23257288634777068,
|
|
"num_tokens": 71010490.0,
|
|
"step": 31810
|
|
},
|
|
{
|
|
"entropy": 5.637456750869751,
|
|
"epoch": 3.57314539226147,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003771228207052095,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.22969030737876892,
|
|
"num_tokens": 71021581.0,
|
|
"step": 31815
|
|
},
|
|
{
|
|
"entropy": 5.66823148727417,
|
|
"epoch": 3.573706969169428,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037708704403257974,
|
|
"loss": 5.023,
|
|
"mean_token_accuracy": 0.2194521725177765,
|
|
"num_tokens": 71033215.0,
|
|
"step": 31820
|
|
},
|
|
{
|
|
"entropy": 5.607202005386353,
|
|
"epoch": 3.574268546077385,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000377051264109459,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.2345375433564186,
|
|
"num_tokens": 71043484.0,
|
|
"step": 31825
|
|
},
|
|
{
|
|
"entropy": 5.611562442779541,
|
|
"epoch": 3.5748301229853428,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003770154809369864,
|
|
"loss": 4.9466,
|
|
"mean_token_accuracy": 0.22975120991468428,
|
|
"num_tokens": 71054101.0,
|
|
"step": 31830
|
|
},
|
|
{
|
|
"entropy": 5.616995477676392,
|
|
"epoch": 3.5753916998933004,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037697969451630135,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21738362014293672,
|
|
"num_tokens": 71065543.0,
|
|
"step": 31835
|
|
},
|
|
{
|
|
"entropy": 5.551387643814087,
|
|
"epoch": 3.575953276801258,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037694390484854323,
|
|
"loss": 4.8763,
|
|
"mean_token_accuracy": 0.2243826150894165,
|
|
"num_tokens": 71076450.0,
|
|
"step": 31840
|
|
},
|
|
{
|
|
"entropy": 5.525101518630981,
|
|
"epoch": 3.5765148537092157,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003769081119348517,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.22952517718076706,
|
|
"num_tokens": 71087625.0,
|
|
"step": 31845
|
|
},
|
|
{
|
|
"entropy": 5.609103345870972,
|
|
"epoch": 3.577076430617173,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037687231577636626,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.2200160026550293,
|
|
"num_tokens": 71098205.0,
|
|
"step": 31850
|
|
},
|
|
{
|
|
"entropy": 5.663154554367066,
|
|
"epoch": 3.5776380075251306,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003768365163742269,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.2242387905716896,
|
|
"num_tokens": 71109207.0,
|
|
"step": 31855
|
|
},
|
|
{
|
|
"entropy": 5.657281303405762,
|
|
"epoch": 3.5781995844330883,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037680071372957327,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.22485006004571914,
|
|
"num_tokens": 71120911.0,
|
|
"step": 31860
|
|
},
|
|
{
|
|
"entropy": 5.70773549079895,
|
|
"epoch": 3.5787611613410455,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037676490784354543,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.21718370765447617,
|
|
"num_tokens": 71131398.0,
|
|
"step": 31865
|
|
},
|
|
{
|
|
"entropy": 5.637452411651611,
|
|
"epoch": 3.579322738249003,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003767290987172835,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.22084566503763198,
|
|
"num_tokens": 71142574.0,
|
|
"step": 31870
|
|
},
|
|
{
|
|
"entropy": 5.679655742645264,
|
|
"epoch": 3.579884315156961,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037669328635192757,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.21779332160949708,
|
|
"num_tokens": 71154624.0,
|
|
"step": 31875
|
|
},
|
|
{
|
|
"entropy": 5.623010206222534,
|
|
"epoch": 3.580445892064918,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000376657470748618,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.2234095513820648,
|
|
"num_tokens": 71165375.0,
|
|
"step": 31880
|
|
},
|
|
{
|
|
"entropy": 5.60014500617981,
|
|
"epoch": 3.5810074689728757,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003766216519084952,
|
|
"loss": 4.9116,
|
|
"mean_token_accuracy": 0.2324896588921547,
|
|
"num_tokens": 71175835.0,
|
|
"step": 31885
|
|
},
|
|
{
|
|
"entropy": 5.650705862045288,
|
|
"epoch": 3.5815690458808334,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003765858298326994,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.2242887258529663,
|
|
"num_tokens": 71187173.0,
|
|
"step": 31890
|
|
},
|
|
{
|
|
"entropy": 5.663408279418945,
|
|
"epoch": 3.582130622788791,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037655000452237154,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.22363545298576354,
|
|
"num_tokens": 71198424.0,
|
|
"step": 31895
|
|
},
|
|
{
|
|
"entropy": 5.687660026550293,
|
|
"epoch": 3.5826921996967487,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003765141759786521,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.21929849833250045,
|
|
"num_tokens": 71210198.0,
|
|
"step": 31900
|
|
},
|
|
{
|
|
"entropy": 5.7059197425842285,
|
|
"epoch": 3.583253776604706,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037647834420268195,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.2187896877527237,
|
|
"num_tokens": 71221367.0,
|
|
"step": 31905
|
|
},
|
|
{
|
|
"entropy": 5.6891844272613525,
|
|
"epoch": 3.5838153535126636,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003764425091956019,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.2270234242081642,
|
|
"num_tokens": 71232413.0,
|
|
"step": 31910
|
|
},
|
|
{
|
|
"entropy": 5.675504684448242,
|
|
"epoch": 3.584376930420621,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037640667095855307,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.2264344573020935,
|
|
"num_tokens": 71244219.0,
|
|
"step": 31915
|
|
},
|
|
{
|
|
"entropy": 5.575151634216309,
|
|
"epoch": 3.5849385073285784,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037637082949267654,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.23117761462926864,
|
|
"num_tokens": 71254452.0,
|
|
"step": 31920
|
|
},
|
|
{
|
|
"entropy": 5.599797105789184,
|
|
"epoch": 3.585500084236536,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003763349847991134,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.2242630124092102,
|
|
"num_tokens": 71265267.0,
|
|
"step": 31925
|
|
},
|
|
{
|
|
"entropy": 5.6813407897949215,
|
|
"epoch": 3.5860616611444938,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000376299136879005,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.22197057902812958,
|
|
"num_tokens": 71277334.0,
|
|
"step": 31930
|
|
},
|
|
{
|
|
"entropy": 5.641323471069336,
|
|
"epoch": 3.5866232380524514,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037626328573349296,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.22803751975297928,
|
|
"num_tokens": 71289159.0,
|
|
"step": 31935
|
|
},
|
|
{
|
|
"entropy": 5.608326959609985,
|
|
"epoch": 3.587184814960409,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003762274313637185,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.2246939480304718,
|
|
"num_tokens": 71300715.0,
|
|
"step": 31940
|
|
},
|
|
{
|
|
"entropy": 5.675917625427246,
|
|
"epoch": 3.5877463918683663,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003761915737708234,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.2255197748541832,
|
|
"num_tokens": 71310948.0,
|
|
"step": 31945
|
|
},
|
|
{
|
|
"entropy": 5.678419065475464,
|
|
"epoch": 3.588307968776324,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037615571295594936,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.21589415967464448,
|
|
"num_tokens": 71321958.0,
|
|
"step": 31950
|
|
},
|
|
{
|
|
"entropy": 5.66158618927002,
|
|
"epoch": 3.5888695456842816,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003761198489202382,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.22316820919513702,
|
|
"num_tokens": 71332522.0,
|
|
"step": 31955
|
|
},
|
|
{
|
|
"entropy": 5.686416721343994,
|
|
"epoch": 3.589431122592239,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003760839816648317,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.22512120008468628,
|
|
"num_tokens": 71344198.0,
|
|
"step": 31960
|
|
},
|
|
{
|
|
"entropy": 5.652038812637329,
|
|
"epoch": 3.5899926995001965,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037604811119087213,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.22866291105747222,
|
|
"num_tokens": 71355094.0,
|
|
"step": 31965
|
|
},
|
|
{
|
|
"entropy": 5.716411018371582,
|
|
"epoch": 3.590554276408154,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003760122374995015,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.21951820850372314,
|
|
"num_tokens": 71366596.0,
|
|
"step": 31970
|
|
},
|
|
{
|
|
"entropy": 5.6650690078735355,
|
|
"epoch": 3.5911158533161114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003759763605918621,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.22824607640504838,
|
|
"num_tokens": 71377607.0,
|
|
"step": 31975
|
|
},
|
|
{
|
|
"entropy": 5.584506511688232,
|
|
"epoch": 3.591677430224069,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037594048046909616,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.22510623335838317,
|
|
"num_tokens": 71388815.0,
|
|
"step": 31980
|
|
},
|
|
{
|
|
"entropy": 5.547568655014038,
|
|
"epoch": 3.5922390071320267,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003759045971323462,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.2227137416601181,
|
|
"num_tokens": 71399600.0,
|
|
"step": 31985
|
|
},
|
|
{
|
|
"entropy": 5.657013750076294,
|
|
"epoch": 3.5928005840399844,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037586871058275476,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.22520325630903243,
|
|
"num_tokens": 71410652.0,
|
|
"step": 31990
|
|
},
|
|
{
|
|
"entropy": 5.619948816299439,
|
|
"epoch": 3.593362160947942,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037583282082146434,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.2237699508666992,
|
|
"num_tokens": 71422656.0,
|
|
"step": 31995
|
|
},
|
|
{
|
|
"entropy": 5.587637281417846,
|
|
"epoch": 3.5939237378558992,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037579692784961785,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.22515411525964737,
|
|
"num_tokens": 71433677.0,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"entropy": 5.639114046096802,
|
|
"epoch": 3.594485314763857,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003757610316683581,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.22129118591547012,
|
|
"num_tokens": 71445922.0,
|
|
"step": 32005
|
|
},
|
|
{
|
|
"entropy": 5.638833618164062,
|
|
"epoch": 3.5950468916718146,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037572513227882807,
|
|
"loss": 4.9398,
|
|
"mean_token_accuracy": 0.2250586748123169,
|
|
"num_tokens": 71457317.0,
|
|
"step": 32010
|
|
},
|
|
{
|
|
"entropy": 5.528602409362793,
|
|
"epoch": 3.595608468579772,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037568922968217065,
|
|
"loss": 4.8989,
|
|
"mean_token_accuracy": 0.22770118862390518,
|
|
"num_tokens": 71468622.0,
|
|
"step": 32015
|
|
},
|
|
{
|
|
"entropy": 5.617005825042725,
|
|
"epoch": 3.5961700454877294,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037565332387952914,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.22692597955465316,
|
|
"num_tokens": 71479254.0,
|
|
"step": 32020
|
|
},
|
|
{
|
|
"entropy": 5.595414447784424,
|
|
"epoch": 3.596731622395687,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037561741487204684,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.22645918577909468,
|
|
"num_tokens": 71489694.0,
|
|
"step": 32025
|
|
},
|
|
{
|
|
"entropy": 5.747386121749878,
|
|
"epoch": 3.5972931993036448,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003755815026608669,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.22176314443349837,
|
|
"num_tokens": 71499983.0,
|
|
"step": 32030
|
|
},
|
|
{
|
|
"entropy": 5.628602838516235,
|
|
"epoch": 3.5978547762116024,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037554558724713305,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.23047693222761154,
|
|
"num_tokens": 71511628.0,
|
|
"step": 32035
|
|
},
|
|
{
|
|
"entropy": 5.750687313079834,
|
|
"epoch": 3.5984163531195597,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003755096686319886,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.2148526817560196,
|
|
"num_tokens": 71524432.0,
|
|
"step": 32040
|
|
},
|
|
{
|
|
"entropy": 5.668411159515381,
|
|
"epoch": 3.5989779300275173,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037547374681657736,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.2269458681344986,
|
|
"num_tokens": 71534858.0,
|
|
"step": 32045
|
|
},
|
|
{
|
|
"entropy": 5.648424530029297,
|
|
"epoch": 3.599539506935475,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037543782180204303,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.22482149302959442,
|
|
"num_tokens": 71547028.0,
|
|
"step": 32050
|
|
},
|
|
{
|
|
"entropy": 5.671810340881348,
|
|
"epoch": 3.600101083843432,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037540189358952955,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.22024428397417067,
|
|
"num_tokens": 71557477.0,
|
|
"step": 32055
|
|
},
|
|
{
|
|
"entropy": 5.658054685592651,
|
|
"epoch": 3.60066266075139,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003753659621801808,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.2246359944343567,
|
|
"num_tokens": 71568568.0,
|
|
"step": 32060
|
|
},
|
|
{
|
|
"entropy": 5.657204103469849,
|
|
"epoch": 3.6012242376593475,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037533002757514095,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.22897179573774337,
|
|
"num_tokens": 71579143.0,
|
|
"step": 32065
|
|
},
|
|
{
|
|
"entropy": 5.632509183883667,
|
|
"epoch": 3.6017858145673047,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000375294089775554,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.22937324792146682,
|
|
"num_tokens": 71590674.0,
|
|
"step": 32070
|
|
},
|
|
{
|
|
"entropy": 5.629206228256225,
|
|
"epoch": 3.6023473914752624,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003752581487825644,
|
|
"loss": 4.9835,
|
|
"mean_token_accuracy": 0.22855179756879807,
|
|
"num_tokens": 71602133.0,
|
|
"step": 32075
|
|
},
|
|
{
|
|
"entropy": 5.607820177078247,
|
|
"epoch": 3.60290896838322,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037522220459731644,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.22317721992731093,
|
|
"num_tokens": 71613735.0,
|
|
"step": 32080
|
|
},
|
|
{
|
|
"entropy": 5.671595287322998,
|
|
"epoch": 3.6034705452911777,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003751862572209546,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.22520669400691987,
|
|
"num_tokens": 71625553.0,
|
|
"step": 32085
|
|
},
|
|
{
|
|
"entropy": 5.531903409957886,
|
|
"epoch": 3.6040321221991354,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00037515030665462345,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.23175375461578368,
|
|
"num_tokens": 71636677.0,
|
|
"step": 32090
|
|
},
|
|
{
|
|
"entropy": 5.615969848632813,
|
|
"epoch": 3.6045936991070926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037511435289946775,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.22157346755266188,
|
|
"num_tokens": 71648040.0,
|
|
"step": 32095
|
|
},
|
|
{
|
|
"entropy": 5.680285215377808,
|
|
"epoch": 3.6051552760150503,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003750783959566322,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.22296175062656404,
|
|
"num_tokens": 71659189.0,
|
|
"step": 32100
|
|
},
|
|
{
|
|
"entropy": 5.654457521438599,
|
|
"epoch": 3.605716852923008,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003750424358272617,
|
|
"loss": 4.8393,
|
|
"mean_token_accuracy": 0.23193256556987762,
|
|
"num_tokens": 71670262.0,
|
|
"step": 32105
|
|
},
|
|
{
|
|
"entropy": 5.569851207733154,
|
|
"epoch": 3.606278429830965,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003750064725125013,
|
|
"loss": 4.949,
|
|
"mean_token_accuracy": 0.22147035747766494,
|
|
"num_tokens": 71680271.0,
|
|
"step": 32110
|
|
},
|
|
{
|
|
"entropy": 5.607356262207031,
|
|
"epoch": 3.606840006738923,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037497050601349605,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.2193510815501213,
|
|
"num_tokens": 71691299.0,
|
|
"step": 32115
|
|
},
|
|
{
|
|
"entropy": 5.649664402008057,
|
|
"epoch": 3.6074015836468805,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037493453633139103,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.22935720682144164,
|
|
"num_tokens": 71702517.0,
|
|
"step": 32120
|
|
},
|
|
{
|
|
"entropy": 5.632906579971314,
|
|
"epoch": 3.607963160554838,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00037489856346733163,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.22655483186244965,
|
|
"num_tokens": 71713386.0,
|
|
"step": 32125
|
|
},
|
|
{
|
|
"entropy": 5.63098177909851,
|
|
"epoch": 3.608524737462796,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003748625874224632,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.23297490179538727,
|
|
"num_tokens": 71724361.0,
|
|
"step": 32130
|
|
},
|
|
{
|
|
"entropy": 5.649335956573486,
|
|
"epoch": 3.609086314370753,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037482660819793134,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.22845545262098313,
|
|
"num_tokens": 71735558.0,
|
|
"step": 32135
|
|
},
|
|
{
|
|
"entropy": 5.692263746261597,
|
|
"epoch": 3.6096478912787107,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003747906257948814,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.22250278443098068,
|
|
"num_tokens": 71747253.0,
|
|
"step": 32140
|
|
},
|
|
{
|
|
"entropy": 5.705237770080567,
|
|
"epoch": 3.6102094681866683,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003747546402144594,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.22072341293096542,
|
|
"num_tokens": 71760223.0,
|
|
"step": 32145
|
|
},
|
|
{
|
|
"entropy": 5.655552625656128,
|
|
"epoch": 3.6107710450946255,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037471865145781094,
|
|
"loss": 4.8977,
|
|
"mean_token_accuracy": 0.22430325746536256,
|
|
"num_tokens": 71771976.0,
|
|
"step": 32150
|
|
},
|
|
{
|
|
"entropy": 5.579137372970581,
|
|
"epoch": 3.611332622002583,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037468265952608196,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.2239880457520485,
|
|
"num_tokens": 71784364.0,
|
|
"step": 32155
|
|
},
|
|
{
|
|
"entropy": 5.6383788108825685,
|
|
"epoch": 3.611894198910541,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003746466644204183,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.21635443717241287,
|
|
"num_tokens": 71795495.0,
|
|
"step": 32160
|
|
},
|
|
{
|
|
"entropy": 5.672932720184326,
|
|
"epoch": 3.612455775818498,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003746106661419663,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.22545754313468933,
|
|
"num_tokens": 71806475.0,
|
|
"step": 32165
|
|
},
|
|
{
|
|
"entropy": 5.677882480621338,
|
|
"epoch": 3.6130173527264557,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000374574664691872,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.2216171532869339,
|
|
"num_tokens": 71816701.0,
|
|
"step": 32170
|
|
},
|
|
{
|
|
"entropy": 5.619472026824951,
|
|
"epoch": 3.6135789296344134,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037453866007128176,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.22459911555051804,
|
|
"num_tokens": 71827860.0,
|
|
"step": 32175
|
|
},
|
|
{
|
|
"entropy": 5.606358432769776,
|
|
"epoch": 3.614140506542371,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037450265228134203,
|
|
"loss": 4.9517,
|
|
"mean_token_accuracy": 0.22627702504396438,
|
|
"num_tokens": 71839631.0,
|
|
"step": 32180
|
|
},
|
|
{
|
|
"entropy": 5.644519090652466,
|
|
"epoch": 3.6147020834503287,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037446664132319925,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.23138739615678788,
|
|
"num_tokens": 71849926.0,
|
|
"step": 32185
|
|
},
|
|
{
|
|
"entropy": 5.590755033493042,
|
|
"epoch": 3.615263660358286,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000374430627198,
|
|
"loss": 4.9403,
|
|
"mean_token_accuracy": 0.22451777011156082,
|
|
"num_tokens": 71860815.0,
|
|
"step": 32190
|
|
},
|
|
{
|
|
"entropy": 5.666025638580322,
|
|
"epoch": 3.6158252372662436,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037439460990689106,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.2335005968809128,
|
|
"num_tokens": 71871814.0,
|
|
"step": 32195
|
|
},
|
|
{
|
|
"entropy": 5.682090187072754,
|
|
"epoch": 3.6163868141742013,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003743585894510192,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.22357660084962844,
|
|
"num_tokens": 71881606.0,
|
|
"step": 32200
|
|
},
|
|
{
|
|
"entropy": 5.619525194168091,
|
|
"epoch": 3.6169483910821585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037432256583153127,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.22635667473077775,
|
|
"num_tokens": 71893371.0,
|
|
"step": 32205
|
|
},
|
|
{
|
|
"entropy": 5.664804363250733,
|
|
"epoch": 3.617509967990116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037428653904957433,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.22806232422590256,
|
|
"num_tokens": 71906068.0,
|
|
"step": 32210
|
|
},
|
|
{
|
|
"entropy": 5.663188028335571,
|
|
"epoch": 3.618071544898074,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003742505091062955,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.22332780659198762,
|
|
"num_tokens": 71917450.0,
|
|
"step": 32215
|
|
},
|
|
{
|
|
"entropy": 5.636331605911255,
|
|
"epoch": 3.6186331218060315,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003742144760028419,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.22246723771095275,
|
|
"num_tokens": 71928333.0,
|
|
"step": 32220
|
|
},
|
|
{
|
|
"entropy": 5.6188201904296875,
|
|
"epoch": 3.619194698713989,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000374178439740361,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.22767563611268998,
|
|
"num_tokens": 71939836.0,
|
|
"step": 32225
|
|
},
|
|
{
|
|
"entropy": 5.700558853149414,
|
|
"epoch": 3.6197562756219464,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003741424003200001,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.2227851465344429,
|
|
"num_tokens": 71951120.0,
|
|
"step": 32230
|
|
},
|
|
{
|
|
"entropy": 5.6883245468139645,
|
|
"epoch": 3.620317852529904,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037410635774290667,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.2281369984149933,
|
|
"num_tokens": 71961547.0,
|
|
"step": 32235
|
|
},
|
|
{
|
|
"entropy": 5.604779624938965,
|
|
"epoch": 3.6208794294378617,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003740703120102284,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.23519971668720246,
|
|
"num_tokens": 71973287.0,
|
|
"step": 32240
|
|
},
|
|
{
|
|
"entropy": 5.649418210983276,
|
|
"epoch": 3.621441006345819,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000374034263123113,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.22913019061088563,
|
|
"num_tokens": 71984205.0,
|
|
"step": 32245
|
|
},
|
|
{
|
|
"entropy": 5.5747096061706545,
|
|
"epoch": 3.6220025832537766,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037399821108270823,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.2219387799501419,
|
|
"num_tokens": 71995090.0,
|
|
"step": 32250
|
|
},
|
|
{
|
|
"entropy": 5.752801752090454,
|
|
"epoch": 3.622564160161734,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000373962155890162,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.22172133028507232,
|
|
"num_tokens": 72005504.0,
|
|
"step": 32255
|
|
},
|
|
{
|
|
"entropy": 5.674772071838379,
|
|
"epoch": 3.6231257370696914,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003739260975466223,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.22820867151021956,
|
|
"num_tokens": 72017250.0,
|
|
"step": 32260
|
|
},
|
|
{
|
|
"entropy": 5.631626939773559,
|
|
"epoch": 3.623687313977649,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037389003605323737,
|
|
"loss": 4.9183,
|
|
"mean_token_accuracy": 0.2308969244360924,
|
|
"num_tokens": 72028089.0,
|
|
"step": 32265
|
|
},
|
|
{
|
|
"entropy": 5.6356974124908445,
|
|
"epoch": 3.6242488908856068,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037385397141115535,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.22351408153772354,
|
|
"num_tokens": 72039140.0,
|
|
"step": 32270
|
|
},
|
|
{
|
|
"entropy": 5.65185775756836,
|
|
"epoch": 3.6248104677935644,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037381790362152453,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.22650923132896422,
|
|
"num_tokens": 72049944.0,
|
|
"step": 32275
|
|
},
|
|
{
|
|
"entropy": 5.593421792984008,
|
|
"epoch": 3.625372044701522,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037378183268549326,
|
|
"loss": 4.9301,
|
|
"mean_token_accuracy": 0.2252177730202675,
|
|
"num_tokens": 72061799.0,
|
|
"step": 32280
|
|
},
|
|
{
|
|
"entropy": 5.619186210632324,
|
|
"epoch": 3.6259336216094793,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003737457586042102,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.22639892101287842,
|
|
"num_tokens": 72073539.0,
|
|
"step": 32285
|
|
},
|
|
{
|
|
"entropy": 5.613251638412476,
|
|
"epoch": 3.626495198517437,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003737096813788238,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.21692138761281968,
|
|
"num_tokens": 72085268.0,
|
|
"step": 32290
|
|
},
|
|
{
|
|
"entropy": 5.735153245925903,
|
|
"epoch": 3.6270567754253946,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003736736010104829,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.21219242066144944,
|
|
"num_tokens": 72096269.0,
|
|
"step": 32295
|
|
},
|
|
{
|
|
"entropy": 5.630683755874633,
|
|
"epoch": 3.627618352333352,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003736375175003363,
|
|
"loss": 4.9538,
|
|
"mean_token_accuracy": 0.23172775655984879,
|
|
"num_tokens": 72108934.0,
|
|
"step": 32300
|
|
},
|
|
{
|
|
"entropy": 5.625913000106811,
|
|
"epoch": 3.6281799292413095,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037360143084953285,
|
|
"loss": 4.9498,
|
|
"mean_token_accuracy": 0.2267285943031311,
|
|
"num_tokens": 72118371.0,
|
|
"step": 32305
|
|
},
|
|
{
|
|
"entropy": 5.546155214309692,
|
|
"epoch": 3.628741506149267,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003735653410592217,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.2364911511540413,
|
|
"num_tokens": 72129187.0,
|
|
"step": 32310
|
|
},
|
|
{
|
|
"entropy": 5.607977962493896,
|
|
"epoch": 3.629303083057225,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037352924813055185,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.23702598810195924,
|
|
"num_tokens": 72141317.0,
|
|
"step": 32315
|
|
},
|
|
{
|
|
"entropy": 5.659655809402466,
|
|
"epoch": 3.6298646599651825,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003734931520646724,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.2300931766629219,
|
|
"num_tokens": 72152754.0,
|
|
"step": 32320
|
|
},
|
|
{
|
|
"entropy": 5.568900680541992,
|
|
"epoch": 3.6304262368731397,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037345705286273285,
|
|
"loss": 4.8398,
|
|
"mean_token_accuracy": 0.2399967774748802,
|
|
"num_tokens": 72162115.0,
|
|
"step": 32325
|
|
},
|
|
{
|
|
"entropy": 5.556031513214111,
|
|
"epoch": 3.6309878137810974,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003734209505258825,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.22634925097227096,
|
|
"num_tokens": 72173633.0,
|
|
"step": 32330
|
|
},
|
|
{
|
|
"entropy": 5.642802715301514,
|
|
"epoch": 3.631549390689055,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037338484505527103,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.21708776205778121,
|
|
"num_tokens": 72185274.0,
|
|
"step": 32335
|
|
},
|
|
{
|
|
"entropy": 5.702963209152221,
|
|
"epoch": 3.6321109675970122,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037334873645204785,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.2217056155204773,
|
|
"num_tokens": 72195991.0,
|
|
"step": 32340
|
|
},
|
|
{
|
|
"entropy": 5.6319904804229735,
|
|
"epoch": 3.63267254450497,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037331262471736285,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.22104616314172745,
|
|
"num_tokens": 72207390.0,
|
|
"step": 32345
|
|
},
|
|
{
|
|
"entropy": 5.631329488754273,
|
|
"epoch": 3.6332341214129276,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037327650985236564,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.22065021991729736,
|
|
"num_tokens": 72218747.0,
|
|
"step": 32350
|
|
},
|
|
{
|
|
"entropy": 5.656863451004028,
|
|
"epoch": 3.633795698320885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003732403918582063,
|
|
"loss": 4.9766,
|
|
"mean_token_accuracy": 0.22498861700296402,
|
|
"num_tokens": 72230623.0,
|
|
"step": 32355
|
|
},
|
|
{
|
|
"entropy": 5.625945377349853,
|
|
"epoch": 3.6343572752288424,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037320427073603475,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.2313379615545273,
|
|
"num_tokens": 72242510.0,
|
|
"step": 32360
|
|
},
|
|
{
|
|
"entropy": 5.602125358581543,
|
|
"epoch": 3.6349188521368,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037316814648700113,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.23096763342618942,
|
|
"num_tokens": 72253498.0,
|
|
"step": 32365
|
|
},
|
|
{
|
|
"entropy": 5.639709615707398,
|
|
"epoch": 3.6354804290447578,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003731320191122557,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.22549523264169694,
|
|
"num_tokens": 72265698.0,
|
|
"step": 32370
|
|
},
|
|
{
|
|
"entropy": 5.604879713058471,
|
|
"epoch": 3.6360420059527154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003730958886129486,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.240188804268837,
|
|
"num_tokens": 72276563.0,
|
|
"step": 32375
|
|
},
|
|
{
|
|
"entropy": 5.634169340133667,
|
|
"epoch": 3.6366035828606726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037305975499023046,
|
|
"loss": 4.9501,
|
|
"mean_token_accuracy": 0.22730478793382644,
|
|
"num_tokens": 72286826.0,
|
|
"step": 32380
|
|
},
|
|
{
|
|
"entropy": 5.727635526657105,
|
|
"epoch": 3.6371651597686303,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003730236182452517,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.21954880207777022,
|
|
"num_tokens": 72299446.0,
|
|
"step": 32385
|
|
},
|
|
{
|
|
"entropy": 5.711078310012818,
|
|
"epoch": 3.637726736676588,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003729874783791629,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.21999457180500032,
|
|
"num_tokens": 72310894.0,
|
|
"step": 32390
|
|
},
|
|
{
|
|
"entropy": 5.657504367828369,
|
|
"epoch": 3.638288313584545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003729513353931148,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.22631181329488753,
|
|
"num_tokens": 72322810.0,
|
|
"step": 32395
|
|
},
|
|
{
|
|
"entropy": 5.650073862075805,
|
|
"epoch": 3.638849890492503,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003729151892882581,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.22693177163600922,
|
|
"num_tokens": 72334509.0,
|
|
"step": 32400
|
|
},
|
|
{
|
|
"entropy": 5.606058168411255,
|
|
"epoch": 3.6394114674004605,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003728790400657439,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.2247232347726822,
|
|
"num_tokens": 72345036.0,
|
|
"step": 32405
|
|
},
|
|
{
|
|
"entropy": 5.6472804069519045,
|
|
"epoch": 3.639973044308418,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037284288772672315,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.22012619078159332,
|
|
"num_tokens": 72356029.0,
|
|
"step": 32410
|
|
},
|
|
{
|
|
"entropy": 5.644060277938843,
|
|
"epoch": 3.640534621216376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037280673227234687,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.22607263475656508,
|
|
"num_tokens": 72366548.0,
|
|
"step": 32415
|
|
},
|
|
{
|
|
"entropy": 5.565021228790283,
|
|
"epoch": 3.641096198124333,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003727705737037662,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.22331393510103226,
|
|
"num_tokens": 72377271.0,
|
|
"step": 32420
|
|
},
|
|
{
|
|
"entropy": 5.655257606506348,
|
|
"epoch": 3.6416577750322907,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003727344120221326,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.2222067356109619,
|
|
"num_tokens": 72388651.0,
|
|
"step": 32425
|
|
},
|
|
{
|
|
"entropy": 5.608814144134522,
|
|
"epoch": 3.6422193519402484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037269824722859743,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.22128880769014359,
|
|
"num_tokens": 72400955.0,
|
|
"step": 32430
|
|
},
|
|
{
|
|
"entropy": 5.666241025924682,
|
|
"epoch": 3.6427809288482056,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003726620793243121,
|
|
"loss": 4.9778,
|
|
"mean_token_accuracy": 0.21824867725372316,
|
|
"num_tokens": 72412372.0,
|
|
"step": 32435
|
|
},
|
|
{
|
|
"entropy": 5.671909332275391,
|
|
"epoch": 3.6433425057561633,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003726259083104284,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.22312819212675095,
|
|
"num_tokens": 72422664.0,
|
|
"step": 32440
|
|
},
|
|
{
|
|
"entropy": 5.645604038238526,
|
|
"epoch": 3.643904082664121,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037258973418809784,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.2219538629055023,
|
|
"num_tokens": 72434829.0,
|
|
"step": 32445
|
|
},
|
|
{
|
|
"entropy": 5.597930145263672,
|
|
"epoch": 3.644465659572078,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003725535569584723,
|
|
"loss": 4.9005,
|
|
"mean_token_accuracy": 0.22618666887283326,
|
|
"num_tokens": 72445140.0,
|
|
"step": 32450
|
|
},
|
|
{
|
|
"entropy": 5.610523319244384,
|
|
"epoch": 3.645027236480036,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037251737662270367,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.23498348593711854,
|
|
"num_tokens": 72455281.0,
|
|
"step": 32455
|
|
},
|
|
{
|
|
"entropy": 5.658924198150634,
|
|
"epoch": 3.6455888133879935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000372481193181944,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.22123669385910033,
|
|
"num_tokens": 72466296.0,
|
|
"step": 32460
|
|
},
|
|
{
|
|
"entropy": 5.621937274932861,
|
|
"epoch": 3.646150390295951,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037244500663734524,
|
|
"loss": 4.9314,
|
|
"mean_token_accuracy": 0.22750208526849747,
|
|
"num_tokens": 72477390.0,
|
|
"step": 32465
|
|
},
|
|
{
|
|
"entropy": 5.590445852279663,
|
|
"epoch": 3.6467119672039088,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003724088169900597,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.2328767716884613,
|
|
"num_tokens": 72488241.0,
|
|
"step": 32470
|
|
},
|
|
{
|
|
"entropy": 5.653968477249146,
|
|
"epoch": 3.647273544111866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037237262424123975,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.22742558866739274,
|
|
"num_tokens": 72498823.0,
|
|
"step": 32475
|
|
},
|
|
{
|
|
"entropy": 5.645147657394409,
|
|
"epoch": 3.6478351210198237,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037233642839203763,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.2197529211640358,
|
|
"num_tokens": 72509399.0,
|
|
"step": 32480
|
|
},
|
|
{
|
|
"entropy": 5.693280839920044,
|
|
"epoch": 3.6483966979277813,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003723002294436059,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.222603502869606,
|
|
"num_tokens": 72519182.0,
|
|
"step": 32485
|
|
},
|
|
{
|
|
"entropy": 5.636052560806275,
|
|
"epoch": 3.6489582748357385,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037226402739709704,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.2289359450340271,
|
|
"num_tokens": 72528852.0,
|
|
"step": 32490
|
|
},
|
|
{
|
|
"entropy": 5.613788366317749,
|
|
"epoch": 3.649519851743696,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003722278222536639,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.22033705115318297,
|
|
"num_tokens": 72540477.0,
|
|
"step": 32495
|
|
},
|
|
{
|
|
"entropy": 5.639712619781494,
|
|
"epoch": 3.650081428651654,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037219161401445914,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.22678638845682145,
|
|
"num_tokens": 72553404.0,
|
|
"step": 32500
|
|
},
|
|
{
|
|
"entropy": 5.6647742748260494,
|
|
"epoch": 3.6506430055596115,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037215540268063573,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.22120453417301178,
|
|
"num_tokens": 72564516.0,
|
|
"step": 32505
|
|
},
|
|
{
|
|
"entropy": 5.592250967025757,
|
|
"epoch": 3.651204582467569,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003721191882533466,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.22748181223869324,
|
|
"num_tokens": 72575888.0,
|
|
"step": 32510
|
|
},
|
|
{
|
|
"entropy": 5.605225324630737,
|
|
"epoch": 3.6517661593755264,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003720829707337449,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.2238485649228096,
|
|
"num_tokens": 72586629.0,
|
|
"step": 32515
|
|
},
|
|
{
|
|
"entropy": 5.642162179946899,
|
|
"epoch": 3.652327736283484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003720467501229836,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.23048356920480728,
|
|
"num_tokens": 72597264.0,
|
|
"step": 32520
|
|
},
|
|
{
|
|
"entropy": 5.689519309997559,
|
|
"epoch": 3.6528893131914417,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003720105264222163,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.2248072937130928,
|
|
"num_tokens": 72608450.0,
|
|
"step": 32525
|
|
},
|
|
{
|
|
"entropy": 5.615471363067627,
|
|
"epoch": 3.653450890099399,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00037197429963259615,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.21962424367666245,
|
|
"num_tokens": 72620538.0,
|
|
"step": 32530
|
|
},
|
|
{
|
|
"entropy": 5.68602876663208,
|
|
"epoch": 3.6540124670073566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003719380697552767,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.221590319275856,
|
|
"num_tokens": 72632589.0,
|
|
"step": 32535
|
|
},
|
|
{
|
|
"entropy": 5.670041418075561,
|
|
"epoch": 3.6545740439153143,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003719018367914115,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.2235955849289894,
|
|
"num_tokens": 72643749.0,
|
|
"step": 32540
|
|
},
|
|
{
|
|
"entropy": 5.61399097442627,
|
|
"epoch": 3.6551356208232715,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003718656007421542,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.21753267347812652,
|
|
"num_tokens": 72655485.0,
|
|
"step": 32545
|
|
},
|
|
{
|
|
"entropy": 5.699527263641357,
|
|
"epoch": 3.655697197731229,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037182936160865866,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.22158667147159578,
|
|
"num_tokens": 72666175.0,
|
|
"step": 32550
|
|
},
|
|
{
|
|
"entropy": 5.6713635444641115,
|
|
"epoch": 3.656258774639187,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003717931193920788,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.21891589909791948,
|
|
"num_tokens": 72675858.0,
|
|
"step": 32555
|
|
},
|
|
{
|
|
"entropy": 5.585183191299438,
|
|
"epoch": 3.6568203515471445,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003717568740935683,
|
|
"loss": 4.8736,
|
|
"mean_token_accuracy": 0.22652027159929275,
|
|
"num_tokens": 72686623.0,
|
|
"step": 32560
|
|
},
|
|
{
|
|
"entropy": 5.625726175308228,
|
|
"epoch": 3.657381928455102,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003717206257142815,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.22797850519418716,
|
|
"num_tokens": 72698002.0,
|
|
"step": 32565
|
|
},
|
|
{
|
|
"entropy": 5.625010919570923,
|
|
"epoch": 3.6579435053630593,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003716843742553724,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.22462593466043473,
|
|
"num_tokens": 72708981.0,
|
|
"step": 32570
|
|
},
|
|
{
|
|
"entropy": 5.5253359317779545,
|
|
"epoch": 3.658505082271017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003716481197179953,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.22451213300228118,
|
|
"num_tokens": 72719764.0,
|
|
"step": 32575
|
|
},
|
|
{
|
|
"entropy": 5.776583051681518,
|
|
"epoch": 3.6590666591789747,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037161186210330464,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.2179058834910393,
|
|
"num_tokens": 72730915.0,
|
|
"step": 32580
|
|
},
|
|
{
|
|
"entropy": 5.7199780464172365,
|
|
"epoch": 3.659628236086932,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037157560141245485,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.2216982513666153,
|
|
"num_tokens": 72741869.0,
|
|
"step": 32585
|
|
},
|
|
{
|
|
"entropy": 5.68287672996521,
|
|
"epoch": 3.6601898129948895,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037153933764660034,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.22401691377162933,
|
|
"num_tokens": 72753638.0,
|
|
"step": 32590
|
|
},
|
|
{
|
|
"entropy": 5.693525171279907,
|
|
"epoch": 3.660751389902847,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000371503070806896,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.22873712778091432,
|
|
"num_tokens": 72765505.0,
|
|
"step": 32595
|
|
},
|
|
{
|
|
"entropy": 5.613092565536499,
|
|
"epoch": 3.661312966810805,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037146680089449643,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.22736771255731583,
|
|
"num_tokens": 72776348.0,
|
|
"step": 32600
|
|
},
|
|
{
|
|
"entropy": 5.638423681259155,
|
|
"epoch": 3.6618745437187625,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037143052791055654,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.22047992646694184,
|
|
"num_tokens": 72787720.0,
|
|
"step": 32605
|
|
},
|
|
{
|
|
"entropy": 5.595162677764892,
|
|
"epoch": 3.6624361206267197,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003713942518562311,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.2186615586280823,
|
|
"num_tokens": 72798947.0,
|
|
"step": 32610
|
|
},
|
|
{
|
|
"entropy": 5.710906887054444,
|
|
"epoch": 3.6629976975346774,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003713579727326754,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.2189458578824997,
|
|
"num_tokens": 72810859.0,
|
|
"step": 32615
|
|
},
|
|
{
|
|
"entropy": 5.6248703956604,
|
|
"epoch": 3.663559274442635,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037132169054104446,
|
|
"loss": 4.8794,
|
|
"mean_token_accuracy": 0.23659075796604156,
|
|
"num_tokens": 72821089.0,
|
|
"step": 32620
|
|
},
|
|
{
|
|
"entropy": 5.571070384979248,
|
|
"epoch": 3.6641208513505923,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037128540528249355,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.22658779919147493,
|
|
"num_tokens": 72832226.0,
|
|
"step": 32625
|
|
},
|
|
{
|
|
"entropy": 5.61276330947876,
|
|
"epoch": 3.66468242825855,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000371249116958178,
|
|
"loss": 4.9735,
|
|
"mean_token_accuracy": 0.22942688316106796,
|
|
"num_tokens": 72843939.0,
|
|
"step": 32630
|
|
},
|
|
{
|
|
"entropy": 5.551273012161255,
|
|
"epoch": 3.6652440051665076,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037121282556925326,
|
|
"loss": 4.8526,
|
|
"mean_token_accuracy": 0.23429082632064818,
|
|
"num_tokens": 72854332.0,
|
|
"step": 32635
|
|
},
|
|
{
|
|
"entropy": 5.724375295639038,
|
|
"epoch": 3.665805582074465,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003711765311168748,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.2127946838736534,
|
|
"num_tokens": 72865530.0,
|
|
"step": 32640
|
|
},
|
|
{
|
|
"entropy": 5.698514842987061,
|
|
"epoch": 3.6663671589824225,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037114023360219824,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.21749623715877534,
|
|
"num_tokens": 72877683.0,
|
|
"step": 32645
|
|
},
|
|
{
|
|
"entropy": 5.656054353713989,
|
|
"epoch": 3.66692873589038,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037110393302637937,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.22979846149682998,
|
|
"num_tokens": 72888926.0,
|
|
"step": 32650
|
|
},
|
|
{
|
|
"entropy": 5.644995927810669,
|
|
"epoch": 3.667490312798338,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037106762939057404,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.2249825656414032,
|
|
"num_tokens": 72901318.0,
|
|
"step": 32655
|
|
},
|
|
{
|
|
"entropy": 5.711053514480591,
|
|
"epoch": 3.6680518897062955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003710313226959381,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.2312316343188286,
|
|
"num_tokens": 72913177.0,
|
|
"step": 32660
|
|
},
|
|
{
|
|
"entropy": 5.739936828613281,
|
|
"epoch": 3.6686134666142527,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003709950129436276,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.21432072222232817,
|
|
"num_tokens": 72924322.0,
|
|
"step": 32665
|
|
},
|
|
{
|
|
"entropy": 5.642151832580566,
|
|
"epoch": 3.6691750435222104,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003709587001347987,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.22696195244789125,
|
|
"num_tokens": 72936287.0,
|
|
"step": 32670
|
|
},
|
|
{
|
|
"entropy": 5.663383865356446,
|
|
"epoch": 3.669736620430168,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037092238427060756,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.21981053054332733,
|
|
"num_tokens": 72949262.0,
|
|
"step": 32675
|
|
},
|
|
{
|
|
"entropy": 5.715323734283447,
|
|
"epoch": 3.6702981973381252,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003708860653522104,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.22486079931259156,
|
|
"num_tokens": 72959283.0,
|
|
"step": 32680
|
|
},
|
|
{
|
|
"entropy": 5.602758884429932,
|
|
"epoch": 3.670859774246083,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003708497433807639,
|
|
"loss": 4.8906,
|
|
"mean_token_accuracy": 0.2356040209531784,
|
|
"num_tokens": 72971063.0,
|
|
"step": 32685
|
|
},
|
|
{
|
|
"entropy": 5.599445962905884,
|
|
"epoch": 3.6714213511540406,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037081341835742433,
|
|
"loss": 4.9022,
|
|
"mean_token_accuracy": 0.22827959507703782,
|
|
"num_tokens": 72980775.0,
|
|
"step": 32690
|
|
},
|
|
{
|
|
"entropy": 5.577727603912353,
|
|
"epoch": 3.671982928061998,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003707770902833483,
|
|
"loss": 4.9437,
|
|
"mean_token_accuracy": 0.2312094822525978,
|
|
"num_tokens": 72992166.0,
|
|
"step": 32695
|
|
},
|
|
{
|
|
"entropy": 5.5895397663116455,
|
|
"epoch": 3.672544504969956,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003707407591596926,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.22165456861257554,
|
|
"num_tokens": 73003194.0,
|
|
"step": 32700
|
|
},
|
|
{
|
|
"entropy": 5.638792276382446,
|
|
"epoch": 3.673106081877913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000370704424987614,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.22051342874765395,
|
|
"num_tokens": 73013375.0,
|
|
"step": 32705
|
|
},
|
|
{
|
|
"entropy": 5.660940217971802,
|
|
"epoch": 3.6736676587858708,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003706680877682694,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.22679072767496108,
|
|
"num_tokens": 73024532.0,
|
|
"step": 32710
|
|
},
|
|
{
|
|
"entropy": 5.592159938812256,
|
|
"epoch": 3.6742292356938284,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037063174750281573,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.223929463326931,
|
|
"num_tokens": 73034721.0,
|
|
"step": 32715
|
|
},
|
|
{
|
|
"entropy": 5.625294208526611,
|
|
"epoch": 3.6747908126017856,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003705954041924102,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.23483358025550843,
|
|
"num_tokens": 73045894.0,
|
|
"step": 32720
|
|
},
|
|
{
|
|
"entropy": 5.526719856262207,
|
|
"epoch": 3.6753523895097433,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037055905783821,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.24768011420965194,
|
|
"num_tokens": 73057370.0,
|
|
"step": 32725
|
|
},
|
|
{
|
|
"entropy": 5.692765426635742,
|
|
"epoch": 3.675913966417701,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037052270844137216,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.21547500938177108,
|
|
"num_tokens": 73067700.0,
|
|
"step": 32730
|
|
},
|
|
{
|
|
"entropy": 5.543291282653809,
|
|
"epoch": 3.676475543325658,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003704863560030543,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.22938599437475204,
|
|
"num_tokens": 73079612.0,
|
|
"step": 32735
|
|
},
|
|
{
|
|
"entropy": 5.641868448257446,
|
|
"epoch": 3.677037120233616,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003704500005244139,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.22180802077054979,
|
|
"num_tokens": 73091060.0,
|
|
"step": 32740
|
|
},
|
|
{
|
|
"entropy": 5.723977088928223,
|
|
"epoch": 3.6775986971415735,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037041364200660835,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.2220599666237831,
|
|
"num_tokens": 73102218.0,
|
|
"step": 32745
|
|
},
|
|
{
|
|
"entropy": 5.707117795944214,
|
|
"epoch": 3.678160274049531,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037037728045079553,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.22166621387004853,
|
|
"num_tokens": 73113669.0,
|
|
"step": 32750
|
|
},
|
|
{
|
|
"entropy": 5.650160789489746,
|
|
"epoch": 3.678721850957489,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000370340915858133,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.22647868543863298,
|
|
"num_tokens": 73124765.0,
|
|
"step": 32755
|
|
},
|
|
{
|
|
"entropy": 5.661921453475952,
|
|
"epoch": 3.679283427865446,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003703045482297788,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.22224469631910324,
|
|
"num_tokens": 73135278.0,
|
|
"step": 32760
|
|
},
|
|
{
|
|
"entropy": 5.514501428604126,
|
|
"epoch": 3.6798450047734037,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003702681775668908,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.23197822272777557,
|
|
"num_tokens": 73145176.0,
|
|
"step": 32765
|
|
},
|
|
{
|
|
"entropy": 5.730945444107055,
|
|
"epoch": 3.6804065816813614,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003702318038706272,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.21860943138599395,
|
|
"num_tokens": 73156001.0,
|
|
"step": 32770
|
|
},
|
|
{
|
|
"entropy": 5.629293298721313,
|
|
"epoch": 3.6809681585893186,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003701954271421459,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.2261963576078415,
|
|
"num_tokens": 73167116.0,
|
|
"step": 32775
|
|
},
|
|
{
|
|
"entropy": 5.704475688934326,
|
|
"epoch": 3.6815297354972762,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037015904738260533,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.22717195749282837,
|
|
"num_tokens": 73178750.0,
|
|
"step": 32780
|
|
},
|
|
{
|
|
"entropy": 5.593186378479004,
|
|
"epoch": 3.682091312405234,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003701226645931637,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.2317711666226387,
|
|
"num_tokens": 73189781.0,
|
|
"step": 32785
|
|
},
|
|
{
|
|
"entropy": 5.586955976486206,
|
|
"epoch": 3.6826528893131916,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003700862787749796,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.2308667555451393,
|
|
"num_tokens": 73200374.0,
|
|
"step": 32790
|
|
},
|
|
{
|
|
"entropy": 5.700134563446045,
|
|
"epoch": 3.6832144662211492,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003700498899292115,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.21543197482824325,
|
|
"num_tokens": 73211613.0,
|
|
"step": 32795
|
|
},
|
|
{
|
|
"entropy": 5.6364459037780765,
|
|
"epoch": 3.6837760431291064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003700134980570181,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.23240369111299514,
|
|
"num_tokens": 73222309.0,
|
|
"step": 32800
|
|
},
|
|
{
|
|
"entropy": 5.732521009445191,
|
|
"epoch": 3.684337620037064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003699771031595579,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.21525893211364747,
|
|
"num_tokens": 73233956.0,
|
|
"step": 32805
|
|
},
|
|
{
|
|
"entropy": 5.707831192016601,
|
|
"epoch": 3.6848991969450218,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036994070523799005,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.2179940551519394,
|
|
"num_tokens": 73245218.0,
|
|
"step": 32810
|
|
},
|
|
{
|
|
"entropy": 5.634533643722534,
|
|
"epoch": 3.685460773852979,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036990430429347334,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.23045898079872132,
|
|
"num_tokens": 73255830.0,
|
|
"step": 32815
|
|
},
|
|
{
|
|
"entropy": 5.595184183120727,
|
|
"epoch": 3.6860223507609367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036986790032716673,
|
|
"loss": 4.8678,
|
|
"mean_token_accuracy": 0.228628534078598,
|
|
"num_tokens": 73266384.0,
|
|
"step": 32820
|
|
},
|
|
{
|
|
"entropy": 5.624413585662841,
|
|
"epoch": 3.6865839276688943,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003698314933402292,
|
|
"loss": 4.9633,
|
|
"mean_token_accuracy": 0.2214408278465271,
|
|
"num_tokens": 73276839.0,
|
|
"step": 32825
|
|
},
|
|
{
|
|
"entropy": 5.702794075012207,
|
|
"epoch": 3.6871455045768515,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003697950833338204,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.2279679670929909,
|
|
"num_tokens": 73287398.0,
|
|
"step": 32830
|
|
},
|
|
{
|
|
"entropy": 5.621437406539917,
|
|
"epoch": 3.687707081484809,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036975867030909933,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.22152847647666932,
|
|
"num_tokens": 73297432.0,
|
|
"step": 32835
|
|
},
|
|
{
|
|
"entropy": 5.5783600330352785,
|
|
"epoch": 3.688268658392767,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036972225426722545,
|
|
"loss": 4.8369,
|
|
"mean_token_accuracy": 0.23077724128961563,
|
|
"num_tokens": 73308539.0,
|
|
"step": 32840
|
|
},
|
|
{
|
|
"entropy": 5.61350154876709,
|
|
"epoch": 3.6888302353007245,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003696858352093582,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.23583424538373948,
|
|
"num_tokens": 73319698.0,
|
|
"step": 32845
|
|
},
|
|
{
|
|
"entropy": 5.608216047286987,
|
|
"epoch": 3.689391812208682,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036964941313665715,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.2248840570449829,
|
|
"num_tokens": 73329747.0,
|
|
"step": 32850
|
|
},
|
|
{
|
|
"entropy": 5.623132133483887,
|
|
"epoch": 3.6899533891166394,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003696129880502823,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.230806303024292,
|
|
"num_tokens": 73340523.0,
|
|
"step": 32855
|
|
},
|
|
{
|
|
"entropy": 5.808594131469727,
|
|
"epoch": 3.690514966024597,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000369576559951393,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.22140643745660782,
|
|
"num_tokens": 73352219.0,
|
|
"step": 32860
|
|
},
|
|
{
|
|
"entropy": 5.64617280960083,
|
|
"epoch": 3.6910765429325547,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036954012884114946,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.22615867406129836,
|
|
"num_tokens": 73363157.0,
|
|
"step": 32865
|
|
},
|
|
{
|
|
"entropy": 5.652135515213013,
|
|
"epoch": 3.691638119840512,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003695036947207115,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.22084517031908035,
|
|
"num_tokens": 73375387.0,
|
|
"step": 32870
|
|
},
|
|
{
|
|
"entropy": 5.733429956436157,
|
|
"epoch": 3.6921996967484696,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036946725759123936,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.21799543797969817,
|
|
"num_tokens": 73388056.0,
|
|
"step": 32875
|
|
},
|
|
{
|
|
"entropy": 5.718516302108765,
|
|
"epoch": 3.6927612736564273,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003694308174538929,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.22190429419279098,
|
|
"num_tokens": 73398510.0,
|
|
"step": 32880
|
|
},
|
|
{
|
|
"entropy": 5.664729976654053,
|
|
"epoch": 3.693322850564385,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00036939437430983274,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.2286695808172226,
|
|
"num_tokens": 73409382.0,
|
|
"step": 32885
|
|
},
|
|
{
|
|
"entropy": 5.590082740783691,
|
|
"epoch": 3.6938844274723426,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036935792816021905,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.22174336165189742,
|
|
"num_tokens": 73419958.0,
|
|
"step": 32890
|
|
},
|
|
{
|
|
"entropy": 5.618281841278076,
|
|
"epoch": 3.6944460043803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00036932147900621234,
|
|
"loss": 4.93,
|
|
"mean_token_accuracy": 0.22876990139484404,
|
|
"num_tokens": 73430982.0,
|
|
"step": 32895
|
|
},
|
|
{
|
|
"entropy": 5.645249080657959,
|
|
"epoch": 3.6950075812882575,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036928502684897314,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.23053960353136063,
|
|
"num_tokens": 73442375.0,
|
|
"step": 32900
|
|
},
|
|
{
|
|
"entropy": 5.600159311294556,
|
|
"epoch": 3.695569158196215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00036924857168966216,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.23516543209552765,
|
|
"num_tokens": 73452212.0,
|
|
"step": 32905
|
|
},
|
|
{
|
|
"entropy": 5.600782346725464,
|
|
"epoch": 3.6961307351041723,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003692121135294401,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.22446924299001694,
|
|
"num_tokens": 73462998.0,
|
|
"step": 32910
|
|
},
|
|
{
|
|
"entropy": 5.534327793121338,
|
|
"epoch": 3.69669231201213,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036917565236946776,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.22987809926271438,
|
|
"num_tokens": 73474387.0,
|
|
"step": 32915
|
|
},
|
|
{
|
|
"entropy": 5.611951780319214,
|
|
"epoch": 3.6972538889200877,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036913918821090616,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.22905476838350297,
|
|
"num_tokens": 73484524.0,
|
|
"step": 32920
|
|
},
|
|
{
|
|
"entropy": 5.622895050048828,
|
|
"epoch": 3.697815465828045,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036910272105491625,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.23482613414525985,
|
|
"num_tokens": 73495286.0,
|
|
"step": 32925
|
|
},
|
|
{
|
|
"entropy": 5.584798526763916,
|
|
"epoch": 3.6983770427360025,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036906625090265925,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.2228279799222946,
|
|
"num_tokens": 73507366.0,
|
|
"step": 32930
|
|
},
|
|
{
|
|
"entropy": 5.5983843326568605,
|
|
"epoch": 3.69893861964396,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036902977775529636,
|
|
"loss": 4.896,
|
|
"mean_token_accuracy": 0.23889735490083694,
|
|
"num_tokens": 73517823.0,
|
|
"step": 32935
|
|
},
|
|
{
|
|
"entropy": 5.615390825271606,
|
|
"epoch": 3.699500196551918,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003689933016139888,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.22329926937818528,
|
|
"num_tokens": 73529199.0,
|
|
"step": 32940
|
|
},
|
|
{
|
|
"entropy": 5.598388624191284,
|
|
"epoch": 3.7000617734598755,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003689568224798981,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.22742086052894592,
|
|
"num_tokens": 73539845.0,
|
|
"step": 32945
|
|
},
|
|
{
|
|
"entropy": 5.680166482925415,
|
|
"epoch": 3.7006233503678327,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003689203403541857,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.22152247577905654,
|
|
"num_tokens": 73551331.0,
|
|
"step": 32950
|
|
},
|
|
{
|
|
"entropy": 5.647387933731079,
|
|
"epoch": 3.7011849272757904,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036888385523801325,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.22625247538089752,
|
|
"num_tokens": 73562155.0,
|
|
"step": 32955
|
|
},
|
|
{
|
|
"entropy": 5.585843896865844,
|
|
"epoch": 3.701746504183748,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036884736713254247,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.22131679505109786,
|
|
"num_tokens": 73573014.0,
|
|
"step": 32960
|
|
},
|
|
{
|
|
"entropy": 5.594900465011596,
|
|
"epoch": 3.7023080810917053,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036881087603893515,
|
|
"loss": 4.9842,
|
|
"mean_token_accuracy": 0.22321300953626633,
|
|
"num_tokens": 73584919.0,
|
|
"step": 32965
|
|
},
|
|
{
|
|
"entropy": 5.61509518623352,
|
|
"epoch": 3.702869657999663,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036877438195835307,
|
|
"loss": 4.934,
|
|
"mean_token_accuracy": 0.22230930328369142,
|
|
"num_tokens": 73596015.0,
|
|
"step": 32970
|
|
},
|
|
{
|
|
"entropy": 5.631366872787476,
|
|
"epoch": 3.7034312349076206,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003687378848919584,
|
|
"loss": 4.9329,
|
|
"mean_token_accuracy": 0.22839731127023696,
|
|
"num_tokens": 73606312.0,
|
|
"step": 32975
|
|
},
|
|
{
|
|
"entropy": 5.729783201217652,
|
|
"epoch": 3.7039928118155783,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036870138484091297,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.21235196441411971,
|
|
"num_tokens": 73617411.0,
|
|
"step": 32980
|
|
},
|
|
{
|
|
"entropy": 5.725080394744873,
|
|
"epoch": 3.704554388723536,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00036866488180637926,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.21879585683345795,
|
|
"num_tokens": 73627725.0,
|
|
"step": 32985
|
|
},
|
|
{
|
|
"entropy": 5.635750102996826,
|
|
"epoch": 3.705115965631493,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003686283757895193,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.2327341377735138,
|
|
"num_tokens": 73639130.0,
|
|
"step": 32990
|
|
},
|
|
{
|
|
"entropy": 5.542126989364624,
|
|
"epoch": 3.705677542539451,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036859186679149555,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.23144273906946183,
|
|
"num_tokens": 73650107.0,
|
|
"step": 32995
|
|
},
|
|
{
|
|
"entropy": 5.5905622959136965,
|
|
"epoch": 3.7062391194474085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003685553548134705,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.22724179476499556,
|
|
"num_tokens": 73659735.0,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"epoch": 3.7062391194474085,
|
|
"eval_entropy": 5.390875964795679,
|
|
"eval_loss": 5.075668811798096,
|
|
"eval_mean_token_accuracy": 0.22865736138038117,
|
|
"eval_num_tokens": 73659735.0,
|
|
"eval_runtime": 18.5899,
|
|
"eval_samples_per_second": 1668.275,
|
|
"eval_steps_per_second": 208.555,
|
|
"step": 33000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.713029729107968e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|