6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1562511335915520.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|