36101 lines
994 KiB
JSON
36101 lines
994 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.729106628242075,
|
|
"eval_steps": 3000,
|
|
"global_step": 18000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742348670959473,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7861,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742372608184814,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7936,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 21838.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742314338684082,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7771,
|
|
"mean_token_accuracy": 6.802721181884409e-05,
|
|
"num_tokens": 33483.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742245483398438,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.728,
|
|
"mean_token_accuracy": 7.44047632906586e-05,
|
|
"num_tokens": 45150.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.74207124710083,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.6308,
|
|
"mean_token_accuracy": 0.0004121576203033328,
|
|
"num_tokens": 55862.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741769409179687,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.5443,
|
|
"mean_token_accuracy": 0.002983335469616577,
|
|
"num_tokens": 66766.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.741297435760497,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3781,
|
|
"mean_token_accuracy": 0.02464218223467469,
|
|
"num_tokens": 77012.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.740566635131836,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2814,
|
|
"mean_token_accuracy": 0.03235357943922281,
|
|
"num_tokens": 89034.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.739375877380372,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1514,
|
|
"mean_token_accuracy": 0.038061602786183354,
|
|
"num_tokens": 100341.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.738532257080077,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0584,
|
|
"mean_token_accuracy": 0.038722694478929044,
|
|
"num_tokens": 111997.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.738390827178955,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.0148,
|
|
"mean_token_accuracy": 0.03572444599121809,
|
|
"num_tokens": 123705.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.737564182281494,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.9071,
|
|
"mean_token_accuracy": 0.03962940648198128,
|
|
"num_tokens": 134091.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.7362642288208,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.8911,
|
|
"mean_token_accuracy": 0.04431229718029499,
|
|
"num_tokens": 145731.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.734374618530273,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8077,
|
|
"mean_token_accuracy": 0.042512409016489984,
|
|
"num_tokens": 156979.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.732056808471679,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7359,
|
|
"mean_token_accuracy": 0.04284955617040396,
|
|
"num_tokens": 167021.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.728988742828369,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6987,
|
|
"mean_token_accuracy": 0.044812921434640884,
|
|
"num_tokens": 179269.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.725158405303954,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6221,
|
|
"mean_token_accuracy": 0.0440741615369916,
|
|
"num_tokens": 190328.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.719916248321534,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4954,
|
|
"mean_token_accuracy": 0.04290707334876061,
|
|
"num_tokens": 201522.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.711879539489747,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4379,
|
|
"mean_token_accuracy": 0.046910974010825154,
|
|
"num_tokens": 212963.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.700801849365234,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4243,
|
|
"mean_token_accuracy": 0.04375532791018486,
|
|
"num_tokens": 224446.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.685577392578125,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2512,
|
|
"mean_token_accuracy": 0.05137390121817589,
|
|
"num_tokens": 235334.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.665137195587159,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.173,
|
|
"mean_token_accuracy": 0.051672637835144995,
|
|
"num_tokens": 247024.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.635279273986816,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0046,
|
|
"mean_token_accuracy": 0.05748001225292683,
|
|
"num_tokens": 258354.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.598550987243652,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9106,
|
|
"mean_token_accuracy": 0.05730769820511341,
|
|
"num_tokens": 271202.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.54614782333374,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7763,
|
|
"mean_token_accuracy": 0.05949556417763233,
|
|
"num_tokens": 282405.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.473622226715088,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6177,
|
|
"mean_token_accuracy": 0.067269791290164,
|
|
"num_tokens": 294211.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.406041431427003,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5544,
|
|
"mean_token_accuracy": 0.06200371570885181,
|
|
"num_tokens": 305420.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.324399662017822,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3911,
|
|
"mean_token_accuracy": 0.060704247653484346,
|
|
"num_tokens": 316430.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.210215950012207,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2694,
|
|
"mean_token_accuracy": 0.06927172876894475,
|
|
"num_tokens": 328406.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.086783313751221,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1457,
|
|
"mean_token_accuracy": 0.06873320862650871,
|
|
"num_tokens": 339051.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.933918571472168,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.0403,
|
|
"mean_token_accuracy": 0.07153546996414661,
|
|
"num_tokens": 350308.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.77935724258423,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9367,
|
|
"mean_token_accuracy": 0.06920299977064133,
|
|
"num_tokens": 362159.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.58675937652588,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8746,
|
|
"mean_token_accuracy": 0.06771804988384247,
|
|
"num_tokens": 375157.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.392772483825684,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7082,
|
|
"mean_token_accuracy": 0.07377725951373577,
|
|
"num_tokens": 387318.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.153958225250244,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.662,
|
|
"mean_token_accuracy": 0.08222539648413658,
|
|
"num_tokens": 398933.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.963881874084473,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5815,
|
|
"mean_token_accuracy": 0.0776383075863123,
|
|
"num_tokens": 410460.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.766354751586913,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5298,
|
|
"mean_token_accuracy": 0.07729721069335938,
|
|
"num_tokens": 421894.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.61376428604126,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5055,
|
|
"mean_token_accuracy": 0.07357447482645511,
|
|
"num_tokens": 432976.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.49586353302002,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5487,
|
|
"mean_token_accuracy": 0.07971205189824104,
|
|
"num_tokens": 444859.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.427717113494873,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4231,
|
|
"mean_token_accuracy": 0.08752711713314057,
|
|
"num_tokens": 456508.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.312041282653809,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4263,
|
|
"mean_token_accuracy": 0.08335452601313591,
|
|
"num_tokens": 469064.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.230023956298828,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.347,
|
|
"mean_token_accuracy": 0.08570738211274147,
|
|
"num_tokens": 480743.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.206699085235595,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3673,
|
|
"mean_token_accuracy": 0.08695473670959472,
|
|
"num_tokens": 493378.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.153348922729492,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3107,
|
|
"mean_token_accuracy": 0.08663721978664399,
|
|
"num_tokens": 505641.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.109747982025146,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3616,
|
|
"mean_token_accuracy": 0.08820611983537674,
|
|
"num_tokens": 517783.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.069980669021607,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.2154,
|
|
"mean_token_accuracy": 0.09702874794602394,
|
|
"num_tokens": 528407.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.088402652740479,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.3335,
|
|
"mean_token_accuracy": 0.0919241763651371,
|
|
"num_tokens": 539974.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.991567897796631,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1789,
|
|
"mean_token_accuracy": 0.09620562493801117,
|
|
"num_tokens": 551127.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.010430145263673,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1818,
|
|
"mean_token_accuracy": 0.09887873977422715,
|
|
"num_tokens": 561980.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.9398411273956295,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2171,
|
|
"mean_token_accuracy": 0.09803635850548745,
|
|
"num_tokens": 573840.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.9045103073120115,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1223,
|
|
"mean_token_accuracy": 0.10269570201635361,
|
|
"num_tokens": 585110.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.831203842163086,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.0168,
|
|
"mean_token_accuracy": 0.10523020774126053,
|
|
"num_tokens": 596902.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.8273866176605225,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1703,
|
|
"mean_token_accuracy": 0.1047072984278202,
|
|
"num_tokens": 608738.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.822991180419922,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0956,
|
|
"mean_token_accuracy": 0.10134880691766739,
|
|
"num_tokens": 621078.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.900579166412354,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1582,
|
|
"mean_token_accuracy": 0.10307180657982826,
|
|
"num_tokens": 632333.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.694871425628662,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9781,
|
|
"mean_token_accuracy": 0.10547222793102265,
|
|
"num_tokens": 644474.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.7671226978302,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.05,
|
|
"mean_token_accuracy": 0.10735271498560905,
|
|
"num_tokens": 655608.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.7116927146911625,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0705,
|
|
"mean_token_accuracy": 0.10069631710648537,
|
|
"num_tokens": 667371.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.697999811172485,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0716,
|
|
"mean_token_accuracy": 0.10165307149291039,
|
|
"num_tokens": 679152.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.703333139419556,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.976,
|
|
"mean_token_accuracy": 0.11086443439126015,
|
|
"num_tokens": 690359.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.646430587768554,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9582,
|
|
"mean_token_accuracy": 0.10852264314889908,
|
|
"num_tokens": 701819.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.659921550750733,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0023,
|
|
"mean_token_accuracy": 0.10957548543810844,
|
|
"num_tokens": 711048.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.590796375274659,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8928,
|
|
"mean_token_accuracy": 0.11393210589885712,
|
|
"num_tokens": 721399.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.65145468711853,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9061,
|
|
"mean_token_accuracy": 0.11852319762110711,
|
|
"num_tokens": 732144.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.4970308303833,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8658,
|
|
"mean_token_accuracy": 0.11263575032353401,
|
|
"num_tokens": 743962.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.605427598953247,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.0196,
|
|
"mean_token_accuracy": 0.11022250354290009,
|
|
"num_tokens": 755641.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.507912826538086,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8509,
|
|
"mean_token_accuracy": 0.11853420287370682,
|
|
"num_tokens": 766798.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.568133211135864,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.9301,
|
|
"mean_token_accuracy": 0.11699827089905739,
|
|
"num_tokens": 778097.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.431187677383423,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8572,
|
|
"mean_token_accuracy": 0.12058786600828171,
|
|
"num_tokens": 789775.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.508008241653442,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9158,
|
|
"mean_token_accuracy": 0.11246205344796181,
|
|
"num_tokens": 800155.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.496634769439697,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.9179,
|
|
"mean_token_accuracy": 0.11470787152647972,
|
|
"num_tokens": 811213.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.542068147659302,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.9034,
|
|
"mean_token_accuracy": 0.10915727838873863,
|
|
"num_tokens": 822832.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.420533800125122,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8752,
|
|
"mean_token_accuracy": 0.11799765825271606,
|
|
"num_tokens": 834824.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.471309661865234,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9009,
|
|
"mean_token_accuracy": 0.11093073859810829,
|
|
"num_tokens": 846969.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.535832786560059,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9809,
|
|
"mean_token_accuracy": 0.10712321475148201,
|
|
"num_tokens": 859271.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.452226400375366,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8774,
|
|
"mean_token_accuracy": 0.11831732466816902,
|
|
"num_tokens": 869754.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.40360279083252,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8011,
|
|
"mean_token_accuracy": 0.1226475939154625,
|
|
"num_tokens": 880519.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.318375492095948,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7696,
|
|
"mean_token_accuracy": 0.11847401708364487,
|
|
"num_tokens": 890765.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.387319278717041,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7752,
|
|
"mean_token_accuracy": 0.11672125980257989,
|
|
"num_tokens": 901717.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.397585868835449,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8494,
|
|
"mean_token_accuracy": 0.11776698976755143,
|
|
"num_tokens": 913334.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.4451488018035885,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.11650485098361969,
|
|
"num_tokens": 924753.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.340163087844848,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7891,
|
|
"mean_token_accuracy": 0.12223831489682198,
|
|
"num_tokens": 935692.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.3431860446929935,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8737,
|
|
"mean_token_accuracy": 0.11860141828656197,
|
|
"num_tokens": 947902.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.3516919136047365,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8063,
|
|
"mean_token_accuracy": 0.12171181738376617,
|
|
"num_tokens": 959437.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.20117769241333,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6245,
|
|
"mean_token_accuracy": 0.12898706570267676,
|
|
"num_tokens": 970191.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.262586164474487,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7321,
|
|
"mean_token_accuracy": 0.12053022459149361,
|
|
"num_tokens": 981811.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.3112424373626705,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8546,
|
|
"mean_token_accuracy": 0.11418978720903397,
|
|
"num_tokens": 994034.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.285151576995849,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7999,
|
|
"mean_token_accuracy": 0.11736572235822677,
|
|
"num_tokens": 1005506.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.276934432983398,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7517,
|
|
"mean_token_accuracy": 0.11421283110976219,
|
|
"num_tokens": 1017103.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.244399690628052,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.84,
|
|
"mean_token_accuracy": 0.11778046488761902,
|
|
"num_tokens": 1029606.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.335804605484009,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.789,
|
|
"mean_token_accuracy": 0.11802555918693543,
|
|
"num_tokens": 1041899.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.2514319896698,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7092,
|
|
"mean_token_accuracy": 0.12920955047011376,
|
|
"num_tokens": 1053577.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.230760812759399,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7625,
|
|
"mean_token_accuracy": 0.12477129399776458,
|
|
"num_tokens": 1065541.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.258627557754517,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7034,
|
|
"mean_token_accuracy": 0.121210016310215,
|
|
"num_tokens": 1076138.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.243265295028687,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.7561,
|
|
"mean_token_accuracy": 0.12767059430480004,
|
|
"num_tokens": 1087620.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.192060947418213,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6443,
|
|
"mean_token_accuracy": 0.12917531430721282,
|
|
"num_tokens": 1099493.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.143154096603394,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.696,
|
|
"mean_token_accuracy": 0.12751599624753,
|
|
"num_tokens": 1110559.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.090892791748047,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6684,
|
|
"mean_token_accuracy": 0.1201030507683754,
|
|
"num_tokens": 1121051.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.2134480476379395,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.12791844457387924,
|
|
"num_tokens": 1132305.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.121208190917969,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6354,
|
|
"mean_token_accuracy": 0.13059915378689765,
|
|
"num_tokens": 1142979.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.124688339233399,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6429,
|
|
"mean_token_accuracy": 0.13205073550343513,
|
|
"num_tokens": 1153889.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.173402786254883,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6555,
|
|
"mean_token_accuracy": 0.12510655000805854,
|
|
"num_tokens": 1166030.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.213367700576782,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.8218,
|
|
"mean_token_accuracy": 0.11716388240456581,
|
|
"num_tokens": 1177545.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.142013311386108,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.63,
|
|
"mean_token_accuracy": 0.13155306726694108,
|
|
"num_tokens": 1188944.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.023855352401734,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6974,
|
|
"mean_token_accuracy": 0.12238200083374977,
|
|
"num_tokens": 1199517.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.1075825691223145,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6283,
|
|
"mean_token_accuracy": 0.12261475175619126,
|
|
"num_tokens": 1211536.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.080765342712402,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5351,
|
|
"mean_token_accuracy": 0.13503727167844773,
|
|
"num_tokens": 1224159.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.064063882827758,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.13505509868264198,
|
|
"num_tokens": 1235226.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.969502115249634,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.1370991587638855,
|
|
"num_tokens": 1245862.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.037106370925903,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5373,
|
|
"mean_token_accuracy": 0.1353856362402439,
|
|
"num_tokens": 1257512.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.028940439224243,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6458,
|
|
"mean_token_accuracy": 0.1271481417119503,
|
|
"num_tokens": 1269317.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.974031114578247,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5319,
|
|
"mean_token_accuracy": 0.12299542650580406,
|
|
"num_tokens": 1281878.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.952550315856934,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5502,
|
|
"mean_token_accuracy": 0.13390207588672637,
|
|
"num_tokens": 1293178.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.94937572479248,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.13220486268401146,
|
|
"num_tokens": 1304969.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.081587600708008,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5722,
|
|
"mean_token_accuracy": 0.13268239945173263,
|
|
"num_tokens": 1317301.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.960885334014892,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5506,
|
|
"mean_token_accuracy": 0.13222013115882875,
|
|
"num_tokens": 1327688.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.99568247795105,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.13380020037293433,
|
|
"num_tokens": 1338750.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.9811159610748295,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.12341757640242576,
|
|
"num_tokens": 1350899.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.057421350479126,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5033,
|
|
"mean_token_accuracy": 0.13546376153826714,
|
|
"num_tokens": 1363184.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.953424024581909,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4861,
|
|
"mean_token_accuracy": 0.1358728751540184,
|
|
"num_tokens": 1374192.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.766305589675904,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4998,
|
|
"mean_token_accuracy": 0.13279664665460586,
|
|
"num_tokens": 1384888.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.100843906402588,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5908,
|
|
"mean_token_accuracy": 0.13604374155402182,
|
|
"num_tokens": 1395139.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.812396669387818,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.13559869676828384,
|
|
"num_tokens": 1407219.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.959701156616211,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4986,
|
|
"mean_token_accuracy": 0.13413800969719886,
|
|
"num_tokens": 1418917.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.8605883598327635,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4729,
|
|
"mean_token_accuracy": 0.13215331062674524,
|
|
"num_tokens": 1430792.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.870712947845459,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.1390850931406021,
|
|
"num_tokens": 1442825.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.9546905040740965,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5848,
|
|
"mean_token_accuracy": 0.1320830576121807,
|
|
"num_tokens": 1454078.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.909980916976929,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.13304588049650193,
|
|
"num_tokens": 1465164.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.899385166168213,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4964,
|
|
"mean_token_accuracy": 0.13703863248229026,
|
|
"num_tokens": 1476813.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.867896032333374,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5169,
|
|
"mean_token_accuracy": 0.13063866794109344,
|
|
"num_tokens": 1488547.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.025978374481201,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.522,
|
|
"mean_token_accuracy": 0.13043418899178505,
|
|
"num_tokens": 1500714.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.821457815170288,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5044,
|
|
"mean_token_accuracy": 0.13662170022726058,
|
|
"num_tokens": 1512212.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.883290338516235,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.471,
|
|
"mean_token_accuracy": 0.13708159923553467,
|
|
"num_tokens": 1523610.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.790850353240967,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4375,
|
|
"mean_token_accuracy": 0.13195957690477372,
|
|
"num_tokens": 1535543.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.966132020950317,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6641,
|
|
"mean_token_accuracy": 0.12745087668299676,
|
|
"num_tokens": 1547183.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.799446535110474,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4042,
|
|
"mean_token_accuracy": 0.14067018032073975,
|
|
"num_tokens": 1559265.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.883531522750855,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.435,
|
|
"mean_token_accuracy": 0.13348256796598434,
|
|
"num_tokens": 1569774.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.758243894577026,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.3664,
|
|
"mean_token_accuracy": 0.14002081379294395,
|
|
"num_tokens": 1579408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.737592172622681,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3952,
|
|
"mean_token_accuracy": 0.14295617043972014,
|
|
"num_tokens": 1591849.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.807192468643189,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4707,
|
|
"mean_token_accuracy": 0.13754646629095077,
|
|
"num_tokens": 1603269.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.934098720550537,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.5128,
|
|
"mean_token_accuracy": 0.12959487438201905,
|
|
"num_tokens": 1613639.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.877666711807251,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.13218488544225693,
|
|
"num_tokens": 1625393.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.748217916488647,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3657,
|
|
"mean_token_accuracy": 0.13785189315676688,
|
|
"num_tokens": 1636355.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.8460822105407715,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4009,
|
|
"mean_token_accuracy": 0.13792139366269113,
|
|
"num_tokens": 1646157.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.716140365600586,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3961,
|
|
"mean_token_accuracy": 0.13261248767375947,
|
|
"num_tokens": 1657827.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.787322759628296,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4788,
|
|
"mean_token_accuracy": 0.14132225662469863,
|
|
"num_tokens": 1669023.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.8325389385223385,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.13686123490333557,
|
|
"num_tokens": 1680048.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.897904634475708,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.6169,
|
|
"mean_token_accuracy": 0.12690431475639344,
|
|
"num_tokens": 1690907.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.893639278411865,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4363,
|
|
"mean_token_accuracy": 0.13882233425974846,
|
|
"num_tokens": 1702337.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.728409624099731,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3874,
|
|
"mean_token_accuracy": 0.13424424231052398,
|
|
"num_tokens": 1713242.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.744375705718994,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.13707793802022933,
|
|
"num_tokens": 1724939.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.712884521484375,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.14935051500797272,
|
|
"num_tokens": 1737311.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.824639749526978,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4514,
|
|
"mean_token_accuracy": 0.13682929798960686,
|
|
"num_tokens": 1749528.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.68354549407959,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3275,
|
|
"mean_token_accuracy": 0.14307046681642532,
|
|
"num_tokens": 1760304.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.660215139389038,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3171,
|
|
"mean_token_accuracy": 0.14092384576797484,
|
|
"num_tokens": 1772014.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.7041209697723385,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.1367984175682068,
|
|
"num_tokens": 1784585.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.728722429275512,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3004,
|
|
"mean_token_accuracy": 0.146743543446064,
|
|
"num_tokens": 1795246.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.596188020706177,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.14472177475690842,
|
|
"num_tokens": 1806826.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.763730049133301,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.14111077263951302,
|
|
"num_tokens": 1818766.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.678760385513305,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.15023117810487746,
|
|
"num_tokens": 1830824.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.609415769577026,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.13778330758213997,
|
|
"num_tokens": 1841792.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.652772665023804,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3008,
|
|
"mean_token_accuracy": 0.14102251529693605,
|
|
"num_tokens": 1854683.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.727771043777466,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.3995,
|
|
"mean_token_accuracy": 0.13676784187555313,
|
|
"num_tokens": 1865826.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.702198505401611,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3485,
|
|
"mean_token_accuracy": 0.14424023181200027,
|
|
"num_tokens": 1876759.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.572908020019531,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.1390812113881111,
|
|
"num_tokens": 1888013.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.834191608428955,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3987,
|
|
"mean_token_accuracy": 0.1389234647154808,
|
|
"num_tokens": 1898964.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.619566154479981,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3096,
|
|
"mean_token_accuracy": 0.14486038088798522,
|
|
"num_tokens": 1909728.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.573022413253784,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2396,
|
|
"mean_token_accuracy": 0.14724621176719666,
|
|
"num_tokens": 1919895.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.622575473785401,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.1686,
|
|
"mean_token_accuracy": 0.1482459105551243,
|
|
"num_tokens": 1930839.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.6008491039276125,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3622,
|
|
"mean_token_accuracy": 0.1424940586090088,
|
|
"num_tokens": 1942605.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.617079734802246,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.3529,
|
|
"mean_token_accuracy": 0.13537877276539803,
|
|
"num_tokens": 1954863.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.722651815414428,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4252,
|
|
"mean_token_accuracy": 0.1417405441403389,
|
|
"num_tokens": 1966088.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.604581260681153,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.14236779659986495,
|
|
"num_tokens": 1978081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.656841897964478,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3249,
|
|
"mean_token_accuracy": 0.1358143836259842,
|
|
"num_tokens": 1991212.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.694861984252929,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.311,
|
|
"mean_token_accuracy": 0.14360752776265145,
|
|
"num_tokens": 2002074.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.539075565338135,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.14888798743486403,
|
|
"num_tokens": 2013039.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.617077302932739,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3741,
|
|
"mean_token_accuracy": 0.1400503121316433,
|
|
"num_tokens": 2024744.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.588595581054688,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.1453889586031437,
|
|
"num_tokens": 2035587.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.616622066497802,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3266,
|
|
"mean_token_accuracy": 0.13622945696115493,
|
|
"num_tokens": 2047924.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.539765977859497,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.14483485221862794,
|
|
"num_tokens": 2060161.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.607950258255005,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2629,
|
|
"mean_token_accuracy": 0.14627112001180648,
|
|
"num_tokens": 2071674.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.590583610534668,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3995,
|
|
"mean_token_accuracy": 0.1397729016840458,
|
|
"num_tokens": 2084025.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.667711496353149,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.14221117421984672,
|
|
"num_tokens": 2094501.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.599315881729126,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3056,
|
|
"mean_token_accuracy": 0.14709803313016892,
|
|
"num_tokens": 2106207.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.5739052295684814,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.1523227147758007,
|
|
"num_tokens": 2116879.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.544489240646362,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2681,
|
|
"mean_token_accuracy": 0.1414512149989605,
|
|
"num_tokens": 2128884.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.482966566085816,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2153,
|
|
"mean_token_accuracy": 0.14321899712085723,
|
|
"num_tokens": 2140810.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.64809398651123,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2752,
|
|
"mean_token_accuracy": 0.13929763957858085,
|
|
"num_tokens": 2152312.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.420036125183105,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.14043607711791992,
|
|
"num_tokens": 2164408.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.556408071517945,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.14646506905555726,
|
|
"num_tokens": 2176050.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.423853635787964,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.15012319162487983,
|
|
"num_tokens": 2187354.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.393097972869873,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.14260236471891402,
|
|
"num_tokens": 2198686.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.461620712280274,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.14377033933997155,
|
|
"num_tokens": 2209780.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.521939277648926,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.15148081481456757,
|
|
"num_tokens": 2221760.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.4953220844268795,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.1426544666290283,
|
|
"num_tokens": 2233767.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.553147888183593,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2132,
|
|
"mean_token_accuracy": 0.1449471965432167,
|
|
"num_tokens": 2244841.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.426078653335571,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.15349577814340593,
|
|
"num_tokens": 2255620.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.492886877059936,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.15196479558944703,
|
|
"num_tokens": 2266345.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.406527471542359,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.14961037039756775,
|
|
"num_tokens": 2277190.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.483725643157959,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.15189518705010413,
|
|
"num_tokens": 2288241.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.433297443389892,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.2272,
|
|
"mean_token_accuracy": 0.144133760035038,
|
|
"num_tokens": 2301092.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.4213059425354,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.1475769981741905,
|
|
"num_tokens": 2313622.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.370494604110718,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.15354661494493485,
|
|
"num_tokens": 2325699.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.43495192527771,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.1460404135286808,
|
|
"num_tokens": 2337816.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.590832901000977,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.2957,
|
|
"mean_token_accuracy": 0.14283925592899321,
|
|
"num_tokens": 2348793.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.46081771850586,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.14770057797431946,
|
|
"num_tokens": 2360209.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.489052057266235,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.14201200753450394,
|
|
"num_tokens": 2370597.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.489638328552246,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.2478,
|
|
"mean_token_accuracy": 0.1417911544442177,
|
|
"num_tokens": 2381466.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.575153255462647,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.3352,
|
|
"mean_token_accuracy": 0.138764651119709,
|
|
"num_tokens": 2394507.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.458651733398438,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.14835959821939468,
|
|
"num_tokens": 2406367.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.432104206085205,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.14652103781700135,
|
|
"num_tokens": 2416962.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.524100685119629,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.13934570401906968,
|
|
"num_tokens": 2429441.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.394040298461914,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.1505374975502491,
|
|
"num_tokens": 2441360.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.361066913604736,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.14372813031077386,
|
|
"num_tokens": 2452928.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.374180650711059,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.15205594003200532,
|
|
"num_tokens": 2464218.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.407055807113648,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.15480452179908752,
|
|
"num_tokens": 2475084.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.378732442855835,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.1464,
|
|
"mean_token_accuracy": 0.14829933345317842,
|
|
"num_tokens": 2486845.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.37392635345459,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.2167,
|
|
"mean_token_accuracy": 0.14155052751302719,
|
|
"num_tokens": 2498049.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.389601182937622,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.15035107880830764,
|
|
"num_tokens": 2509511.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.484518432617188,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.156458543241024,
|
|
"num_tokens": 2521518.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.210693788528443,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 5.9549,
|
|
"mean_token_accuracy": 0.1586344212293625,
|
|
"num_tokens": 2533141.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.256671905517578,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.1536861389875412,
|
|
"num_tokens": 2542907.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.330707740783692,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.14371281042695044,
|
|
"num_tokens": 2554497.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.479738664627075,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.1489127516746521,
|
|
"num_tokens": 2567035.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.258924865722657,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.15842699110507966,
|
|
"num_tokens": 2578003.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.524848222732544,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.305,
|
|
"mean_token_accuracy": 0.14301338717341422,
|
|
"num_tokens": 2590272.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.27402629852295,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.14725035130977632,
|
|
"num_tokens": 2602874.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.340481901168824,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.15673150569200517,
|
|
"num_tokens": 2613835.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.4138932704925535,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.14377753883600236,
|
|
"num_tokens": 2624986.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.416733598709106,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.1885,
|
|
"mean_token_accuracy": 0.13901318833231927,
|
|
"num_tokens": 2637654.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.371509313583374,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.1510764852166176,
|
|
"num_tokens": 2648947.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.312252235412598,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.14612228646874428,
|
|
"num_tokens": 2659573.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.283674192428589,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.15488046854734422,
|
|
"num_tokens": 2671491.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.3300315856933596,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.1487934708595276,
|
|
"num_tokens": 2682705.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.23258752822876,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.15133922249078752,
|
|
"num_tokens": 2693539.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.278180265426636,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.1541109189391136,
|
|
"num_tokens": 2705403.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.453830718994141,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.14809799268841745,
|
|
"num_tokens": 2717320.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.294747066497803,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14518905133008958,
|
|
"num_tokens": 2730056.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.351133012771607,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.15574622750282288,
|
|
"num_tokens": 2741399.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.388057708740234,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.1420239381492138,
|
|
"num_tokens": 2752277.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.356492948532105,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14670252203941345,
|
|
"num_tokens": 2763172.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.38686170578003,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 6.1064,
|
|
"mean_token_accuracy": 0.1515388995409012,
|
|
"num_tokens": 2775096.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.348104858398438,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.145056813955307,
|
|
"num_tokens": 2786007.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.295395755767823,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.15835101902484894,
|
|
"num_tokens": 2797265.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.344145345687866,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.15130333825945855,
|
|
"num_tokens": 2809427.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.2863054275512695,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.15372449159622192,
|
|
"num_tokens": 2822880.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.415712070465088,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 6.172,
|
|
"mean_token_accuracy": 0.14482916817069053,
|
|
"num_tokens": 2834760.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.345460033416748,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.14920846298336982,
|
|
"num_tokens": 2846517.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.268563079833984,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.15922427102923392,
|
|
"num_tokens": 2857280.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.290250253677368,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.15346607118844985,
|
|
"num_tokens": 2869735.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.315689992904663,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 6.0386,
|
|
"mean_token_accuracy": 0.1542970433831215,
|
|
"num_tokens": 2881681.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.181022119522095,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.15502342879772185,
|
|
"num_tokens": 2893828.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.151469087600708,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 6.0066,
|
|
"mean_token_accuracy": 0.15098301693797112,
|
|
"num_tokens": 2905804.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.467128086090088,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.1455710545182228,
|
|
"num_tokens": 2918709.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.319386768341064,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.15271421596407891,
|
|
"num_tokens": 2930589.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.2710630893707275,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.15638522952795028,
|
|
"num_tokens": 2940635.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.209631776809692,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.16009382605552674,
|
|
"num_tokens": 2952731.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.254339933395386,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 6.0027,
|
|
"mean_token_accuracy": 0.15292049050331116,
|
|
"num_tokens": 2964544.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.232159233093261,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.15449643433094024,
|
|
"num_tokens": 2974996.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.179900312423706,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.1571894556283951,
|
|
"num_tokens": 2986496.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.219573736190796,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.15346220433712005,
|
|
"num_tokens": 2997693.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.187070655822754,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 5.9838,
|
|
"mean_token_accuracy": 0.15567831546068192,
|
|
"num_tokens": 3009155.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.1994123458862305,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.16280196905136107,
|
|
"num_tokens": 3020944.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.196508884429932,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.15572714507579805,
|
|
"num_tokens": 3032893.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.2522900104522705,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.15061216205358505,
|
|
"num_tokens": 3044937.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.236337089538575,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.9482,
|
|
"mean_token_accuracy": 0.15663958489894866,
|
|
"num_tokens": 3056071.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.207484483718872,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.14877638295292855,
|
|
"num_tokens": 3067724.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.282546806335449,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 6.0031,
|
|
"mean_token_accuracy": 0.15774892270565033,
|
|
"num_tokens": 3080779.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.203645133972168,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.15141114294528962,
|
|
"num_tokens": 3091991.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.1824891567230225,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.1594395488500595,
|
|
"num_tokens": 3103713.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.157753753662109,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.15652020871639252,
|
|
"num_tokens": 3115891.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.1673017024993895,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.863,
|
|
"mean_token_accuracy": 0.16944663524627684,
|
|
"num_tokens": 3126223.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.263637685775757,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.15185227915644645,
|
|
"num_tokens": 3137537.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.291316413879395,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.15476293712854386,
|
|
"num_tokens": 3150126.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.224523258209229,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.16093770563602447,
|
|
"num_tokens": 3161684.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.1495531558990475,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.1610415458679199,
|
|
"num_tokens": 3172342.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.276655769348144,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.16042522042989732,
|
|
"num_tokens": 3183681.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.0783570289611815,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.8443,
|
|
"mean_token_accuracy": 0.16978892534971238,
|
|
"num_tokens": 3194122.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.182632637023926,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.15853887796401978,
|
|
"num_tokens": 3205719.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.120689725875854,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.15988747626543046,
|
|
"num_tokens": 3216262.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.274352216720581,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 5.9881,
|
|
"mean_token_accuracy": 0.15093525648117065,
|
|
"num_tokens": 3228035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.099394607543945,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.1615759938955307,
|
|
"num_tokens": 3239643.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.1452710151672365,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.16112854480743408,
|
|
"num_tokens": 3250293.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.273663139343261,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.1478336751461029,
|
|
"num_tokens": 3262448.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.064791679382324,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.1563238486647606,
|
|
"num_tokens": 3274041.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.223370218276978,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.1560527950525284,
|
|
"num_tokens": 3285063.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.2211846828460695,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9666,
|
|
"mean_token_accuracy": 0.15824110060930252,
|
|
"num_tokens": 3297031.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.197072458267212,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9573,
|
|
"mean_token_accuracy": 0.1547205552458763,
|
|
"num_tokens": 3308187.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.1259284019470215,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.9549,
|
|
"mean_token_accuracy": 0.15546363741159439,
|
|
"num_tokens": 3319439.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.13748083114624,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.9476,
|
|
"mean_token_accuracy": 0.1569317899644375,
|
|
"num_tokens": 3331715.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.180286836624146,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.9111,
|
|
"mean_token_accuracy": 0.1668043091893196,
|
|
"num_tokens": 3342281.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.317266130447388,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.15571026653051376,
|
|
"num_tokens": 3353530.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.173709964752197,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.1503211587667465,
|
|
"num_tokens": 3365083.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.193066835403442,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.1586127519607544,
|
|
"num_tokens": 3378143.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.231985139846802,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.15540362745523453,
|
|
"num_tokens": 3388438.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.073607492446899,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.15305885225534438,
|
|
"num_tokens": 3400150.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.05352897644043,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.8103,
|
|
"mean_token_accuracy": 0.16507214605808257,
|
|
"num_tokens": 3411073.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.134577798843384,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.8741,
|
|
"mean_token_accuracy": 0.16767435967922212,
|
|
"num_tokens": 3422196.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.159465312957764,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.1562460742890835,
|
|
"num_tokens": 3432568.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.127354431152344,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.9367,
|
|
"mean_token_accuracy": 0.15517643094062805,
|
|
"num_tokens": 3444096.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.010924053192139,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.1662687450647354,
|
|
"num_tokens": 3455502.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.194846773147583,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.15202689915895462,
|
|
"num_tokens": 3467753.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.0664191246032715,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.16286454498767852,
|
|
"num_tokens": 3479206.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.076856899261474,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.16005290448665618,
|
|
"num_tokens": 3490914.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.107672548294067,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.15861159712076187,
|
|
"num_tokens": 3502932.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.048060894012451,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.16491712927818297,
|
|
"num_tokens": 3515071.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.208171081542969,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.15694793835282325,
|
|
"num_tokens": 3526845.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.080694913864136,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.15591877698898315,
|
|
"num_tokens": 3538810.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.19296703338623,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.16947668939828872,
|
|
"num_tokens": 3549570.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.932188987731934,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.17169633954763414,
|
|
"num_tokens": 3560937.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.1333564758300785,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.8803,
|
|
"mean_token_accuracy": 0.15864527374505996,
|
|
"num_tokens": 3573603.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.011618709564209,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.8981,
|
|
"mean_token_accuracy": 0.15385786592960357,
|
|
"num_tokens": 3586034.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.00404839515686,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.16424645334482194,
|
|
"num_tokens": 3597305.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.191066837310791,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.1484566166996956,
|
|
"num_tokens": 3608758.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.153885412216186,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.15386258363723754,
|
|
"num_tokens": 3621508.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.169773721694947,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.9308,
|
|
"mean_token_accuracy": 0.16340596377849578,
|
|
"num_tokens": 3634826.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.981789493560791,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.1757243752479553,
|
|
"num_tokens": 3646427.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.004927635192871,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.15893372148275375,
|
|
"num_tokens": 3658157.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.1353168964385985,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.1580752119421959,
|
|
"num_tokens": 3670695.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.068402624130249,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.1568877637386322,
|
|
"num_tokens": 3683379.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.990541267395019,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.1711265340447426,
|
|
"num_tokens": 3694411.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.020878696441651,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.17313530445098876,
|
|
"num_tokens": 3703833.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.092939853668213,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.16913823708891867,
|
|
"num_tokens": 3714702.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.116333436965943,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.1631587713956833,
|
|
"num_tokens": 3726000.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.10855507850647,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.16023391783237456,
|
|
"num_tokens": 3737681.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.14500937461853,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.9447,
|
|
"mean_token_accuracy": 0.160616697371006,
|
|
"num_tokens": 3749477.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.12149567604065,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.9172,
|
|
"mean_token_accuracy": 0.1614253431558609,
|
|
"num_tokens": 3759946.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.0639667987823485,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.16388048231601715,
|
|
"num_tokens": 3770147.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.004903888702392,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.1723175212740898,
|
|
"num_tokens": 3781028.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.069085884094238,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.8428,
|
|
"mean_token_accuracy": 0.15636067241430282,
|
|
"num_tokens": 3792529.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.152743339538574,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.1637915402650833,
|
|
"num_tokens": 3804630.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.922781467437744,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.17320418655872344,
|
|
"num_tokens": 3815019.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.049646425247192,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.1636585474014282,
|
|
"num_tokens": 3825648.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.026040172576904,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.16479419767856598,
|
|
"num_tokens": 3836779.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.989983701705933,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.15931192189455032,
|
|
"num_tokens": 3848350.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.11183648109436,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.1647849351167679,
|
|
"num_tokens": 3859792.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.995904159545899,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.16283721774816512,
|
|
"num_tokens": 3871539.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.97924485206604,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.16463494151830674,
|
|
"num_tokens": 3885025.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.080967426300049,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.15857994854450225,
|
|
"num_tokens": 3896519.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.997112226486206,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.17066951245069503,
|
|
"num_tokens": 3907636.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.9870668888092045,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.163779553771019,
|
|
"num_tokens": 3917746.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.008543872833252,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.17229880392551422,
|
|
"num_tokens": 3928901.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.945359992980957,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.16977249681949616,
|
|
"num_tokens": 3940094.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.0175048351287845,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.16932837516069413,
|
|
"num_tokens": 3952714.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.957449197769165,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.17156666070222854,
|
|
"num_tokens": 3963107.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.997269058227539,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.17136422395706177,
|
|
"num_tokens": 3973454.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.957687091827393,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.16045114547014236,
|
|
"num_tokens": 3985352.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.06954288482666,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.8073,
|
|
"mean_token_accuracy": 0.16711310297250748,
|
|
"num_tokens": 3997088.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.022908163070679,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.8296,
|
|
"mean_token_accuracy": 0.1672845110297203,
|
|
"num_tokens": 4008551.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.984336090087891,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.16413284242153167,
|
|
"num_tokens": 4020886.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.037380981445312,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.1607511505484581,
|
|
"num_tokens": 4032811.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.000102710723877,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.16719766408205033,
|
|
"num_tokens": 4044102.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.994718551635742,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.8172,
|
|
"mean_token_accuracy": 0.1658351629972458,
|
|
"num_tokens": 4056849.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.982969522476196,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.1637706860899925,
|
|
"num_tokens": 4068392.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.006184864044189,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.170590578019619,
|
|
"num_tokens": 4078949.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.909857225418091,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.16255858093500136,
|
|
"num_tokens": 4091432.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.954454946517944,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.6951,
|
|
"mean_token_accuracy": 0.17012006640434266,
|
|
"num_tokens": 4103001.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.986909008026123,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.16849690526723862,
|
|
"num_tokens": 4113570.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.007826423645019,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.16274026334285735,
|
|
"num_tokens": 4125658.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.95023546218872,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.7205,
|
|
"mean_token_accuracy": 0.16709082424640656,
|
|
"num_tokens": 4137424.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.011094236373902,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.16791113317012787,
|
|
"num_tokens": 4149772.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.905970621109009,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.1733687311410904,
|
|
"num_tokens": 4162246.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.918607234954834,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.17318637818098068,
|
|
"num_tokens": 4173449.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.937366533279419,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.1625620037317276,
|
|
"num_tokens": 4185560.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.952977085113526,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.15584002658724785,
|
|
"num_tokens": 4197843.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.022454023361206,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.16660276055335999,
|
|
"num_tokens": 4210009.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.942712497711182,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.15909999683499337,
|
|
"num_tokens": 4222213.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.004428100585938,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.16446920484304428,
|
|
"num_tokens": 4234159.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.9961381435394285,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.8588,
|
|
"mean_token_accuracy": 0.15720370337367057,
|
|
"num_tokens": 4246358.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.0960883617401125,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.1618606984615326,
|
|
"num_tokens": 4256698.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.9101903438568115,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.7071,
|
|
"mean_token_accuracy": 0.17886844426393508,
|
|
"num_tokens": 4268007.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.921268177032471,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.1664751335978508,
|
|
"num_tokens": 4278583.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.077760076522827,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.1648312047123909,
|
|
"num_tokens": 4290267.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.952408123016357,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.17537832111120225,
|
|
"num_tokens": 4302177.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.861745071411133,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.6961,
|
|
"mean_token_accuracy": 0.17122533768415452,
|
|
"num_tokens": 4312420.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.0441864967346195,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.16632328778505326,
|
|
"num_tokens": 4324050.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.901515483856201,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.17299336791038514,
|
|
"num_tokens": 4335336.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.852649927139282,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.17085058093070984,
|
|
"num_tokens": 4346239.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.94590048789978,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.1664916157722473,
|
|
"num_tokens": 4357195.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.875322675704956,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.17268287986516953,
|
|
"num_tokens": 4368905.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.9875816822052,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.16864405423402787,
|
|
"num_tokens": 4381708.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.846536254882812,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.18302999585866928,
|
|
"num_tokens": 4393199.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.953036260604859,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.1608387678861618,
|
|
"num_tokens": 4403986.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.000203561782837,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.1680416136980057,
|
|
"num_tokens": 4415574.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.88345947265625,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.1759544551372528,
|
|
"num_tokens": 4427579.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.957119131088257,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.7284,
|
|
"mean_token_accuracy": 0.16889535933732985,
|
|
"num_tokens": 4440045.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.919621276855469,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.16399643570184708,
|
|
"num_tokens": 4450129.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.897604322433471,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.17348277419805527,
|
|
"num_tokens": 4461378.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.938304138183594,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.17170394212007523,
|
|
"num_tokens": 4472249.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.890934944152832,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.1649644747376442,
|
|
"num_tokens": 4484243.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.9530542373657225,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.16919784843921662,
|
|
"num_tokens": 4495776.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.853722429275512,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.16727603524923323,
|
|
"num_tokens": 4508581.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.9266825199127195,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.16845113039016724,
|
|
"num_tokens": 4519753.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.900664520263672,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.1777681216597557,
|
|
"num_tokens": 4529957.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.974092197418213,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.16701797097921373,
|
|
"num_tokens": 4541181.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.877654409408569,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.17389168292284013,
|
|
"num_tokens": 4552235.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.943179893493652,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.1742224797606468,
|
|
"num_tokens": 4564045.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.8289329528808596,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.1785324141383171,
|
|
"num_tokens": 4575141.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.852221345901489,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.17090109288692473,
|
|
"num_tokens": 4586491.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.9237569808959964,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.1718616396188736,
|
|
"num_tokens": 4598421.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.894081020355225,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.18285724371671677,
|
|
"num_tokens": 4609688.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.882657384872436,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.16469601690769195,
|
|
"num_tokens": 4621169.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.9078254222869875,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.17368836998939513,
|
|
"num_tokens": 4632512.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.930011129379272,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.16718964874744416,
|
|
"num_tokens": 4644356.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.975589370727539,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.1692662999033928,
|
|
"num_tokens": 4655601.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.867001152038574,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.16788003146648406,
|
|
"num_tokens": 4666813.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.944839382171631,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.16712078899145127,
|
|
"num_tokens": 4679123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.912882137298584,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.17612844854593276,
|
|
"num_tokens": 4690485.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.806442070007324,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.1725752279162407,
|
|
"num_tokens": 4702573.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.891991090774536,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.16615684181451798,
|
|
"num_tokens": 4715653.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.882970237731934,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.7004,
|
|
"mean_token_accuracy": 0.17499724328517913,
|
|
"num_tokens": 4726051.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.934564733505249,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.16007425934076308,
|
|
"num_tokens": 4738176.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.954264545440674,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.16757950633764268,
|
|
"num_tokens": 4749547.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.838888549804688,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.1716952934861183,
|
|
"num_tokens": 4761967.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.834277725219726,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.1739967070519924,
|
|
"num_tokens": 4772847.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.932867527008057,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.17146496921777726,
|
|
"num_tokens": 4785049.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.833413457870483,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.16502633690834045,
|
|
"num_tokens": 4797484.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.859524917602539,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.1668789342045784,
|
|
"num_tokens": 4809422.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.92907977104187,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.16625447124242781,
|
|
"num_tokens": 4822340.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.860308408737183,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.6352,
|
|
"mean_token_accuracy": 0.17530228346586227,
|
|
"num_tokens": 4833382.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.790621709823609,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.1817137658596039,
|
|
"num_tokens": 4843916.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.927386856079101,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.17769275158643721,
|
|
"num_tokens": 4855420.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.880288362503052,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.1706031545996666,
|
|
"num_tokens": 4866540.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.895658493041992,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.6665,
|
|
"mean_token_accuracy": 0.17256468534469604,
|
|
"num_tokens": 4878860.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.960579252243042,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.16489656418561935,
|
|
"num_tokens": 4889692.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.970758581161499,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.17567683905363082,
|
|
"num_tokens": 4901337.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.75920524597168,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.6448,
|
|
"mean_token_accuracy": 0.17524836361408233,
|
|
"num_tokens": 4912340.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.857781076431275,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.17784797996282578,
|
|
"num_tokens": 4923429.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.896333789825439,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.16947495341300964,
|
|
"num_tokens": 4934826.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.881085062026978,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.17018158435821534,
|
|
"num_tokens": 4945189.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.932586526870727,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.1765411153435707,
|
|
"num_tokens": 4956060.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.858534717559815,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.6717,
|
|
"mean_token_accuracy": 0.17596034407615663,
|
|
"num_tokens": 4967710.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.857064723968506,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.16734581142663957,
|
|
"num_tokens": 4978716.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.874509191513061,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.17040223330259324,
|
|
"num_tokens": 4990742.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.943036460876465,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.17488541454076767,
|
|
"num_tokens": 5001217.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.846171760559082,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.16881862580776213,
|
|
"num_tokens": 5012750.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.865509939193726,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.17801522612571716,
|
|
"num_tokens": 5023818.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.9269102096557615,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.7176,
|
|
"mean_token_accuracy": 0.16671841889619826,
|
|
"num_tokens": 5035060.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.882676506042481,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.16046614050865174,
|
|
"num_tokens": 5046780.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.83563551902771,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.16501837968826294,
|
|
"num_tokens": 5059152.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.86581654548645,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.6854,
|
|
"mean_token_accuracy": 0.17040270417928696,
|
|
"num_tokens": 5069971.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.828520584106445,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.6356,
|
|
"mean_token_accuracy": 0.17748477756977082,
|
|
"num_tokens": 5080640.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.851872873306275,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.17382104694843292,
|
|
"num_tokens": 5091240.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.754461812973022,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.6739,
|
|
"mean_token_accuracy": 0.17026726752519608,
|
|
"num_tokens": 5102920.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.863530015945434,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.7022,
|
|
"mean_token_accuracy": 0.17059502005577087,
|
|
"num_tokens": 5114240.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.968141746520996,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.9208,
|
|
"mean_token_accuracy": 0.15989586859941482,
|
|
"num_tokens": 5126653.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.998019552230835,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.1644024819135666,
|
|
"num_tokens": 5138778.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.859699535369873,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.17633095979690552,
|
|
"num_tokens": 5148670.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.68029522895813,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.16909311413764955,
|
|
"num_tokens": 5159617.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.894393634796143,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.7241,
|
|
"mean_token_accuracy": 0.1727438136935234,
|
|
"num_tokens": 5171225.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.87973313331604,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.1702487885951996,
|
|
"num_tokens": 5184586.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.842156028747558,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.1675831764936447,
|
|
"num_tokens": 5196089.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.868828344345093,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.17021534889936446,
|
|
"num_tokens": 5207581.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.812510681152344,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.672,
|
|
"mean_token_accuracy": 0.1744819015264511,
|
|
"num_tokens": 5219108.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.866617918014526,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.17249889373779298,
|
|
"num_tokens": 5231137.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.9222582340240475,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.17626527845859527,
|
|
"num_tokens": 5243528.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.688040399551392,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.17519633769989013,
|
|
"num_tokens": 5254869.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.8270598411560055,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.17478814274072646,
|
|
"num_tokens": 5265370.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.782625007629394,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.17365225702524184,
|
|
"num_tokens": 5277812.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.785833263397217,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.1779184401035309,
|
|
"num_tokens": 5289107.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.854281902313232,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.16607864797115326,
|
|
"num_tokens": 5301489.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.707867050170899,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.6112,
|
|
"mean_token_accuracy": 0.18296469151973724,
|
|
"num_tokens": 5313273.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.856090545654297,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.17394472658634186,
|
|
"num_tokens": 5324227.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.788931798934937,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.18264526426792144,
|
|
"num_tokens": 5335138.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.759352922439575,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.17215364724397658,
|
|
"num_tokens": 5345652.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.9246961116790775,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.17096742987632751,
|
|
"num_tokens": 5357999.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.823276519775391,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.6663,
|
|
"mean_token_accuracy": 0.1679316133260727,
|
|
"num_tokens": 5369032.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.7893892288208,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.17573301643133163,
|
|
"num_tokens": 5380692.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.879408645629883,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.16351985484361647,
|
|
"num_tokens": 5392320.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.847774028778076,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.17470421493053437,
|
|
"num_tokens": 5404374.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.8599584102630615,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.17138945311307907,
|
|
"num_tokens": 5415471.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.725100374221801,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.1748400166630745,
|
|
"num_tokens": 5425971.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.821712970733643,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.18096609115600587,
|
|
"num_tokens": 5437638.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.868386602401733,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.17262430340051652,
|
|
"num_tokens": 5449463.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.809400224685669,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.7433,
|
|
"mean_token_accuracy": 0.17124372869729995,
|
|
"num_tokens": 5460972.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.957932853698731,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.16553788185119628,
|
|
"num_tokens": 5471575.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.7461940288543705,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.17493402808904648,
|
|
"num_tokens": 5483041.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.791565608978272,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.17630909532308578,
|
|
"num_tokens": 5494040.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.730622577667236,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.18595009446144103,
|
|
"num_tokens": 5504217.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.860027551651001,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.6931,
|
|
"mean_token_accuracy": 0.1753861427307129,
|
|
"num_tokens": 5517180.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.809644031524658,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.16900173276662828,
|
|
"num_tokens": 5529626.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.8468280792236325,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.18043770939111708,
|
|
"num_tokens": 5540844.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.825774335861206,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.5693,
|
|
"mean_token_accuracy": 0.17974244356155394,
|
|
"num_tokens": 5551732.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.826646757125855,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.17213926166296006,
|
|
"num_tokens": 5562692.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.881090593338013,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.1720082253217697,
|
|
"num_tokens": 5574884.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.716880178451538,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.18319079726934434,
|
|
"num_tokens": 5585335.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.850202512741089,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.17081967294216155,
|
|
"num_tokens": 5597621.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.732968711853028,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.17374192029237748,
|
|
"num_tokens": 5609795.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.789673328399658,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.173040571808815,
|
|
"num_tokens": 5621473.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.892057800292969,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.7274,
|
|
"mean_token_accuracy": 0.17482251077890396,
|
|
"num_tokens": 5635064.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.872965669631958,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.16974180638790132,
|
|
"num_tokens": 5647382.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.820632839202881,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.17786978632211686,
|
|
"num_tokens": 5658417.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.767739152908325,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.18194347023963928,
|
|
"num_tokens": 5672190.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.772201633453369,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.1847991779446602,
|
|
"num_tokens": 5684259.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.729731464385987,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.1762344717979431,
|
|
"num_tokens": 5696505.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.725724935531616,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.5436,
|
|
"mean_token_accuracy": 0.181012162566185,
|
|
"num_tokens": 5707638.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.763240242004395,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.18620459139347076,
|
|
"num_tokens": 5719098.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.9247959613800045,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.1620590589940548,
|
|
"num_tokens": 5731345.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.656325578689575,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.17786547392606736,
|
|
"num_tokens": 5742604.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.699789333343506,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.18326022177934648,
|
|
"num_tokens": 5754620.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.7961937427520756,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.17634303420782088,
|
|
"num_tokens": 5764764.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.671987724304199,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.1902934193611145,
|
|
"num_tokens": 5776341.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.814025735855102,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.16588144600391388,
|
|
"num_tokens": 5788604.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.8230632781982425,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.17924741953611373,
|
|
"num_tokens": 5800194.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.757388734817505,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.18109989911317825,
|
|
"num_tokens": 5812978.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.717558908462524,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.18487590551376343,
|
|
"num_tokens": 5824591.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.745062971115113,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.17669124156236649,
|
|
"num_tokens": 5835970.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.807597732543945,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.16880002468824387,
|
|
"num_tokens": 5848687.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.737652158737182,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.17555102258920668,
|
|
"num_tokens": 5860820.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.786333513259888,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.1809490665793419,
|
|
"num_tokens": 5872172.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.769077014923096,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.17688888311386108,
|
|
"num_tokens": 5883574.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.845238304138183,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.17598800212144852,
|
|
"num_tokens": 5895223.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.752743339538574,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.17801688909530639,
|
|
"num_tokens": 5907448.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.751397609710693,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.17808189988136292,
|
|
"num_tokens": 5918906.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.76022891998291,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.1827773556113243,
|
|
"num_tokens": 5930619.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.866481304168701,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.17080766707658768,
|
|
"num_tokens": 5941554.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.791235780715942,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.6619,
|
|
"mean_token_accuracy": 0.1792931705713272,
|
|
"num_tokens": 5953309.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.759411811828613,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.17513532787561417,
|
|
"num_tokens": 5965286.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.769647026062012,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.17810043692588806,
|
|
"num_tokens": 5976558.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.803124666213989,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.16947010159492493,
|
|
"num_tokens": 5988793.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.7729833126068115,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.16540661901235582,
|
|
"num_tokens": 5999825.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.835980033874511,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.17402078658342363,
|
|
"num_tokens": 6010408.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.805245876312256,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.17170876115560532,
|
|
"num_tokens": 6021161.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.706417989730835,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.18810333758592607,
|
|
"num_tokens": 6032646.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.766708278656006,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.17591285109519958,
|
|
"num_tokens": 6045019.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.657771825790405,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.1834905758500099,
|
|
"num_tokens": 6055644.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.78851728439331,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.5693,
|
|
"mean_token_accuracy": 0.17673975676298143,
|
|
"num_tokens": 6066488.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.758440732955933,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.17449358552694322,
|
|
"num_tokens": 6078300.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.734206056594848,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.1704964131116867,
|
|
"num_tokens": 6089180.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.757406234741211,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.1837097004055977,
|
|
"num_tokens": 6099093.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.790572166442871,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.1773001104593277,
|
|
"num_tokens": 6109161.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.86971116065979,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.17001539021730422,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.717875337600708,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.17720083743333817,
|
|
"num_tokens": 6132398.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.713741064071655,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.17020554840564728,
|
|
"num_tokens": 6143099.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.752955055236816,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.1820665955543518,
|
|
"num_tokens": 6154815.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.738240671157837,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.1818923234939575,
|
|
"num_tokens": 6165696.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.721163082122803,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.17519191652536392,
|
|
"num_tokens": 6177042.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.815378189086914,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.1751040607690811,
|
|
"num_tokens": 6188691.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.593714475631714,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.18646937608718872,
|
|
"num_tokens": 6199931.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.693178653717041,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.18345472663640977,
|
|
"num_tokens": 6211493.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.793261384963989,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.1827055275440216,
|
|
"num_tokens": 6221505.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.638125991821289,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.1871676668524742,
|
|
"num_tokens": 6233058.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.74454984664917,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.17437177300453185,
|
|
"num_tokens": 6244713.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.722670650482177,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.17518469989299773,
|
|
"num_tokens": 6256624.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.696188926696777,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.1736260771751404,
|
|
"num_tokens": 6271134.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.834325361251831,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.17634287625551223,
|
|
"num_tokens": 6282082.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.782431602478027,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.17405078411102295,
|
|
"num_tokens": 6293869.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.699025249481201,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.17163943350315095,
|
|
"num_tokens": 6304858.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.754938268661499,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.1830345094203949,
|
|
"num_tokens": 6316738.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.702230501174927,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.17675393223762512,
|
|
"num_tokens": 6327691.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.787597799301148,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.17426677644252778,
|
|
"num_tokens": 6337964.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.631732511520386,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.1759776771068573,
|
|
"num_tokens": 6349764.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.8128139019012455,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.18075311332941055,
|
|
"num_tokens": 6360538.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.763351535797119,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.17973174452781676,
|
|
"num_tokens": 6372489.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.568811273574829,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.18664876222610474,
|
|
"num_tokens": 6383080.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.806193017959595,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.1757884532213211,
|
|
"num_tokens": 6394033.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.715140008926392,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.17878031432628633,
|
|
"num_tokens": 6404990.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.701559019088745,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.18534403890371323,
|
|
"num_tokens": 6416337.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.730889225006104,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.6656,
|
|
"mean_token_accuracy": 0.1772391602396965,
|
|
"num_tokens": 6427892.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.69028673171997,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.17937600910663604,
|
|
"num_tokens": 6440300.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.708783483505249,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.18418766260147096,
|
|
"num_tokens": 6451499.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.712428379058838,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.18144695162773133,
|
|
"num_tokens": 6462882.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.6650489330291744,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.1818947970867157,
|
|
"num_tokens": 6475042.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.719558477401733,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.1792231246829033,
|
|
"num_tokens": 6486245.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.716267395019531,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.18538395762443544,
|
|
"num_tokens": 6497705.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.62763934135437,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.1870325416326523,
|
|
"num_tokens": 6508193.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.725575256347656,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.6016,
|
|
"mean_token_accuracy": 0.1776618927717209,
|
|
"num_tokens": 6519228.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.755958032608032,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.180067740380764,
|
|
"num_tokens": 6530743.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.667758846282959,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.17980502247810365,
|
|
"num_tokens": 6542588.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.799747085571289,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.16938518285751342,
|
|
"num_tokens": 6554002.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.747061014175415,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.6675,
|
|
"mean_token_accuracy": 0.17701776772737504,
|
|
"num_tokens": 6563358.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.683012914657593,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.17571266144514083,
|
|
"num_tokens": 6574986.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.7084794521331785,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.18074920177459716,
|
|
"num_tokens": 6587407.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.637572622299194,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.1878151774406433,
|
|
"num_tokens": 6598483.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.657338953018188,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.5831,
|
|
"mean_token_accuracy": 0.18044260144233704,
|
|
"num_tokens": 6610749.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.7645731449127195,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.17333664000034332,
|
|
"num_tokens": 6621762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.7428053855896,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.1731718435883522,
|
|
"num_tokens": 6632296.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.733534955978394,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.18240266442298889,
|
|
"num_tokens": 6644413.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.6336816310882565,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.17972939014434813,
|
|
"num_tokens": 6655634.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.676279926300049,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.1837601602077484,
|
|
"num_tokens": 6665977.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.707220602035522,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.17969339042901994,
|
|
"num_tokens": 6677165.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.689497089385986,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.17441802322864533,
|
|
"num_tokens": 6688182.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.734628391265869,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.17993243038654327,
|
|
"num_tokens": 6699259.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.700125122070313,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.17867809534072876,
|
|
"num_tokens": 6710071.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.7129288673400875,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.1841597393155098,
|
|
"num_tokens": 6720267.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.750007438659668,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.17657051831483841,
|
|
"num_tokens": 6730919.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.648938798904419,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.18033284693956375,
|
|
"num_tokens": 6741480.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.743981218338012,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.18312747478485109,
|
|
"num_tokens": 6751816.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.641194438934326,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.18100760728120804,
|
|
"num_tokens": 6763645.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.674943637847901,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.18233796060085297,
|
|
"num_tokens": 6774795.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.654936456680298,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.18299856334924697,
|
|
"num_tokens": 6786833.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.561620569229126,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.18655213415622712,
|
|
"num_tokens": 6798134.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.713185405731201,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.18436760306358338,
|
|
"num_tokens": 6807918.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.7143415927886965,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.17538298517465592,
|
|
"num_tokens": 6818689.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.6440918922424315,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.18471998870372772,
|
|
"num_tokens": 6830871.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.652586126327515,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.18692311495542527,
|
|
"num_tokens": 6842857.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.662132787704468,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.18150224685668945,
|
|
"num_tokens": 6853727.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.701902055740357,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.181272454559803,
|
|
"num_tokens": 6864728.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.726777839660644,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.17763462513685227,
|
|
"num_tokens": 6875001.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.619700956344604,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.18973949998617173,
|
|
"num_tokens": 6887026.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.502902475233371,
|
|
"eval_loss": 5.541717052459717,
|
|
"eval_mean_token_accuracy": 0.1886520807157706,
|
|
"eval_num_tokens": 6887026.0,
|
|
"eval_runtime": 20.5725,
|
|
"eval_samples_per_second": 1595.091,
|
|
"eval_steps_per_second": 199.392,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.856368923187256,
|
|
"epoch": 0.2886647454370797,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995805505395328,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.1774316482245922,
|
|
"num_tokens": 6900118.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.697432231903076,
|
|
"epoch": 0.28914505283381364,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995784555218778,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.18242888450622557,
|
|
"num_tokens": 6912135.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.604808378219604,
|
|
"epoch": 0.2896253602305475,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995763552901779,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.18907646983861923,
|
|
"num_tokens": 6923781.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.707881021499634,
|
|
"epoch": 0.29010566762728146,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995742498444818,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.17432108521461487,
|
|
"num_tokens": 6935804.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.645840358734131,
|
|
"epoch": 0.2905859750240154,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995721391848387,
|
|
"loss": 5.5479,
|
|
"mean_token_accuracy": 0.1852487027645111,
|
|
"num_tokens": 6948289.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.6874512195587155,
|
|
"epoch": 0.2910662824207493,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995700233112972,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.1854916110634804,
|
|
"num_tokens": 6958719.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.667976808547974,
|
|
"epoch": 0.2915465898174832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995679022239066,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.19045528024435043,
|
|
"num_tokens": 6969041.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.699865007400513,
|
|
"epoch": 0.2920268972142171,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995657759227162,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.182636097073555,
|
|
"num_tokens": 6981206.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.718282699584961,
|
|
"epoch": 0.29250720461095103,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995636444077751,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.185975481569767,
|
|
"num_tokens": 6993169.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.693597221374512,
|
|
"epoch": 0.2929875120076849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995615076791333,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.18187058120965957,
|
|
"num_tokens": 7005175.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.718658876419068,
|
|
"epoch": 0.29346781940441885,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995593657368399,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.18206669241189957,
|
|
"num_tokens": 7016738.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.677747821807861,
|
|
"epoch": 0.29394812680115273,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499557218580945,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.19187912195920945,
|
|
"num_tokens": 7028399.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.676383399963379,
|
|
"epoch": 0.29442843419788667,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995550662114981,
|
|
"loss": 5.609,
|
|
"mean_token_accuracy": 0.1750513270497322,
|
|
"num_tokens": 7039528.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.552373743057251,
|
|
"epoch": 0.29490874159462055,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995529086285495,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.1948387324810028,
|
|
"num_tokens": 7051399.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.549876499176025,
|
|
"epoch": 0.2953890489913545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499550745832149,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.19237693697214125,
|
|
"num_tokens": 7062452.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.653821849822998,
|
|
"epoch": 0.29586935638808837,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995485778223471,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.18380301892757417,
|
|
"num_tokens": 7074052.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.735548591613769,
|
|
"epoch": 0.2963496637848223,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995464045991939,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.17654668986797334,
|
|
"num_tokens": 7086692.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.676431322097779,
|
|
"epoch": 0.2968299711815562,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049954422616274,
|
|
"loss": 5.5379,
|
|
"mean_token_accuracy": 0.18212951272726058,
|
|
"num_tokens": 7098221.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.604320764541626,
|
|
"epoch": 0.2973102785782901,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995420425130359,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.19011141061782838,
|
|
"num_tokens": 7110129.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.742700242996216,
|
|
"epoch": 0.297790585975024,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995398536501324,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.1788194879889488,
|
|
"num_tokens": 7121523.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.67659215927124,
|
|
"epoch": 0.29827089337175794,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995376595740801,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.1874501124024391,
|
|
"num_tokens": 7133482.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.569614505767822,
|
|
"epoch": 0.2987512007684918,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995354602849302,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.1866934195160866,
|
|
"num_tokens": 7144031.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.696511077880859,
|
|
"epoch": 0.29923150816522576,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995332557827337,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.17538492977619172,
|
|
"num_tokens": 7155469.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.712473821640015,
|
|
"epoch": 0.29971181556195964,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995310460675416,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.17630098164081573,
|
|
"num_tokens": 7167077.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.611568403244019,
|
|
"epoch": 0.3001921229586936,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995288311394053,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.18795533925294877,
|
|
"num_tokens": 7178917.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.720008277893067,
|
|
"epoch": 0.30067243035542746,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995266109983764,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.18024739027023315,
|
|
"num_tokens": 7190284.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.6326478004455565,
|
|
"epoch": 0.3011527377521614,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995243856445062,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.1853068143129349,
|
|
"num_tokens": 7202391.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.651069784164429,
|
|
"epoch": 0.3016330451488953,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995221550778466,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.18516746163368225,
|
|
"num_tokens": 7212882.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.580076694488525,
|
|
"epoch": 0.3021133525456292,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995199192984491,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.18979058265686036,
|
|
"num_tokens": 7224102.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.668196296691894,
|
|
"epoch": 0.3025936599423631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995176783063657,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.19092514961957932,
|
|
"num_tokens": 7234579.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.632351970672607,
|
|
"epoch": 0.30307396733909703,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995154321016487,
|
|
"loss": 5.5527,
|
|
"mean_token_accuracy": 0.17617070972919463,
|
|
"num_tokens": 7246065.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.689699316024781,
|
|
"epoch": 0.3035542747358309,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995131806843499,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.17578233033418655,
|
|
"num_tokens": 7258899.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.697991991043091,
|
|
"epoch": 0.30403458213256485,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995109240545218,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.16840812861919402,
|
|
"num_tokens": 7271887.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.684932518005371,
|
|
"epoch": 0.3045148895292987,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995086622122167,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.1787776455283165,
|
|
"num_tokens": 7282773.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.610663270950317,
|
|
"epoch": 0.30499519692603266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995063951574871,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.19089628905057907,
|
|
"num_tokens": 7294460.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.563593482971191,
|
|
"epoch": 0.30547550432276654,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995041228903856,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.18796637505292893,
|
|
"num_tokens": 7305125.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.523098659515381,
|
|
"epoch": 0.3059558117195005,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499501845410965,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.18510405570268632,
|
|
"num_tokens": 7317738.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.672911310195923,
|
|
"epoch": 0.30643611911623436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994995627192781,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.19007018804550171,
|
|
"num_tokens": 7329820.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.664368581771851,
|
|
"epoch": 0.3069164265129683,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994972748153781,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.18072844594717025,
|
|
"num_tokens": 7341471.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.655959177017212,
|
|
"epoch": 0.30739673390970224,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499494981699318,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.18741880357265472,
|
|
"num_tokens": 7352459.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.657233381271363,
|
|
"epoch": 0.3078770413064361,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499492683371151,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.19309578239917755,
|
|
"num_tokens": 7363129.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.672110652923584,
|
|
"epoch": 0.30835734870317005,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994903798309306,
|
|
"loss": 5.4805,
|
|
"mean_token_accuracy": 0.18603945672512054,
|
|
"num_tokens": 7373726.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.638332557678223,
|
|
"epoch": 0.30883765609990393,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994880710787102,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.18476174771785736,
|
|
"num_tokens": 7383847.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.636308574676514,
|
|
"epoch": 0.30931796349663787,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994857571145432,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.17792272418737412,
|
|
"num_tokens": 7396425.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.722712135314941,
|
|
"epoch": 0.30979827089337175,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994834379384837,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.17942839562892915,
|
|
"num_tokens": 7407591.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.641121482849121,
|
|
"epoch": 0.3102785782901057,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994811135505851,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.18451326191425324,
|
|
"num_tokens": 7419668.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.71372013092041,
|
|
"epoch": 0.31075888568683957,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994787839509018,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.17802973836660385,
|
|
"num_tokens": 7431969.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.7248636245727536,
|
|
"epoch": 0.3112391930835735,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994764491394876,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.17835410982370375,
|
|
"num_tokens": 7443467.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.701698255538941,
|
|
"epoch": 0.3117195004803074,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994741091163969,
|
|
"loss": 5.5316,
|
|
"mean_token_accuracy": 0.1843402549624443,
|
|
"num_tokens": 7455220.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.625455045700074,
|
|
"epoch": 0.3121998078770413,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499471763881684,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.1868407368659973,
|
|
"num_tokens": 7466452.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.6683906555175785,
|
|
"epoch": 0.3126801152737752,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994694134354031,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.19345567375421524,
|
|
"num_tokens": 7478798.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.67936692237854,
|
|
"epoch": 0.31316042267050914,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499467057777609,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.18261555582284927,
|
|
"num_tokens": 7491039.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.6556963443756105,
|
|
"epoch": 0.313640730067243,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994646969083565,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.18663194477558137,
|
|
"num_tokens": 7501455.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.637513589859009,
|
|
"epoch": 0.31412103746397696,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994623308277002,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.1870144411921501,
|
|
"num_tokens": 7513484.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.64736270904541,
|
|
"epoch": 0.31460134486071084,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499459959535695,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.18189150094985962,
|
|
"num_tokens": 7524868.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.552604866027832,
|
|
"epoch": 0.3150816522574448,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994575830323962,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.19823386669158935,
|
|
"num_tokens": 7536290.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.544449758529663,
|
|
"epoch": 0.31556195965417866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994552013178586,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.1855172723531723,
|
|
"num_tokens": 7546994.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.641019678115844,
|
|
"epoch": 0.3160422670509126,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499452814392138,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.18413483053445817,
|
|
"num_tokens": 7559231.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.566317939758301,
|
|
"epoch": 0.3165225744476465,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994504222552894,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.18553677350282669,
|
|
"num_tokens": 7570894.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.681057786941528,
|
|
"epoch": 0.3170028818443804,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994480249073684,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.1790008470416069,
|
|
"num_tokens": 7581765.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.637446880340576,
|
|
"epoch": 0.3174831892411143,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994456223484308,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.19088079780340195,
|
|
"num_tokens": 7591828.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.554597568511963,
|
|
"epoch": 0.31796349663784823,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994432145785323,
|
|
"loss": 5.4722,
|
|
"mean_token_accuracy": 0.1824389725923538,
|
|
"num_tokens": 7604230.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.606625604629516,
|
|
"epoch": 0.3184438040345821,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994408015977288,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.18280257880687714,
|
|
"num_tokens": 7615780.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.642516803741455,
|
|
"epoch": 0.31892411143131605,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994383834060764,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.18346021175384522,
|
|
"num_tokens": 7627633.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.595742130279541,
|
|
"epoch": 0.31940441882804993,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994359600036311,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.17850975096225738,
|
|
"num_tokens": 7639487.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.604001712799072,
|
|
"epoch": 0.31988472622478387,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994335313904493,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.19206003099679947,
|
|
"num_tokens": 7649976.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.730104207992554,
|
|
"epoch": 0.32036503362151775,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994310975665873,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.17577773928642274,
|
|
"num_tokens": 7662555.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.589729261398316,
|
|
"epoch": 0.3208453410182517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994286585321017,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.19029964059591292,
|
|
"num_tokens": 7673869.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.544617462158203,
|
|
"epoch": 0.32132564841498557,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499426214287049,
|
|
"loss": 5.4966,
|
|
"mean_token_accuracy": 0.1829109936952591,
|
|
"num_tokens": 7687149.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.741382598876953,
|
|
"epoch": 0.3218059558117195,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994237648314862,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.17744301110506058,
|
|
"num_tokens": 7698352.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.543857479095459,
|
|
"epoch": 0.3222862632084534,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994213101654697,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.1924407362937927,
|
|
"num_tokens": 7709117.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.600641250610352,
|
|
"epoch": 0.3227665706051873,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499418850289057,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.19088683724403382,
|
|
"num_tokens": 7721731.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.544538974761963,
|
|
"epoch": 0.32324687800192126,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994163852023048,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.18850311189889907,
|
|
"num_tokens": 7733010.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.525831890106201,
|
|
"epoch": 0.32372718539865514,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994139149052706,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.19822303503751754,
|
|
"num_tokens": 7743905.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.6324950695037845,
|
|
"epoch": 0.3242074927953891,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994114393980117,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.19600466936826705,
|
|
"num_tokens": 7754891.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.663243675231934,
|
|
"epoch": 0.32468780019212296,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.18069053292274476,
|
|
"num_tokens": 7766831.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.604099988937378,
|
|
"epoch": 0.3251681075888569,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994064727530496,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.17826617062091826,
|
|
"num_tokens": 7778239.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.653008317947387,
|
|
"epoch": 0.3256484149855908,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994039816154618,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.19269052892923355,
|
|
"num_tokens": 7789449.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.6737199306488035,
|
|
"epoch": 0.3261287223823247,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049940148526788,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.1831203058362007,
|
|
"num_tokens": 7799507.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.631627130508423,
|
|
"epoch": 0.3266090297790586,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993989837103618,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.18923803716897963,
|
|
"num_tokens": 7811730.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.536287784576416,
|
|
"epoch": 0.3270893371757925,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993964769429657,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.19673447757959367,
|
|
"num_tokens": 7823108.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.599535274505615,
|
|
"epoch": 0.3275696445725264,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993939649657498,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.19003001600503922,
|
|
"num_tokens": 7835384.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.610070323944091,
|
|
"epoch": 0.32804995196926034,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993914477787721,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.18963380604982377,
|
|
"num_tokens": 7845860.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.621730661392212,
|
|
"epoch": 0.3285302593659942,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993889253820915,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.17740807086229324,
|
|
"num_tokens": 7856861.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.639326095581055,
|
|
"epoch": 0.32901056676272816,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993863977757663,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.18733595162630082,
|
|
"num_tokens": 7868902.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.672629690170288,
|
|
"epoch": 0.32949087415946204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993838649598552,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.183916312456131,
|
|
"num_tokens": 7880369.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.671369504928589,
|
|
"epoch": 0.329971181556196,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993813269344171,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.18307242691516876,
|
|
"num_tokens": 7892041.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.581494331359863,
|
|
"epoch": 0.33045148895292986,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993787836995108,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.18829255700111389,
|
|
"num_tokens": 7903644.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.620500564575195,
|
|
"epoch": 0.3309317963496638,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993762352551954,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.18013794720172882,
|
|
"num_tokens": 7915679.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.64208025932312,
|
|
"epoch": 0.3314121037463977,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993736816015301,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.18466965854167938,
|
|
"num_tokens": 7928020.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.69989047050476,
|
|
"epoch": 0.3318924111431316,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993711227385742,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.18176510632038118,
|
|
"num_tokens": 7940521.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.655500411987305,
|
|
"epoch": 0.3323727185398655,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993685586663871,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.18216118961572647,
|
|
"num_tokens": 7952234.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.635805416107178,
|
|
"epoch": 0.33285302593659943,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993659893850281,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.17915908247232437,
|
|
"num_tokens": 7964900.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.744531679153442,
|
|
"epoch": 0.3333333333333333,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993634148945573,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.1796124041080475,
|
|
"num_tokens": 7976661.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.607192420959473,
|
|
"epoch": 0.33381364073006725,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993608351950341,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.18725300580263138,
|
|
"num_tokens": 7987605.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.562268924713135,
|
|
"epoch": 0.33429394812680113,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993582502865185,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.18697861582040787,
|
|
"num_tokens": 7998879.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.567245864868164,
|
|
"epoch": 0.33477425552353507,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993556601690706,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1914919763803482,
|
|
"num_tokens": 8010634.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.679268884658813,
|
|
"epoch": 0.33525456292026895,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993530648427505,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.1801712170243263,
|
|
"num_tokens": 8022134.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.6034410953521725,
|
|
"epoch": 0.3357348703170029,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004993504643076184,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.18599268943071365,
|
|
"num_tokens": 8034454.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.599052667617798,
|
|
"epoch": 0.33621517771373677,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993478585637347,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.18078571557998657,
|
|
"num_tokens": 8046175.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.7199992656707765,
|
|
"epoch": 0.3366954851104707,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993452476111599,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.18013250231742858,
|
|
"num_tokens": 8057335.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.586530065536499,
|
|
"epoch": 0.3371757925072046,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993426314499546,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.1908952072262764,
|
|
"num_tokens": 8068860.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.594693231582641,
|
|
"epoch": 0.3376560999039385,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993400100801796,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.18420050293207169,
|
|
"num_tokens": 8078957.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.66205792427063,
|
|
"epoch": 0.3381364073006724,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993373835018956,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.18294065147638322,
|
|
"num_tokens": 8090143.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.5398303985595705,
|
|
"epoch": 0.33861671469740634,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993347517151638,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.18879144489765168,
|
|
"num_tokens": 8101961.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.4673174858093265,
|
|
"epoch": 0.3390970220941403,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993321147200452,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.19397564828395844,
|
|
"num_tokens": 8112635.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.604259014129639,
|
|
"epoch": 0.33957732949087416,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499329472516601,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.18167405426502228,
|
|
"num_tokens": 8123730.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.667423391342163,
|
|
"epoch": 0.3400576368876081,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993268251048925,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.1836775466799736,
|
|
"num_tokens": 8135258.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.5028644561767575,
|
|
"epoch": 0.340537944284342,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993241724849814,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.19033643305301667,
|
|
"num_tokens": 8145946.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.662060403823853,
|
|
"epoch": 0.3410182516810759,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499321514656929,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.1833277702331543,
|
|
"num_tokens": 8158422.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.606411266326904,
|
|
"epoch": 0.3414985590778098,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004993188516207972,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.1768040969967842,
|
|
"num_tokens": 8170849.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.514929866790771,
|
|
"epoch": 0.34197886647454373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993161833766478,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.18714098483324051,
|
|
"num_tokens": 8180907.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.671570301055908,
|
|
"epoch": 0.3424591738712776,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993135099245426,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.18224213421344757,
|
|
"num_tokens": 8193418.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.67411527633667,
|
|
"epoch": 0.34293948126801155,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993108312645438,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.18666320145130158,
|
|
"num_tokens": 8203873.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.6935811042785645,
|
|
"epoch": 0.34341978866474543,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993081473967135,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.18074584752321243,
|
|
"num_tokens": 8215150.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.700850534439087,
|
|
"epoch": 0.34390009606147937,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993054583211143,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.1836441859602928,
|
|
"num_tokens": 8225732.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.634114217758179,
|
|
"epoch": 0.34438040345821325,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993027640378081,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.185074183344841,
|
|
"num_tokens": 8237523.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.618394422531128,
|
|
"epoch": 0.3448607108549472,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499300064546858,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.1912684604525566,
|
|
"num_tokens": 8249660.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.516906976699829,
|
|
"epoch": 0.34534101825168106,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992973598483264,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.19338289052248,
|
|
"num_tokens": 8261224.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.524252653121948,
|
|
"epoch": 0.345821325648415,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499294649942276,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.185163913667202,
|
|
"num_tokens": 8272177.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.612853193283081,
|
|
"epoch": 0.3463016330451489,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992919348287699,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.18935857117176055,
|
|
"num_tokens": 8284449.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.605484247207642,
|
|
"epoch": 0.3467819404418828,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992892145078711,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.18779500126838683,
|
|
"num_tokens": 8297028.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.562705135345459,
|
|
"epoch": 0.3472622478386167,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992864889796427,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.19613474160432814,
|
|
"num_tokens": 8308348.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.527529048919678,
|
|
"epoch": 0.34774255523535064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992837582441481,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.199290631711483,
|
|
"num_tokens": 8318951.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.601118087768555,
|
|
"epoch": 0.3482228626320845,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992810223014506,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.1820528596639633,
|
|
"num_tokens": 8329979.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.646680927276611,
|
|
"epoch": 0.34870317002881845,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992782811516137,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.19204390794038773,
|
|
"num_tokens": 8340332.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.583606863021851,
|
|
"epoch": 0.34918347742555234,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992755347947011,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.18399002254009247,
|
|
"num_tokens": 8350376.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.597890138626099,
|
|
"epoch": 0.34966378482228627,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992727832307766,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.19591260701417923,
|
|
"num_tokens": 8361884.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.475208282470703,
|
|
"epoch": 0.35014409221902015,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992700264599039,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.19753890484571457,
|
|
"num_tokens": 8372914.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.60008659362793,
|
|
"epoch": 0.3506243996157541,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992672644821473,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.18138848543167113,
|
|
"num_tokens": 8385800.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.554371166229248,
|
|
"epoch": 0.35110470701248797,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992644972975707,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.19483094215393065,
|
|
"num_tokens": 8397783.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.555364084243775,
|
|
"epoch": 0.3515850144092219,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992617249062383,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.18674605190753937,
|
|
"num_tokens": 8409096.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.537117862701416,
|
|
"epoch": 0.3520653218059558,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992589473082147,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.18975790739059448,
|
|
"num_tokens": 8420833.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.574448442459106,
|
|
"epoch": 0.3525456292026897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992561645035641,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.18563806414604186,
|
|
"num_tokens": 8431848.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.6661418914794925,
|
|
"epoch": 0.3530259365994236,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992533764923515,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.1792108342051506,
|
|
"num_tokens": 8443620.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.611227035522461,
|
|
"epoch": 0.35350624399615754,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992505832746412,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.18762343227863312,
|
|
"num_tokens": 8455339.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.482066965103149,
|
|
"epoch": 0.3539865513928914,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992477848504983,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.19950634986162186,
|
|
"num_tokens": 8466342.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.584598255157471,
|
|
"epoch": 0.35446685878962536,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992449812199877,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.1848418191075325,
|
|
"num_tokens": 8476955.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.463259553909301,
|
|
"epoch": 0.3549471661863593,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992421723831745,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.1894671216607094,
|
|
"num_tokens": 8488148.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.579493665695191,
|
|
"epoch": 0.3554274735830932,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992393583401239,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.19188293665647507,
|
|
"num_tokens": 8499014.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.596961259841919,
|
|
"epoch": 0.3559077809798271,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992365390909014,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.1892913430929184,
|
|
"num_tokens": 8510191.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.530703353881836,
|
|
"epoch": 0.356388088376561,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992337146355721,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.19771458804607392,
|
|
"num_tokens": 8522368.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.531358337402343,
|
|
"epoch": 0.35686839577329493,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992308849742019,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.19607473760843278,
|
|
"num_tokens": 8533692.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.5771454811096195,
|
|
"epoch": 0.3573487031700288,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992280501068563,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.19042604863643647,
|
|
"num_tokens": 8545283.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.5737833976745605,
|
|
"epoch": 0.35782901056676275,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992252100336012,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.1912136569619179,
|
|
"num_tokens": 8555094.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.527818250656128,
|
|
"epoch": 0.35830931796349663,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992223647545027,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.18504495024681092,
|
|
"num_tokens": 8565179.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.519126605987549,
|
|
"epoch": 0.35878962536023057,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992195142696266,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.18766072690486907,
|
|
"num_tokens": 8575764.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.4557945728302,
|
|
"epoch": 0.35926993275696445,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992166585790391,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.19553449004888535,
|
|
"num_tokens": 8586052.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.583512306213379,
|
|
"epoch": 0.3597502401536984,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992137976828067,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.19101378172636033,
|
|
"num_tokens": 8597832.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.5705725193023685,
|
|
"epoch": 0.36023054755043227,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992109315809955,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.19249336719512938,
|
|
"num_tokens": 8609917.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.69265661239624,
|
|
"epoch": 0.3607108549471662,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992080602736725,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.1859462156891823,
|
|
"num_tokens": 8620137.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.549279022216797,
|
|
"epoch": 0.3611911623439001,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992051837609039,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.19426160603761672,
|
|
"num_tokens": 8630620.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.510299491882324,
|
|
"epoch": 0.361671469740634,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992023020427568,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.1957526132464409,
|
|
"num_tokens": 8642820.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.564976978302002,
|
|
"epoch": 0.3621517771373679,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991994151192979,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.19904405623674393,
|
|
"num_tokens": 8654081.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.531849479675293,
|
|
"epoch": 0.36263208453410184,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991965229905943,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.192228265106678,
|
|
"num_tokens": 8665097.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.514793777465821,
|
|
"epoch": 0.3631123919308357,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991936256567133,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.19535750299692153,
|
|
"num_tokens": 8676576.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.521311712265015,
|
|
"epoch": 0.36359269932756966,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499190723117722,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.18837981969118117,
|
|
"num_tokens": 8689217.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.622129154205322,
|
|
"epoch": 0.36407300672430354,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991878153736877,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.18299184441566468,
|
|
"num_tokens": 8701101.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.557949209213257,
|
|
"epoch": 0.3645533141210375,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991849024246781,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.19008831381797792,
|
|
"num_tokens": 8712769.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.458853769302368,
|
|
"epoch": 0.36503362151777136,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991819842707608,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.2006710723042488,
|
|
"num_tokens": 8724691.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.4897819519042965,
|
|
"epoch": 0.3655139289145053,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991790609120035,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.19308259785175325,
|
|
"num_tokens": 8738008.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.647251939773559,
|
|
"epoch": 0.3659942363112392,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499176132348474,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.18489226400852204,
|
|
"num_tokens": 8750353.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.543689203262329,
|
|
"epoch": 0.3664745437079731,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991731985802405,
|
|
"loss": 5.3135,
|
|
"mean_token_accuracy": 0.19515877068042756,
|
|
"num_tokens": 8761319.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.528530597686768,
|
|
"epoch": 0.366954851104707,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991702596073708,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.1902092441916466,
|
|
"num_tokens": 8772722.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.622223711013794,
|
|
"epoch": 0.36743515850144093,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991673154299335,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.1838071256875992,
|
|
"num_tokens": 8783886.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.535996437072754,
|
|
"epoch": 0.3679154658981748,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991643660479967,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.19513945132493973,
|
|
"num_tokens": 8795161.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.46628737449646,
|
|
"epoch": 0.36839577329490875,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991614114616289,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1940271556377411,
|
|
"num_tokens": 8805417.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.544608211517334,
|
|
"epoch": 0.3688760806916426,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991584516708988,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.1853586256504059,
|
|
"num_tokens": 8817980.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.467247343063354,
|
|
"epoch": 0.36935638808837656,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991554866758751,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.20033943504095078,
|
|
"num_tokens": 8829814.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.451752996444702,
|
|
"epoch": 0.36983669548511044,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991525164766265,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.18811409920454025,
|
|
"num_tokens": 8840220.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.552777338027954,
|
|
"epoch": 0.3703170028818444,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991495410732222,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.1898484781384468,
|
|
"num_tokens": 8852156.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.594563436508179,
|
|
"epoch": 0.37079731027857826,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991465604657311,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.187318854033947,
|
|
"num_tokens": 8863362.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.513800191879272,
|
|
"epoch": 0.3712776176753122,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991435746542224,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.19056402444839476,
|
|
"num_tokens": 8874957.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.482952213287353,
|
|
"epoch": 0.37175792507204614,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991405836387655,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.197955721616745,
|
|
"num_tokens": 8886171.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.56112813949585,
|
|
"epoch": 0.37223823246878,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991375874194298,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.1880374550819397,
|
|
"num_tokens": 8898103.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.602141952514648,
|
|
"epoch": 0.37271853986551395,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499134585996285,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.1887554794549942,
|
|
"num_tokens": 8910195.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.508390951156616,
|
|
"epoch": 0.37319884726224783,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991315793694004,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.19307397454977035,
|
|
"num_tokens": 8922865.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.484298133850098,
|
|
"epoch": 0.37367915465898177,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991285675388463,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.18590802401304246,
|
|
"num_tokens": 8933913.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.5140993118286135,
|
|
"epoch": 0.37415946205571565,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991255505046922,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.19200728535652162,
|
|
"num_tokens": 8945749.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.537529420852661,
|
|
"epoch": 0.3746397694524496,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991225282670083,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.18832141906023026,
|
|
"num_tokens": 8957454.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.528447246551513,
|
|
"epoch": 0.37512007684918347,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499119500825865,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.18769167214632035,
|
|
"num_tokens": 8968173.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.521517038345337,
|
|
"epoch": 0.3756003842459174,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991164681813323,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.18790487796068192,
|
|
"num_tokens": 8979187.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.518652725219726,
|
|
"epoch": 0.3760806916426513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991134303334807,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.20245950520038605,
|
|
"num_tokens": 8990007.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.553478336334228,
|
|
"epoch": 0.3765609990393852,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991103872823807,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.18004781156778335,
|
|
"num_tokens": 9001108.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.619579839706421,
|
|
"epoch": 0.3770413064361191,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499107339028103,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.19069913476705552,
|
|
"num_tokens": 9012704.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.548769998550415,
|
|
"epoch": 0.37752161383285304,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991042855707184,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.19307264387607576,
|
|
"num_tokens": 9024351.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.503924798965454,
|
|
"epoch": 0.3780019212295869,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991012269102977,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19487868547439574,
|
|
"num_tokens": 9035099.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.519660615921021,
|
|
"epoch": 0.37848222862632086,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990981630469119,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.18882775455713272,
|
|
"num_tokens": 9045675.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.537562656402588,
|
|
"epoch": 0.37896253602305474,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990950939806323,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.19698236733675004,
|
|
"num_tokens": 9057133.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.509730100631714,
|
|
"epoch": 0.3794428434197887,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049909201971153,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.19401778131723404,
|
|
"num_tokens": 9067806.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.4276715278625485,
|
|
"epoch": 0.37992315081652256,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004990889402396763,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.18785732090473176,
|
|
"num_tokens": 9079893.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.5233067035675045,
|
|
"epoch": 0.3804034582132565,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990858555651431,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.19050756096839905,
|
|
"num_tokens": 9091583.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.550552558898926,
|
|
"epoch": 0.3808837656099904,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004990827656880015,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.19440562576055526,
|
|
"num_tokens": 9102919.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.55585036277771,
|
|
"epoch": 0.3813640730067243,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990796706083235,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.19796214401721954,
|
|
"num_tokens": 9113876.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.59228892326355,
|
|
"epoch": 0.3818443804034582,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990765703261809,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.18200291842222213,
|
|
"num_tokens": 9125630.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.526579856872559,
|
|
"epoch": 0.38232468780019213,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990734648416458,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.19169966876506805,
|
|
"num_tokens": 9137302.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.550363063812256,
|
|
"epoch": 0.382804995196926,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990703541547901,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.19655774384737015,
|
|
"num_tokens": 9148048.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.562456321716309,
|
|
"epoch": 0.38328530259365995,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990672382656863,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.18959662169218064,
|
|
"num_tokens": 9158656.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.56610336303711,
|
|
"epoch": 0.38376560999039383,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990641171744064,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.19112168550491332,
|
|
"num_tokens": 9169324.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.399512863159179,
|
|
"epoch": 0.38424591738712777,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004990609908810231,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.19454552084207535,
|
|
"num_tokens": 9180238.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.376609754562378,
|
|
"epoch": 0.38472622478386165,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990578593856089,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.2046573966741562,
|
|
"num_tokens": 9190766.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.454186868667603,
|
|
"epoch": 0.3852065321805956,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990547226882366,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.19985881298780442,
|
|
"num_tokens": 9202445.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.507049560546875,
|
|
"epoch": 0.38568683957732947,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990515807889788,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.19425778985023498,
|
|
"num_tokens": 9212383.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.473901653289795,
|
|
"epoch": 0.3861671469740634,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990484336879087,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.19954835772514343,
|
|
"num_tokens": 9223619.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.52939658164978,
|
|
"epoch": 0.3866474543707973,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990452813850992,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.19099583178758622,
|
|
"num_tokens": 9234137.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.567514371871948,
|
|
"epoch": 0.3871277617675312,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990421238806236,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.19362707138061525,
|
|
"num_tokens": 9246093.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.600132036209106,
|
|
"epoch": 0.38760806916426516,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004990389611745551,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.1820152521133423,
|
|
"num_tokens": 9258021.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.531111192703247,
|
|
"epoch": 0.38808837656099904,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990357932669672,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.19151132330298423,
|
|
"num_tokens": 9267668.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.555135822296142,
|
|
"epoch": 0.388568683957733,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990326201579335,
|
|
"loss": 5.3786,
|
|
"mean_token_accuracy": 0.19348617643117905,
|
|
"num_tokens": 9279381.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.542493009567261,
|
|
"epoch": 0.38904899135446686,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990294418475274,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.18056786358356475,
|
|
"num_tokens": 9292578.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.516183137893677,
|
|
"epoch": 0.3895292987512008,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990262583358231,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.19588701725006102,
|
|
"num_tokens": 9304116.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.597984457015992,
|
|
"epoch": 0.3900096061479347,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990230696228943,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.1904660478234291,
|
|
"num_tokens": 9315877.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.475490474700928,
|
|
"epoch": 0.3904899135446686,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990198757088149,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.19458492398262023,
|
|
"num_tokens": 9326859.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.58276252746582,
|
|
"epoch": 0.3909702209414025,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990166765936593,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.18486582040786742,
|
|
"num_tokens": 9338067.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.546846532821656,
|
|
"epoch": 0.3914505283381364,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990134722775016,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.187855264544487,
|
|
"num_tokens": 9349564.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.414843559265137,
|
|
"epoch": 0.3919308357348703,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990102627604162,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.1960006907582283,
|
|
"num_tokens": 9359962.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.485929679870606,
|
|
"epoch": 0.39241114313160425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990070480424778,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1965571403503418,
|
|
"num_tokens": 9370251.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.533813524246216,
|
|
"epoch": 0.3928914505283381,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990038281237608,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.18898686170578002,
|
|
"num_tokens": 9381848.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.484734725952149,
|
|
"epoch": 0.39337175792507206,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990006030043401,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.20044010877609253,
|
|
"num_tokens": 9392475.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.5963152885437015,
|
|
"epoch": 0.39385206532180594,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989973726842906,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.1849365934729576,
|
|
"num_tokens": 9404014.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.491301393508911,
|
|
"epoch": 0.3943323727185399,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989941371636872,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.19178524613380432,
|
|
"num_tokens": 9415590.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.5896271705627445,
|
|
"epoch": 0.39481268011527376,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989908964426051,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.18390681594610214,
|
|
"num_tokens": 9427486.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.546288394927979,
|
|
"epoch": 0.3952929875120077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989876505211194,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.19701245725154876,
|
|
"num_tokens": 9438212.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.515650272369385,
|
|
"epoch": 0.3957732949087416,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989843993993056,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.2009940892457962,
|
|
"num_tokens": 9450922.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.440005683898926,
|
|
"epoch": 0.3962536023054755,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989811430772392,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.19450163543224336,
|
|
"num_tokens": 9461676.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.344911766052246,
|
|
"epoch": 0.3967339097022094,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989778815549957,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.20104293823242186,
|
|
"num_tokens": 9473517.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.577360010147094,
|
|
"epoch": 0.39721421709894333,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989746148326508,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.18508757799863815,
|
|
"num_tokens": 9485660.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.579628562927246,
|
|
"epoch": 0.3976945244956772,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989713429102805,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.19365087002515793,
|
|
"num_tokens": 9495983.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.469569396972656,
|
|
"epoch": 0.39817483189241115,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989680657879607,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.18402469903230667,
|
|
"num_tokens": 9507438.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.426924133300782,
|
|
"epoch": 0.39865513928914503,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989647834657675,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.198352387547493,
|
|
"num_tokens": 9517508.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.44339165687561,
|
|
"epoch": 0.39913544668587897,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498961495943777,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.1967193603515625,
|
|
"num_tokens": 9527641.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.540214347839355,
|
|
"epoch": 0.39961575408261285,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989582032220656,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.19204745441675186,
|
|
"num_tokens": 9538762.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.516460227966308,
|
|
"epoch": 0.4000960614793468,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989549053007096,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.18793113082647322,
|
|
"num_tokens": 9550246.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.502830600738525,
|
|
"epoch": 0.40057636887608067,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989516021797858,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.19199627488851548,
|
|
"num_tokens": 9562341.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.535028886795044,
|
|
"epoch": 0.4010566762728146,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498948293859371,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1898772045969963,
|
|
"num_tokens": 9574484.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.534992408752442,
|
|
"epoch": 0.4015369836695485,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989449803395415,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.19608523249626159,
|
|
"num_tokens": 9585241.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.468052387237549,
|
|
"epoch": 0.4020172910662824,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989416616203747,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.1911933347582817,
|
|
"num_tokens": 9598683.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.513876485824585,
|
|
"epoch": 0.4024975984630163,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989383377019476,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.19253019839525223,
|
|
"num_tokens": 9610127.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.517180013656616,
|
|
"epoch": 0.40297790585975024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989350085843371,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.19974516332149506,
|
|
"num_tokens": 9620009.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.484110546112061,
|
|
"epoch": 0.4034582132564842,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989316742676207,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.19785863012075425,
|
|
"num_tokens": 9632479.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.5497448444366455,
|
|
"epoch": 0.40393852065321806,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989283347518757,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.1979358360171318,
|
|
"num_tokens": 9644447.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.5536425590515135,
|
|
"epoch": 0.404418828049952,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989249900371797,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.18938606530427932,
|
|
"num_tokens": 9656886.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.545026254653931,
|
|
"epoch": 0.4048991354466859,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989216401236103,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.19519829005002975,
|
|
"num_tokens": 9667079.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.529067039489746,
|
|
"epoch": 0.4053794428434198,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989182850112455,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.1907690182328224,
|
|
"num_tokens": 9678237.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.505252885818481,
|
|
"epoch": 0.4058597502401537,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989149247001629,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.19691054970026017,
|
|
"num_tokens": 9688809.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.588089275360107,
|
|
"epoch": 0.40634005763688763,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989115591904407,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.19740096628665924,
|
|
"num_tokens": 9700460.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.427215480804444,
|
|
"epoch": 0.4068203650336215,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989081884821569,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.1917317107319832,
|
|
"num_tokens": 9711379.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.469858884811401,
|
|
"epoch": 0.40730067243035545,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989048125753899,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.19672452807426452,
|
|
"num_tokens": 9722792.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.494458913803101,
|
|
"epoch": 0.40778097982708933,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498901431470218,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.20301805436611176,
|
|
"num_tokens": 9733524.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.522690963745117,
|
|
"epoch": 0.40826128722382327,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988980451667198,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.1912778690457344,
|
|
"num_tokens": 9745430.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.482702207565308,
|
|
"epoch": 0.40874159462055715,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988946536649737,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.19407545924186706,
|
|
"num_tokens": 9756927.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.499572801589966,
|
|
"epoch": 0.4092219020172911,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988912569650585,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.19387470036745072,
|
|
"num_tokens": 9768350.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.421212005615234,
|
|
"epoch": 0.40970220941402496,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988878550670533,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.20099008083343506,
|
|
"num_tokens": 9779238.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.573772144317627,
|
|
"epoch": 0.4101825168107589,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988844479710369,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.1879114717245102,
|
|
"num_tokens": 9789262.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.564293384552002,
|
|
"epoch": 0.4106628242074928,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988810356770884,
|
|
"loss": 5.4091,
|
|
"mean_token_accuracy": 0.18880746513605118,
|
|
"num_tokens": 9800909.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.496455192565918,
|
|
"epoch": 0.4111431316042267,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498877618185287,
|
|
"loss": 5.3581,
|
|
"mean_token_accuracy": 0.19070667028427124,
|
|
"num_tokens": 9812538.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.536595296859741,
|
|
"epoch": 0.4116234390009606,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988741954957121,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.19641655087471008,
|
|
"num_tokens": 9824071.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.6177077293396,
|
|
"epoch": 0.41210374639769454,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988707676084432,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.18990107327699662,
|
|
"num_tokens": 9836713.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.447091197967529,
|
|
"epoch": 0.4125840537944284,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988673345235597,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.20155235081911088,
|
|
"num_tokens": 9847336.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.426625394821167,
|
|
"epoch": 0.41306436119116235,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988638962411416,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19377581775188446,
|
|
"num_tokens": 9858567.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.58170371055603,
|
|
"epoch": 0.41354466858789624,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988604527612685,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.18546154350042343,
|
|
"num_tokens": 9869254.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.49974217414856,
|
|
"epoch": 0.4140249759846302,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988570040840205,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.1991979733109474,
|
|
"num_tokens": 9879635.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.499043226242065,
|
|
"epoch": 0.41450528338136405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988535502094774,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.19734057039022446,
|
|
"num_tokens": 9891728.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.407152795791626,
|
|
"epoch": 0.414985590778098,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988500911377198,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.20194266736507416,
|
|
"num_tokens": 9903140.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.497075414657592,
|
|
"epoch": 0.41546589817483187,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988466268688276,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.19730229377746583,
|
|
"num_tokens": 9915562.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.466583013534546,
|
|
"epoch": 0.4159462055715658,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988431574028814,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18944159001111985,
|
|
"num_tokens": 9925720.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.473245573043823,
|
|
"epoch": 0.4164265129682997,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988396827399618,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.18902098536491393,
|
|
"num_tokens": 9936492.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.466447401046753,
|
|
"epoch": 0.4169068203650336,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988362028801495,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.1947108045220375,
|
|
"num_tokens": 9948658.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.3531107902526855,
|
|
"epoch": 0.4173871277617675,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988327178235253,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.20573291480541228,
|
|
"num_tokens": 9959710.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.44560546875,
|
|
"epoch": 0.41786743515850144,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988292275701699,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.201713927090168,
|
|
"num_tokens": 9970302.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.492425775527954,
|
|
"epoch": 0.4183477425552353,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988257321201646,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.1949488937854767,
|
|
"num_tokens": 9981776.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.523925399780273,
|
|
"epoch": 0.41882804995196926,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988222314735902,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.19040057361125945,
|
|
"num_tokens": 9993471.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.486939239501953,
|
|
"epoch": 0.41930835734870314,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988187256305284,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.19147758185863495,
|
|
"num_tokens": 10003818.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.505752801895142,
|
|
"epoch": 0.4197886647454371,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004988152145910603,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.1822121411561966,
|
|
"num_tokens": 10015507.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.463770151138306,
|
|
"epoch": 0.420268972142171,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988116983552675,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.19791281670331956,
|
|
"num_tokens": 10026994.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.5234503746032715,
|
|
"epoch": 0.4207492795389049,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988081769232317,
|
|
"loss": 5.3918,
|
|
"mean_token_accuracy": 0.18441696614027023,
|
|
"num_tokens": 10039547.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.551583099365234,
|
|
"epoch": 0.42122958693563883,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988046502950346,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.18687499761581422,
|
|
"num_tokens": 10050568.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.486132717132568,
|
|
"epoch": 0.4217098943323727,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498801118470758,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.19416816681623458,
|
|
"num_tokens": 10061780.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.424616432189941,
|
|
"epoch": 0.42219020172910665,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498797581450484,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.19230710566043854,
|
|
"num_tokens": 10073101.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.416293430328369,
|
|
"epoch": 0.42267050912584053,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987940392342948,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.2088324695825577,
|
|
"num_tokens": 10084397.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.491214942932129,
|
|
"epoch": 0.42315081652257447,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987904918222726,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.19810907989740373,
|
|
"num_tokens": 10095635.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.479027223587036,
|
|
"epoch": 0.42363112391930835,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987869392144996,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.19832460433244706,
|
|
"num_tokens": 10107744.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.490473031997681,
|
|
"epoch": 0.4241114313160423,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987833814110584,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.20135310888290406,
|
|
"num_tokens": 10118552.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.539815855026245,
|
|
"epoch": 0.42459173871277617,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987798184120316,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.18230431973934175,
|
|
"num_tokens": 10130813.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.508615732192993,
|
|
"epoch": 0.4250720461095101,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987762502175018,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.19132392406463622,
|
|
"num_tokens": 10142196.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.464332962036133,
|
|
"epoch": 0.425552353506244,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498772676827552,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.19948423951864241,
|
|
"num_tokens": 10155012.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.57846999168396,
|
|
"epoch": 0.4260326609029779,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987690982422652,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.18706874996423722,
|
|
"num_tokens": 10166160.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.522313594818115,
|
|
"epoch": 0.4265129682997118,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987655144617243,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.20063513666391372,
|
|
"num_tokens": 10177663.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.375979614257813,
|
|
"epoch": 0.42699327569644574,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987619254860126,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.19971249848604203,
|
|
"num_tokens": 10189127.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.6217639446258545,
|
|
"epoch": 0.4274735830931796,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987583313152134,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.18543484210968017,
|
|
"num_tokens": 10200765.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.549590063095093,
|
|
"epoch": 0.42795389048991356,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987547319494104,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.1949366256594658,
|
|
"num_tokens": 10213047.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.442988586425781,
|
|
"epoch": 0.42843419788664744,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987511273886867,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.19754956513643265,
|
|
"num_tokens": 10223790.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.459202003479004,
|
|
"epoch": 0.4289145052833814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987475176331263,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.1940561830997467,
|
|
"num_tokens": 10235077.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.473429822921753,
|
|
"epoch": 0.42939481268011526,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987439026828129,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.18319856822490693,
|
|
"num_tokens": 10248844.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.477560234069824,
|
|
"epoch": 0.4298751200768492,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987402825378305,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.20397989749908446,
|
|
"num_tokens": 10259013.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.415616893768311,
|
|
"epoch": 0.4303554274735831,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987366571982631,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.1972719058394432,
|
|
"num_tokens": 10271415.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.422343492507935,
|
|
"epoch": 0.430835734870317,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987330266641948,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.1948784276843071,
|
|
"num_tokens": 10283204.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.6114311695098875,
|
|
"epoch": 0.4313160422670509,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987293909357101,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.18742620199918747,
|
|
"num_tokens": 10294111.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.581851005554199,
|
|
"epoch": 0.43179634966378483,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987257500128933,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.18764484524726868,
|
|
"num_tokens": 10305417.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.395129203796387,
|
|
"epoch": 0.4322766570605187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987221038958288,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.1968950569629669,
|
|
"num_tokens": 10316416.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.500883483886719,
|
|
"epoch": 0.43275696445725265,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987184525846015,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.19381477385759355,
|
|
"num_tokens": 10328251.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.576789140701294,
|
|
"epoch": 0.4332372718539865,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987147960792958,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.2026128277182579,
|
|
"num_tokens": 10340189.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.517544603347778,
|
|
"epoch": 0.43371757925072046,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987111343799971,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.19870852380990983,
|
|
"num_tokens": 10351660.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.44553165435791,
|
|
"epoch": 0.43419788664745435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049870746748679,
|
|
"loss": 5.3297,
|
|
"mean_token_accuracy": 0.20142713338136672,
|
|
"num_tokens": 10362240.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.593466901779175,
|
|
"epoch": 0.4346781940441883,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987037953997598,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.1988833874464035,
|
|
"num_tokens": 10373646.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.518941736221313,
|
|
"epoch": 0.43515850144092216,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987001181189918,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.19442962855100632,
|
|
"num_tokens": 10385540.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.463319301605225,
|
|
"epoch": 0.4356388088376561,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986964356445713,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.18751094341278077,
|
|
"num_tokens": 10396641.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.520946311950683,
|
|
"epoch": 0.43611911623439004,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004986927479765837,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.1867692619562149,
|
|
"num_tokens": 10408165.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.497635459899902,
|
|
"epoch": 0.4365994236311239,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986890551151148,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.19946397095918655,
|
|
"num_tokens": 10419646.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.523741340637207,
|
|
"epoch": 0.43707973102785785,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004986853570602503,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.19331791996955872,
|
|
"num_tokens": 10431051.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.550788021087646,
|
|
"epoch": 0.43756003842459174,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986816538120758,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.19162560999393463,
|
|
"num_tokens": 10441833.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.500361967086792,
|
|
"epoch": 0.43804034582132567,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986779453706778,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.19241643697023392,
|
|
"num_tokens": 10453544.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.463518905639648,
|
|
"epoch": 0.43852065321805955,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986742317361419,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.203299880027771,
|
|
"num_tokens": 10464140.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.399764585494995,
|
|
"epoch": 0.4390009606147935,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986705129085546,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.2020416811108589,
|
|
"num_tokens": 10475739.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.392376852035523,
|
|
"epoch": 0.43948126801152737,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986667888880021,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.19916050434112548,
|
|
"num_tokens": 10487451.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.517410039901733,
|
|
"epoch": 0.4399615754082613,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004986630596745709,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.18609982579946518,
|
|
"num_tokens": 10499367.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.501122951507568,
|
|
"epoch": 0.4404418828049952,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004986593252683477,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.20240044444799424,
|
|
"num_tokens": 10511192.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.355871057510376,
|
|
"epoch": 0.4409221902017291,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004986555856694191,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.1964319482445717,
|
|
"num_tokens": 10522754.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.496637916564941,
|
|
"epoch": 0.441402497598463,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986518408778718,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.19111744016408921,
|
|
"num_tokens": 10533439.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.532086610794067,
|
|
"epoch": 0.44188280499519694,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986480908937929,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.1926120012998581,
|
|
"num_tokens": 10543654.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.415794229507446,
|
|
"epoch": 0.4423631123919308,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004986443357172695,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.20263231545686722,
|
|
"num_tokens": 10554936.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.4605597972869875,
|
|
"epoch": 0.44284341978866476,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986405753483887,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.19735531955957414,
|
|
"num_tokens": 10566410.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.415651798248291,
|
|
"epoch": 0.44332372718539864,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986368097872377,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.20439960807561874,
|
|
"num_tokens": 10577258.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.472713136672974,
|
|
"epoch": 0.4438040345821326,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004986330390339042,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.18763157576322556,
|
|
"num_tokens": 10588783.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.480615234375,
|
|
"epoch": 0.44428434197886646,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986292630884755,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.19710481464862822,
|
|
"num_tokens": 10599778.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.469374418258667,
|
|
"epoch": 0.4447646493756004,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986254819510393,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.19919881820678711,
|
|
"num_tokens": 10611211.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.413115835189819,
|
|
"epoch": 0.4452449567723343,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004986216956216835,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.19978490620851516,
|
|
"num_tokens": 10624535.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.4416268825531,
|
|
"epoch": 0.4457252641690682,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498617904100496,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.20863130688667297,
|
|
"num_tokens": 10635206.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.463654565811157,
|
|
"epoch": 0.4462055715658021,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004986141073875646,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.201672001183033,
|
|
"num_tokens": 10646993.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.48512830734253,
|
|
"epoch": 0.44668587896253603,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986103054829779,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.2007357358932495,
|
|
"num_tokens": 10657262.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.403297567367554,
|
|
"epoch": 0.4471661863592699,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986064983868237,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.19511503875255584,
|
|
"num_tokens": 10668962.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.472931337356568,
|
|
"epoch": 0.44764649375600385,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986026860991906,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.2026796132326126,
|
|
"num_tokens": 10680183.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.464430570602417,
|
|
"epoch": 0.44812680115273773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985988686201672,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.2030675396323204,
|
|
"num_tokens": 10691221.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.424674081802368,
|
|
"epoch": 0.44860710854947167,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004985950459498419,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.196148057281971,
|
|
"num_tokens": 10703462.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.459426212310791,
|
|
"epoch": 0.44908741594620555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985912180883037,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.20200904756784438,
|
|
"num_tokens": 10713774.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.5548125267028805,
|
|
"epoch": 0.4495677233429395,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985873850356411,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.1845877066254616,
|
|
"num_tokens": 10725109.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.397817230224609,
|
|
"epoch": 0.45004803073967337,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985835467919436,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.20077286958694457,
|
|
"num_tokens": 10735695.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.483892774581909,
|
|
"epoch": 0.4505283381364073,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985797033572999,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.19386701732873918,
|
|
"num_tokens": 10747554.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.512508583068848,
|
|
"epoch": 0.4510086455331412,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985758547317994,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.18999562412500381,
|
|
"num_tokens": 10759175.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.417887115478516,
|
|
"epoch": 0.4514889529298751,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985720009155315,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.20482773035764695,
|
|
"num_tokens": 10770365.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.4461572647094725,
|
|
"epoch": 0.45196926032660906,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004985681419085856,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.19507471323013306,
|
|
"num_tokens": 10783096.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.581644058227539,
|
|
"epoch": 0.45244956772334294,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985642777110513,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.1869310349225998,
|
|
"num_tokens": 10795312.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.452152299880981,
|
|
"epoch": 0.4529298751200769,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985604083230183,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.2009225845336914,
|
|
"num_tokens": 10806451.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.526147890090942,
|
|
"epoch": 0.45341018251681076,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985565337445765,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.1906057119369507,
|
|
"num_tokens": 10818185.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.482672786712646,
|
|
"epoch": 0.4538904899135447,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985526539758158,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.20601669698953629,
|
|
"num_tokens": 10830203.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.4190130710601805,
|
|
"epoch": 0.4543707973102786,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985487690168263,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.18741826564073563,
|
|
"num_tokens": 10842953.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.5741410732269285,
|
|
"epoch": 0.4548511047070125,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498544878867698,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.18697847574949264,
|
|
"num_tokens": 10853322.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.561968040466309,
|
|
"epoch": 0.4553314121037464,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985409835285215,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.19417425841093064,
|
|
"num_tokens": 10865480.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.412830018997193,
|
|
"epoch": 0.45581171950048033,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004985370829993873,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.20566776990890503,
|
|
"num_tokens": 10875700.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.3993151664733885,
|
|
"epoch": 0.4562920268972142,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985331772803857,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.2014310747385025,
|
|
"num_tokens": 10887350.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.467971897125244,
|
|
"epoch": 0.45677233429394815,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985292663716074,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.20225307792425157,
|
|
"num_tokens": 10899355.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.428152656555175,
|
|
"epoch": 0.457252641690682,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985253502731435,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.20248417258262635,
|
|
"num_tokens": 10911521.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.416923904418946,
|
|
"epoch": 0.45773294908741596,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985214289850845,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.198773592710495,
|
|
"num_tokens": 10923363.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.4589427471160885,
|
|
"epoch": 0.45821325648414984,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985175025075217,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.19519922137260437,
|
|
"num_tokens": 10934965.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.454138708114624,
|
|
"epoch": 0.4586935638808838,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985135708405462,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.19089499861001968,
|
|
"num_tokens": 10946126.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.477924776077271,
|
|
"epoch": 0.45917387127761766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985096339842493,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.19339967668056487,
|
|
"num_tokens": 10957667.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.545849800109863,
|
|
"epoch": 0.4596541786743516,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985056919387224,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.18823254704475403,
|
|
"num_tokens": 10969999.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.41518816947937,
|
|
"epoch": 0.4601344860710855,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985017447040569,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.20441642850637437,
|
|
"num_tokens": 10980672.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.48996148109436,
|
|
"epoch": 0.4606147934678194,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984977922803447,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.19866116493940353,
|
|
"num_tokens": 10991471.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.486412715911865,
|
|
"epoch": 0.4610951008645533,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984938346676772,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.19478911012411118,
|
|
"num_tokens": 11001960.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.4865155696868895,
|
|
"epoch": 0.46157540826128723,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984898718661468,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.1981212764978409,
|
|
"num_tokens": 11013274.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.451283502578735,
|
|
"epoch": 0.4620557156580211,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984859038758451,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.20715891271829606,
|
|
"num_tokens": 11024635.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.433674955368042,
|
|
"epoch": 0.46253602305475505,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984819306968642,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.19718215018510818,
|
|
"num_tokens": 11036317.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.42262544631958,
|
|
"epoch": 0.46301633045148893,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984779523292966,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.19868568778038026,
|
|
"num_tokens": 11047776.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.468826246261597,
|
|
"epoch": 0.46349663784822287,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984739687732345,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.19802550822496415,
|
|
"num_tokens": 11058746.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.5128639221191404,
|
|
"epoch": 0.46397694524495675,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984699800287705,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.20043063014745713,
|
|
"num_tokens": 11068892.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.408717489242553,
|
|
"epoch": 0.4644572526416907,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498465986095997,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.19579166322946548,
|
|
"num_tokens": 11080038.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.472234773635864,
|
|
"epoch": 0.46493756003842457,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004984619869750069,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.1964089199900627,
|
|
"num_tokens": 11091261.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.4085136413574215,
|
|
"epoch": 0.4654178674351585,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000498457982665893,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.20610643029212952,
|
|
"num_tokens": 11103015.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.436830282211304,
|
|
"epoch": 0.4658981748318924,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984539731687483,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.20579486936330796,
|
|
"num_tokens": 11115075.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.442226076126099,
|
|
"epoch": 0.4663784822286263,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984499584836659,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.1985790029168129,
|
|
"num_tokens": 11125937.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.377442836761475,
|
|
"epoch": 0.4668587896253602,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498445938610739,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.19439325779676436,
|
|
"num_tokens": 11136863.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.506417942047119,
|
|
"epoch": 0.46733909702209414,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004984419135500608,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.1882396310567856,
|
|
"num_tokens": 11149934.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.458478593826294,
|
|
"epoch": 0.4678194044188281,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004984378833017249,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.19723816961050034,
|
|
"num_tokens": 11162208.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.413547992706299,
|
|
"epoch": 0.46829971181556196,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984338478658248,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.20006574541330338,
|
|
"num_tokens": 11172892.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.431224966049195,
|
|
"epoch": 0.4687800192122959,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004984298072424542,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.1992043063044548,
|
|
"num_tokens": 11184339.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.502774572372436,
|
|
"epoch": 0.4692603266090298,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498425761431707,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.19476044476032256,
|
|
"num_tokens": 11195681.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.493816280364991,
|
|
"epoch": 0.4697406340057637,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498421710433677,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.19128585755825042,
|
|
"num_tokens": 11207982.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.483510208129883,
|
|
"epoch": 0.4702209414024976,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004984176542484584,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.19832695871591569,
|
|
"num_tokens": 11218901.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.44309253692627,
|
|
"epoch": 0.47070124879923153,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984135928761452,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.1971297085285187,
|
|
"num_tokens": 11230764.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.404109621047974,
|
|
"epoch": 0.4711815561959654,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984095263168317,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.20275018364191055,
|
|
"num_tokens": 11241489.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.323462438583374,
|
|
"epoch": 0.47166186359269935,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004984054545706124,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.20271165519952775,
|
|
"num_tokens": 11254500.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.522977447509765,
|
|
"epoch": 0.47214217098943323,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498401377637582,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.19759004861116408,
|
|
"num_tokens": 11266235.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.496246385574341,
|
|
"epoch": 0.47262247838616717,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498397295517835,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.2055661290884018,
|
|
"num_tokens": 11277471.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.299065113067627,
|
|
"epoch": 0.47310278578290105,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983932082114659,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.1982652187347412,
|
|
"num_tokens": 11290501.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.365055990219116,
|
|
"epoch": 0.473583093179635,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983891157185699,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.20084365904331208,
|
|
"num_tokens": 11301933.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.53194489479065,
|
|
"epoch": 0.47406340057636887,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004983850180392421,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.19544000029563904,
|
|
"num_tokens": 11314539.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.431021738052368,
|
|
"epoch": 0.4745437079731028,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983809151735775,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.2043837860226631,
|
|
"num_tokens": 11326641.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.432755041122436,
|
|
"epoch": 0.4750240153698367,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983768071216713,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.19281973093748092,
|
|
"num_tokens": 11337214.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.50832953453064,
|
|
"epoch": 0.4755043227665706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983726938836189,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19941286742687225,
|
|
"num_tokens": 11349540.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.456822681427002,
|
|
"epoch": 0.4759846301633045,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983685754595159,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.19759729653596877,
|
|
"num_tokens": 11359817.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.4768458843231205,
|
|
"epoch": 0.47646493756003844,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983644518494578,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.19250783771276475,
|
|
"num_tokens": 11371120.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.432148504257202,
|
|
"epoch": 0.4769452449567723,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983603230535403,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.19729024767875672,
|
|
"num_tokens": 11382071.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.5168249130249025,
|
|
"epoch": 0.47742555235350626,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983561890718594,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.19242861419916152,
|
|
"num_tokens": 11392938.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.450941562652588,
|
|
"epoch": 0.47790585975024014,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498352049904511,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.20305142253637315,
|
|
"num_tokens": 11405416.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.508961009979248,
|
|
"epoch": 0.4783861671469741,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004983479055515914,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.20404793471097946,
|
|
"num_tokens": 11417008.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.527329063415527,
|
|
"epoch": 0.47886647454370795,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983437560131964,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.19856828600168228,
|
|
"num_tokens": 11428154.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.492621564865113,
|
|
"epoch": 0.4793467819404419,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983396012894228,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.19633501172065734,
|
|
"num_tokens": 11438559.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.542058324813842,
|
|
"epoch": 0.47982708933717577,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983354413803666,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.19670478701591493,
|
|
"num_tokens": 11449501.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.477359104156494,
|
|
"epoch": 0.4803073967339097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983312762861248,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.19538429677486419,
|
|
"num_tokens": 11461841.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.437913608551026,
|
|
"epoch": 0.4807877041306436,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983271060067939,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.1939387947320938,
|
|
"num_tokens": 11472876.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.463352012634277,
|
|
"epoch": 0.4812680115273775,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983229305424707,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.19564484804868698,
|
|
"num_tokens": 11484541.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.357038974761963,
|
|
"epoch": 0.4817483189241114,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983187498932522,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.2028007611632347,
|
|
"num_tokens": 11496071.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.440415382385254,
|
|
"epoch": 0.48222862632084534,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983145640592354,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.20138738602399825,
|
|
"num_tokens": 11507574.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.407825231552124,
|
|
"epoch": 0.4827089337175792,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004983103730405176,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.1994578644633293,
|
|
"num_tokens": 11519738.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.44564151763916,
|
|
"epoch": 0.48318924111431316,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498306176837196,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.20174362659454345,
|
|
"num_tokens": 11530669.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.339068937301636,
|
|
"epoch": 0.48366954851104704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983019754493681,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.20591068565845488,
|
|
"num_tokens": 11541680.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.395600891113281,
|
|
"epoch": 0.484149855907781,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982977688771314,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.20142578184604645,
|
|
"num_tokens": 11553204.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.490286111831665,
|
|
"epoch": 0.4846301633045149,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982935571205835,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.19183812588453292,
|
|
"num_tokens": 11564841.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.383268785476685,
|
|
"epoch": 0.4851104707012488,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982893401798223,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.19594986587762833,
|
|
"num_tokens": 11576723.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.508152198791504,
|
|
"epoch": 0.48559077809798273,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982851180549456,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.20382197946310043,
|
|
"num_tokens": 11587727.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.397392129898071,
|
|
"epoch": 0.4860710854947166,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004982808907460515,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.19967495501041413,
|
|
"num_tokens": 11598508.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.381629896163941,
|
|
"epoch": 0.48655139289145055,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982766582532382,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.21083337366580962,
|
|
"num_tokens": 11609684.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.4771734237670895,
|
|
"epoch": 0.48703170028818443,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004982724205766038,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.1882675915956497,
|
|
"num_tokens": 11621642.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.437322425842285,
|
|
"epoch": 0.48751200768491837,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982681777162468,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.20069642812013627,
|
|
"num_tokens": 11632778.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.369609785079956,
|
|
"epoch": 0.48799231508165225,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982639296722657,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.20479831099510193,
|
|
"num_tokens": 11643581.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.553722763061524,
|
|
"epoch": 0.4884726224783862,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982596764447591,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.18944673985242844,
|
|
"num_tokens": 11656126.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.555953025817871,
|
|
"epoch": 0.48895292987512007,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004982554180338258,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.20326795130968095,
|
|
"num_tokens": 11667765.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.452979564666748,
|
|
"epoch": 0.489433237271854,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982511544395646,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.1876109227538109,
|
|
"num_tokens": 11679268.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.435997009277344,
|
|
"epoch": 0.4899135446685879,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982468856620745,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.1989291250705719,
|
|
"num_tokens": 11690049.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.418230962753296,
|
|
"epoch": 0.4903938520653218,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982426117014545,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.20710271149873732,
|
|
"num_tokens": 11701782.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.3447777271270756,
|
|
"epoch": 0.4908741594620557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982383325578041,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.20545895248651505,
|
|
"num_tokens": 11712488.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.42593560218811,
|
|
"epoch": 0.49135446685878964,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982340482312226,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.20071271657943726,
|
|
"num_tokens": 11724036.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.431950998306275,
|
|
"epoch": 0.4918347742555235,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982297587218092,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.20244450569152833,
|
|
"num_tokens": 11736461.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.306575965881348,
|
|
"epoch": 0.49231508165225746,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982254640296637,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.20527953356504441,
|
|
"num_tokens": 11747549.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.507662391662597,
|
|
"epoch": 0.49279538904899134,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982211641548857,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.1891992837190628,
|
|
"num_tokens": 11759012.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.526328086853027,
|
|
"epoch": 0.4932756964457253,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004982168590975752,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.2013460800051689,
|
|
"num_tokens": 11770535.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.426211404800415,
|
|
"epoch": 0.49375600384245916,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004982125488578321,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.19810220301151277,
|
|
"num_tokens": 11783708.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.425791931152344,
|
|
"epoch": 0.4942363112391931,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982082334357563,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.19922201484441757,
|
|
"num_tokens": 11794565.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.49116005897522,
|
|
"epoch": 0.494716618635927,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982039128314481,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.20095377862453462,
|
|
"num_tokens": 11805631.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.464397668838501,
|
|
"epoch": 0.4951969260326609,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004981995870450079,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.19358218610286712,
|
|
"num_tokens": 11817041.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.476817989349366,
|
|
"epoch": 0.4956772334293948,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981952560765361,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.20246486365795135,
|
|
"num_tokens": 11829090.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.552751302719116,
|
|
"epoch": 0.49615754082612873,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004981909199261331,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.19026300311088562,
|
|
"num_tokens": 11839980.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.479401350021362,
|
|
"epoch": 0.4966378482228626,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981865785938998,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.2002490922808647,
|
|
"num_tokens": 11851217.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.454754829406738,
|
|
"epoch": 0.49711815561959655,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004981822320799367,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.19824722409248352,
|
|
"num_tokens": 11862506.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.468531942367553,
|
|
"epoch": 0.49759846301633043,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981778803843449,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.19249559938907623,
|
|
"num_tokens": 11874844.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.37927017211914,
|
|
"epoch": 0.49807877041306436,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981735235072256,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.20914469212293624,
|
|
"num_tokens": 11885231.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.451508522033691,
|
|
"epoch": 0.49855907780979825,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981691614486796,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.19635699987411498,
|
|
"num_tokens": 11897222.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.426901960372925,
|
|
"epoch": 0.4990393852065322,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981647942088084,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.20007238537073135,
|
|
"num_tokens": 11909493.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.46443395614624,
|
|
"epoch": 0.49951969260326606,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981604217877135,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.19994568228721618,
|
|
"num_tokens": 11920833.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.374874830245972,
|
|
"epoch": 0.5,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000498156044185496,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.20849472433328628,
|
|
"num_tokens": 11932910.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.472115802764892,
|
|
"epoch": 0.5004803073967339,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004981516614022579,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.20777840912342072,
|
|
"num_tokens": 11944536.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.3710695743560795,
|
|
"epoch": 0.5009606147934679,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004981472734381008,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.21034069657325744,
|
|
"num_tokens": 11955724.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.4173582077026365,
|
|
"epoch": 0.5014409221902018,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004981428802931267,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.19853321313858033,
|
|
"num_tokens": 11965921.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.393053817749023,
|
|
"epoch": 0.5019212295869356,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981384819674375,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.20426609814167024,
|
|
"num_tokens": 11976356.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.421328163146972,
|
|
"epoch": 0.5024015369836695,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004981340784611354,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.19965131282806398,
|
|
"num_tokens": 11987959.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.4045751094818115,
|
|
"epoch": 0.5028818443804035,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004981296697743224,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19689224511384965,
|
|
"num_tokens": 12000089.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.423994159698486,
|
|
"epoch": 0.5033621517771374,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981252559071012,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.19833589643239974,
|
|
"num_tokens": 12011286.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.423003005981445,
|
|
"epoch": 0.5038424591738713,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981208368595739,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.20282577574253083,
|
|
"num_tokens": 12022809.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.41456823348999,
|
|
"epoch": 0.5043227665706052,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004981164126318435,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.20664438009262084,
|
|
"num_tokens": 12034311.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.352087926864624,
|
|
"epoch": 0.5048030739673391,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981119832240124,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.2058908760547638,
|
|
"num_tokens": 12046405.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.403067541122437,
|
|
"epoch": 0.505283381364073,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981075486361837,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.20067661106586457,
|
|
"num_tokens": 12059022.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.455043697357178,
|
|
"epoch": 0.5057636887608069,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004981031088684601,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.19721019566059111,
|
|
"num_tokens": 12070666.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.368303918838501,
|
|
"epoch": 0.5062439961575408,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980986639209448,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.1998736724257469,
|
|
"num_tokens": 12082702.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.434964847564697,
|
|
"epoch": 0.5067243035542748,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498094213793741,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.20490046739578247,
|
|
"num_tokens": 12094034.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.493093633651734,
|
|
"epoch": 0.5072046109510087,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498089758486952,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.19067712724208832,
|
|
"num_tokens": 12104597.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.403679609298706,
|
|
"epoch": 0.5076849183477425,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980852980006812,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.19560959041118622,
|
|
"num_tokens": 12116577.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.415004301071167,
|
|
"epoch": 0.5081652257444764,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980808323350323,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.20038611441850662,
|
|
"num_tokens": 12128005.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.4781105518341064,
|
|
"epoch": 0.5086455331412104,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980763614901089,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.19442284256219863,
|
|
"num_tokens": 12138591.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.39280104637146,
|
|
"epoch": 0.5091258405379443,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004980718854660146,
|
|
"loss": 5.2806,
|
|
"mean_token_accuracy": 0.19946790486574173,
|
|
"num_tokens": 12150010.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.450536012649536,
|
|
"epoch": 0.5096061479346782,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980674042628537,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.19617518782615662,
|
|
"num_tokens": 12161268.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.40824556350708,
|
|
"epoch": 0.5100864553314121,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049806291788073,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.20174606293439865,
|
|
"num_tokens": 12172647.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.378707695007324,
|
|
"epoch": 0.510566762728146,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980584263197477,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.20215070098638535,
|
|
"num_tokens": 12183521.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.561006641387939,
|
|
"epoch": 0.5110470701248799,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980539295800111,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.189036226272583,
|
|
"num_tokens": 12193616.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.400166749954224,
|
|
"epoch": 0.5115273775216138,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980494276616246,
|
|
"loss": 5.2676,
|
|
"mean_token_accuracy": 0.20074494928121567,
|
|
"num_tokens": 12204817.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.429664373397827,
|
|
"epoch": 0.5120076849183477,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004980449205646926,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.19333904087543488,
|
|
"num_tokens": 12217281.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.4758501052856445,
|
|
"epoch": 0.5124879923150817,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049804040828932,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.20643760561943053,
|
|
"num_tokens": 12228705.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.434673309326172,
|
|
"epoch": 0.5129682997118156,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980358908356113,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.19399532228708266,
|
|
"num_tokens": 12240010.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.469569444656372,
|
|
"epoch": 0.5134486071085494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980313682036717,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.18981159925460817,
|
|
"num_tokens": 12251384.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.468781137466431,
|
|
"epoch": 0.5139289145052833,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980268403936058,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.2020355612039566,
|
|
"num_tokens": 12262548.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.365769529342652,
|
|
"epoch": 0.5144092219020173,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980223074055189,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.20694259703159332,
|
|
"num_tokens": 12274022.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.356425142288208,
|
|
"epoch": 0.5148895292987512,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980177692395164,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20629165470600128,
|
|
"num_tokens": 12285000.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.3721396923065186,
|
|
"epoch": 0.5153698366954851,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980132258957035,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.20583453625440598,
|
|
"num_tokens": 12297472.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.450796461105346,
|
|
"epoch": 0.515850144092219,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980086773741856,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.20129702389240264,
|
|
"num_tokens": 12309310.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.513828754425049,
|
|
"epoch": 0.516330451488953,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980041236750685,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.1947031006217003,
|
|
"num_tokens": 12321897.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.365801286697388,
|
|
"epoch": 0.5168107588856868,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979995647984577,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.21287835389375687,
|
|
"num_tokens": 12333484.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.361044645309448,
|
|
"epoch": 0.5172910662824207,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979950007444593,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19991326928138733,
|
|
"num_tokens": 12345154.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.523871421813965,
|
|
"epoch": 0.5177713736791547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979904315131792,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.20229610055685043,
|
|
"num_tokens": 12354934.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.526210021972656,
|
|
"epoch": 0.5182516810758886,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004979858571047233,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.18547400534152986,
|
|
"num_tokens": 12367729.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.430369281768799,
|
|
"epoch": 0.5187319884726225,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979812775191979,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.20352086722850798,
|
|
"num_tokens": 12380366.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.38416748046875,
|
|
"epoch": 0.5192122958693564,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004979766927567094,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.20023151189088823,
|
|
"num_tokens": 12392338.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.4360593318939205,
|
|
"epoch": 0.5196926032660903,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979721028173643,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.20083916634321214,
|
|
"num_tokens": 12403280.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.423532342910766,
|
|
"epoch": 0.5201729106628242,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497967507701269,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.20973516553640364,
|
|
"num_tokens": 12414279.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.330219173431397,
|
|
"epoch": 0.5206532180595581,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979629074085303,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.2057455897331238,
|
|
"num_tokens": 12425486.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.383903932571411,
|
|
"epoch": 0.521133525456292,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979583019392548,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.197030608355999,
|
|
"num_tokens": 12437295.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.453045797348023,
|
|
"epoch": 0.521613832853026,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979536912935497,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.20004693865776063,
|
|
"num_tokens": 12448684.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.344678163528442,
|
|
"epoch": 0.5220941402497599,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000497949075471522,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.20942751616239547,
|
|
"num_tokens": 12461209.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.403510189056396,
|
|
"epoch": 0.5225744476464937,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979444544732786,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.2020719200372696,
|
|
"num_tokens": 12472863.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.473718738555908,
|
|
"epoch": 0.5230547550432276,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497939828298927,
|
|
"loss": 5.2529,
|
|
"mean_token_accuracy": 0.19780154377222062,
|
|
"num_tokens": 12483510.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.493526983261108,
|
|
"epoch": 0.5235350624399616,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979351969485747,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.20614576786756517,
|
|
"num_tokens": 12495532.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.331623220443726,
|
|
"epoch": 0.5240153698366955,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004979305604223291,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.20410754680633544,
|
|
"num_tokens": 12508413.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.441117906570435,
|
|
"epoch": 0.5244956772334294,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004979259187202978,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.19907164871692656,
|
|
"num_tokens": 12520705.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.409723711013794,
|
|
"epoch": 0.5249759846301633,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004979212718425887,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.20305572897195817,
|
|
"num_tokens": 12531560.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.4244619846344,
|
|
"epoch": 0.5254562920268973,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979166197893096,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.19547750949859619,
|
|
"num_tokens": 12542539.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.45615406036377,
|
|
"epoch": 0.5259365994236311,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004979119625605683,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.1936646193265915,
|
|
"num_tokens": 12555228.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.49875955581665,
|
|
"epoch": 0.526416906820365,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979073001564734,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.20251004844903947,
|
|
"num_tokens": 12565715.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.384497928619385,
|
|
"epoch": 0.5268972142170989,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979026325771328,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.2064637765288353,
|
|
"num_tokens": 12576896.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.405694818496704,
|
|
"epoch": 0.5273775216138329,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978979598226549,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.2032501608133316,
|
|
"num_tokens": 12588117.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.410942697525025,
|
|
"epoch": 0.5278578290105668,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978932818931483,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.20206186026334763,
|
|
"num_tokens": 12599987.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.416629457473755,
|
|
"epoch": 0.5283381364073007,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004978885987887216,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.19667774587869644,
|
|
"num_tokens": 12611453.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.485828018188476,
|
|
"epoch": 0.5288184438040345,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004978839105094833,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.19864051192998886,
|
|
"num_tokens": 12623068.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.522905397415161,
|
|
"epoch": 0.5292987512007685,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978792170555426,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.20180642753839492,
|
|
"num_tokens": 12634952.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.36653881072998,
|
|
"epoch": 0.5297790585975024,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004978745184270083,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.19374970197677613,
|
|
"num_tokens": 12647027.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.3338127613067625,
|
|
"epoch": 0.5302593659942363,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978698146239893,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.21439087390899658,
|
|
"num_tokens": 12657249.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.367515945434571,
|
|
"epoch": 0.5307396733909702,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978651056465952,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.21495115906000137,
|
|
"num_tokens": 12666714.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.394702577590943,
|
|
"epoch": 0.5312199807877042,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000497860391494935,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.20139539241790771,
|
|
"num_tokens": 12678627.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.4351770877838135,
|
|
"epoch": 0.531700288184438,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978556721691183,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.20127318799495697,
|
|
"num_tokens": 12691009.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.465825033187866,
|
|
"epoch": 0.5321805955811719,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004978509476692547,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.20153638124465942,
|
|
"num_tokens": 12702503.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.42263445854187,
|
|
"epoch": 0.5326609029779059,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004978462179954538,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.1988968476653099,
|
|
"num_tokens": 12714018.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.464064216613769,
|
|
"epoch": 0.5331412103746398,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004978414831478253,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.1973311722278595,
|
|
"num_tokens": 12726726.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.43575873374939,
|
|
"epoch": 0.5336215177713737,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978367431264794,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.20618546158075332,
|
|
"num_tokens": 12737790.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.361739540100098,
|
|
"epoch": 0.5341018251681076,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004978319979315261,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.208463391661644,
|
|
"num_tokens": 12749473.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.364939260482788,
|
|
"epoch": 0.5345821325648416,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978272475630752,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.19929825365543366,
|
|
"num_tokens": 12762220.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.297778844833374,
|
|
"epoch": 0.5350624399615754,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978224920212374,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.21749102622270583,
|
|
"num_tokens": 12772788.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.309448289871216,
|
|
"epoch": 0.5355427473583093,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978177313061232,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.2052545115351677,
|
|
"num_tokens": 12784552.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.41003098487854,
|
|
"epoch": 0.5360230547550432,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004978129654178426,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.2056588351726532,
|
|
"num_tokens": 12797618.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.341778707504273,
|
|
"epoch": 0.5365033621517772,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004978081943565067,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.20799061506986619,
|
|
"num_tokens": 12807789.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.352446842193603,
|
|
"epoch": 0.5369836695485111,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004978034181222261,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.20836423486471176,
|
|
"num_tokens": 12819020.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.427563714981079,
|
|
"epoch": 0.537463976945245,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977986367151119,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.20499080568552017,
|
|
"num_tokens": 12829527.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.465697336196899,
|
|
"epoch": 0.5379442843419788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977938501352747,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.1949279174208641,
|
|
"num_tokens": 12840821.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.425854110717774,
|
|
"epoch": 0.5384245917387128,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977890583828259,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.20402238070964812,
|
|
"num_tokens": 12853314.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.391624546051025,
|
|
"epoch": 0.5389048991354467,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977842614578768,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.19749133437871932,
|
|
"num_tokens": 12863507.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.46206259727478,
|
|
"epoch": 0.5393852065321806,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004977794593605386,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.20185458809137344,
|
|
"num_tokens": 12874142.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.448383426666259,
|
|
"epoch": 0.5398655139289145,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497774652090923,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.20888919681310653,
|
|
"num_tokens": 12884548.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.408846235275268,
|
|
"epoch": 0.5403458213256485,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977698396491414,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.20425238758325576,
|
|
"num_tokens": 12895562.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.377727460861206,
|
|
"epoch": 0.5408261287223823,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977650220353055,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.20899862796068192,
|
|
"num_tokens": 12905308.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.416336870193481,
|
|
"epoch": 0.5413064361191162,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004977601992495274,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.1985734537243843,
|
|
"num_tokens": 12916731.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.499758577346801,
|
|
"epoch": 0.5417867435158501,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004977553712919189,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.19841110557317734,
|
|
"num_tokens": 12927609.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.48809289932251,
|
|
"epoch": 0.5422670509125841,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977505381625921,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.20091182738542557,
|
|
"num_tokens": 12939445.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.3469054222106935,
|
|
"epoch": 0.542747358309318,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977456998616593,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.20222190767526627,
|
|
"num_tokens": 12951638.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.41858024597168,
|
|
"epoch": 0.5432276657060519,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004977408563892327,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.20416037291288375,
|
|
"num_tokens": 12963157.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.420162773132324,
|
|
"epoch": 0.5437079731027857,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004977360077454249,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.20356156826019287,
|
|
"num_tokens": 12974187.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.425640296936035,
|
|
"epoch": 0.5441882804995197,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004977311539303483,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.20451467484235764,
|
|
"num_tokens": 12986612.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.445303249359131,
|
|
"epoch": 0.5446685878962536,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004977262949441158,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.1936507433652878,
|
|
"num_tokens": 12998343.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.426596975326538,
|
|
"epoch": 0.5451488952929875,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977214307868399,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.19719243794679642,
|
|
"num_tokens": 13009272.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.4442291259765625,
|
|
"epoch": 0.5456292026897214,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497716561458634,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.2025150775909424,
|
|
"num_tokens": 13019961.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.337080335617065,
|
|
"epoch": 0.5461095100864554,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977116869596107,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.21013278812170028,
|
|
"num_tokens": 13030827.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.512407302856445,
|
|
"epoch": 0.5465898174831892,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004977068072898834,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.19139074683189392,
|
|
"num_tokens": 13043702.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.321547794342041,
|
|
"epoch": 0.5470701248799231,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004977019224495652,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.21801694482564926,
|
|
"num_tokens": 13054474.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.418253993988037,
|
|
"epoch": 0.547550432276657,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004976970324387698,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.19925144761800767,
|
|
"num_tokens": 13064920.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.466699647903442,
|
|
"epoch": 0.548030739673391,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004976921372576104,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.19982881247997283,
|
|
"num_tokens": 13077214.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.408265924453735,
|
|
"epoch": 0.5485110470701249,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004976872369062011,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.20192686319351197,
|
|
"num_tokens": 13089472.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.431948947906494,
|
|
"epoch": 0.5489913544668588,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976823313846552,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.20262414515018462,
|
|
"num_tokens": 13100369.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.446697759628296,
|
|
"epoch": 0.5494716618635928,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976774206930869,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.1937856212258339,
|
|
"num_tokens": 13110813.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.437151050567627,
|
|
"epoch": 0.5499519692603266,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004976725048316101,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.19881620407104492,
|
|
"num_tokens": 13121946.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.381475877761841,
|
|
"epoch": 0.5504322766570605,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976675838003388,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.2081285908818245,
|
|
"num_tokens": 13133286.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.313736009597778,
|
|
"epoch": 0.5509125840537944,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976626575993877,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.20784352719783783,
|
|
"num_tokens": 13145023.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.394445276260376,
|
|
"epoch": 0.5513928914505284,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976577262288705,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.2103104829788208,
|
|
"num_tokens": 13156379.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.3467165470123295,
|
|
"epoch": 0.5518731988472623,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976527896889023,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.20986340045928956,
|
|
"num_tokens": 13166313.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.429497957229614,
|
|
"epoch": 0.5523535062439962,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976478479795974,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.19818944931030275,
|
|
"num_tokens": 13177968.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.474160671234131,
|
|
"epoch": 0.55283381364073,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004976429011010706,
|
|
"loss": 5.2459,
|
|
"mean_token_accuracy": 0.19883870631456374,
|
|
"num_tokens": 13189464.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.4211649894714355,
|
|
"epoch": 0.553314121037464,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004976379490534366,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.1968870386481285,
|
|
"num_tokens": 13201716.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.333693933486939,
|
|
"epoch": 0.5537944284341979,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976329918368107,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.2027762144804001,
|
|
"num_tokens": 13212976.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.284528350830078,
|
|
"epoch": 0.5542747358309318,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976280294513079,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.2174160435795784,
|
|
"num_tokens": 13225265.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.542007732391357,
|
|
"epoch": 0.5547550432276657,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976230618970431,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.19177584052085878,
|
|
"num_tokens": 13236443.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.422015762329101,
|
|
"epoch": 0.5552353506243997,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497618089174132,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.20211009085178375,
|
|
"num_tokens": 13248681.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.404659843444824,
|
|
"epoch": 0.5557156580211335,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976131112826898,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.20601932406425477,
|
|
"num_tokens": 13258719.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.38159499168396,
|
|
"epoch": 0.5561959654178674,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004976081282228323,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.20101721435785294,
|
|
"num_tokens": 13270544.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.448766994476318,
|
|
"epoch": 0.5566762728146013,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497603139994675,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.2087673708796501,
|
|
"num_tokens": 13280759.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.360471391677857,
|
|
"epoch": 0.5571565802113353,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004975981465983338,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.20586378425359725,
|
|
"num_tokens": 13292496.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.401841354370117,
|
|
"epoch": 0.5576368876080692,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975931480339246,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.20023439824581146,
|
|
"num_tokens": 13303003.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.420393943786621,
|
|
"epoch": 0.5581171950048031,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975881443015635,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.1995705708861351,
|
|
"num_tokens": 13315036.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.421544075012207,
|
|
"epoch": 0.5585975024015369,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004975831354013667,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.20443224906921387,
|
|
"num_tokens": 13327529.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.392531394958496,
|
|
"epoch": 0.5590778097982709,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975781213334503,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.20537647753953933,
|
|
"num_tokens": 13339494.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.3966124057769775,
|
|
"epoch": 0.5595581171950048,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004975731020979309,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.1961645483970642,
|
|
"num_tokens": 13351184.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.362166261672973,
|
|
"epoch": 0.5600384245917387,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975680776949249,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.20512876957654952,
|
|
"num_tokens": 13362402.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.353017520904541,
|
|
"epoch": 0.5605187319884726,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975630481245492,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.20023051798343658,
|
|
"num_tokens": 13375257.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.425220394134522,
|
|
"epoch": 0.5609990393852066,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975580133869202,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.20563430041074754,
|
|
"num_tokens": 13385917.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.464968347549439,
|
|
"epoch": 0.5614793467819404,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975529734821552,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.19981267303228378,
|
|
"num_tokens": 13397962.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.3529034614562985,
|
|
"epoch": 0.5619596541786743,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975479284103708,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.20526334643363953,
|
|
"num_tokens": 13408654.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.384210205078125,
|
|
"epoch": 0.5624399615754082,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975428781716845,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.19574617892503737,
|
|
"num_tokens": 13419790.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.380592012405396,
|
|
"epoch": 0.5629202689721422,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004975378227662134,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.20264835506677628,
|
|
"num_tokens": 13430305.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.405235004425049,
|
|
"epoch": 0.5634005763688761,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004975327621940746,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.2009672775864601,
|
|
"num_tokens": 13441730.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.463106536865235,
|
|
"epoch": 0.56388088376561,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975276964553861,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19950135201215743,
|
|
"num_tokens": 13452003.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.404791688919067,
|
|
"epoch": 0.5643611911623438,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004975226255502651,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.21076515614986419,
|
|
"num_tokens": 13463953.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.432207298278809,
|
|
"epoch": 0.5648414985590778,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975175494788297,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.1974237620830536,
|
|
"num_tokens": 13473820.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.487738800048828,
|
|
"epoch": 0.5653218059558117,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004975124682411974,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19671275615692138,
|
|
"num_tokens": 13484181.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.40929765701294,
|
|
"epoch": 0.5658021133525456,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975073818374863,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.20096203088760375,
|
|
"num_tokens": 13494480.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.3118654727935795,
|
|
"epoch": 0.5662824207492796,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975022902678145,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.2076367437839508,
|
|
"num_tokens": 13506026.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.476935243606567,
|
|
"epoch": 0.5667627281460135,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004974971935323003,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.20008840560913085,
|
|
"num_tokens": 13516849.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.421756887435913,
|
|
"epoch": 0.5672430355427474,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974920916310619,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.21029401570558548,
|
|
"num_tokens": 13527386.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.331386566162109,
|
|
"epoch": 0.5677233429394812,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004974869845642178,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.19540005028247834,
|
|
"num_tokens": 13540238.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.373654794692993,
|
|
"epoch": 0.5682036503362152,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974818723318866,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.20982492417097093,
|
|
"num_tokens": 13551808.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.362733602523804,
|
|
"epoch": 0.5686839577329491,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974767549341868,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.20436372607946396,
|
|
"num_tokens": 13563795.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.401230192184448,
|
|
"epoch": 0.569164265129683,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974716323712376,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.20615062415599822,
|
|
"num_tokens": 13575168.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.444679498672485,
|
|
"epoch": 0.5696445725264169,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004974665046431576,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.20031835585832597,
|
|
"num_tokens": 13587013.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.343590927124024,
|
|
"epoch": 0.5701248799231509,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004974613717500659,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.201158507168293,
|
|
"num_tokens": 13598138.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.401383972167968,
|
|
"epoch": 0.5706051873198847,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974562336920818,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.19973291605710983,
|
|
"num_tokens": 13609174.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.388366174697876,
|
|
"epoch": 0.5710854947166186,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974510904693245,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.2057375952601433,
|
|
"num_tokens": 13619724.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.371340560913086,
|
|
"epoch": 0.5715658021133525,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004974459420819134,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.20603399574756623,
|
|
"num_tokens": 13631114.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.3572710990905765,
|
|
"epoch": 0.5720461095100865,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000497440788529968,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.21193038523197175,
|
|
"num_tokens": 13643035.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.400407028198242,
|
|
"epoch": 0.5725264169068204,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974356298136081,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.20063706189393998,
|
|
"num_tokens": 13656603.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.342504930496216,
|
|
"epoch": 0.5730067243035543,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004974304659329533,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.1998682886362076,
|
|
"num_tokens": 13668420.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.455368614196777,
|
|
"epoch": 0.5734870317002881,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974252968881236,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.20192921459674834,
|
|
"num_tokens": 13680521.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.350187969207764,
|
|
"epoch": 0.5739673390970221,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497420122679239,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.20842599123716354,
|
|
"num_tokens": 13692503.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.2690104961395265,
|
|
"epoch": 0.574447646493756,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974149433064196,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.21867085844278336,
|
|
"num_tokens": 13703318.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.399303197860718,
|
|
"epoch": 0.5749279538904899,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974097587697856,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.206535005569458,
|
|
"num_tokens": 13713957.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.395474147796631,
|
|
"epoch": 0.5754082612872238,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974045690694575,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.1992923304438591,
|
|
"num_tokens": 13725300.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.409423303604126,
|
|
"epoch": 0.5758885686839578,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973993742055557,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.1999870002269745,
|
|
"num_tokens": 13735463.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.498396158218384,
|
|
"epoch": 0.5763688760806917,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004973941741782007,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.19305443316698073,
|
|
"num_tokens": 13749062.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5763688760806917,
|
|
"eval_entropy": 5.276854424055816,
|
|
"eval_loss": 5.225351333618164,
|
|
"eval_mean_token_accuracy": 0.20968423810569994,
|
|
"eval_num_tokens": 13749062.0,
|
|
"eval_runtime": 20.3469,
|
|
"eval_samples_per_second": 1612.776,
|
|
"eval_steps_per_second": 201.603,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.507682180404663,
|
|
"epoch": 0.5768491834774255,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004973889689875135,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.19679196029901505,
|
|
"num_tokens": 13761766.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.4325401306152346,
|
|
"epoch": 0.5773294908741594,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004973837586336147,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.20890117585659027,
|
|
"num_tokens": 13774702.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.384126806259156,
|
|
"epoch": 0.5778097982708934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973785431166254,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.20279618799686433,
|
|
"num_tokens": 13786215.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.310927629470825,
|
|
"epoch": 0.5782901056676273,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004973733224366666,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.2078191965818405,
|
|
"num_tokens": 13797697.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.393148756027221,
|
|
"epoch": 0.5787704130643612,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004973680965938597,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.19953060895204544,
|
|
"num_tokens": 13810085.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.440446615219116,
|
|
"epoch": 0.579250720461095,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004973628655883258,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.2112879380583763,
|
|
"num_tokens": 13822054.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.308295011520386,
|
|
"epoch": 0.579731027857829,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004973576294201865,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.20866511911153793,
|
|
"num_tokens": 13834342.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.392531824111939,
|
|
"epoch": 0.5802113352545629,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973523880895633,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.20254832059144973,
|
|
"num_tokens": 13846598.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.4282753467559814,
|
|
"epoch": 0.5806916426512968,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973471415965779,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.2048051655292511,
|
|
"num_tokens": 13857515.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.277294540405274,
|
|
"epoch": 0.5811719500480308,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497341889941352,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.21426718682050705,
|
|
"num_tokens": 13868333.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.380367660522461,
|
|
"epoch": 0.5816522574447647,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973366331240078,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.19820500016212464,
|
|
"num_tokens": 13879048.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.45005612373352,
|
|
"epoch": 0.5821325648414986,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000497331371144667,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.19521532952785492,
|
|
"num_tokens": 13891358.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.555275964736938,
|
|
"epoch": 0.5826128722382324,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004973261040034521,
|
|
"loss": 5.337,
|
|
"mean_token_accuracy": 0.19242704659700394,
|
|
"num_tokens": 13902680.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.437145233154297,
|
|
"epoch": 0.5830931796349664,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004973208317004852,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.19754131138324738,
|
|
"num_tokens": 13913863.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.391775846481323,
|
|
"epoch": 0.5835734870317003,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004973155542358889,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.20516717433929443,
|
|
"num_tokens": 13924917.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.244808101654053,
|
|
"epoch": 0.5840537944284342,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973102716097853,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.21175803244113922,
|
|
"num_tokens": 13936022.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.398709774017334,
|
|
"epoch": 0.5845341018251681,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973049838222973,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.20188779830932618,
|
|
"num_tokens": 13947594.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.45729923248291,
|
|
"epoch": 0.5850144092219021,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004972996908735479,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.20191690623760222,
|
|
"num_tokens": 13960698.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.432854318618775,
|
|
"epoch": 0.585494716618636,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972943927636597,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.19990049600601195,
|
|
"num_tokens": 13971004.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.319571924209595,
|
|
"epoch": 0.5859750240153698,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972890894927558,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.20630076825618743,
|
|
"num_tokens": 13982500.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.440045642852783,
|
|
"epoch": 0.5864553314121037,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004972837810609592,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.19672017246484758,
|
|
"num_tokens": 13994129.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.4005941390991214,
|
|
"epoch": 0.5869356388088377,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004972784674683933,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20621030330657958,
|
|
"num_tokens": 14005581.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.3971480369567875,
|
|
"epoch": 0.5874159462055716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972731487151815,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.19602007120847703,
|
|
"num_tokens": 14015866.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.32234902381897,
|
|
"epoch": 0.5878962536023055,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004972678248014471,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.2103286936879158,
|
|
"num_tokens": 14027002.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.335332298278809,
|
|
"epoch": 0.5883765609990393,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972624957273139,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.20955925732851027,
|
|
"num_tokens": 14038962.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.407047748565674,
|
|
"epoch": 0.5888568683957733,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004972571614929055,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.20621419847011566,
|
|
"num_tokens": 14049956.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.349813795089721,
|
|
"epoch": 0.5893371757925072,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004972518220983457,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.19567009508609773,
|
|
"num_tokens": 14062413.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.441522932052612,
|
|
"epoch": 0.5898174831892411,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004972464775437586,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.2031310349702835,
|
|
"num_tokens": 14075166.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.3587822914123535,
|
|
"epoch": 0.590297790585975,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972411278292683,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.20347016900777817,
|
|
"num_tokens": 14085208.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.4898213863372805,
|
|
"epoch": 0.590778097982709,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972357729549988,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.19587990939617156,
|
|
"num_tokens": 14096688.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.285847282409668,
|
|
"epoch": 0.5912584053794429,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004972304129210746,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.2174968883395195,
|
|
"num_tokens": 14108737.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.3329627990722654,
|
|
"epoch": 0.5917387127761767,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972250477276202,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.20658324509859086,
|
|
"num_tokens": 14120121.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.411608648300171,
|
|
"epoch": 0.5922190201729106,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972196773747599,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.20749558806419371,
|
|
"num_tokens": 14132157.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.398129272460937,
|
|
"epoch": 0.5926993275696446,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972143018626186,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.20636329650878907,
|
|
"num_tokens": 14143092.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.367132663726807,
|
|
"epoch": 0.5931796349663785,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972089211913211,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.2018151894211769,
|
|
"num_tokens": 14153973.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.44025616645813,
|
|
"epoch": 0.5936599423631124,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004972035353609923,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.19832804501056672,
|
|
"num_tokens": 14164919.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.363344812393189,
|
|
"epoch": 0.5941402497598463,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004971981443717572,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.20389323830604553,
|
|
"num_tokens": 14176803.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.399188041687012,
|
|
"epoch": 0.5946205571565802,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004971927482237409,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20608593374490738,
|
|
"num_tokens": 14190087.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.413725757598877,
|
|
"epoch": 0.5951008645533141,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004971873469170689,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.1945589154958725,
|
|
"num_tokens": 14202242.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.398504304885864,
|
|
"epoch": 0.595581171950048,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004971819404518664,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.20060925036668778,
|
|
"num_tokens": 14214020.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.381116056442261,
|
|
"epoch": 0.5960614793467819,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497176528828259,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.21497955918312073,
|
|
"num_tokens": 14225455.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.353500747680664,
|
|
"epoch": 0.5965417867435159,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971711120463722,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.20500801354646683,
|
|
"num_tokens": 14235955.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.375237035751343,
|
|
"epoch": 0.5970220941402498,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497165690106332,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.19845893681049348,
|
|
"num_tokens": 14246107.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.3678923606872555,
|
|
"epoch": 0.5975024015369836,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004971602630082642,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.20864950567483903,
|
|
"num_tokens": 14257042.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.472493362426758,
|
|
"epoch": 0.5979827089337176,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971548307522947,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.20245518237352372,
|
|
"num_tokens": 14268670.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.377494239807129,
|
|
"epoch": 0.5984630163304515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971493933385498,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.20630712062120438,
|
|
"num_tokens": 14279538.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.414871692657471,
|
|
"epoch": 0.5989433237271854,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004971439507671556,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.1970711052417755,
|
|
"num_tokens": 14291928.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.361718320846558,
|
|
"epoch": 0.5994236311239193,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971385030382384,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.21058811992406845,
|
|
"num_tokens": 14302958.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.366803550720215,
|
|
"epoch": 0.5999039385206533,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004971330501519248,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.20230466574430467,
|
|
"num_tokens": 14315585.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.370356225967408,
|
|
"epoch": 0.6003842459173871,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971275921083414,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.19949132800102234,
|
|
"num_tokens": 14327228.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.456876754760742,
|
|
"epoch": 0.600864553314121,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000497122128907615,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.1960901215672493,
|
|
"num_tokens": 14338079.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.405800151824951,
|
|
"epoch": 0.6013448607108549,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004971166605498722,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.20986559689044954,
|
|
"num_tokens": 14350220.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.4046306133270265,
|
|
"epoch": 0.6018251681075889,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971111870352401,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.19570092260837554,
|
|
"num_tokens": 14360761.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.411710166931153,
|
|
"epoch": 0.6023054755043228,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004971057083638458,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.19667310267686844,
|
|
"num_tokens": 14372056.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.449746131896973,
|
|
"epoch": 0.6027857829010567,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004971002245358166,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.2034950837492943,
|
|
"num_tokens": 14382601.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.502539539337159,
|
|
"epoch": 0.6032660902977905,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004970947355512795,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.1946375623345375,
|
|
"num_tokens": 14393749.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.410051679611206,
|
|
"epoch": 0.6037463976945245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004970892414103622,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.20318698436021804,
|
|
"num_tokens": 14405001.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.2667793273925785,
|
|
"epoch": 0.6042267050912584,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970837421131921,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.2096172794699669,
|
|
"num_tokens": 14415875.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.286073923110962,
|
|
"epoch": 0.6047070124879923,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004970782376598972,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.2067411571741104,
|
|
"num_tokens": 14426896.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.405176019668579,
|
|
"epoch": 0.6051873198847262,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004970727280506048,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.19822773188352585,
|
|
"num_tokens": 14438712.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.366730976104736,
|
|
"epoch": 0.6056676272814602,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970672132854431,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.2072374239563942,
|
|
"num_tokens": 14450952.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.375285816192627,
|
|
"epoch": 0.6061479346781941,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004970616933645403,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.20972792506217958,
|
|
"num_tokens": 14462139.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.342713022232056,
|
|
"epoch": 0.6066282420749279,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970561682880242,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.20053506791591644,
|
|
"num_tokens": 14472817.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.435551548004151,
|
|
"epoch": 0.6071085494716618,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004970506380560233,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.19702088534832002,
|
|
"num_tokens": 14484241.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.358173513412476,
|
|
"epoch": 0.6075888568683958,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004970451026686659,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.20801975429058076,
|
|
"num_tokens": 14496327.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.4454488277435305,
|
|
"epoch": 0.6080691642651297,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970395621260806,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.2013298511505127,
|
|
"num_tokens": 14508041.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.380289793014526,
|
|
"epoch": 0.6085494716618636,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497034016428396,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.2099742606282234,
|
|
"num_tokens": 14519023.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.3358838081359865,
|
|
"epoch": 0.6090297790585975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970284655757409,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.20207929313182832,
|
|
"num_tokens": 14530783.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.323081588745117,
|
|
"epoch": 0.6095100864553314,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004970229095682439,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.21023871153593063,
|
|
"num_tokens": 14541680.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.435118198394775,
|
|
"epoch": 0.6099903938520653,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970173484060344,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.2042371079325676,
|
|
"num_tokens": 14553792.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.402137231826782,
|
|
"epoch": 0.6104707012487992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004970117820892414,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.20145614594221115,
|
|
"num_tokens": 14565410.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.349171495437622,
|
|
"epoch": 0.6109510086455331,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970062106179939,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.21112052351236343,
|
|
"num_tokens": 14576722.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.304983901977539,
|
|
"epoch": 0.6114313160422671,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004970006339924214,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.20732355117797852,
|
|
"num_tokens": 14589443.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.434252738952637,
|
|
"epoch": 0.611911623439001,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004969950522126534,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.2017510011792183,
|
|
"num_tokens": 14600731.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.355280113220215,
|
|
"epoch": 0.6123919308357348,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004969894652788196,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20615158677101136,
|
|
"num_tokens": 14611152.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.3859740734100345,
|
|
"epoch": 0.6128722382324687,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969838731910494,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.19662473648786544,
|
|
"num_tokens": 14624526.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.387487840652466,
|
|
"epoch": 0.6133525456292027,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004969782759494729,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.2045746326446533,
|
|
"num_tokens": 14635527.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.406077814102173,
|
|
"epoch": 0.6138328530259366,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049697267355422,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.20498718023300172,
|
|
"num_tokens": 14647372.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.445775747299194,
|
|
"epoch": 0.6143131604226705,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004969670660054208,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.19989146590232848,
|
|
"num_tokens": 14659216.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.367588233947754,
|
|
"epoch": 0.6147934678194045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004969614533032054,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.20359105616807938,
|
|
"num_tokens": 14670336.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.3030132293701175,
|
|
"epoch": 0.6152737752161384,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969558354477041,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.20928442031145095,
|
|
"num_tokens": 14680668.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.450578737258911,
|
|
"epoch": 0.6157540826128722,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004969502124390474,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.19934382736682893,
|
|
"num_tokens": 14691521.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.384614753723144,
|
|
"epoch": 0.6162343900096061,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004969445842773658,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.19918035417795182,
|
|
"num_tokens": 14702473.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.2964098930358885,
|
|
"epoch": 0.6167146974063401,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00049693895096279,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.21094553917646408,
|
|
"num_tokens": 14713057.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.466319036483765,
|
|
"epoch": 0.617195004803074,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004969333124954508,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.20121494084596633,
|
|
"num_tokens": 14725203.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.368270969390869,
|
|
"epoch": 0.6176753121998079,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969276688754791,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.21081485748291015,
|
|
"num_tokens": 14735851.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.409839010238647,
|
|
"epoch": 0.6181556195965417,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004969220201030059,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.20156096816062927,
|
|
"num_tokens": 14747876.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.35882453918457,
|
|
"epoch": 0.6186359269932757,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969163661781624,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.20750847607851028,
|
|
"num_tokens": 14758673.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.356964063644409,
|
|
"epoch": 0.6191162343900096,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004969107071010798,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.21266389042139053,
|
|
"num_tokens": 14770505.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.409646034240723,
|
|
"epoch": 0.6195965417867435,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969050428718895,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.2044648692011833,
|
|
"num_tokens": 14782518.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.3640015602111815,
|
|
"epoch": 0.6200768491834774,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000496899373490723,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.20533745139837264,
|
|
"num_tokens": 14794608.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.279078722000122,
|
|
"epoch": 0.6205571565802114,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496893698957712,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.21289287358522416,
|
|
"num_tokens": 14804725.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.3700212955474855,
|
|
"epoch": 0.6210374639769453,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004968880192729882,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.20586251765489577,
|
|
"num_tokens": 14816178.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.403106689453125,
|
|
"epoch": 0.6215177713736791,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968823344366835,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.20386140942573547,
|
|
"num_tokens": 14827808.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.360554599761963,
|
|
"epoch": 0.621998078770413,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004968766444489298,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.20528022646903993,
|
|
"num_tokens": 14839423.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.4183426856994625,
|
|
"epoch": 0.622478386167147,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004968709493098593,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.20158216804265977,
|
|
"num_tokens": 14849678.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.29888949394226,
|
|
"epoch": 0.6229586935638809,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004968652490196041,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.2096124991774559,
|
|
"num_tokens": 14860912.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.33175048828125,
|
|
"epoch": 0.6234390009606148,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004968595435782967,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.2063300833106041,
|
|
"num_tokens": 14873028.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.440436887741089,
|
|
"epoch": 0.6239193083573487,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968538329860695,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.2024908572435379,
|
|
"num_tokens": 14883985.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.378928375244141,
|
|
"epoch": 0.6243996157540826,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968481172430549,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.19753631800413132,
|
|
"num_tokens": 14896569.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.364883756637573,
|
|
"epoch": 0.6248799231508165,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496842396349386,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.2137938216328621,
|
|
"num_tokens": 14907874.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.373042011260987,
|
|
"epoch": 0.6253602305475504,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004968366703051952,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.20926458686590194,
|
|
"num_tokens": 14919501.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.381571102142334,
|
|
"epoch": 0.6258405379442843,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968309391106157,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.20996756106615067,
|
|
"num_tokens": 14929876.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.341601610183716,
|
|
"epoch": 0.6263208453410183,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004968252027657806,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.19952473938465118,
|
|
"num_tokens": 14941317.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.438979721069336,
|
|
"epoch": 0.6268011527377522,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004968194612708229,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.2054247587919235,
|
|
"num_tokens": 14953038.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.3664439678192135,
|
|
"epoch": 0.627281460134486,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004968137146258759,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.20507377833127977,
|
|
"num_tokens": 14964664.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.308587884902954,
|
|
"epoch": 0.6277617675312199,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004968079628310732,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.21032082587480544,
|
|
"num_tokens": 14975761.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.3652996063232425,
|
|
"epoch": 0.6282420749279539,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004968022058865482,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21104391366243364,
|
|
"num_tokens": 14987670.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.274520540237427,
|
|
"epoch": 0.6287223823246878,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967964437924346,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.2170848950743675,
|
|
"num_tokens": 14999390.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.277483415603638,
|
|
"epoch": 0.6292026897214217,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967906765488662,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.2040777400135994,
|
|
"num_tokens": 15011691.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.503132438659668,
|
|
"epoch": 0.6296829971181557,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004967849041559769,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.1987210288643837,
|
|
"num_tokens": 15023539.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.421987104415893,
|
|
"epoch": 0.6301633045148896,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004967791266139006,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.20429675430059432,
|
|
"num_tokens": 15035529.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.388417196273804,
|
|
"epoch": 0.6306436119116234,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004967733439227716,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.20449272841215133,
|
|
"num_tokens": 15047072.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.462882852554321,
|
|
"epoch": 0.6311239193083573,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496767556082724,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.20441177487373352,
|
|
"num_tokens": 15058951.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.340635299682617,
|
|
"epoch": 0.6316042267050913,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004967617630938924,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.2027214825153351,
|
|
"num_tokens": 15070647.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.359203815460205,
|
|
"epoch": 0.6320845341018252,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000496755964956411,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.214221815764904,
|
|
"num_tokens": 15082324.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.454973316192627,
|
|
"epoch": 0.6325648414985591,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004967501616704147,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.19362415224313737,
|
|
"num_tokens": 15094641.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.512524747848511,
|
|
"epoch": 0.633045148895293,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000496744353236038,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.20515937954187394,
|
|
"num_tokens": 15106610.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.316631317138672,
|
|
"epoch": 0.633525456292027,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496738539653416,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.2065408021211624,
|
|
"num_tokens": 15118463.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.368905019760132,
|
|
"epoch": 0.6340057636887608,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967327209226835,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.20500614792108535,
|
|
"num_tokens": 15130154.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.33020339012146,
|
|
"epoch": 0.6344860710854947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004967268970439755,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.2092069447040558,
|
|
"num_tokens": 15140854.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.348890876770019,
|
|
"epoch": 0.6349663784822286,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967210680174274,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.20893919169902803,
|
|
"num_tokens": 15151075.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.276489782333374,
|
|
"epoch": 0.6354466858789626,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967152338431745,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.21342816352844238,
|
|
"num_tokens": 15162091.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.469628238677979,
|
|
"epoch": 0.6359269932756965,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004967093945213523,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.19746701270341874,
|
|
"num_tokens": 15175321.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.356293153762818,
|
|
"epoch": 0.6364073006724303,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967035500520962,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.20989479422569274,
|
|
"num_tokens": 15187058.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.331836318969726,
|
|
"epoch": 0.6368876080691642,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966977004355421,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.20630037039518356,
|
|
"num_tokens": 15198886.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.422998762130737,
|
|
"epoch": 0.6373679154658982,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966918456718256,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.20441487729549407,
|
|
"num_tokens": 15211026.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.296787548065185,
|
|
"epoch": 0.6378482228626321,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966859857610828,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.220084510743618,
|
|
"num_tokens": 15222094.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.332780265808106,
|
|
"epoch": 0.638328530259366,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004966801207034497,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.20379241108894347,
|
|
"num_tokens": 15232464.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.384597682952881,
|
|
"epoch": 0.6388088376560999,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004966742504990624,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.21576141864061354,
|
|
"num_tokens": 15244564.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.409323883056641,
|
|
"epoch": 0.6392891450528339,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966683751480572,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.20846149772405625,
|
|
"num_tokens": 15255822.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.405325174331665,
|
|
"epoch": 0.6397694524495677,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004966624946505706,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.20112401843070984,
|
|
"num_tokens": 15267336.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.314798498153687,
|
|
"epoch": 0.6402497598463016,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966566090067391,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.21503283828496933,
|
|
"num_tokens": 15278073.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.38770694732666,
|
|
"epoch": 0.6407300672430355,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004966507182166993,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.2004816472530365,
|
|
"num_tokens": 15290119.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.335741662979126,
|
|
"epoch": 0.6412103746397695,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000496644822280588,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.21979963630437852,
|
|
"num_tokens": 15302235.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.4044074535369875,
|
|
"epoch": 0.6416906820365034,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496638921198542,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.1978975474834442,
|
|
"num_tokens": 15312924.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.258697032928467,
|
|
"epoch": 0.6421709894332372,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966330149706984,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.2174426257610321,
|
|
"num_tokens": 15323453.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.366060256958008,
|
|
"epoch": 0.6426512968299711,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966271035971944,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.20978365391492843,
|
|
"num_tokens": 15334907.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.318216466903687,
|
|
"epoch": 0.6431316042267051,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004966211870781671,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.2098609283566475,
|
|
"num_tokens": 15347211.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.380016231536866,
|
|
"epoch": 0.643611911623439,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000496615265413754,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.19554162472486497,
|
|
"num_tokens": 15360171.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.494077539443969,
|
|
"epoch": 0.6440922190201729,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004966093386040923,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.200219264626503,
|
|
"num_tokens": 15372209.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.472732496261597,
|
|
"epoch": 0.6445725264169068,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00049660340664932,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.1996981367468834,
|
|
"num_tokens": 15383753.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.405660104751587,
|
|
"epoch": 0.6450528338136408,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004965974695495746,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.20617100447416306,
|
|
"num_tokens": 15395202.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.414996671676636,
|
|
"epoch": 0.6455331412103746,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965915273049938,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.2064132273197174,
|
|
"num_tokens": 15407121.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.3160027980804445,
|
|
"epoch": 0.6460134486071085,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004965855799157158,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.20736252665519714,
|
|
"num_tokens": 15418063.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.366697835922241,
|
|
"epoch": 0.6464937560038425,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965796273818787,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.20420271903276443,
|
|
"num_tokens": 15428830.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.377196502685547,
|
|
"epoch": 0.6469740634005764,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965736697036206,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.20707596838474274,
|
|
"num_tokens": 15441009.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.348188161849976,
|
|
"epoch": 0.6474543707973103,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965677068810798,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.2150086358189583,
|
|
"num_tokens": 15453008.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.387296867370606,
|
|
"epoch": 0.6479346781940442,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965617389143947,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.21275878548622132,
|
|
"num_tokens": 15463907.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.37171573638916,
|
|
"epoch": 0.6484149855907781,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496555765803704,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.20476562082767485,
|
|
"num_tokens": 15474706.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.381946277618408,
|
|
"epoch": 0.648895292987512,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965497875491462,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.20566535592079163,
|
|
"num_tokens": 15486355.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.358781623840332,
|
|
"epoch": 0.6493756003842459,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965438041508604,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.204537133872509,
|
|
"num_tokens": 15498184.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.442220735549927,
|
|
"epoch": 0.6498559077809798,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004965378156089851,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.20726177841424942,
|
|
"num_tokens": 15509461.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.3696051120758055,
|
|
"epoch": 0.6503362151777138,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004965318219236597,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.20339030772447586,
|
|
"num_tokens": 15520169.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.36608362197876,
|
|
"epoch": 0.6508165225744477,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965258230950232,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.20085227489471436,
|
|
"num_tokens": 15532783.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.3955810546875,
|
|
"epoch": 0.6512968299711815,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965198191232148,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.2016945704817772,
|
|
"num_tokens": 15543639.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.314856004714966,
|
|
"epoch": 0.6517771373679154,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000496513810008374,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.20794354528188705,
|
|
"num_tokens": 15555149.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.4096475601196286,
|
|
"epoch": 0.6522574447646494,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965077957506403,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.2052864596247673,
|
|
"num_tokens": 15566922.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.413950634002686,
|
|
"epoch": 0.6527377521613833,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004965017763501533,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.20561592280864716,
|
|
"num_tokens": 15578047.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.402902221679687,
|
|
"epoch": 0.6532180595581172,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004964957518070529,
|
|
"loss": 5.2523,
|
|
"mean_token_accuracy": 0.20033413618803025,
|
|
"num_tokens": 15590378.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.404299926757813,
|
|
"epoch": 0.6536983669548511,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964897221214788,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.20550832003355027,
|
|
"num_tokens": 15600866.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.3758461475372314,
|
|
"epoch": 0.654178674351585,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000496483687293571,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.2104722484946251,
|
|
"num_tokens": 15612617.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.326417875289917,
|
|
"epoch": 0.6546589817483189,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004964776473234696,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.21460745334625245,
|
|
"num_tokens": 15624446.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.363725805282593,
|
|
"epoch": 0.6551392891450528,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496471602211315,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.21014775931835175,
|
|
"num_tokens": 15635300.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.2954082012176515,
|
|
"epoch": 0.6556195965417867,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964655519572475,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.21060389876365662,
|
|
"num_tokens": 15646452.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.343070220947266,
|
|
"epoch": 0.6560999039385207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964594965614072,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.19869527518749236,
|
|
"num_tokens": 15658514.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.444543123245239,
|
|
"epoch": 0.6565802113352546,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004964534360239353,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.20481337755918502,
|
|
"num_tokens": 15670222.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.355707502365112,
|
|
"epoch": 0.6570605187319885,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496447370344972,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.20832472741603852,
|
|
"num_tokens": 15681627.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.334160852432251,
|
|
"epoch": 0.6575408261287223,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004964412995246584,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20418668687343597,
|
|
"num_tokens": 15692632.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.333785629272461,
|
|
"epoch": 0.6580211335254563,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004964352235631354,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.20951071083545686,
|
|
"num_tokens": 15704736.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.403020715713501,
|
|
"epoch": 0.6585014409221902,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496429142460544,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.20581095218658446,
|
|
"num_tokens": 15717057.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.4708630561828615,
|
|
"epoch": 0.6589817483189241,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964230562170254,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.19407797306776048,
|
|
"num_tokens": 15728577.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.398970651626587,
|
|
"epoch": 0.659462055715658,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964169648327209,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.20342856347560884,
|
|
"num_tokens": 15739714.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.328509426116943,
|
|
"epoch": 0.659942363112392,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000496410868307772,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.21793588548898696,
|
|
"num_tokens": 15751339.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.481879854202271,
|
|
"epoch": 0.6604226705091258,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004964047666423203,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.19867317825555803,
|
|
"num_tokens": 15763177.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.409116172790528,
|
|
"epoch": 0.6609029779058597,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963986598365072,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.2040127009153366,
|
|
"num_tokens": 15774691.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.393391704559326,
|
|
"epoch": 0.6613832853025937,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004963925478904746,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.20786909610033036,
|
|
"num_tokens": 15785561.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.3978273391723635,
|
|
"epoch": 0.6618635926993276,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963864308043645,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.20175087749958037,
|
|
"num_tokens": 15795687.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.352889776229858,
|
|
"epoch": 0.6623439000960615,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004963803085783189,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.21015525460243226,
|
|
"num_tokens": 15807191.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.351000213623047,
|
|
"epoch": 0.6628242074927954,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004963741812124799,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.20978523343801497,
|
|
"num_tokens": 15819585.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.425973606109619,
|
|
"epoch": 0.6633045148895294,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004963680487069898,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.2027926877140999,
|
|
"num_tokens": 15831580.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.349288368225098,
|
|
"epoch": 0.6637848222862632,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004963619110619908,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.20835866779088974,
|
|
"num_tokens": 15843848.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.4336811065673825,
|
|
"epoch": 0.6642651296829971,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004963557682776256,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.2000281497836113,
|
|
"num_tokens": 15855091.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.367064666748047,
|
|
"epoch": 0.664745437079731,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004963496203540368,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.209804530441761,
|
|
"num_tokens": 15866676.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.315239763259887,
|
|
"epoch": 0.665225744476465,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963434672913671,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.21167042702436448,
|
|
"num_tokens": 15877901.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.353574323654175,
|
|
"epoch": 0.6657060518731989,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004963373090897592,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.19783878028392793,
|
|
"num_tokens": 15889284.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.339661121368408,
|
|
"epoch": 0.6661863592699327,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004963311457493563,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.21966685503721237,
|
|
"num_tokens": 15901218.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.2811511039733885,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004963249772703015,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.21470819264650345,
|
|
"num_tokens": 15912452.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.336771821975708,
|
|
"epoch": 0.6671469740634006,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004963188036527378,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.21019225418567658,
|
|
"num_tokens": 15924353.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.421128368377685,
|
|
"epoch": 0.6676272814601345,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963126248968087,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.21308566331863404,
|
|
"num_tokens": 15936295.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.352389764785767,
|
|
"epoch": 0.6681075888568684,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963064410026577,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20642731785774232,
|
|
"num_tokens": 15948407.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.332984447479248,
|
|
"epoch": 0.6685878962536023,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004963002519704281,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.21129985451698302,
|
|
"num_tokens": 15959975.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.376897144317627,
|
|
"epoch": 0.6690682036503363,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000496294057800264,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.21263132989406586,
|
|
"num_tokens": 15973084.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.265993642807007,
|
|
"epoch": 0.6695485110470701,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004962878584923089,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.21592305302619935,
|
|
"num_tokens": 15984444.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.305892658233643,
|
|
"epoch": 0.670028818443804,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004962816540467068,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.20955159217119218,
|
|
"num_tokens": 15996611.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.386642932891846,
|
|
"epoch": 0.6705091258405379,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962754444636017,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.20707219392061232,
|
|
"num_tokens": 16007144.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.366505765914917,
|
|
"epoch": 0.6709894332372719,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496269229743138,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.21360071897506713,
|
|
"num_tokens": 16018878.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.381399822235108,
|
|
"epoch": 0.6714697406340058,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004962630098854597,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.20536957830190658,
|
|
"num_tokens": 16031273.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.413681316375732,
|
|
"epoch": 0.6719500480307397,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004962567848907113,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.20079512894153595,
|
|
"num_tokens": 16043101.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.318014860153198,
|
|
"epoch": 0.6724303554274735,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962505547590374,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.20945301800966262,
|
|
"num_tokens": 16054922.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.396268272399903,
|
|
"epoch": 0.6729106628242075,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004962443194905826,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.20081157833337784,
|
|
"num_tokens": 16065461.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.4040364742279055,
|
|
"epoch": 0.6733909702209414,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004962380790854916,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.2002710297703743,
|
|
"num_tokens": 16076715.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.355012989044189,
|
|
"epoch": 0.6738712776176753,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004962318335439094,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.20772433429956436,
|
|
"num_tokens": 16088937.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.2813855648040775,
|
|
"epoch": 0.6743515850144092,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004962255828659809,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.2119379833340645,
|
|
"num_tokens": 16100004.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.383071804046631,
|
|
"epoch": 0.6748318924111432,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004962193270518513,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.21044733077287675,
|
|
"num_tokens": 16112435.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.407391500473023,
|
|
"epoch": 0.675312199807877,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004962130661016659,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.20217737704515457,
|
|
"num_tokens": 16124246.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.461057853698731,
|
|
"epoch": 0.6757925072046109,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004962068000155699,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.198933644592762,
|
|
"num_tokens": 16136291.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.320038795471191,
|
|
"epoch": 0.6762728146013448,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004962005287937088,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.21186097264289855,
|
|
"num_tokens": 16148641.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.278940725326538,
|
|
"epoch": 0.6767531219980788,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961942524362283,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.21842436641454696,
|
|
"num_tokens": 16159152.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.430412340164184,
|
|
"epoch": 0.6772334293948127,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961879709432741,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.2026938483119011,
|
|
"num_tokens": 16170019.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.471914958953858,
|
|
"epoch": 0.6777137367915466,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000496181684314992,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.2016692951321602,
|
|
"num_tokens": 16181714.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.356434917449951,
|
|
"epoch": 0.6781940441882806,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004961753925515279,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.20125249475240709,
|
|
"num_tokens": 16192822.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.275795412063599,
|
|
"epoch": 0.6786743515850144,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000496169095653028,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.21073099970817566,
|
|
"num_tokens": 16203660.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.325348663330078,
|
|
"epoch": 0.6791546589817483,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004961627936196384,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.21378066390752792,
|
|
"num_tokens": 16215495.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.3263932228088375,
|
|
"epoch": 0.6796349663784822,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004961564864515055,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.21500083506107331,
|
|
"num_tokens": 16227532.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.210251903533935,
|
|
"epoch": 0.6801152737752162,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961501741487757,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.22491745799779891,
|
|
"num_tokens": 16238979.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.257687902450561,
|
|
"epoch": 0.6805955811719501,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961438567115955,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.2157309889793396,
|
|
"num_tokens": 16249146.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.328334665298462,
|
|
"epoch": 0.681075888568684,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004961375341401116,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.20423975288867952,
|
|
"num_tokens": 16262269.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.306555271148682,
|
|
"epoch": 0.6815561959654178,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004961312064344708,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.20990136563777922,
|
|
"num_tokens": 16273877.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.452419185638428,
|
|
"epoch": 0.6820365033621518,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00049612487359482,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.20249960869550704,
|
|
"num_tokens": 16285623.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.304304552078247,
|
|
"epoch": 0.6825168107588857,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004961185356213062,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.21544889062643052,
|
|
"num_tokens": 16296242.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.395910406112671,
|
|
"epoch": 0.6829971181556196,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004961121925140767,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.2042468562722206,
|
|
"num_tokens": 16308400.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.32966685295105,
|
|
"epoch": 0.6834774255523535,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004961058442732786,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.2054202064871788,
|
|
"num_tokens": 16319201.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.377595663070679,
|
|
"epoch": 0.6839577329490875,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004960994908990594,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.20573489218950272,
|
|
"num_tokens": 16331462.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.393956184387207,
|
|
"epoch": 0.6844380403458213,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004960931323915665,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.20968266874551772,
|
|
"num_tokens": 16343428.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.357161569595337,
|
|
"epoch": 0.6849183477425552,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004960867687509475,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.2101307913661003,
|
|
"num_tokens": 16356270.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.320086574554443,
|
|
"epoch": 0.6853986551392891,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004960803999773504,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.21285180747509003,
|
|
"num_tokens": 16367039.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.287798166275024,
|
|
"epoch": 0.6858789625360231,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004960740260709228,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.20892418622970582,
|
|
"num_tokens": 16378601.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.391539478302002,
|
|
"epoch": 0.686359269932757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004960676470318128,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.20675097703933715,
|
|
"num_tokens": 16391096.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.38094654083252,
|
|
"epoch": 0.6868395773294909,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004960612628601683,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.21334029734134674,
|
|
"num_tokens": 16401527.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.368460702896118,
|
|
"epoch": 0.6873198847262247,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004960548735561379,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.1959829643368721,
|
|
"num_tokens": 16413948.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.388773012161255,
|
|
"epoch": 0.6878001921229587,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004960484791198697,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.2110881209373474,
|
|
"num_tokens": 16425718.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.325989294052124,
|
|
"epoch": 0.6882804995196926,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960420795515121,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.20842294991016388,
|
|
"num_tokens": 16437606.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.349394035339356,
|
|
"epoch": 0.6887608069164265,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004960356748512138,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.21175835877656937,
|
|
"num_tokens": 16448964.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.346666526794434,
|
|
"epoch": 0.6892411143131604,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004960292650191236,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.20859440714120864,
|
|
"num_tokens": 16459974.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.354806232452392,
|
|
"epoch": 0.6897214217098944,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960228500553899,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.20838966369628906,
|
|
"num_tokens": 16471143.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.325416851043701,
|
|
"epoch": 0.6902017291066282,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004960164299601623,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.2170963853597641,
|
|
"num_tokens": 16482090.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.337446212768555,
|
|
"epoch": 0.6906820365033621,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004960100047335892,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.21201336532831191,
|
|
"num_tokens": 16493695.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.377599382400513,
|
|
"epoch": 0.691162343900096,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960035743758202,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.2069594830274582,
|
|
"num_tokens": 16505317.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.360534524917602,
|
|
"epoch": 0.69164265129683,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959971388870044,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.21057302355766297,
|
|
"num_tokens": 16516719.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.389997863769532,
|
|
"epoch": 0.6921229586935639,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004959906982672912,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.21127886027097703,
|
|
"num_tokens": 16528302.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.300697278976441,
|
|
"epoch": 0.6926032660902978,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959842525168302,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.20713712573051452,
|
|
"num_tokens": 16538471.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.38419771194458,
|
|
"epoch": 0.6930835734870316,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004959778016357712,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.21198445409536362,
|
|
"num_tokens": 16549283.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.357424736022949,
|
|
"epoch": 0.6935638808837656,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959713456242637,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.20383756011724471,
|
|
"num_tokens": 16560895.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.325250196456909,
|
|
"epoch": 0.6940441882804995,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004959648844824576,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.20396466106176375,
|
|
"num_tokens": 16571306.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.334082889556885,
|
|
"epoch": 0.6945244956772334,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004959584182105032,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.21128447055816652,
|
|
"num_tokens": 16582399.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.3108282566070555,
|
|
"epoch": 0.6950048030739674,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004959519468085504,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.21449533402919768,
|
|
"num_tokens": 16593617.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.2841941833496096,
|
|
"epoch": 0.6954851104707013,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004959454702767494,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.2121504694223404,
|
|
"num_tokens": 16604109.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.440049934387207,
|
|
"epoch": 0.6959654178674352,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004959389886152507,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.20011045187711715,
|
|
"num_tokens": 16616007.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.356936025619507,
|
|
"epoch": 0.696445725264169,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959325018242048,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.21180123090744019,
|
|
"num_tokens": 16627609.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.3580810070037845,
|
|
"epoch": 0.696926032660903,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004959260099037622,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.20908065438270568,
|
|
"num_tokens": 16639842.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.399222755432129,
|
|
"epoch": 0.6974063400576369,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004959195128540737,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.19815656840801238,
|
|
"num_tokens": 16651620.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.355722284317016,
|
|
"epoch": 0.6978866474543708,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049591301067529,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.21143410950899125,
|
|
"num_tokens": 16663637.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.389974164962768,
|
|
"epoch": 0.6983669548511047,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004959065033675623,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.20641382783651352,
|
|
"num_tokens": 16675685.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.404815292358398,
|
|
"epoch": 0.6988472622478387,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004958999909310414,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.20364335775375367,
|
|
"num_tokens": 16686268.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.314729261398315,
|
|
"epoch": 0.6993275696445725,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004958934733658788,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.2107451230287552,
|
|
"num_tokens": 16698382.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.401017141342163,
|
|
"epoch": 0.6998078770413064,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004958869506722256,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.197574682533741,
|
|
"num_tokens": 16710421.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.336795282363892,
|
|
"epoch": 0.7002881844380403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004958804228502332,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.20648131370544434,
|
|
"num_tokens": 16721658.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.342508554458618,
|
|
"epoch": 0.7007684918347743,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004958738899000534,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.21296579837799073,
|
|
"num_tokens": 16734100.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.27999963760376,
|
|
"epoch": 0.7012487992315082,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004958673518218377,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.20937683433294296,
|
|
"num_tokens": 16746386.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.394632768630982,
|
|
"epoch": 0.7017291066282421,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958608086157379,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.2117364674806595,
|
|
"num_tokens": 16756967.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.303658199310303,
|
|
"epoch": 0.7022094140249759,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495854260281906,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.2125537723302841,
|
|
"num_tokens": 16767454.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.257411861419678,
|
|
"epoch": 0.7026897214217099,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004958477068204941,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.21460433155298234,
|
|
"num_tokens": 16779533.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.380031585693359,
|
|
"epoch": 0.7031700288184438,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495841148231654,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.2042733311653137,
|
|
"num_tokens": 16792019.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.324429702758789,
|
|
"epoch": 0.7036503362151777,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004958345845155383,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.208876533806324,
|
|
"num_tokens": 16803089.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.329727077484131,
|
|
"epoch": 0.7041306436119116,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004958280156722992,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.21587250381708145,
|
|
"num_tokens": 16813651.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.299258184432984,
|
|
"epoch": 0.7046109510086456,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004958214417020894,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.2162966713309288,
|
|
"num_tokens": 16825460.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.291118955612182,
|
|
"epoch": 0.7050912584053795,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004958148626050614,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.20754572451114656,
|
|
"num_tokens": 16836344.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.365191316604614,
|
|
"epoch": 0.7055715658021133,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.2099486321210861,
|
|
"num_tokens": 16848274.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.336651563644409,
|
|
"epoch": 0.7060518731988472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495801689031162,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.2086411789059639,
|
|
"num_tokens": 16860363.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.343815040588379,
|
|
"epoch": 0.7065321805955812,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004957950945545965,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.21170026808977127,
|
|
"num_tokens": 16872037.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.398956394195556,
|
|
"epoch": 0.7070124879923151,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004957884949518246,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.20197186172008513,
|
|
"num_tokens": 16883845.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.369536352157593,
|
|
"epoch": 0.707492795389049,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957818902229992,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.20235901623964309,
|
|
"num_tokens": 16894965.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.33243498802185,
|
|
"epoch": 0.7079731027857828,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004957752803682741,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.20662362724542618,
|
|
"num_tokens": 16907475.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.288620376586914,
|
|
"epoch": 0.7084534101825168,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957686653878024,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.21257337927818298,
|
|
"num_tokens": 16918825.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.3551513195037845,
|
|
"epoch": 0.7089337175792507,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000495762045281738,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.2085180938243866,
|
|
"num_tokens": 16930663.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.3533955097198485,
|
|
"epoch": 0.7094140249759846,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957554200502344,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.21151500940322876,
|
|
"num_tokens": 16942089.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.293340587615967,
|
|
"epoch": 0.7098943323727186,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004957487896934454,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.21003037244081496,
|
|
"num_tokens": 16954203.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.334824132919311,
|
|
"epoch": 0.7103746397694525,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000495742154211525,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.21513081043958665,
|
|
"num_tokens": 16966047.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.254987525939941,
|
|
"epoch": 0.7108549471661864,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004957355136046272,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.22170827835798262,
|
|
"num_tokens": 16977726.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.294209098815918,
|
|
"epoch": 0.7113352545629202,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004957288678729064,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.2174298956990242,
|
|
"num_tokens": 16990917.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.328539800643921,
|
|
"epoch": 0.7118155619596542,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004957222170165166,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.21558848768472672,
|
|
"num_tokens": 17001703.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.292131423950195,
|
|
"epoch": 0.7122958693563881,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004957155610356124,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.2204562246799469,
|
|
"num_tokens": 17011918.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.37599744796753,
|
|
"epoch": 0.712776176753122,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004957088999303481,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.20711808353662492,
|
|
"num_tokens": 17022653.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.290156650543213,
|
|
"epoch": 0.7132564841498559,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004957022337008787,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21836102157831191,
|
|
"num_tokens": 17034775.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.225661277770996,
|
|
"epoch": 0.7137367915465899,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004956955623473587,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.20644650906324385,
|
|
"num_tokens": 17046835.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.398440313339234,
|
|
"epoch": 0.7142170989433237,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000495688885869943,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.2106576070189476,
|
|
"num_tokens": 17059163.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.384093618392944,
|
|
"epoch": 0.7146974063400576,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004956822042687868,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.2023412600159645,
|
|
"num_tokens": 17070777.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.348931884765625,
|
|
"epoch": 0.7151777137367915,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956755175440451,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20869874954223633,
|
|
"num_tokens": 17083770.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.30858964920044,
|
|
"epoch": 0.7156580211335255,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956688256958731,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.2089409723877907,
|
|
"num_tokens": 17096049.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.297193479537964,
|
|
"epoch": 0.7161383285302594,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004956621287244262,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.21683794260025024,
|
|
"num_tokens": 17107030.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.283672761917114,
|
|
"epoch": 0.7166186359269933,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956554266298599,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.2142602503299713,
|
|
"num_tokens": 17118638.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.337230777740478,
|
|
"epoch": 0.7170989433237271,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004956487194123298,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.21441817730665208,
|
|
"num_tokens": 17129783.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.354993724822998,
|
|
"epoch": 0.7175792507204611,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956420070719918,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.20522771626710892,
|
|
"num_tokens": 17141939.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.33065185546875,
|
|
"epoch": 0.718059558117195,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004956352896090014,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.209945510327816,
|
|
"num_tokens": 17153471.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.377154397964477,
|
|
"epoch": 0.7185398655139289,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004956285670235147,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.20324529111385345,
|
|
"num_tokens": 17164659.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.365829992294311,
|
|
"epoch": 0.7190201729106628,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004956218393156879,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.21276272982358932,
|
|
"num_tokens": 17175749.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.347799062728882,
|
|
"epoch": 0.7195004803073968,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004956151064856772,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20691333562135697,
|
|
"num_tokens": 17187482.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.36266975402832,
|
|
"epoch": 0.7199807877041307,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004956083685336386,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.2102682575583458,
|
|
"num_tokens": 17199904.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.294642639160156,
|
|
"epoch": 0.7204610951008645,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004956016254597289,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.2057345390319824,
|
|
"num_tokens": 17210649.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.315365982055664,
|
|
"epoch": 0.7209414024975984,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004955948772641044,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.20532299131155013,
|
|
"num_tokens": 17223069.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.353263902664184,
|
|
"epoch": 0.7214217098943324,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000495588123946922,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.2147880971431732,
|
|
"num_tokens": 17235144.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.321065664291382,
|
|
"epoch": 0.7219020172910663,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004955813655083384,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.21144529730081557,
|
|
"num_tokens": 17246816.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.261761426925659,
|
|
"epoch": 0.7223823246878002,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004955746019485104,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.2119804099202156,
|
|
"num_tokens": 17259056.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.37423620223999,
|
|
"epoch": 0.722862632084534,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000495567833267595,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.2050064355134964,
|
|
"num_tokens": 17270391.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.378805780410767,
|
|
"epoch": 0.723342939481268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004955610594657496,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.2114293783903122,
|
|
"num_tokens": 17281608.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.32564344406128,
|
|
"epoch": 0.7238232468780019,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955542805431313,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.2033885821700096,
|
|
"num_tokens": 17293649.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.317047834396362,
|
|
"epoch": 0.7243035542747358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004955474964998976,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.20984159260988236,
|
|
"num_tokens": 17305548.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.42264142036438,
|
|
"epoch": 0.7247838616714697,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955407073362058,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.2094628021121025,
|
|
"num_tokens": 17317380.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.299745035171509,
|
|
"epoch": 0.7252641690682037,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955339130522136,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.21057516485452651,
|
|
"num_tokens": 17329263.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.399845981597901,
|
|
"epoch": 0.7257444764649376,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495527113648079,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.2001323252916336,
|
|
"num_tokens": 17343268.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.397094821929931,
|
|
"epoch": 0.7262247838616714,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004955203091239596,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.21608648151159288,
|
|
"num_tokens": 17353979.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.316676187515259,
|
|
"epoch": 0.7267050912584054,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004955134994800134,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.2056532934308052,
|
|
"num_tokens": 17367587.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.377186918258667,
|
|
"epoch": 0.7271853986551393,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004955066847163984,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.20674082040786743,
|
|
"num_tokens": 17379093.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.4029582977294925,
|
|
"epoch": 0.7276657060518732,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954998648332731,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.21390697807073594,
|
|
"num_tokens": 17391254.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.292646169662476,
|
|
"epoch": 0.7281460134486071,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004954930398307956,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.20810437351465225,
|
|
"num_tokens": 17402532.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.3182543277740475,
|
|
"epoch": 0.7286263208453411,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004954862097091245,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.21028677821159364,
|
|
"num_tokens": 17413849.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.284389686584473,
|
|
"epoch": 0.729106628242075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954793744684184,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.22128271758556367,
|
|
"num_tokens": 17424982.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.410014343261719,
|
|
"epoch": 0.7295869356388088,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004954725341088358,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.19626507610082627,
|
|
"num_tokens": 17437774.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.351722478866577,
|
|
"epoch": 0.7300672430355427,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004954656886305356,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.2156132310628891,
|
|
"num_tokens": 17448676.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.390631580352784,
|
|
"epoch": 0.7305475504322767,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004954588380336768,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.2094218835234642,
|
|
"num_tokens": 17459576.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.2572461605072025,
|
|
"epoch": 0.7310278578290106,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954519823184184,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.2232707619667053,
|
|
"num_tokens": 17471220.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.351441144943237,
|
|
"epoch": 0.7315081652257445,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954451214849196,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.2026347577571869,
|
|
"num_tokens": 17483939.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.342600393295288,
|
|
"epoch": 0.7319884726224783,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004954382555333397,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.21264499872922898,
|
|
"num_tokens": 17496058.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.345719623565674,
|
|
"epoch": 0.7324687800192123,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000495431384463838,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.2090696319937706,
|
|
"num_tokens": 17507750.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.333091878890992,
|
|
"epoch": 0.7329490874159462,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004954245082765741,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.2161535307765007,
|
|
"num_tokens": 17520208.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.3212285995483395,
|
|
"epoch": 0.7334293948126801,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954176269717077,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.2168772906064987,
|
|
"num_tokens": 17531655.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.288695287704468,
|
|
"epoch": 0.733909702209414,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954107405493984,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.20704424679279326,
|
|
"num_tokens": 17543766.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.39906325340271,
|
|
"epoch": 0.734390009606148,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004954038490098064,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.2022583708167076,
|
|
"num_tokens": 17555710.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.259468269348145,
|
|
"epoch": 0.7348703170028819,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004953969523530914,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.21729554384946823,
|
|
"num_tokens": 17566674.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.337100553512573,
|
|
"epoch": 0.7353506243996157,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004953900505794136,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.20614737570285796,
|
|
"num_tokens": 17579320.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.362096786499023,
|
|
"epoch": 0.7358309317963496,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004953831436889332,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.20341226309537888,
|
|
"num_tokens": 17590679.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.318915176391601,
|
|
"epoch": 0.7363112391930836,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004953762316818106,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.22266588509082794,
|
|
"num_tokens": 17600928.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.181799268722534,
|
|
"epoch": 0.7367915465898175,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004953693145582064,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.22265284806489943,
|
|
"num_tokens": 17611906.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.29643874168396,
|
|
"epoch": 0.7372718539865514,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000495362392318281,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.20780395865440368,
|
|
"num_tokens": 17623165.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.417064428329468,
|
|
"epoch": 0.7377521613832853,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004953554649621951,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.2159091964364052,
|
|
"num_tokens": 17633632.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.3001707077026365,
|
|
"epoch": 0.7382324687800192,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953485324901098,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.2171645864844322,
|
|
"num_tokens": 17644801.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.240055942535401,
|
|
"epoch": 0.7387127761767531,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004953415949021857,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.21038098484277726,
|
|
"num_tokens": 17656852.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.37674355506897,
|
|
"epoch": 0.739193083573487,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004953346521985843,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20611296445131302,
|
|
"num_tokens": 17667538.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.311875581741333,
|
|
"epoch": 0.7396733909702209,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004953277043794663,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.21544387340545654,
|
|
"num_tokens": 17680049.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.234278678894043,
|
|
"epoch": 0.7401536983669549,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004953207514449933,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.21067160964012147,
|
|
"num_tokens": 17692611.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.300888967514038,
|
|
"epoch": 0.7406340057636888,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004953137933953267,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.2198130175471306,
|
|
"num_tokens": 17704145.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.386393070220947,
|
|
"epoch": 0.7411143131604226,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000495306830230628,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20425367802381517,
|
|
"num_tokens": 17715467.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.333774900436401,
|
|
"epoch": 0.7415946205571565,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004952998619510589,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.21887701898813247,
|
|
"num_tokens": 17726709.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.2914834976196286,
|
|
"epoch": 0.7420749279538905,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004952928885567811,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.21903081089258195,
|
|
"num_tokens": 17736896.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.3399537086486815,
|
|
"epoch": 0.7425552353506244,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952859100479566,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.21103069484233855,
|
|
"num_tokens": 17747658.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.316709375381469,
|
|
"epoch": 0.7430355427473583,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004952789264247474,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.21338920295238495,
|
|
"num_tokens": 17757833.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.305129671096802,
|
|
"epoch": 0.7435158501440923,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004952719376873156,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.211634960770607,
|
|
"num_tokens": 17769144.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.374722719192505,
|
|
"epoch": 0.7439961575408262,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952649438358234,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.20525980591773987,
|
|
"num_tokens": 17781357.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.385539102554321,
|
|
"epoch": 0.74447646493756,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004952579448704334,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.21078045517206193,
|
|
"num_tokens": 17793640.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.2819897651672365,
|
|
"epoch": 0.7449567723342939,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000495250940791308,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.21097445785999297,
|
|
"num_tokens": 17804228.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.339059591293335,
|
|
"epoch": 0.7454370797310279,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004952439315986096,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.20897524207830429,
|
|
"num_tokens": 17816153.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.319443893432617,
|
|
"epoch": 0.7459173871277618,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004952369172925012,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.2127428486943245,
|
|
"num_tokens": 17828464.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.1952742576599125,
|
|
"epoch": 0.7463976945244957,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952298978731454,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.2162572294473648,
|
|
"num_tokens": 17840126.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.2883213520050045,
|
|
"epoch": 0.7468780019212296,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004952228733407055,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.2149747520685196,
|
|
"num_tokens": 17851735.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.366294908523559,
|
|
"epoch": 0.7473583093179635,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004952158436953444,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.2114664375782013,
|
|
"num_tokens": 17862897.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.313674354553223,
|
|
"epoch": 0.7478386167146974,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004952088089372252,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.21095989942550658,
|
|
"num_tokens": 17874235.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.271867799758911,
|
|
"epoch": 0.7483189241114313,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952017690665114,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.21265782564878463,
|
|
"num_tokens": 17885677.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.295902299880981,
|
|
"epoch": 0.7487992315081652,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004951947240833664,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.22135131806135178,
|
|
"num_tokens": 17896204.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.401530933380127,
|
|
"epoch": 0.7492795389048992,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004951876739879537,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.20960492491722107,
|
|
"num_tokens": 17908514.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.322813844680786,
|
|
"epoch": 0.7497598463016331,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004951806187804371,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.21876536309719086,
|
|
"num_tokens": 17918493.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.326866960525512,
|
|
"epoch": 0.7502401536983669,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004951735584609804,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.22170157581567765,
|
|
"num_tokens": 17929016.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.232990503311157,
|
|
"epoch": 0.7507204610951008,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004951664930297474,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.21907253712415695,
|
|
"num_tokens": 17940674.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.33362078666687,
|
|
"epoch": 0.7512007684918348,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000495159422486902,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.21004875600337983,
|
|
"num_tokens": 17951431.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.461094093322754,
|
|
"epoch": 0.7516810758885687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951523468326088,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.1986626997590065,
|
|
"num_tokens": 17961434.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.225731706619262,
|
|
"epoch": 0.7521613832853026,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004951452660670317,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.2228434443473816,
|
|
"num_tokens": 17971917.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.320591306686401,
|
|
"epoch": 0.7526416906820365,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004951381801903352,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.2175981417298317,
|
|
"num_tokens": 17983754.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.2798316955566404,
|
|
"epoch": 0.7531219980787704,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951310892026839,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.21510851234197617,
|
|
"num_tokens": 17994088.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.287669277191162,
|
|
"epoch": 0.7536023054755043,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004951239931042424,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.2126523733139038,
|
|
"num_tokens": 18004847.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.280338907241822,
|
|
"epoch": 0.7540826128722382,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004951168918951753,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.2177275761961937,
|
|
"num_tokens": 18015756.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.32873501777649,
|
|
"epoch": 0.7545629202689721,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004951097855756476,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.2071801796555519,
|
|
"num_tokens": 18026417.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.344317817687989,
|
|
"epoch": 0.7550432276657061,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951026741458243,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.21667793840169908,
|
|
"num_tokens": 18038205.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.316375350952148,
|
|
"epoch": 0.75552353506244,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950955576058705,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.21096965074539184,
|
|
"num_tokens": 18049223.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.336969518661499,
|
|
"epoch": 0.7560038424591738,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004950884359559513,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.21117515116930008,
|
|
"num_tokens": 18061855.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.303632736206055,
|
|
"epoch": 0.7564841498559077,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004950813091962324,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.21592069119215013,
|
|
"num_tokens": 18073969.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.2876753330230715,
|
|
"epoch": 0.7569644572526417,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004950741773268788,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.21702596992254258,
|
|
"num_tokens": 18085786.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.307117223739624,
|
|
"epoch": 0.7574447646493756,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004950670403480562,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.21541053354740142,
|
|
"num_tokens": 18096263.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.346331977844239,
|
|
"epoch": 0.7579250720461095,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004950598982599306,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.20096708238124847,
|
|
"num_tokens": 18108769.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.337701368331909,
|
|
"epoch": 0.7584053794428435,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004950527510626675,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.21063445061445235,
|
|
"num_tokens": 18120255.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.317314004898071,
|
|
"epoch": 0.7588856868395774,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004950455987564329,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.21230723857879638,
|
|
"num_tokens": 18132016.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.235875082015991,
|
|
"epoch": 0.7593659942363112,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950384413413931,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.21308435648679733,
|
|
"num_tokens": 18144101.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.325856113433838,
|
|
"epoch": 0.7598463016330451,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004950312788177139,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.2153721734881401,
|
|
"num_tokens": 18155086.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.308596611022949,
|
|
"epoch": 0.7603266090297791,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004950241111855618,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.2081622749567032,
|
|
"num_tokens": 18166902.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.32182354927063,
|
|
"epoch": 0.760806916426513,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004950169384451031,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.21735523790121078,
|
|
"num_tokens": 18178258.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.352345991134643,
|
|
"epoch": 0.7612872238232469,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004950097605965045,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.210062612593174,
|
|
"num_tokens": 18190580.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.320205307006836,
|
|
"epoch": 0.7617675312199808,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004950025776399326,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.20400335639715195,
|
|
"num_tokens": 18204912.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.29908857345581,
|
|
"epoch": 0.7622478386167147,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000494995389575554,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.2059864118695259,
|
|
"num_tokens": 18215129.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.350721025466919,
|
|
"epoch": 0.7627281460134486,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004949881964035357,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.20530935972929001,
|
|
"num_tokens": 18225640.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.286278200149536,
|
|
"epoch": 0.7632084534101825,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004949809981240448,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.21892179399728776,
|
|
"num_tokens": 18236641.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.26062421798706,
|
|
"epoch": 0.7636887608069164,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004949737947372483,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.2104298949241638,
|
|
"num_tokens": 18249244.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.310193872451782,
|
|
"epoch": 0.7641690682036504,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004949665862433134,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.21164610683918,
|
|
"num_tokens": 18261595.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.3195353031158445,
|
|
"epoch": 0.7646493756003843,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004949593726424077,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.2200590491294861,
|
|
"num_tokens": 18272609.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.372045040130615,
|
|
"epoch": 0.7651296829971181,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004949521539346985,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.2114073231816292,
|
|
"num_tokens": 18283886.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.324134111404419,
|
|
"epoch": 0.765609990393852,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004949449301203533,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.21158874928951263,
|
|
"num_tokens": 18294794.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.4366968154907225,
|
|
"epoch": 0.766090297790586,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004949377011995399,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.21228455603122712,
|
|
"num_tokens": 18306250.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.340616130828858,
|
|
"epoch": 0.7665706051873199,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004949304671724263,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.21048405021429062,
|
|
"num_tokens": 18317743.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.228299283981324,
|
|
"epoch": 0.7670509125840538,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004949232280391802,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.2171640947461128,
|
|
"num_tokens": 18328287.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.335189914703369,
|
|
"epoch": 0.7675312199807877,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004949159837999698,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.21385425478219985,
|
|
"num_tokens": 18341354.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.3781873226165775,
|
|
"epoch": 0.7680115273775217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949087344549633,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.211006361246109,
|
|
"num_tokens": 18353822.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.426526784896851,
|
|
"epoch": 0.7684918347742555,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000494901480004329,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.20886593610048293,
|
|
"num_tokens": 18365491.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.216927862167358,
|
|
"epoch": 0.7689721421709894,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004948942204482351,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.2179023265838623,
|
|
"num_tokens": 18376329.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.3637172222137455,
|
|
"epoch": 0.7694524495677233,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948869557868506,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.20768971890211105,
|
|
"num_tokens": 18387105.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.328100728988647,
|
|
"epoch": 0.7699327569644573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004948796860203439,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.21017084866762162,
|
|
"num_tokens": 18398113.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.298739337921143,
|
|
"epoch": 0.7704130643611912,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004948724111488838,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.21512434482574463,
|
|
"num_tokens": 18409315.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.250368309020996,
|
|
"epoch": 0.770893371757925,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948651311726391,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.20720863193273545,
|
|
"num_tokens": 18421110.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.390936231613159,
|
|
"epoch": 0.7713736791546589,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004948578460917789,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.20120172798633576,
|
|
"num_tokens": 18433145.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.371417808532715,
|
|
"epoch": 0.7718539865513929,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004948505559064725,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.20843850672245026,
|
|
"num_tokens": 18444689.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.253040599822998,
|
|
"epoch": 0.7723342939481268,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004948432606168889,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.21591003835201264,
|
|
"num_tokens": 18455943.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.241221237182617,
|
|
"epoch": 0.7728146013448607,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004948359602231976,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.22146230190992355,
|
|
"num_tokens": 18466763.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.326995897293091,
|
|
"epoch": 0.7732949087415946,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004948286547255681,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.2059281811118126,
|
|
"num_tokens": 18477647.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.320351505279541,
|
|
"epoch": 0.7737752161383286,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049482134412417,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21767931133508683,
|
|
"num_tokens": 18488465.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.38111310005188,
|
|
"epoch": 0.7742555235350624,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494814028419173,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.21288521140813826,
|
|
"num_tokens": 18500705.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.305369520187378,
|
|
"epoch": 0.7747358309317963,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494806707610747,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.20895128846168518,
|
|
"num_tokens": 18512253.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.272834920883179,
|
|
"epoch": 0.7752161383285303,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000494799381699062,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.21451279073953627,
|
|
"num_tokens": 18524231.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.330621957778931,
|
|
"epoch": 0.7756964457252642,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004947920506842879,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.2131388247013092,
|
|
"num_tokens": 18535824.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.388787317276001,
|
|
"epoch": 0.7761767531219981,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004947847145665951,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.21210116147994995,
|
|
"num_tokens": 18547957.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.354956579208374,
|
|
"epoch": 0.776657060518732,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947773733461539,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.21181995272636414,
|
|
"num_tokens": 18559297.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.319439172744751,
|
|
"epoch": 0.777137367915466,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947700270231347,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.2115650311112404,
|
|
"num_tokens": 18570264.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.31670651435852,
|
|
"epoch": 0.7776176753121998,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004947626755977079,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.2182663455605507,
|
|
"num_tokens": 18582417.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.315745639801025,
|
|
"epoch": 0.7780979827089337,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004947553190700444,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20888791233301163,
|
|
"num_tokens": 18593703.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.2798949718475345,
|
|
"epoch": 0.7785782901056676,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000494747957440315,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.2135533094406128,
|
|
"num_tokens": 18605050.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.354808568954468,
|
|
"epoch": 0.7790585975024016,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004947405907086905,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.2063086912035942,
|
|
"num_tokens": 18616962.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.334105730056763,
|
|
"epoch": 0.7795389048991355,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004947332188753419,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.20836649388074874,
|
|
"num_tokens": 18628640.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.331886911392212,
|
|
"epoch": 0.7800192122958693,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004947258419404405,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.21381895393133163,
|
|
"num_tokens": 18640488.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.291768789291382,
|
|
"epoch": 0.7804995196926032,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004947184599041576,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.21476706862449646,
|
|
"num_tokens": 18652095.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.316578006744384,
|
|
"epoch": 0.7809798270893372,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004947110727666644,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.21738332957029344,
|
|
"num_tokens": 18662767.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.310438251495361,
|
|
"epoch": 0.7814601344860711,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004947036805281325,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.21001635640859603,
|
|
"num_tokens": 18673568.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.324797773361206,
|
|
"epoch": 0.781940441882805,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004946962831887336,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.2199598118662834,
|
|
"num_tokens": 18684456.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.324702310562134,
|
|
"epoch": 0.7824207492795389,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004946888807486393,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.2081282526254654,
|
|
"num_tokens": 18695942.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.383227586746216,
|
|
"epoch": 0.7829010566762729,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004946814732080214,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.2143351122736931,
|
|
"num_tokens": 18708110.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.393184947967529,
|
|
"epoch": 0.7833813640730067,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004946740605670523,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.21153907775878905,
|
|
"num_tokens": 18718864.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.28409972190857,
|
|
"epoch": 0.7838616714697406,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004946666428259037,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.2152516469359398,
|
|
"num_tokens": 18730338.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.335810041427612,
|
|
"epoch": 0.7843419788664745,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004946592199847478,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.2030445009469986,
|
|
"num_tokens": 18743433.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.3633277893066404,
|
|
"epoch": 0.7848222862632085,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004946517920437571,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.2141033723950386,
|
|
"num_tokens": 18754631.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.301661586761474,
|
|
"epoch": 0.7853025936599424,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004946443590031041,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.21534345000982286,
|
|
"num_tokens": 18766118.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.342631435394287,
|
|
"epoch": 0.7857829010566763,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004946369208629613,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.21304913461208344,
|
|
"num_tokens": 18777743.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.286459875106812,
|
|
"epoch": 0.7862632084534101,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004946294776235013,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.22060092389583588,
|
|
"num_tokens": 18789684.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.23939881324768,
|
|
"epoch": 0.7867435158501441,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004946220292848971,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.22219572216272354,
|
|
"num_tokens": 18801088.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.358049631118774,
|
|
"epoch": 0.787223823246878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004946145758473214,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.20678872466087342,
|
|
"num_tokens": 18812478.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.467737150192261,
|
|
"epoch": 0.7877041306436119,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004946071173109475,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.20962309837341309,
|
|
"num_tokens": 18823573.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.267007637023926,
|
|
"epoch": 0.7881844380403458,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004945996536759484,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.21415299624204637,
|
|
"num_tokens": 18833880.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.241205549240112,
|
|
"epoch": 0.7886647454370798,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945921849424974,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.21975141912698745,
|
|
"num_tokens": 18844367.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.304120779037476,
|
|
"epoch": 0.7891450528338136,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004945847111107679,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.2121942937374115,
|
|
"num_tokens": 18856309.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.314821767807007,
|
|
"epoch": 0.7896253602305475,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004945772321809334,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.21399861425161362,
|
|
"num_tokens": 18868873.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.268496990203857,
|
|
"epoch": 0.7901056676272814,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004945697481531677,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.21906338334083558,
|
|
"num_tokens": 18879953.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.366976308822632,
|
|
"epoch": 0.7905859750240154,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004945622590276443,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.20272180885076524,
|
|
"num_tokens": 18892220.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.297091627120972,
|
|
"epoch": 0.7910662824207493,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945547648045373,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.21427067816257478,
|
|
"num_tokens": 18903261.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.310686302185059,
|
|
"epoch": 0.7915465898174832,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004945472654840206,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.21500401198863983,
|
|
"num_tokens": 18913702.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.351102113723755,
|
|
"epoch": 0.7920268972142172,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945397610662683,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.20690100342035295,
|
|
"num_tokens": 18925024.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.334754991531372,
|
|
"epoch": 0.792507204610951,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945322515514547,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.2204364687204361,
|
|
"num_tokens": 18935939.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.307905960083008,
|
|
"epoch": 0.7929875120076849,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000494524736939754,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.21556220948696136,
|
|
"num_tokens": 18946091.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.399036645889282,
|
|
"epoch": 0.7934678194044188,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004945172172313408,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.2064470589160919,
|
|
"num_tokens": 18957471.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.386903285980225,
|
|
"epoch": 0.7939481268011528,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945096924263896,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.2030111223459244,
|
|
"num_tokens": 18969462.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.305887937545776,
|
|
"epoch": 0.7944284341978867,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945021625250753,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.21238125264644622,
|
|
"num_tokens": 18980228.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.4317296028137205,
|
|
"epoch": 0.7949087415946205,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944946275275724,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.20731725990772248,
|
|
"num_tokens": 18991661.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.365469264984131,
|
|
"epoch": 0.7953890489913544,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004944870874340561,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.21165201663970948,
|
|
"num_tokens": 19003082.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.2959887981414795,
|
|
"epoch": 0.7958693563880884,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004944795422447013,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.21387497037649156,
|
|
"num_tokens": 19015408.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.31446328163147,
|
|
"epoch": 0.7963496637848223,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004944719919596835,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.20918508470058442,
|
|
"num_tokens": 19027246.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.330003833770752,
|
|
"epoch": 0.7968299711815562,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004944644365791776,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21609344631433486,
|
|
"num_tokens": 19038126.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.248894691467285,
|
|
"epoch": 0.7973102785782901,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494456876103359,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.21988851577043533,
|
|
"num_tokens": 19047998.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.234155702590942,
|
|
"epoch": 0.7977905859750241,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944493105324035,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.20772979855537416,
|
|
"num_tokens": 19058969.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.331974935531616,
|
|
"epoch": 0.7982708933717579,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004944417398664866,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.21943309009075165,
|
|
"num_tokens": 19070314.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.355373430252075,
|
|
"epoch": 0.7987512007684918,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004944341641057843,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.21280787289142608,
|
|
"num_tokens": 19082575.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.220653247833252,
|
|
"epoch": 0.7992315081652257,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004944265832504721,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.21947354674339295,
|
|
"num_tokens": 19095719.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.322908163070679,
|
|
"epoch": 0.7997118155619597,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004944189973007262,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.21176481544971465,
|
|
"num_tokens": 19106894.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.276044750213623,
|
|
"epoch": 0.8001921229586936,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004944114062567229,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20959357172250748,
|
|
"num_tokens": 19118206.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.342751836776733,
|
|
"epoch": 0.8006724303554275,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004944038101186381,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20593350678682326,
|
|
"num_tokens": 19129613.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.252099800109863,
|
|
"epoch": 0.8011527377521613,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004943962088866483,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.22004282772541045,
|
|
"num_tokens": 19142214.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.3283671855926515,
|
|
"epoch": 0.8016330451488953,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004943886025609301,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.20648059546947478,
|
|
"num_tokens": 19153906.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.354359197616577,
|
|
"epoch": 0.8021133525456292,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049438099114166,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.21217445731163026,
|
|
"num_tokens": 19163677.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.348628282546997,
|
|
"epoch": 0.8025936599423631,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004943733746290147,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.21198754161596298,
|
|
"num_tokens": 19175240.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.2392906665802,
|
|
"epoch": 0.803073967339097,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000494365753023171,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.21993402093648912,
|
|
"num_tokens": 19185529.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.244513607025146,
|
|
"epoch": 0.803554274735831,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004943581263243059,
|
|
"loss": 5.0151,
|
|
"mean_token_accuracy": 0.21945263296365738,
|
|
"num_tokens": 19197153.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.3825513362884525,
|
|
"epoch": 0.8040345821325648,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943504945325965,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.20574712306261062,
|
|
"num_tokens": 19208439.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.2956318855285645,
|
|
"epoch": 0.8045148895292987,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004943428576482198,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.22122190296649932,
|
|
"num_tokens": 19218570.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.301136016845703,
|
|
"epoch": 0.8049951969260326,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004943352156713535,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.21469674855470658,
|
|
"num_tokens": 19229080.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.31347622871399,
|
|
"epoch": 0.8054755043227666,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004943275686021747,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.21027496755123137,
|
|
"num_tokens": 19239299.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.346045398712159,
|
|
"epoch": 0.8059558117195005,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494319916440861,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.2164299339056015,
|
|
"num_tokens": 19250691.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.313060712814331,
|
|
"epoch": 0.8064361191162344,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004943122591875901,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.21821473985910417,
|
|
"num_tokens": 19260868.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.374499034881592,
|
|
"epoch": 0.8069164265129684,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004943045968425398,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.20281388759613037,
|
|
"num_tokens": 19271924.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.298399114608765,
|
|
"epoch": 0.8073967339097022,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004942969294058878,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.21425133496522902,
|
|
"num_tokens": 19283340.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.376578998565674,
|
|
"epoch": 0.8078770413064361,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004942892568778125,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.2053971216082573,
|
|
"num_tokens": 19294903.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.339735746383667,
|
|
"epoch": 0.80835734870317,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004942815792584917,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.21638937890529633,
|
|
"num_tokens": 19305670.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.309265804290772,
|
|
"epoch": 0.808837656099904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004942738965481038,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.21457275450229646,
|
|
"num_tokens": 19317043.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.347166347503662,
|
|
"epoch": 0.8093179634966379,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004942662087468272,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.2117277964949608,
|
|
"num_tokens": 19329161.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.353507375717163,
|
|
"epoch": 0.8097982708933718,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004942585158548402,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.21253862231969833,
|
|
"num_tokens": 19340706.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.335525274276733,
|
|
"epoch": 0.8102785782901056,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004942508178723214,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.21018424034118652,
|
|
"num_tokens": 19352422.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.308629179000855,
|
|
"epoch": 0.8107588856868396,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942431147994499,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.21313876658678055,
|
|
"num_tokens": 19364109.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.327165222167968,
|
|
"epoch": 0.8112391930835735,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004942354066364042,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.20890050232410431,
|
|
"num_tokens": 19377386.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.365875768661499,
|
|
"epoch": 0.8117195004803074,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004942276933833634,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.22000565975904465,
|
|
"num_tokens": 19388453.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.295984983444214,
|
|
"epoch": 0.8121998078770413,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004942199750405064,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.20670417100191116,
|
|
"num_tokens": 19402240.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.258763217926026,
|
|
"epoch": 0.8126801152737753,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004942122516080127,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.21323904544115066,
|
|
"num_tokens": 19414260.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.299350690841675,
|
|
"epoch": 0.8131604226705091,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004942045230860614,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.22043641954660415,
|
|
"num_tokens": 19426356.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.316803073883056,
|
|
"epoch": 0.813640730067243,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004941967894748319,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.21335528641939164,
|
|
"num_tokens": 19438881.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.307995319366455,
|
|
"epoch": 0.8141210374639769,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004941890507745039,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.21741548627614976,
|
|
"num_tokens": 19450109.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.339286184310913,
|
|
"epoch": 0.8146013448607109,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004941813069852569,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.21550847738981246,
|
|
"num_tokens": 19461155.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.384352827072144,
|
|
"epoch": 0.8150816522574448,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004941735581072708,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.2092205196619034,
|
|
"num_tokens": 19474364.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.29510498046875,
|
|
"epoch": 0.8155619596541787,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004941658041407255,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.22788828760385513,
|
|
"num_tokens": 19485271.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.401016283035278,
|
|
"epoch": 0.8160422670509125,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000494158045085801,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.20572369545698166,
|
|
"num_tokens": 19497117.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.316471719741822,
|
|
"epoch": 0.8165225744476465,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941502809426776,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.22313307523727416,
|
|
"num_tokens": 19507035.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.269172239303589,
|
|
"epoch": 0.8170028818443804,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004941425117115354,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.21908250898122789,
|
|
"num_tokens": 19517791.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.3007204055786135,
|
|
"epoch": 0.8174831892411143,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004941347373925547,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.21650118231773377,
|
|
"num_tokens": 19529577.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.38005576133728,
|
|
"epoch": 0.8179634966378482,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004941269579859161,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.21187126487493516,
|
|
"num_tokens": 19542355.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.364114713668823,
|
|
"epoch": 0.8184438040345822,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004941191734918002,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.2115686759352684,
|
|
"num_tokens": 19553819.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.396454381942749,
|
|
"epoch": 0.818924111431316,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000494111383910388,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.20575836300849915,
|
|
"num_tokens": 19565816.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.357280206680298,
|
|
"epoch": 0.8194044188280499,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004941035892418597,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.21611402779817582,
|
|
"num_tokens": 19577991.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.2707319259643555,
|
|
"epoch": 0.8198847262247838,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004940957894863968,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.21393628418445587,
|
|
"num_tokens": 19590225.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.27478437423706,
|
|
"epoch": 0.8203650336215178,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004940879846441804,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.21745798140764236,
|
|
"num_tokens": 19602966.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.3669677734375,
|
|
"epoch": 0.8208453410182517,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004940801747153914,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.21446783542633058,
|
|
"num_tokens": 19613148.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.204024362564087,
|
|
"epoch": 0.8213256484149856,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004940723597002113,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.2210802286863327,
|
|
"num_tokens": 19624361.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.263888263702393,
|
|
"epoch": 0.8218059558117194,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004940645395988216,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.21569721698760985,
|
|
"num_tokens": 19635915.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.32338581085205,
|
|
"epoch": 0.8222862632084534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004940567144114036,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.213149556517601,
|
|
"num_tokens": 19646701.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.397061777114868,
|
|
"epoch": 0.8227665706051873,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004940488841381393,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.20417173057794571,
|
|
"num_tokens": 19657804.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.3243170261383055,
|
|
"epoch": 0.8232468780019212,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004940410487792103,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.2131007120013237,
|
|
"num_tokens": 19670202.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.189413356781006,
|
|
"epoch": 0.8237271853986552,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004940332083347986,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.22380575090646743,
|
|
"num_tokens": 19681362.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.2682023525238035,
|
|
"epoch": 0.8242074927953891,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004940253628050861,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.21063031405210494,
|
|
"num_tokens": 19693429.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.3783766746521,
|
|
"epoch": 0.824687800192123,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004940175121902552,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.21518770307302476,
|
|
"num_tokens": 19704667.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.340273189544678,
|
|
"epoch": 0.8251681075888568,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000494009656490488,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.2150629296898842,
|
|
"num_tokens": 19716002.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.292360639572143,
|
|
"epoch": 0.8256484149855908,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940017957059668,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.2156504735350609,
|
|
"num_tokens": 19726626.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.283418798446656,
|
|
"epoch": 0.8261287223823247,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004939939298368742,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.2193497434258461,
|
|
"num_tokens": 19738250.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.388076734542847,
|
|
"epoch": 0.8266090297790586,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004939860588833929,
|
|
"loss": 5.1439,
|
|
"mean_token_accuracy": 0.21405116617679595,
|
|
"num_tokens": 19750119.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.331124305725098,
|
|
"epoch": 0.8270893371757925,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004939781828457055,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.2072782665491104,
|
|
"num_tokens": 19761709.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.315014505386353,
|
|
"epoch": 0.8275696445725265,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000493970301723995,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.20685304403305055,
|
|
"num_tokens": 19773562.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.446702003479004,
|
|
"epoch": 0.8280499519692603,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004939624155184443,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.2104032278060913,
|
|
"num_tokens": 19785327.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.359643220901489,
|
|
"epoch": 0.8285302593659942,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004939545242292365,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20667675733566285,
|
|
"num_tokens": 19796760.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.308028364181519,
|
|
"epoch": 0.8290105667627281,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004939466278565547,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.2150641441345215,
|
|
"num_tokens": 19807271.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.313430118560791,
|
|
"epoch": 0.8294908741594621,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004939387264005825,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.21965315490961074,
|
|
"num_tokens": 19818098.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.293922281265258,
|
|
"epoch": 0.829971181556196,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004939308198615031,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.2094389334321022,
|
|
"num_tokens": 19829482.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.35375599861145,
|
|
"epoch": 0.8304514889529299,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004939229082395001,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.21330081075429916,
|
|
"num_tokens": 19840883.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.2586931705474855,
|
|
"epoch": 0.8309317963496637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939149915347573,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.214984729886055,
|
|
"num_tokens": 19852619.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.241670894622803,
|
|
"epoch": 0.8314121037463977,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004939070697474585,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.21540726274251937,
|
|
"num_tokens": 19863316.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.366820907592773,
|
|
"epoch": 0.8318924111431316,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004938991428777875,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.20902374088764192,
|
|
"num_tokens": 19873965.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.341080045700073,
|
|
"epoch": 0.8323727185398655,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004938912109259284,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.21835167855024337,
|
|
"num_tokens": 19884685.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.299511289596557,
|
|
"epoch": 0.8328530259365994,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004938832738920654,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.2188192769885063,
|
|
"num_tokens": 19897594.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.319777631759644,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938753317763826,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.21023986041545867,
|
|
"num_tokens": 19908093.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.3774059295654295,
|
|
"epoch": 0.8338136407300673,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004938673845790646,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.20775313973426818,
|
|
"num_tokens": 19920502.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.304855537414551,
|
|
"epoch": 0.8342939481268011,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004938594323002957,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.22236857414245606,
|
|
"num_tokens": 19931437.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.25332350730896,
|
|
"epoch": 0.834774255523535,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004938514749402609,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.22307854443788527,
|
|
"num_tokens": 19942592.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.373629379272461,
|
|
"epoch": 0.835254562920269,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004938435124991447,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.20217681378126146,
|
|
"num_tokens": 19953802.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.3222345352172855,
|
|
"epoch": 0.8357348703170029,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004938355449771318,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.21385653614997863,
|
|
"num_tokens": 19964686.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.328238582611084,
|
|
"epoch": 0.8362151777137368,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004938275723744075,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.21361002326011658,
|
|
"num_tokens": 19975603.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.350365352630615,
|
|
"epoch": 0.8366954851104706,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938195946911567,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.20661740452051164,
|
|
"num_tokens": 19986205.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.309024286270142,
|
|
"epoch": 0.8371757925072046,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938116119275645,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.2178403377532959,
|
|
"num_tokens": 19997323.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.322895765304565,
|
|
"epoch": 0.8376560999039385,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004938036240838166,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.21827513724565506,
|
|
"num_tokens": 20007334.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.380735874176025,
|
|
"epoch": 0.8381364073006724,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004937956311600983,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.21377009898424149,
|
|
"num_tokens": 20017476.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.267600107192993,
|
|
"epoch": 0.8386167146974063,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004937876331565951,
|
|
"loss": 5.0259,
|
|
"mean_token_accuracy": 0.2086850881576538,
|
|
"num_tokens": 20029323.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.30078706741333,
|
|
"epoch": 0.8390970220941403,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004937796300734926,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.2136402577161789,
|
|
"num_tokens": 20040317.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.355309295654297,
|
|
"epoch": 0.8395773294908742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937716219109769,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.2191210150718689,
|
|
"num_tokens": 20050495.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.409572982788086,
|
|
"epoch": 0.840057636887608,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937636086692336,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.20902793407440184,
|
|
"num_tokens": 20061185.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.313978672027588,
|
|
"epoch": 0.840537944284342,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493755590348449,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.2170210987329483,
|
|
"num_tokens": 20073746.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.354018449783325,
|
|
"epoch": 0.8410182516810759,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004937475669488091,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.21518562585115433,
|
|
"num_tokens": 20085667.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.337803506851197,
|
|
"epoch": 0.8414985590778098,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004937395384705004,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.22205119878053664,
|
|
"num_tokens": 20096017.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.3429093837738035,
|
|
"epoch": 0.8419788664745437,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004937315049137089,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.2147764354944229,
|
|
"num_tokens": 20106928.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.276442146301269,
|
|
"epoch": 0.8424591738712777,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004937234662786216,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.21512675285339355,
|
|
"num_tokens": 20118768.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.441260242462159,
|
|
"epoch": 0.8429394812680115,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004937154225654246,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.2048684075474739,
|
|
"num_tokens": 20129009.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.357914113998413,
|
|
"epoch": 0.8434197886647454,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004937073737743051,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.21020389646291732,
|
|
"num_tokens": 20141577.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.350571393966675,
|
|
"epoch": 0.8439000960614793,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004936993199054499,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.21455888897180558,
|
|
"num_tokens": 20153636.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.274769496917725,
|
|
"epoch": 0.8443804034582133,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004936912609590458,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.20932869762182235,
|
|
"num_tokens": 20165719.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.337386274337769,
|
|
"epoch": 0.8448607108549472,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00049368319693528,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.20842975080013276,
|
|
"num_tokens": 20178260.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.367832612991333,
|
|
"epoch": 0.8453410182516811,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004936751278343397,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.21095074713230133,
|
|
"num_tokens": 20189667.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.304063606262207,
|
|
"epoch": 0.845821325648415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936670536564123,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20925893038511276,
|
|
"num_tokens": 20201451.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.329834413528443,
|
|
"epoch": 0.8463016330451489,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004936589744016853,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.2122049480676651,
|
|
"num_tokens": 20213257.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.369869899749756,
|
|
"epoch": 0.8467819404418828,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493650890070346,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.22126171737909317,
|
|
"num_tokens": 20225301.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.323382091522217,
|
|
"epoch": 0.8472622478386167,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004936428006625824,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.21794600486755372,
|
|
"num_tokens": 20236183.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.384713172912598,
|
|
"epoch": 0.8477425552353506,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004936347061785823,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.20530274510383606,
|
|
"num_tokens": 20248663.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.287231683731079,
|
|
"epoch": 0.8482228626320846,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004936266066185334,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.22344885915517806,
|
|
"num_tokens": 20259293.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.332286167144775,
|
|
"epoch": 0.8487031700288185,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004936185019826239,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.20209504365921022,
|
|
"num_tokens": 20270601.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.358151865005493,
|
|
"epoch": 0.8491834774255523,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004936103922710419,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.2156426265835762,
|
|
"num_tokens": 20281471.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.3148139953613285,
|
|
"epoch": 0.8496637848222862,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004936022774839759,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.21583481580018998,
|
|
"num_tokens": 20291941.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.338487911224365,
|
|
"epoch": 0.8501440922190202,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004935941576216141,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.21150692254304887,
|
|
"num_tokens": 20302631.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.362058115005493,
|
|
"epoch": 0.8506243996157541,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000493586032684145,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.21292876452207565,
|
|
"num_tokens": 20314955.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.350996446609497,
|
|
"epoch": 0.851104707012488,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004935779026717573,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.21308736354112626,
|
|
"num_tokens": 20326791.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.3356614112854,
|
|
"epoch": 0.8515850144092219,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004935697675846396,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.21524236649274825,
|
|
"num_tokens": 20338912.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.308983659744262,
|
|
"epoch": 0.8520653218059558,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004935616274229811,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.22042587101459504,
|
|
"num_tokens": 20349414.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.350616359710694,
|
|
"epoch": 0.8525456292026897,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004935534821869705,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.21534484028816223,
|
|
"num_tokens": 20360346.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.318821430206299,
|
|
"epoch": 0.8530259365994236,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004935453318767971,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.21585288643836975,
|
|
"num_tokens": 20371965.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.290925931930542,
|
|
"epoch": 0.8535062439961575,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049353717649265,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.21714648455381394,
|
|
"num_tokens": 20382632.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.309684562683105,
|
|
"epoch": 0.8539865513928915,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004935290160347185,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.22077393382787705,
|
|
"num_tokens": 20395796.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.371646690368652,
|
|
"epoch": 0.8544668587896254,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004935208505031922,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.21296919584274293,
|
|
"num_tokens": 20407113.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.323896789550782,
|
|
"epoch": 0.8549471661863592,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004935126798982606,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.21373020261526107,
|
|
"num_tokens": 20419012.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.346958494186401,
|
|
"epoch": 0.8554274735830932,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004935045042201135,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.2121588334441185,
|
|
"num_tokens": 20430337.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.299887800216675,
|
|
"epoch": 0.8559077809798271,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004934963234689407,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.21244479566812516,
|
|
"num_tokens": 20441614.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.2709190368652346,
|
|
"epoch": 0.856388088376561,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000493488137644932,
|
|
"loss": 4.9437,
|
|
"mean_token_accuracy": 0.23149601966142655,
|
|
"num_tokens": 20453170.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.215207290649414,
|
|
"epoch": 0.8568683957732949,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934799467482774,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.2231559380888939,
|
|
"num_tokens": 20464585.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.308840417861939,
|
|
"epoch": 0.8573487031700289,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004934717507791673,
|
|
"loss": 4.9315,
|
|
"mean_token_accuracy": 0.22737429589033126,
|
|
"num_tokens": 20473903.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.294377183914184,
|
|
"epoch": 0.8578290105667628,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004934635497377919,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.2123822271823883,
|
|
"num_tokens": 20484778.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.30147066116333,
|
|
"epoch": 0.8583093179634966,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004934553436243415,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20890430063009263,
|
|
"num_tokens": 20495534.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.427492570877075,
|
|
"epoch": 0.8587896253602305,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004934471324390067,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.2112024948000908,
|
|
"num_tokens": 20506853.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.349243688583374,
|
|
"epoch": 0.8592699327569645,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004934389161819783,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.21444510966539382,
|
|
"num_tokens": 20519112.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.330943059921265,
|
|
"epoch": 0.8597502401536984,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934306948534467,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.21188867688179017,
|
|
"num_tokens": 20530060.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.325530385971069,
|
|
"epoch": 0.8602305475504323,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004934224684536031,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.21269427388906478,
|
|
"num_tokens": 20541802.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.217118740081787,
|
|
"epoch": 0.8607108549471661,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004934142369826382,
|
|
"loss": 4.9448,
|
|
"mean_token_accuracy": 0.21972814798355103,
|
|
"num_tokens": 20552494.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.263307809829712,
|
|
"epoch": 0.8611911623439001,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934060004407434,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.21869284063577651,
|
|
"num_tokens": 20564467.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.3266034603118895,
|
|
"epoch": 0.861671469740634,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004933977588281099,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.21143877506256104,
|
|
"num_tokens": 20575399.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.3816609382629395,
|
|
"epoch": 0.8621517771373679,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004933895121449288,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.2143782913684845,
|
|
"num_tokens": 20586212.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.381245183944702,
|
|
"epoch": 0.8626320845341018,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004933812603913917,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.21167492717504502,
|
|
"num_tokens": 20597020.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.309660530090332,
|
|
"epoch": 0.8631123919308358,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004933730035676903,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.21938903480768204,
|
|
"num_tokens": 20609447.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.296952104568481,
|
|
"epoch": 0.8635926993275697,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004933647416740161,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.21478643417358398,
|
|
"num_tokens": 20621780.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.230030345916748,
|
|
"epoch": 0.8640730067243035,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000493356474710561,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.21845945864915847,
|
|
"num_tokens": 20632331.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.259495449066162,
|
|
"epoch": 0.8645533141210374,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000493348202677517,
|
|
"loss": 4.9448,
|
|
"mean_token_accuracy": 0.21981340497732163,
|
|
"num_tokens": 20643357.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8645533141210374,
|
|
"eval_entropy": 5.105816888553465,
|
|
"eval_loss": 5.076680660247803,
|
|
"eval_mean_token_accuracy": 0.2218917549339403,
|
|
"eval_num_tokens": 20643357.0,
|
|
"eval_runtime": 20.5176,
|
|
"eval_samples_per_second": 1599.357,
|
|
"eval_steps_per_second": 199.926,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.257414388656616,
|
|
"epoch": 0.8650336215177714,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004933399255750761,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.2279314413666725,
|
|
"num_tokens": 20655212.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.18083233833313,
|
|
"epoch": 0.8655139289145053,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004933316434034304,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.2268202692270279,
|
|
"num_tokens": 20666467.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.249035120010376,
|
|
"epoch": 0.8659942363112392,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004933233561627723,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.22251613289117814,
|
|
"num_tokens": 20677709.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.347827529907226,
|
|
"epoch": 0.866474543707973,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004933150638532942,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.2098282754421234,
|
|
"num_tokens": 20688880.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.354618978500366,
|
|
"epoch": 0.866954851104707,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004933067664751885,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.20214222967624665,
|
|
"num_tokens": 20701384.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.4045837879180905,
|
|
"epoch": 0.8674351585014409,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000493298464028648,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.20311639308929444,
|
|
"num_tokens": 20713736.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.233702325820923,
|
|
"epoch": 0.8679154658981748,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004932901565138653,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.22202753722667695,
|
|
"num_tokens": 20725424.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.275396633148193,
|
|
"epoch": 0.8683957732949087,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004932818439310334,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.22160872668027878,
|
|
"num_tokens": 20737454.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.378441905975341,
|
|
"epoch": 0.8688760806916427,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004932735262803452,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.21170372068881987,
|
|
"num_tokens": 20748882.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.307307863235474,
|
|
"epoch": 0.8693563880883766,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004932652035619939,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.22109982520341873,
|
|
"num_tokens": 20759622.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.22042236328125,
|
|
"epoch": 0.8698366954851104,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004932568757761727,
|
|
"loss": 5.0036,
|
|
"mean_token_accuracy": 0.2156627357006073,
|
|
"num_tokens": 20770658.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.360762596130371,
|
|
"epoch": 0.8703170028818443,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004932485429230748,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.21593075841665268,
|
|
"num_tokens": 20782176.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.3962634086608885,
|
|
"epoch": 0.8707973102785783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000493240205002894,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.20037866979837418,
|
|
"num_tokens": 20793592.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.272551965713501,
|
|
"epoch": 0.8712776176753122,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004932318620158235,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.20937321633100509,
|
|
"num_tokens": 20804226.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.293966007232666,
|
|
"epoch": 0.8717579250720461,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004932235139620574,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.2059372454881668,
|
|
"num_tokens": 20815336.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.303473329544067,
|
|
"epoch": 0.8722382324687801,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004932151608417892,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.22488995939493178,
|
|
"num_tokens": 20826936.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.31711745262146,
|
|
"epoch": 0.872718539865514,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004932068026552127,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.21242650598287582,
|
|
"num_tokens": 20838159.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.312888813018799,
|
|
"epoch": 0.8731988472622478,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004931984394025224,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.21303476840257646,
|
|
"num_tokens": 20848605.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.321499013900757,
|
|
"epoch": 0.8736791546589817,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004931900710839123,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.20912399590015412,
|
|
"num_tokens": 20860494.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.3393552780151365,
|
|
"epoch": 0.8741594620557157,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004931816976995766,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.22151022404432297,
|
|
"num_tokens": 20871327.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.329251146316528,
|
|
"epoch": 0.8746397694524496,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004931733192497097,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.21618774831295012,
|
|
"num_tokens": 20883032.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.298555946350097,
|
|
"epoch": 0.8751200768491835,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004931649357345062,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.208712400496006,
|
|
"num_tokens": 20894327.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.250638675689697,
|
|
"epoch": 0.8756003842459174,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004931565471541606,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.22427091002464294,
|
|
"num_tokens": 20905489.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.286103105545044,
|
|
"epoch": 0.8760806916426513,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004931481535088679,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.21668339520692825,
|
|
"num_tokens": 20917044.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.334398460388184,
|
|
"epoch": 0.8765609990393852,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004931397547988229,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.22056288719177247,
|
|
"num_tokens": 20928065.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.317741775512696,
|
|
"epoch": 0.8770413064361191,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004931313510242204,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.22060995995998384,
|
|
"num_tokens": 20939396.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.409996843338012,
|
|
"epoch": 0.877521613832853,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004931229421852557,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.21052352637052535,
|
|
"num_tokens": 20950844.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.324803447723388,
|
|
"epoch": 0.878001921229587,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000493114528282124,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.21677727848291398,
|
|
"num_tokens": 20961567.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.393394327163696,
|
|
"epoch": 0.8784822286263209,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004931061093150206,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.21145831793546677,
|
|
"num_tokens": 20972762.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.292376232147217,
|
|
"epoch": 0.8789625360230547,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004930976852841409,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.2131545901298523,
|
|
"num_tokens": 20983848.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.336713695526123,
|
|
"epoch": 0.8794428434197886,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004930892561896806,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.21815279573202134,
|
|
"num_tokens": 20996418.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.299078750610351,
|
|
"epoch": 0.8799231508165226,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004930808220318354,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.22307819426059722,
|
|
"num_tokens": 21008714.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.337980461120606,
|
|
"epoch": 0.8804034582132565,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004930723828108012,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.21855155974626542,
|
|
"num_tokens": 21020453.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.19245924949646,
|
|
"epoch": 0.8808837656099904,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004930639385267736,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.21736301332712174,
|
|
"num_tokens": 21032211.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.328020286560059,
|
|
"epoch": 0.8813640730067243,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000493055489179949,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.21161713302135468,
|
|
"num_tokens": 21042995.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.2503900051116945,
|
|
"epoch": 0.8818443804034583,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004930470347705234,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.2217685118317604,
|
|
"num_tokens": 21054306.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.2508961200714115,
|
|
"epoch": 0.8823246878001921,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493038575298693,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.21045205146074294,
|
|
"num_tokens": 21067144.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.453606033325196,
|
|
"epoch": 0.882804995196926,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004930301107646545,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.20695163756608964,
|
|
"num_tokens": 21078885.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.375695276260376,
|
|
"epoch": 0.8832853025936599,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004930216411686042,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.20614762604236603,
|
|
"num_tokens": 21089482.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.3646275997161865,
|
|
"epoch": 0.8837656099903939,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004930131665107387,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.2073780119419098,
|
|
"num_tokens": 21102046.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.301938152313232,
|
|
"epoch": 0.8842459173871278,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493004686791255,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.22085978239774703,
|
|
"num_tokens": 21112827.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.347720098495484,
|
|
"epoch": 0.8847262247838616,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929962020103496,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.21277096420526503,
|
|
"num_tokens": 21123108.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.327457427978516,
|
|
"epoch": 0.8852065321805955,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004929877121682198,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.21482013314962387,
|
|
"num_tokens": 21134955.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.298318815231323,
|
|
"epoch": 0.8856868395773295,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004929792172650627,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.2209932342171669,
|
|
"num_tokens": 21146415.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.269450330734253,
|
|
"epoch": 0.8861671469740634,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004929707173010753,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.2169800043106079,
|
|
"num_tokens": 21158691.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.286174011230469,
|
|
"epoch": 0.8866474543707973,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004929622122764552,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.20771564245224,
|
|
"num_tokens": 21170063.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.35341739654541,
|
|
"epoch": 0.8871277617675313,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004929537021913997,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.2150398701429367,
|
|
"num_tokens": 21182427.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.295762729644776,
|
|
"epoch": 0.8876080691642652,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004929451870461064,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.21771469414234162,
|
|
"num_tokens": 21195011.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.277560806274414,
|
|
"epoch": 0.888088376560999,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004929366668407731,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.21904293745756148,
|
|
"num_tokens": 21207886.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.262913417816162,
|
|
"epoch": 0.8885686839577329,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004929281415755974,
|
|
"loss": 5.0166,
|
|
"mean_token_accuracy": 0.2223418965935707,
|
|
"num_tokens": 21219285.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.35864372253418,
|
|
"epoch": 0.8890489913544669,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004929196112507775,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.21464316844940184,
|
|
"num_tokens": 21231208.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.266012334823609,
|
|
"epoch": 0.8895292987512008,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004929110758665112,
|
|
"loss": 4.949,
|
|
"mean_token_accuracy": 0.22016118466854095,
|
|
"num_tokens": 21242573.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.195144367218018,
|
|
"epoch": 0.8900096061479347,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004929025354229969,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.23063782900571822,
|
|
"num_tokens": 21254966.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.2937798500061035,
|
|
"epoch": 0.8904899135446686,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004928939899204326,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.2160419911146164,
|
|
"num_tokens": 21266167.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.3060510635375975,
|
|
"epoch": 0.8909702209414025,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000492885439359017,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.2171102836728096,
|
|
"num_tokens": 21277036.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.27428035736084,
|
|
"epoch": 0.8914505283381364,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004928768837389485,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.2206757366657257,
|
|
"num_tokens": 21288887.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.359797573089599,
|
|
"epoch": 0.8919308357348703,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004928683230604257,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.20907775461673736,
|
|
"num_tokens": 21300664.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.369063186645508,
|
|
"epoch": 0.8924111431316042,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004928597573236474,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.22261392325162888,
|
|
"num_tokens": 21311535.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.205429887771606,
|
|
"epoch": 0.8928914505283382,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004928511865288123,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.21946772336959838,
|
|
"num_tokens": 21323248.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.300801181793213,
|
|
"epoch": 0.8933717579250721,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004928426106761197,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.22177083194255828,
|
|
"num_tokens": 21334901.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.42064323425293,
|
|
"epoch": 0.8938520653218059,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004928340297657685,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.21599564850330352,
|
|
"num_tokens": 21345902.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.3670220375061035,
|
|
"epoch": 0.8943323727185398,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004928254437979578,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.21022968739271164,
|
|
"num_tokens": 21358240.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.222878789901733,
|
|
"epoch": 0.8948126801152738,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004928168527728873,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.22085811495780944,
|
|
"num_tokens": 21368209.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.245668983459472,
|
|
"epoch": 0.8952929875120077,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004928082566907562,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.2106561541557312,
|
|
"num_tokens": 21379484.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.307284164428711,
|
|
"epoch": 0.8957732949087416,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004927996555517642,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.22022853195667266,
|
|
"num_tokens": 21391750.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.355575513839722,
|
|
"epoch": 0.8962536023054755,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927910493561109,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.21547525823116304,
|
|
"num_tokens": 21402583.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.277576589584351,
|
|
"epoch": 0.8967339097022095,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000492782438103996,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.21128913015127182,
|
|
"num_tokens": 21412892.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.345271873474121,
|
|
"epoch": 0.8972142170989433,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004927738217956197,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.21566333174705504,
|
|
"num_tokens": 21422828.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.270195531845093,
|
|
"epoch": 0.8976945244956772,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004927652004311819,
|
|
"loss": 5.0398,
|
|
"mean_token_accuracy": 0.2132311299443245,
|
|
"num_tokens": 21434441.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.3531371593475345,
|
|
"epoch": 0.8981748318924111,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927565740108828,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.2080637738108635,
|
|
"num_tokens": 21445945.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.365895414352417,
|
|
"epoch": 0.8986551392891451,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004927479425349226,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.21809532791376113,
|
|
"num_tokens": 21457265.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.318217945098877,
|
|
"epoch": 0.899135446685879,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004927393060035018,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.21724823713302613,
|
|
"num_tokens": 21469090.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.314179182052612,
|
|
"epoch": 0.8996157540826129,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004927306644168207,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.20749806016683578,
|
|
"num_tokens": 21480280.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.282311058044433,
|
|
"epoch": 0.9000960614793467,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927220177750803,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.22260210216045379,
|
|
"num_tokens": 21491856.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.335117483139038,
|
|
"epoch": 0.9005763688760807,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004927133660784811,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.21102717220783235,
|
|
"num_tokens": 21501814.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.303743076324463,
|
|
"epoch": 0.9010566762728146,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004927047093272241,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.20949456393718718,
|
|
"num_tokens": 21514725.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.253428888320923,
|
|
"epoch": 0.9015369836695485,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049269604752151,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.21872983127832413,
|
|
"num_tokens": 21526523.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.233908987045288,
|
|
"epoch": 0.9020172910662824,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004926873806615403,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.2216762572526932,
|
|
"num_tokens": 21537947.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.368795680999756,
|
|
"epoch": 0.9024975984630164,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004926787087475158,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.2061220183968544,
|
|
"num_tokens": 21550238.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.311097574234009,
|
|
"epoch": 0.9029779058597502,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004926700317796382,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.20790619254112244,
|
|
"num_tokens": 21561546.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.334554672241211,
|
|
"epoch": 0.9034582132564841,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004926613497581088,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.21458321809768677,
|
|
"num_tokens": 21572034.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.314224481582642,
|
|
"epoch": 0.9039385206532181,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004926526626831292,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.21127951443195342,
|
|
"num_tokens": 21583427.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.323285484313965,
|
|
"epoch": 0.904418828049952,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004926439705549011,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.22292256802320481,
|
|
"num_tokens": 21595071.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.362425994873047,
|
|
"epoch": 0.9048991354466859,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926352733736262,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.21533829867839813,
|
|
"num_tokens": 21606007.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.321221590042114,
|
|
"epoch": 0.9053794428434198,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004926265711395065,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.22038442194461821,
|
|
"num_tokens": 21617988.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.287924909591675,
|
|
"epoch": 0.9058597502401537,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000492617863852744,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.21507909744977952,
|
|
"num_tokens": 21629832.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.332758474349975,
|
|
"epoch": 0.9063400576368876,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004926091515135409,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.21201392114162446,
|
|
"num_tokens": 21641295.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.222718286514282,
|
|
"epoch": 0.9068203650336215,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004926004341220995,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.2242590680718422,
|
|
"num_tokens": 21652829.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.377830553054809,
|
|
"epoch": 0.9073006724303554,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004925917116786222,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.21289454251527787,
|
|
"num_tokens": 21665032.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.192275762557983,
|
|
"epoch": 0.9077809798270894,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004925829841833114,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.22847405821084976,
|
|
"num_tokens": 21675814.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.296262598037719,
|
|
"epoch": 0.9082612872238233,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004925742516363699,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.21277222335338591,
|
|
"num_tokens": 21687581.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.394920587539673,
|
|
"epoch": 0.9087415946205571,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004925655140380002,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.2096257135272026,
|
|
"num_tokens": 21700167.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.283988761901855,
|
|
"epoch": 0.909221902017291,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004925567713884054,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.21196956932544708,
|
|
"num_tokens": 21712309.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.2896644115448,
|
|
"epoch": 0.909702209414025,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004925480236877884,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.22438355833292006,
|
|
"num_tokens": 21723391.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.2911313533782955,
|
|
"epoch": 0.9101825168107589,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004925392709363522,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.2249067857861519,
|
|
"num_tokens": 21735052.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.352796840667724,
|
|
"epoch": 0.9106628242074928,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004925305131343001,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.21458436995744706,
|
|
"num_tokens": 21746424.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.297646236419678,
|
|
"epoch": 0.9111431316042267,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925217502818355,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.20450981706380844,
|
|
"num_tokens": 21756960.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.337455415725708,
|
|
"epoch": 0.9116234390009607,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004925129823791616,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.2231251060962677,
|
|
"num_tokens": 21767621.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.3207447052001955,
|
|
"epoch": 0.9121037463976945,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004925042094264822,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.21652277708053588,
|
|
"num_tokens": 21779403.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.419968128204346,
|
|
"epoch": 0.9125840537944284,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000492495431424001,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.2041369467973709,
|
|
"num_tokens": 21791039.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.412250423431397,
|
|
"epoch": 0.9130643611911623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924866483719216,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.20689541846513748,
|
|
"num_tokens": 21803731.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.355454349517823,
|
|
"epoch": 0.9135446685878963,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004924778602704481,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.21267575472593309,
|
|
"num_tokens": 21816139.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.201633596420288,
|
|
"epoch": 0.9140249759846302,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004924690671197845,
|
|
"loss": 4.8997,
|
|
"mean_token_accuracy": 0.22566184848546983,
|
|
"num_tokens": 21826861.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.271975994110107,
|
|
"epoch": 0.914505283381364,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004924602689201348,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21879444122314454,
|
|
"num_tokens": 21838083.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.374385118484497,
|
|
"epoch": 0.9149855907780979,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924514656717034,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.2184382125735283,
|
|
"num_tokens": 21849232.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.329132318496704,
|
|
"epoch": 0.9154658981748319,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004924426573746948,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.20795187950134278,
|
|
"num_tokens": 21861650.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.422512435913086,
|
|
"epoch": 0.9159462055715658,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004924338440293131,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.2082384929060936,
|
|
"num_tokens": 21873369.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.344800615310669,
|
|
"epoch": 0.9164265129682997,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004924250256357635,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.21400937885046006,
|
|
"num_tokens": 21884563.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.3391252040863035,
|
|
"epoch": 0.9169068203650336,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004924162021942502,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.2152358904480934,
|
|
"num_tokens": 21896114.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.3133988857269285,
|
|
"epoch": 0.9173871277617676,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004924073737049784,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.21783629804849625,
|
|
"num_tokens": 21907386.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.369202375411987,
|
|
"epoch": 0.9178674351585014,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004923985401681528,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.21062783598899842,
|
|
"num_tokens": 21918312.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.308900165557861,
|
|
"epoch": 0.9183477425552353,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004923897015839788,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.22436386495828628,
|
|
"num_tokens": 21930101.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.292035293579102,
|
|
"epoch": 0.9188280499519692,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004923808579526613,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.2129116103053093,
|
|
"num_tokens": 21941739.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.337066507339477,
|
|
"epoch": 0.9193083573487032,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923720092744059,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.20284460484981537,
|
|
"num_tokens": 21953342.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.431700658798218,
|
|
"epoch": 0.9197886647454371,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004923631555494179,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.21172126829624177,
|
|
"num_tokens": 21963506.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.416760063171386,
|
|
"epoch": 0.920268972142171,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004923542967779028,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.20800400525331497,
|
|
"num_tokens": 21975078.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.312153387069702,
|
|
"epoch": 0.920749279538905,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004923454329600664,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.220147505402565,
|
|
"num_tokens": 21987128.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.307622241973877,
|
|
"epoch": 0.9212295869356388,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004923365640961143,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.21051793098449706,
|
|
"num_tokens": 22000106.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.287277126312256,
|
|
"epoch": 0.9217098943323727,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004923276901862526,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.21869908571243285,
|
|
"num_tokens": 22010571.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.292158126831055,
|
|
"epoch": 0.9221902017291066,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004923188112306874,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.22657813280820846,
|
|
"num_tokens": 22021399.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.278562927246094,
|
|
"epoch": 0.9226705091258406,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004923099272296246,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.225027696788311,
|
|
"num_tokens": 22032302.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.288332986831665,
|
|
"epoch": 0.9231508165225745,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004923010381832706,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.22630874663591385,
|
|
"num_tokens": 22043762.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.315436363220215,
|
|
"epoch": 0.9236311239193083,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004922921440918318,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.216742105782032,
|
|
"num_tokens": 22054885.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.395463275909424,
|
|
"epoch": 0.9241114313160422,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004922832449555144,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.21242223531007767,
|
|
"num_tokens": 22066627.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.231215333938598,
|
|
"epoch": 0.9245917387127762,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004922743407745255,
|
|
"loss": 4.9493,
|
|
"mean_token_accuracy": 0.2193763792514801,
|
|
"num_tokens": 22078062.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.252799940109253,
|
|
"epoch": 0.9250720461095101,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004922654315490714,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.21605497002601623,
|
|
"num_tokens": 22089465.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.359333848953247,
|
|
"epoch": 0.925552353506244,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004922565172793593,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.21062738597393035,
|
|
"num_tokens": 22101688.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.303273153305054,
|
|
"epoch": 0.9260326609029779,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004922475979655958,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.21809319108724595,
|
|
"num_tokens": 22112912.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.376863670349121,
|
|
"epoch": 0.9265129682997119,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004922386736079883,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.20430486649274826,
|
|
"num_tokens": 22125079.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.399107027053833,
|
|
"epoch": 0.9269932756964457,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004922297442067438,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.21919684559106828,
|
|
"num_tokens": 22137146.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.290425968170166,
|
|
"epoch": 0.9274735830931796,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004922208097620697,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.2125719115138054,
|
|
"num_tokens": 22148330.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.198112821578979,
|
|
"epoch": 0.9279538904899135,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004922118702741735,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.21460361033678055,
|
|
"num_tokens": 22160511.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.272160196304322,
|
|
"epoch": 0.9284341978866475,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004922029257432625,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.21831436455249786,
|
|
"num_tokens": 22171298.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.290419483184815,
|
|
"epoch": 0.9289145052833814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004921939761695446,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.2194742515683174,
|
|
"num_tokens": 22181897.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.365936231613159,
|
|
"epoch": 0.9293948126801153,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004921850215532275,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.21000879108905793,
|
|
"num_tokens": 22194630.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.338303852081299,
|
|
"epoch": 0.9298751200768491,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004921760618945192,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.22115323841571807,
|
|
"num_tokens": 22206041.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.235793876647949,
|
|
"epoch": 0.9303554274735831,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004921670971936276,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.2168429970741272,
|
|
"num_tokens": 22218434.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.342576122283935,
|
|
"epoch": 0.930835734870317,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004921581274507607,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.2160658285021782,
|
|
"num_tokens": 22229182.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.352722263336181,
|
|
"epoch": 0.9313160422670509,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000492149152666127,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.2135388433933258,
|
|
"num_tokens": 22241142.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.345702457427978,
|
|
"epoch": 0.9317963496637848,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004921401728399348,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.21110692471265793,
|
|
"num_tokens": 22252695.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.25837812423706,
|
|
"epoch": 0.9322766570605188,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004921311879723926,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.22741474211215973,
|
|
"num_tokens": 22264159.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.351061916351318,
|
|
"epoch": 0.9327569644572526,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004921221980637088,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.21683979779481888,
|
|
"num_tokens": 22276154.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.227136898040771,
|
|
"epoch": 0.9332372718539865,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004921132031140925,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.21565686166286469,
|
|
"num_tokens": 22288328.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.304116153717041,
|
|
"epoch": 0.9337175792507204,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004921042031237521,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.21462499499320983,
|
|
"num_tokens": 22300154.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.1878763198852536,
|
|
"epoch": 0.9341978866474544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004920951980928969,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.2327744632959366,
|
|
"num_tokens": 22311176.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.310220766067505,
|
|
"epoch": 0.9346781940441883,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920861880217359,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.20979525297880172,
|
|
"num_tokens": 22321953.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.334324312210083,
|
|
"epoch": 0.9351585014409222,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004920771729104781,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.21282278150320053,
|
|
"num_tokens": 22333152.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.331171083450317,
|
|
"epoch": 0.9356388088376562,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004920681527593329,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.2176915407180786,
|
|
"num_tokens": 22344848.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.336834526062011,
|
|
"epoch": 0.93611911623439,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004920591275685098,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.21831881552934645,
|
|
"num_tokens": 22355100.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.26859483718872,
|
|
"epoch": 0.9365994236311239,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004920500973382184,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.21681536734104156,
|
|
"num_tokens": 22366045.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.305310678482056,
|
|
"epoch": 0.9370797310278578,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004920410620686682,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.2125216856598854,
|
|
"num_tokens": 22378781.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.415491151809692,
|
|
"epoch": 0.9375600384245918,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004920320217600689,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.20829002559185028,
|
|
"num_tokens": 22390121.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.221384143829345,
|
|
"epoch": 0.9380403458213257,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004920229764126306,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.22019549906253816,
|
|
"num_tokens": 22402261.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.325441837310791,
|
|
"epoch": 0.9385206532180596,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004920139260265632,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.2173736497759819,
|
|
"num_tokens": 22413939.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.332404899597168,
|
|
"epoch": 0.9390009606147934,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004920048706020769,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.21830356419086455,
|
|
"num_tokens": 22425439.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.371865844726562,
|
|
"epoch": 0.9394812680115274,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004919958101393817,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.20449171662330629,
|
|
"num_tokens": 22436989.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.323634767532349,
|
|
"epoch": 0.9399615754082613,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004919867446386883,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.2105829283595085,
|
|
"num_tokens": 22449181.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.232287263870239,
|
|
"epoch": 0.9404418828049952,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000491977674100207,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.22316348552703857,
|
|
"num_tokens": 22460592.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.227112054824829,
|
|
"epoch": 0.9409221902017291,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004919685985241483,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.22545062750577927,
|
|
"num_tokens": 22471718.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.34343409538269,
|
|
"epoch": 0.9414024975984631,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000491959517910723,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.22044717222452165,
|
|
"num_tokens": 22482413.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.309344339370727,
|
|
"epoch": 0.9418828049951969,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004919504322601421,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.22121099829673768,
|
|
"num_tokens": 22494016.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.344629096984863,
|
|
"epoch": 0.9423631123919308,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004919413415726162,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.21001959443092347,
|
|
"num_tokens": 22505015.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.296896314620971,
|
|
"epoch": 0.9428434197886647,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004919322458483566,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.22266780734062194,
|
|
"num_tokens": 22516691.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.29275689125061,
|
|
"epoch": 0.9433237271853987,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004919231450875745,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.21753636747598648,
|
|
"num_tokens": 22527740.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.308889532089234,
|
|
"epoch": 0.9438040345821326,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004919140392904809,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.21616793125867845,
|
|
"num_tokens": 22537685.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.304792594909668,
|
|
"epoch": 0.9442843419788665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919049284572875,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.22687974125146865,
|
|
"num_tokens": 22548282.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.22439866065979,
|
|
"epoch": 0.9447646493756003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004918958125882058,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.22663719952106476,
|
|
"num_tokens": 22559277.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.267339181900025,
|
|
"epoch": 0.9452449567723343,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004918866916834474,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.2146475836634636,
|
|
"num_tokens": 22570664.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.2743912696838375,
|
|
"epoch": 0.9457252641690682,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918775657432239,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.22660233676433564,
|
|
"num_tokens": 22580410.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.277211666107178,
|
|
"epoch": 0.9462055715658021,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004918684347677474,
|
|
"loss": 5.039,
|
|
"mean_token_accuracy": 0.21700216829776764,
|
|
"num_tokens": 22591630.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.331323719024658,
|
|
"epoch": 0.946685878962536,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004918592987572298,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.21700206100940705,
|
|
"num_tokens": 22603658.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.326457786560058,
|
|
"epoch": 0.94716618635927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004918501577118832,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20917609184980393,
|
|
"num_tokens": 22614812.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.3182945728302,
|
|
"epoch": 0.9476464937560038,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049184101163192,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.21937220692634582,
|
|
"num_tokens": 22626924.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.3337548732757565,
|
|
"epoch": 0.9481268011527377,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004918318605175522,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.21688777357339858,
|
|
"num_tokens": 22638715.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.3768586158752445,
|
|
"epoch": 0.9486071085494716,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004918227043689924,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.20171089470386505,
|
|
"num_tokens": 22650257.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.285763502120972,
|
|
"epoch": 0.9490874159462056,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004918135431864534,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.2165541961789131,
|
|
"num_tokens": 22662480.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.320038270950318,
|
|
"epoch": 0.9495677233429395,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004918043769701478,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.21225260347127914,
|
|
"num_tokens": 22673927.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.421506738662719,
|
|
"epoch": 0.9500480307396734,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004917952057202882,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.22341705113649368,
|
|
"num_tokens": 22684670.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.345195150375366,
|
|
"epoch": 0.9505283381364072,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004917860294370877,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.21528895944356918,
|
|
"num_tokens": 22696571.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.2262468338012695,
|
|
"epoch": 0.9510086455331412,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004917768481207593,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.2241267055273056,
|
|
"num_tokens": 22708987.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.3272013664245605,
|
|
"epoch": 0.9514889529298751,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004917676617715162,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.2255505859851837,
|
|
"num_tokens": 22720769.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.325541019439697,
|
|
"epoch": 0.951969260326609,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004917584703895717,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.2248534604907036,
|
|
"num_tokens": 22732592.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.341712427139282,
|
|
"epoch": 0.952449567723343,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004917492739751391,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.2100845068693161,
|
|
"num_tokens": 22744440.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.2824348449707035,
|
|
"epoch": 0.9529298751200769,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000491740072528432,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.22085337042808534,
|
|
"num_tokens": 22756336.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.276133012771607,
|
|
"epoch": 0.9534101825168108,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000491730866049664,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.218307289481163,
|
|
"num_tokens": 22768256.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.373374366760254,
|
|
"epoch": 0.9538904899135446,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004917216545390489,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.2128934845328331,
|
|
"num_tokens": 22779693.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.252909517288208,
|
|
"epoch": 0.9543707973102786,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004917124379968004,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.22259168773889543,
|
|
"num_tokens": 22791417.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.314621305465698,
|
|
"epoch": 0.9548511047070125,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004917032164231327,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.2184122011065483,
|
|
"num_tokens": 22803541.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.350073528289795,
|
|
"epoch": 0.9553314121037464,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004916939898182598,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.2114892363548279,
|
|
"num_tokens": 22814648.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.308345985412598,
|
|
"epoch": 0.9558117195004803,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004916847581823958,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.21593945175409318,
|
|
"num_tokens": 22825672.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.321901035308838,
|
|
"epoch": 0.9562920268972143,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004916755215157552,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.21585459858179093,
|
|
"num_tokens": 22837663.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.1985584735870365,
|
|
"epoch": 0.9567723342939481,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004916662798185524,
|
|
"loss": 4.9117,
|
|
"mean_token_accuracy": 0.22356192171573638,
|
|
"num_tokens": 22849531.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.287479257583618,
|
|
"epoch": 0.957252641690682,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004916570330910019,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.21371769309043884,
|
|
"num_tokens": 22861784.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.359367609024048,
|
|
"epoch": 0.9577329490874159,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004916477813333185,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.21287578344345093,
|
|
"num_tokens": 22873482.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.291937971115113,
|
|
"epoch": 0.9582132564841499,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004916385245457168,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.22742630243301393,
|
|
"num_tokens": 22883917.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.296640205383301,
|
|
"epoch": 0.9586935638808838,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000491629262728412,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.21566283106803893,
|
|
"num_tokens": 22896167.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.306282901763916,
|
|
"epoch": 0.9591738712776177,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004916199958816188,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.22311149090528487,
|
|
"num_tokens": 22908350.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.423825216293335,
|
|
"epoch": 0.9596541786743515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004916107240055527,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.21201742738485335,
|
|
"num_tokens": 22918913.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.234002780914307,
|
|
"epoch": 0.9601344860710855,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004916014471004287,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.22406509816646575,
|
|
"num_tokens": 22929336.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.2801703929901125,
|
|
"epoch": 0.9606147934678194,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004915921651664622,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.22406738847494126,
|
|
"num_tokens": 22940406.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.272706508636475,
|
|
"epoch": 0.9610951008645533,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000491582878203869,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.22016689628362657,
|
|
"num_tokens": 22951518.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.221579217910767,
|
|
"epoch": 0.9615754082612872,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004915735862128643,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.22297402024269103,
|
|
"num_tokens": 22962309.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.273044633865356,
|
|
"epoch": 0.9620557156580212,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915642891936641,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.22229177355766297,
|
|
"num_tokens": 22973996.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.327480220794678,
|
|
"epoch": 0.962536023054755,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004915549871464841,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.2156223922967911,
|
|
"num_tokens": 22984964.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.337840604782104,
|
|
"epoch": 0.9630163304514889,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004915456800715403,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.2138780251145363,
|
|
"num_tokens": 22996058.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.255268812179565,
|
|
"epoch": 0.9634966378482228,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000491536367969049,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.22478612661361694,
|
|
"num_tokens": 23006140.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.312407064437866,
|
|
"epoch": 0.9639769452449568,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004915270508392261,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.20972624123096467,
|
|
"num_tokens": 23018129.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.301064348220825,
|
|
"epoch": 0.9644572526416907,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000491517728682288,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.2261952519416809,
|
|
"num_tokens": 23028673.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.280163097381592,
|
|
"epoch": 0.9649375600384246,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004915084014984512,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.21806405037641524,
|
|
"num_tokens": 23040778.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.25103120803833,
|
|
"epoch": 0.9654178674351584,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004914990692879322,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.22474465519189835,
|
|
"num_tokens": 23052170.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.27877836227417,
|
|
"epoch": 0.9658981748318924,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004914897320509478,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.21973779201507568,
|
|
"num_tokens": 23063455.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.216304969787598,
|
|
"epoch": 0.9663784822286263,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004914803897877146,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.22572595328092576,
|
|
"num_tokens": 23075009.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.315200138092041,
|
|
"epoch": 0.9668587896253602,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004914710424984495,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.21734508275985717,
|
|
"num_tokens": 23085921.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.401891756057739,
|
|
"epoch": 0.9673390970220941,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004914616901833696,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.2135796830058098,
|
|
"num_tokens": 23098181.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.235289621353149,
|
|
"epoch": 0.9678194044188281,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000491452332842692,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.2181957945227623,
|
|
"num_tokens": 23109904.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.254552268981934,
|
|
"epoch": 0.968299711815562,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000491442970476634,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.21354663074016572,
|
|
"num_tokens": 23122356.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.326158571243286,
|
|
"epoch": 0.9687800192122958,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004914336030854129,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.22547461986541747,
|
|
"num_tokens": 23134055.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.2711694717407225,
|
|
"epoch": 0.9692603266090298,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004914242306692461,
|
|
"loss": 4.9318,
|
|
"mean_token_accuracy": 0.22541950941085814,
|
|
"num_tokens": 23145388.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.320354270935058,
|
|
"epoch": 0.9697406340057637,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004914148532283516,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.2125547632575035,
|
|
"num_tokens": 23157083.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.292527151107788,
|
|
"epoch": 0.9702209414024976,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004914054707629466,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.21674777716398239,
|
|
"num_tokens": 23169154.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.247109508514404,
|
|
"epoch": 0.9707012487992315,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004913960832732493,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.22086829096078872,
|
|
"num_tokens": 23179879.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.293065595626831,
|
|
"epoch": 0.9711815561959655,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004913866907594774,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.22173525691032409,
|
|
"num_tokens": 23190632.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.340832281112671,
|
|
"epoch": 0.9716618635926993,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004913772932218491,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.2083672121167183,
|
|
"num_tokens": 23202060.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.319643831253051,
|
|
"epoch": 0.9721421709894332,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004913678906605825,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.2105837881565094,
|
|
"num_tokens": 23214103.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.295312833786011,
|
|
"epoch": 0.9726224783861671,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004913584830758961,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.2220668837428093,
|
|
"num_tokens": 23224676.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.322965097427368,
|
|
"epoch": 0.9731027857829011,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004913490704680081,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.2244173675775528,
|
|
"num_tokens": 23235478.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.3065777778625485,
|
|
"epoch": 0.973583093179635,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004913396528371371,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.2148100584745407,
|
|
"num_tokens": 23246913.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.30057692527771,
|
|
"epoch": 0.9740634005763689,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004913302301835018,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.22148966491222383,
|
|
"num_tokens": 23258472.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.423332357406617,
|
|
"epoch": 0.9745437079731027,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000491320802507321,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.21000604927539826,
|
|
"num_tokens": 23270443.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.339012289047242,
|
|
"epoch": 0.9750240153698367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913113698088133,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.22221570163965226,
|
|
"num_tokens": 23281199.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.255923652648926,
|
|
"epoch": 0.9755043227665706,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000491301932088198,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.22189567387104034,
|
|
"num_tokens": 23291980.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.344850254058838,
|
|
"epoch": 0.9759846301633045,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004912924893456942,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.21910030394792557,
|
|
"num_tokens": 23303673.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.370257949829101,
|
|
"epoch": 0.9764649375600384,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000491283041581521,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.21531369239091874,
|
|
"num_tokens": 23315830.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.329200983047485,
|
|
"epoch": 0.9769452449567724,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004912735887958978,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.2086866796016693,
|
|
"num_tokens": 23329860.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.299621105194092,
|
|
"epoch": 0.9774255523535063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004912641309890441,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.22276197224855424,
|
|
"num_tokens": 23340610.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.320596599578858,
|
|
"epoch": 0.9779058597502401,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004912546681611794,
|
|
"loss": 5.0117,
|
|
"mean_token_accuracy": 0.22064222544431686,
|
|
"num_tokens": 23352153.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.203898668289185,
|
|
"epoch": 0.978386167146974,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004912452003125234,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.22719736844301225,
|
|
"num_tokens": 23363630.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.227733564376831,
|
|
"epoch": 0.978866474543708,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000491235727443296,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.2205884799361229,
|
|
"num_tokens": 23375922.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.28243670463562,
|
|
"epoch": 0.9793467819404419,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004912262495537171,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.22314028739929198,
|
|
"num_tokens": 23386446.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.233039617538452,
|
|
"epoch": 0.9798270893371758,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004912167666440068,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.2282136857509613,
|
|
"num_tokens": 23398458.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.2609985828399655,
|
|
"epoch": 0.9803073967339097,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004912072787143852,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.21498909443616868,
|
|
"num_tokens": 23409725.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.272522068023681,
|
|
"epoch": 0.9807877041306436,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004911977857650725,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.21943185329437256,
|
|
"num_tokens": 23420468.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.332421112060547,
|
|
"epoch": 0.9812680115273775,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004911882877962893,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.21914395987987517,
|
|
"num_tokens": 23431386.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.358121871948242,
|
|
"epoch": 0.9817483189241114,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004911787848082559,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.21337175965309144,
|
|
"num_tokens": 23442759.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.281925106048584,
|
|
"epoch": 0.9822286263208453,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004911692768011931,
|
|
"loss": 4.9801,
|
|
"mean_token_accuracy": 0.22400446087121964,
|
|
"num_tokens": 23454372.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.33894681930542,
|
|
"epoch": 0.9827089337175793,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004911597637753217,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.2187868058681488,
|
|
"num_tokens": 23465557.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.225747585296631,
|
|
"epoch": 0.9831892411143132,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004911502457308623,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.22567014694213866,
|
|
"num_tokens": 23475850.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.277099466323852,
|
|
"epoch": 0.983669548511047,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000491140722668036,
|
|
"loss": 4.9192,
|
|
"mean_token_accuracy": 0.22129582911729812,
|
|
"num_tokens": 23487145.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.3396094799041744,
|
|
"epoch": 0.984149855907781,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000491131194587064,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.21096159070730208,
|
|
"num_tokens": 23498112.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.261802673339844,
|
|
"epoch": 0.9846301633045149,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004911216614881675,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.22017350196838378,
|
|
"num_tokens": 23509865.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.3418288230896,
|
|
"epoch": 0.9851104707012488,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004911121233715677,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.20582640171051025,
|
|
"num_tokens": 23521153.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.365827178955078,
|
|
"epoch": 0.9855907780979827,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004911025802374861,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.2073143869638443,
|
|
"num_tokens": 23532372.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.32112488746643,
|
|
"epoch": 0.9860710854947167,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004910930320861442,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.2127837210893631,
|
|
"num_tokens": 23543494.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.318867874145508,
|
|
"epoch": 0.9865513928914506,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004910834789177639,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.21226928234100342,
|
|
"num_tokens": 23554020.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.389520168304443,
|
|
"epoch": 0.9870317002881844,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004910739207325668,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.20811130553483964,
|
|
"num_tokens": 23565032.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.2658943176269535,
|
|
"epoch": 0.9875120076849183,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004910643575307749,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.21730590909719466,
|
|
"num_tokens": 23576243.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.329636526107788,
|
|
"epoch": 0.9879923150816523,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004910547893126102,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.21497938483953477,
|
|
"num_tokens": 23586111.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.401381397247315,
|
|
"epoch": 0.9884726224783862,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004910452160782948,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.2173905149102211,
|
|
"num_tokens": 23597718.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.421349334716797,
|
|
"epoch": 0.9889529298751201,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000491035637828051,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.21132976412773133,
|
|
"num_tokens": 23608241.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.343850946426391,
|
|
"epoch": 0.989433237271854,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004910260545621012,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.21641749143600464,
|
|
"num_tokens": 23619120.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.2459266662597654,
|
|
"epoch": 0.9899135446685879,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004910164662806679,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.220149265229702,
|
|
"num_tokens": 23630642.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.280236625671387,
|
|
"epoch": 0.9903938520653218,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004910068729839736,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.2208244577050209,
|
|
"num_tokens": 23641987.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.361133337020874,
|
|
"epoch": 0.9908741594620557,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004909972746722413,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.21449990570545197,
|
|
"num_tokens": 23653144.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.3274835586547855,
|
|
"epoch": 0.9913544668587896,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004909876713456935,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.21489083021879196,
|
|
"num_tokens": 23663807.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.265501928329468,
|
|
"epoch": 0.9918347742555236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004909780630045534,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.21479107737541198,
|
|
"num_tokens": 23674341.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.313705635070801,
|
|
"epoch": 0.9923150816522575,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000490968449649044,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.21427397578954696,
|
|
"num_tokens": 23685415.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.354645824432373,
|
|
"epoch": 0.9927953890489913,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004909588312793884,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.21836657524108888,
|
|
"num_tokens": 23696652.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.322224950790405,
|
|
"epoch": 0.9932756964457252,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004909492078958101,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.21910196542739868,
|
|
"num_tokens": 23708939.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.329898309707642,
|
|
"epoch": 0.9937560038424592,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909395794985324,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.22160798758268357,
|
|
"num_tokens": 23720587.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.212257671356201,
|
|
"epoch": 0.9942363112391931,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909299460877788,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.21783942431211473,
|
|
"num_tokens": 23732345.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.319120836257935,
|
|
"epoch": 0.994716618635927,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004909203076637732,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.21097601056098939,
|
|
"num_tokens": 23743149.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.431218957901001,
|
|
"epoch": 0.9951969260326609,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004909106642267392,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.22831811606884003,
|
|
"num_tokens": 23755508.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.3201478004455565,
|
|
"epoch": 0.9956772334293948,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909010157769006,
|
|
"loss": 4.9265,
|
|
"mean_token_accuracy": 0.21484524011611938,
|
|
"num_tokens": 23766313.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.201734733581543,
|
|
"epoch": 0.9961575408261287,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004908913623144814,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.22972951531410218,
|
|
"num_tokens": 23777776.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.274585151672364,
|
|
"epoch": 0.9966378482228626,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000490881703839706,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.22188824266195298,
|
|
"num_tokens": 23791143.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.4015251159667965,
|
|
"epoch": 0.9971181556195965,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004908720403527984,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.21200073957443238,
|
|
"num_tokens": 23802446.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.237569379806518,
|
|
"epoch": 0.9975984630163305,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000490862371853983,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.225716295838356,
|
|
"num_tokens": 23813757.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.2882232666015625,
|
|
"epoch": 0.9980787704130644,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004908526983434844,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.22053395211696625,
|
|
"num_tokens": 23824934.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.36096305847168,
|
|
"epoch": 0.9985590778097982,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000490843019821527,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.21364704370498658,
|
|
"num_tokens": 23836872.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.370064306259155,
|
|
"epoch": 0.9990393852065321,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004908333362883358,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.21344525068998338,
|
|
"num_tokens": 23847853.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.229442596435547,
|
|
"epoch": 0.9995196926032661,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004908236477441353,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.22030858248472213,
|
|
"num_tokens": 23859208.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.2494025230407715,
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004908139541891505,
|
|
"loss": 4.9125,
|
|
"mean_token_accuracy": 0.21675375252962112,
|
|
"num_tokens": 23868536.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.293199300765991,
|
|
"epoch": 1.0004803073967339,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004908042556236066,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.22597189098596573,
|
|
"num_tokens": 23881335.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.254992341995239,
|
|
"epoch": 1.0009606147934678,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004907945520477286,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.22956397831439973,
|
|
"num_tokens": 23891694.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.215055465698242,
|
|
"epoch": 1.0014409221902016,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004907848434617419,
|
|
"loss": 4.893,
|
|
"mean_token_accuracy": 0.2204670086503029,
|
|
"num_tokens": 23903560.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.399254512786865,
|
|
"epoch": 1.0019212295869357,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000490775129865872,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.21031637787818908,
|
|
"num_tokens": 23914525.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.337696266174317,
|
|
"epoch": 1.0024015369836696,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004907654112603442,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.22915695756673812,
|
|
"num_tokens": 23926492.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.323674726486206,
|
|
"epoch": 1.0028818443804035,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004907556876453843,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.22227881997823715,
|
|
"num_tokens": 23936326.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.182170820236206,
|
|
"epoch": 1.0033621517771374,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000490745959021218,
|
|
"loss": 4.7483,
|
|
"mean_token_accuracy": 0.23461511135101318,
|
|
"num_tokens": 23947173.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.274474573135376,
|
|
"epoch": 1.0038424591738713,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004907362253880711,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.22500903010368348,
|
|
"num_tokens": 23959771.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.2912805557250975,
|
|
"epoch": 1.0043227665706052,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004907264867461697,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.21977281719446182,
|
|
"num_tokens": 23970908.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.290959215164184,
|
|
"epoch": 1.004803073967339,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004907167430957399,
|
|
"loss": 4.9255,
|
|
"mean_token_accuracy": 0.2222078859806061,
|
|
"num_tokens": 23981640.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.343271112442016,
|
|
"epoch": 1.005283381364073,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004907069944370077,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.22303155362606047,
|
|
"num_tokens": 23992913.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.301690578460693,
|
|
"epoch": 1.005763688760807,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004906972407701998,
|
|
"loss": 4.9276,
|
|
"mean_token_accuracy": 0.21680889129638672,
|
|
"num_tokens": 24003819.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.35593957901001,
|
|
"epoch": 1.006243996157541,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004906874820955423,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.21943112313747407,
|
|
"num_tokens": 24013997.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.270966720581055,
|
|
"epoch": 1.0067243035542748,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004906777184132621,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.22099461406469345,
|
|
"num_tokens": 24025244.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.209639310836792,
|
|
"epoch": 1.0072046109510087,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004906679497235856,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.22530390471220016,
|
|
"num_tokens": 24037701.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.3423683643341064,
|
|
"epoch": 1.0076849183477425,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004906581760267397,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.21493847221136092,
|
|
"num_tokens": 24049369.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.308267736434937,
|
|
"epoch": 1.0081652257444764,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004906483973229513,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.22020021975040435,
|
|
"num_tokens": 24060625.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.396644020080567,
|
|
"epoch": 1.0086455331412103,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004906386136124476,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.2171130135655403,
|
|
"num_tokens": 24072527.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.3431336879730225,
|
|
"epoch": 1.0091258405379442,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906288248954554,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.212793792784214,
|
|
"num_tokens": 24083979.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.250096321105957,
|
|
"epoch": 1.0096061479346783,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004906190311722023,
|
|
"loss": 4.9512,
|
|
"mean_token_accuracy": 0.23015525937080383,
|
|
"num_tokens": 24095926.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.266572952270508,
|
|
"epoch": 1.0100864553314122,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004906092324429155,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.22860115319490432,
|
|
"num_tokens": 24107898.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.282457256317139,
|
|
"epoch": 1.010566762728146,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004905994287078227,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.2233198642730713,
|
|
"num_tokens": 24118713.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.297702121734619,
|
|
"epoch": 1.01104707012488,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004905896199671512,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.2241787478327751,
|
|
"num_tokens": 24130410.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.342277193069458,
|
|
"epoch": 1.0115273775216138,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000490579806221129,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.22304771840572357,
|
|
"num_tokens": 24140961.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.344465446472168,
|
|
"epoch": 1.0120076849183477,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004905699874699838,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.21675881445407869,
|
|
"num_tokens": 24153467.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.216631698608398,
|
|
"epoch": 1.0124879923150816,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004905601637139436,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.23213185220956803,
|
|
"num_tokens": 24163873.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.208134746551513,
|
|
"epoch": 1.0129682997118155,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004905503349532365,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.2266341492533684,
|
|
"num_tokens": 24175852.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.306021118164063,
|
|
"epoch": 1.0134486071085496,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905405011880906,
|
|
"loss": 4.959,
|
|
"mean_token_accuracy": 0.21902575045824052,
|
|
"num_tokens": 24187759.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.3029039859771725,
|
|
"epoch": 1.0139289145052834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905306624187343,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.2295238882303238,
|
|
"num_tokens": 24199725.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.358688926696777,
|
|
"epoch": 1.0144092219020173,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004905208186453961,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.21626694053411483,
|
|
"num_tokens": 24210739.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.410381507873535,
|
|
"epoch": 1.0148895292987512,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004905109698683044,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.20980968177318574,
|
|
"num_tokens": 24221873.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.286979103088379,
|
|
"epoch": 1.015369836695485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905011160876878,
|
|
"loss": 4.9277,
|
|
"mean_token_accuracy": 0.22375238835811614,
|
|
"num_tokens": 24233503.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.290537309646607,
|
|
"epoch": 1.015850144092219,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004904912573037753,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.21561606079339982,
|
|
"num_tokens": 24244465.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.200752258300781,
|
|
"epoch": 1.0163304514889528,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004904813935167957,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.23283761590719224,
|
|
"num_tokens": 24255807.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.367958974838257,
|
|
"epoch": 1.0168107588856867,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004904715247269779,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.21134057641029358,
|
|
"num_tokens": 24268195.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.212702703475952,
|
|
"epoch": 1.0172910662824208,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004904616509345514,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.23314002603292466,
|
|
"num_tokens": 24278915.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.295047807693481,
|
|
"epoch": 1.0177713736791547,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004904517721397449,
|
|
"loss": 4.9495,
|
|
"mean_token_accuracy": 0.22524905800819398,
|
|
"num_tokens": 24289115.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.274462699890137,
|
|
"epoch": 1.0182516810758886,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004904418883427881,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.2187797248363495,
|
|
"num_tokens": 24300646.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.41163067817688,
|
|
"epoch": 1.0187319884726225,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004904319995439104,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.21684447228908538,
|
|
"num_tokens": 24312344.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.279205369949341,
|
|
"epoch": 1.0192122958693564,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004904221057433412,
|
|
"loss": 4.8669,
|
|
"mean_token_accuracy": 0.22528597414493562,
|
|
"num_tokens": 24323382.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.232626342773438,
|
|
"epoch": 1.0196926032660902,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004904122069413105,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.22401325404644012,
|
|
"num_tokens": 24336820.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.3195243835449215,
|
|
"epoch": 1.0201729106628241,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000490402303138048,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.23095823377370833,
|
|
"num_tokens": 24348547.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.440805959701538,
|
|
"epoch": 1.0206532180595582,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004903923943337836,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.21796878874301912,
|
|
"num_tokens": 24359586.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.336941242218018,
|
|
"epoch": 1.021133525456292,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004903824805287475,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.2144855499267578,
|
|
"num_tokens": 24371647.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.27585072517395,
|
|
"epoch": 1.021613832853026,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004903725617231696,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.22204346507787703,
|
|
"num_tokens": 24382308.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.287150144577026,
|
|
"epoch": 1.0220941402497599,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004903626379172805,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.22454781234264373,
|
|
"num_tokens": 24393224.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.253025197982788,
|
|
"epoch": 1.0225744476464937,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004903527091113102,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.21651980876922608,
|
|
"num_tokens": 24405220.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.3822685241699215,
|
|
"epoch": 1.0230547550432276,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004903427753054897,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.21896112263202666,
|
|
"num_tokens": 24416406.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.313386344909668,
|
|
"epoch": 1.0235350624399615,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004903328365000492,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.2194376766681671,
|
|
"num_tokens": 24428595.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.293087387084961,
|
|
"epoch": 1.0240153698366954,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004903228926952199,
|
|
"loss": 4.8835,
|
|
"mean_token_accuracy": 0.2266172245144844,
|
|
"num_tokens": 24439568.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.331427764892578,
|
|
"epoch": 1.0244956772334295,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004903129438912322,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.22128244787454604,
|
|
"num_tokens": 24451736.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.270129108428955,
|
|
"epoch": 1.0249759846301634,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903029900883174,
|
|
"loss": 4.918,
|
|
"mean_token_accuracy": 0.22806022465229034,
|
|
"num_tokens": 24463463.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.270495271682739,
|
|
"epoch": 1.0254562920268973,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004902930312867063,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.21874859780073166,
|
|
"num_tokens": 24474425.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.301710224151611,
|
|
"epoch": 1.0259365994236311,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004902830674866306,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.22608961910009384,
|
|
"num_tokens": 24486482.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.266700887680054,
|
|
"epoch": 1.026416906820365,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004902730986883211,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.21900726854801178,
|
|
"num_tokens": 24497709.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.234407234191894,
|
|
"epoch": 1.026897214217099,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004902631248920096,
|
|
"loss": 4.8561,
|
|
"mean_token_accuracy": 0.2288163810968399,
|
|
"num_tokens": 24508406.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.191047334671021,
|
|
"epoch": 1.0273775216138328,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004902531460979274,
|
|
"loss": 4.9388,
|
|
"mean_token_accuracy": 0.22442299723625184,
|
|
"num_tokens": 24520688.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.226489925384522,
|
|
"epoch": 1.0278578290105667,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004902431623063065,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.2278974398970604,
|
|
"num_tokens": 24531473.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.290788841247559,
|
|
"epoch": 1.0283381364073008,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004902331735173785,
|
|
"loss": 4.9469,
|
|
"mean_token_accuracy": 0.2165723830461502,
|
|
"num_tokens": 24543263.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.271428537368775,
|
|
"epoch": 1.0288184438040346,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004902231797313752,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.23228764683008193,
|
|
"num_tokens": 24554067.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.167349195480346,
|
|
"epoch": 1.0292987512007685,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004902131809485288,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.22995859682559966,
|
|
"num_tokens": 24566291.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.331067228317261,
|
|
"epoch": 1.0297790585975024,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004902031771690713,
|
|
"loss": 4.9887,
|
|
"mean_token_accuracy": 0.21750802993774415,
|
|
"num_tokens": 24579248.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.246852731704712,
|
|
"epoch": 1.0302593659942363,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004901931683932352,
|
|
"loss": 4.8802,
|
|
"mean_token_accuracy": 0.23387933373451233,
|
|
"num_tokens": 24591047.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.2813355922698975,
|
|
"epoch": 1.0307396733909702,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004901831546212526,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.22457009106874465,
|
|
"num_tokens": 24602454.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.300665473937988,
|
|
"epoch": 1.031219980787704,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004901731358533562,
|
|
"loss": 4.955,
|
|
"mean_token_accuracy": 0.22458935976028443,
|
|
"num_tokens": 24614168.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.267854976654053,
|
|
"epoch": 1.031700288184438,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004901631120897785,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.22566644847393036,
|
|
"num_tokens": 24625588.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.210066604614258,
|
|
"epoch": 1.032180595581172,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004901530833307522,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.22341966181993483,
|
|
"num_tokens": 24637744.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.210735225677491,
|
|
"epoch": 1.032660902977906,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004901430495765103,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.2281223639845848,
|
|
"num_tokens": 24649631.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.2933001041412355,
|
|
"epoch": 1.0331412103746398,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004901330108272855,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.2268349662423134,
|
|
"num_tokens": 24660622.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.347838592529297,
|
|
"epoch": 1.0336215177713737,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004901229670833111,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.22697934210300447,
|
|
"num_tokens": 24671072.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.296618270874023,
|
|
"epoch": 1.0341018251681076,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004901129183448201,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.2204180106520653,
|
|
"num_tokens": 24683160.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.317634391784668,
|
|
"epoch": 1.0345821325648414,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004901028646120459,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.22374529987573624,
|
|
"num_tokens": 24694703.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.255117511749267,
|
|
"epoch": 1.0350624399615753,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000490092805885222,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.22411986738443374,
|
|
"num_tokens": 24706429.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.230753803253174,
|
|
"epoch": 1.0355427473583094,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004900827421645816,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.22461774647235871,
|
|
"num_tokens": 24717682.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.374640655517578,
|
|
"epoch": 1.0360230547550433,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004900726734503589,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.22123361825942994,
|
|
"num_tokens": 24728789.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.253545188903809,
|
|
"epoch": 1.0365033621517772,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004900625997427872,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.22918343991041185,
|
|
"num_tokens": 24739788.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.274608182907104,
|
|
"epoch": 1.036983669548511,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004900525210421006,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.22019654512405396,
|
|
"num_tokens": 24751828.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.279634046554565,
|
|
"epoch": 1.037463976945245,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004900424373485329,
|
|
"loss": 4.9009,
|
|
"mean_token_accuracy": 0.22578034847974776,
|
|
"num_tokens": 24762061.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.228778457641601,
|
|
"epoch": 1.0379442843419788,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004900323486623185,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.23133113384246826,
|
|
"num_tokens": 24774018.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.281899785995483,
|
|
"epoch": 1.0384245917387127,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004900222549836914,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.22909178584814072,
|
|
"num_tokens": 24785206.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.283967733383179,
|
|
"epoch": 1.0389048991354466,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000490012156312886,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.22111720144748687,
|
|
"num_tokens": 24797730.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.329795598983765,
|
|
"epoch": 1.0393852065321807,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004900020526501369,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.215685074031353,
|
|
"num_tokens": 24809267.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.304945468902588,
|
|
"epoch": 1.0398655139289146,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004899919439956785,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.21904153376817703,
|
|
"num_tokens": 24820461.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.209194087982178,
|
|
"epoch": 1.0403458213256485,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004899818303497455,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.22479467391967772,
|
|
"num_tokens": 24831959.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.277595329284668,
|
|
"epoch": 1.0408261287223823,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004899717117125728,
|
|
"loss": 4.902,
|
|
"mean_token_accuracy": 0.22602858990430832,
|
|
"num_tokens": 24843655.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.2578856468200685,
|
|
"epoch": 1.0413064361191162,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004899615880843953,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.222823603451252,
|
|
"num_tokens": 24855643.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.253402853012085,
|
|
"epoch": 1.04178674351585,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899514594654481,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.22823970913887023,
|
|
"num_tokens": 24865745.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.251532649993896,
|
|
"epoch": 1.042267050912584,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004899413258559662,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.23186295330524445,
|
|
"num_tokens": 24876567.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.200701713562012,
|
|
"epoch": 1.0427473583093179,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004899311872561849,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.2282094195485115,
|
|
"num_tokens": 24888294.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.301605081558227,
|
|
"epoch": 1.043227665706052,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899210436663398,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.21438444703817366,
|
|
"num_tokens": 24899559.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.303590583801269,
|
|
"epoch": 1.0437079731027858,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004899108950866661,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.22406211197376252,
|
|
"num_tokens": 24911205.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.289543342590332,
|
|
"epoch": 1.0441882804995197,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004899007415173997,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.2237152114510536,
|
|
"num_tokens": 24922635.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.238494157791138,
|
|
"epoch": 1.0446685878962536,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004898905829587762,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.227601321041584,
|
|
"num_tokens": 24932941.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.342963600158692,
|
|
"epoch": 1.0451488952929875,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004898804194110313,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.21749904304742812,
|
|
"num_tokens": 24943980.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.283752536773681,
|
|
"epoch": 1.0456292026897214,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004898702508744012,
|
|
"loss": 4.938,
|
|
"mean_token_accuracy": 0.21805933862924576,
|
|
"num_tokens": 24955233.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.297315216064453,
|
|
"epoch": 1.0461095100864553,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004898600773491221,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.22163694649934768,
|
|
"num_tokens": 24966971.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.326498079299927,
|
|
"epoch": 1.0465898174831891,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004898498988354297,
|
|
"loss": 4.9579,
|
|
"mean_token_accuracy": 0.21869100481271744,
|
|
"num_tokens": 24977515.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.265054941177368,
|
|
"epoch": 1.0470701248799232,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004898397153335608,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.22534895837306976,
|
|
"num_tokens": 24988131.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.319674301147461,
|
|
"epoch": 1.0475504322766571,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004898295268437517,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.21869747936725617,
|
|
"num_tokens": 24999238.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.322566652297974,
|
|
"epoch": 1.048030739673391,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004898193333662388,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.21660760790109634,
|
|
"num_tokens": 25011443.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.293665027618408,
|
|
"epoch": 1.0485110470701249,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004898091349012588,
|
|
"loss": 4.8366,
|
|
"mean_token_accuracy": 0.23066906929016112,
|
|
"num_tokens": 25022151.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.30192232131958,
|
|
"epoch": 1.0489913544668588,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004897989314490486,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.22567637264728546,
|
|
"num_tokens": 25032730.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.183132839202881,
|
|
"epoch": 1.0494716618635926,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004897887230098451,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.2282209262251854,
|
|
"num_tokens": 25044455.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.2000367641448975,
|
|
"epoch": 1.0499519692603265,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004897785095838852,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.23589441031217576,
|
|
"num_tokens": 25056647.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.2434666633605955,
|
|
"epoch": 1.0504322766570606,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004897682911714061,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.22648960947990418,
|
|
"num_tokens": 25067618.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.2661614418029785,
|
|
"epoch": 1.0509125840537945,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000489758067772645,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.22530801892280578,
|
|
"num_tokens": 25079753.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.25759072303772,
|
|
"epoch": 1.0513928914505284,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004897478393878392,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.227142034471035,
|
|
"num_tokens": 25091023.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.307993602752686,
|
|
"epoch": 1.0518731988472623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004897376060172264,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.21730315536260605,
|
|
"num_tokens": 25101396.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.2809041976928714,
|
|
"epoch": 1.0523535062439962,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004897273676610438,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.22182614654302596,
|
|
"num_tokens": 25112562.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.317814540863037,
|
|
"epoch": 1.05283381364073,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004897171243195295,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.22584954649209976,
|
|
"num_tokens": 25124401.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.302470779418945,
|
|
"epoch": 1.053314121037464,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000489706875992921,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.22385627627372742,
|
|
"num_tokens": 25137345.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.281220722198486,
|
|
"epoch": 1.0537944284341978,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004896966226814565,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.22321151047945023,
|
|
"num_tokens": 25149300.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.270255279541016,
|
|
"epoch": 1.054274735830932,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004896863643853739,
|
|
"loss": 4.8818,
|
|
"mean_token_accuracy": 0.2298416957259178,
|
|
"num_tokens": 25159510.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.297906160354614,
|
|
"epoch": 1.0547550432276658,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004896761011049114,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.22594620287418365,
|
|
"num_tokens": 25172346.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.313401985168457,
|
|
"epoch": 1.0552353506243997,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896658328403074,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.22099042534828187,
|
|
"num_tokens": 25183471.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.3346278190612795,
|
|
"epoch": 1.0557156580211335,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004896555595918001,
|
|
"loss": 4.946,
|
|
"mean_token_accuracy": 0.22378867417573928,
|
|
"num_tokens": 25195067.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.303468322753906,
|
|
"epoch": 1.0561959654178674,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004896452813596281,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.21814843267202377,
|
|
"num_tokens": 25206165.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.293003129959106,
|
|
"epoch": 1.0566762728146013,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004896349981440301,
|
|
"loss": 4.8925,
|
|
"mean_token_accuracy": 0.23229259997606277,
|
|
"num_tokens": 25217229.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.341006088256836,
|
|
"epoch": 1.0571565802113352,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004896247099452447,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.21171170324087143,
|
|
"num_tokens": 25229349.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.296307182312011,
|
|
"epoch": 1.057636887608069,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004896144167635108,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.22395490854978561,
|
|
"num_tokens": 25240367.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.306979560852051,
|
|
"epoch": 1.0581171950048032,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896041185990675,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.2123871147632599,
|
|
"num_tokens": 25252025.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.269337797164917,
|
|
"epoch": 1.058597502401537,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004895938154521538,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.22544264942407607,
|
|
"num_tokens": 25264846.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.251443147659302,
|
|
"epoch": 1.059077809798271,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004895835073230089,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.22455534040927888,
|
|
"num_tokens": 25276150.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.310081577301025,
|
|
"epoch": 1.0595581171950048,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004895731942118722,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.22364803850650788,
|
|
"num_tokens": 25287819.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.310041189193726,
|
|
"epoch": 1.0600384245917387,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004895628761189829,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.22848904728889466,
|
|
"num_tokens": 25300467.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.221130514144898,
|
|
"epoch": 1.0605187319884726,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004895525530445809,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.22139581441879272,
|
|
"num_tokens": 25312447.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.286418676376343,
|
|
"epoch": 1.0609990393852065,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004895422249889057,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.21897991001605988,
|
|
"num_tokens": 25324160.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.280583286285401,
|
|
"epoch": 1.0614793467819403,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004895318919521971,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.23299532979726792,
|
|
"num_tokens": 25335106.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.232498216629028,
|
|
"epoch": 1.0619596541786744,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895215539346949,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.22556574940681456,
|
|
"num_tokens": 25345246.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.275879144668579,
|
|
"epoch": 1.0624399615754083,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004895112109366393,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.2209514021873474,
|
|
"num_tokens": 25356665.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.267789745330811,
|
|
"epoch": 1.0629202689721422,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004895008629582703,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.22779023945331572,
|
|
"num_tokens": 25368128.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.233451700210571,
|
|
"epoch": 1.063400576368876,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004894905099998283,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.22865607142448424,
|
|
"num_tokens": 25379061.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.300530958175659,
|
|
"epoch": 1.06388088376561,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004894801520615535,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.22815064042806626,
|
|
"num_tokens": 25390157.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.2611652374267575,
|
|
"epoch": 1.0643611911623438,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004894697891436863,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.218513622879982,
|
|
"num_tokens": 25400446.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.287797832489014,
|
|
"epoch": 1.0648414985590777,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004894594212464676,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.2200704663991928,
|
|
"num_tokens": 25412064.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.278355884552002,
|
|
"epoch": 1.0653218059558118,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004894490483701381,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.2245079308748245,
|
|
"num_tokens": 25422898.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.274604225158692,
|
|
"epoch": 1.0658021133525457,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004894386705149382,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.2200019583106041,
|
|
"num_tokens": 25434318.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.245290517807007,
|
|
"epoch": 1.0662824207492796,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004894282876811093,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.23230667263269425,
|
|
"num_tokens": 25444941.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.285471773147583,
|
|
"epoch": 1.0667627281460135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004894178998688921,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.2204962283372879,
|
|
"num_tokens": 25455971.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.233206558227539,
|
|
"epoch": 1.0672430355427474,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894075070785281,
|
|
"loss": 4.8678,
|
|
"mean_token_accuracy": 0.22446452230215072,
|
|
"num_tokens": 25467587.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.214283084869384,
|
|
"epoch": 1.0677233429394812,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004893971093102585,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.22773121148347855,
|
|
"num_tokens": 25479137.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.386748743057251,
|
|
"epoch": 1.0682036503362151,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004893867065643245,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.21161104440689088,
|
|
"num_tokens": 25491755.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.208349180221558,
|
|
"epoch": 1.068683957732949,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004893762988409678,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.23219916224479675,
|
|
"num_tokens": 25503581.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.265662050247192,
|
|
"epoch": 1.069164265129683,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004893658861404301,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.22379011511802674,
|
|
"num_tokens": 25515032.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.283497142791748,
|
|
"epoch": 1.069644572526417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004893554684629529,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.22841296792030336,
|
|
"num_tokens": 25526347.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.3323094844818115,
|
|
"epoch": 1.0701248799231509,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004893450458087784,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.22349520325660704,
|
|
"num_tokens": 25538287.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.190786218643188,
|
|
"epoch": 1.0706051873198847,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004893346181781483,
|
|
"loss": 4.8794,
|
|
"mean_token_accuracy": 0.23554282635450363,
|
|
"num_tokens": 25548431.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.28824257850647,
|
|
"epoch": 1.0710854947166186,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004893241855713048,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.2194781094789505,
|
|
"num_tokens": 25558706.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.357638692855835,
|
|
"epoch": 1.0715658021133525,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004893137479884903,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.22288246005773543,
|
|
"num_tokens": 25569920.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.269709682464599,
|
|
"epoch": 1.0720461095100864,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004893033054299468,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.23387812227010726,
|
|
"num_tokens": 25581340.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.28145399093628,
|
|
"epoch": 1.0725264169068203,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000489292857895917,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.221514730155468,
|
|
"num_tokens": 25592477.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.286905956268311,
|
|
"epoch": 1.0730067243035544,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004892824053866432,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.2295848935842514,
|
|
"num_tokens": 25604583.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.395840263366699,
|
|
"epoch": 1.0734870317002883,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004892719479023683,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.21810856014490126,
|
|
"num_tokens": 25614743.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.163461780548095,
|
|
"epoch": 1.0739673390970221,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000489261485443335,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.23315737247467042,
|
|
"num_tokens": 25626796.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.250571060180664,
|
|
"epoch": 1.074447646493756,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004892510180097863,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.2275239869952202,
|
|
"num_tokens": 25638014.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.27679214477539,
|
|
"epoch": 1.07492795389049,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004892405456019651,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.22645066678524017,
|
|
"num_tokens": 25649555.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.315376949310303,
|
|
"epoch": 1.0754082612872238,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004892300682201147,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.2191445305943489,
|
|
"num_tokens": 25662886.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.306099557876587,
|
|
"epoch": 1.0758885686839577,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004892195858644782,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.22910475581884385,
|
|
"num_tokens": 25673802.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.264354944229126,
|
|
"epoch": 1.0763688760806915,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000489209098535299,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.22870259135961532,
|
|
"num_tokens": 25685545.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.215815162658691,
|
|
"epoch": 1.0768491834774256,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004891986062328205,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.22934622168540955,
|
|
"num_tokens": 25697955.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.297185564041138,
|
|
"epoch": 1.0773294908741595,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004891881089572865,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.21804916709661484,
|
|
"num_tokens": 25709707.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.28114423751831,
|
|
"epoch": 1.0778097982708934,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004891776067089406,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.2236069604754448,
|
|
"num_tokens": 25720576.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.25132999420166,
|
|
"epoch": 1.0782901056676273,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004891670994880266,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.23449163734912873,
|
|
"num_tokens": 25731387.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.203381156921386,
|
|
"epoch": 1.0787704130643612,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004891565872947888,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.2348889797925949,
|
|
"num_tokens": 25741813.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.252008581161499,
|
|
"epoch": 1.079250720461095,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004891460701294706,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.22653912752866745,
|
|
"num_tokens": 25753763.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.249889850616455,
|
|
"epoch": 1.079731027857829,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004891355479923167,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.22707249969244003,
|
|
"num_tokens": 25765269.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.279524326324463,
|
|
"epoch": 1.080211335254563,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004891250208835712,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.22635491490364074,
|
|
"num_tokens": 25776841.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.341002321243286,
|
|
"epoch": 1.080691642651297,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004891144888034784,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.21188949644565583,
|
|
"num_tokens": 25788151.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.237669897079468,
|
|
"epoch": 1.0811719500480308,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004891039517522832,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.23270726650953294,
|
|
"num_tokens": 25799194.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.282653665542602,
|
|
"epoch": 1.0816522574447647,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004890934097302299,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.21839313507080077,
|
|
"num_tokens": 25809483.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.217053174972534,
|
|
"epoch": 1.0821325648414986,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004890828627375632,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.21417620033025742,
|
|
"num_tokens": 25820781.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.337426948547363,
|
|
"epoch": 1.0826128722382324,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004890723107745283,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.21760281026363373,
|
|
"num_tokens": 25832111.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.314812707901001,
|
|
"epoch": 1.0830931796349663,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004890617538413699,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.22515095472335817,
|
|
"num_tokens": 25843300.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.282426404953003,
|
|
"epoch": 1.0835734870317002,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004890511919383333,
|
|
"loss": 4.9074,
|
|
"mean_token_accuracy": 0.21843766123056413,
|
|
"num_tokens": 25855337.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.376343154907227,
|
|
"epoch": 1.084053794428434,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004890406250656636,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.22181759178638458,
|
|
"num_tokens": 25866683.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.2536664485931395,
|
|
"epoch": 1.0845341018251682,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004890300532236062,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.2275771200656891,
|
|
"num_tokens": 25878041.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.297029256820679,
|
|
"epoch": 1.085014409221902,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004890194764124064,
|
|
"loss": 4.8915,
|
|
"mean_token_accuracy": 0.22013041079044343,
|
|
"num_tokens": 25889059.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.2153486728668215,
|
|
"epoch": 1.085494716618636,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004890088946323099,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.23682618737220765,
|
|
"num_tokens": 25900062.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.302586841583252,
|
|
"epoch": 1.0859750240153698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004889983078835623,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.21880530714988708,
|
|
"num_tokens": 25911813.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.296090364456177,
|
|
"epoch": 1.0864553314121037,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.22777592539787292,
|
|
"num_tokens": 25922321.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.267679595947266,
|
|
"epoch": 1.0869356388088376,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004889771194810974,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.23168697506189345,
|
|
"num_tokens": 25933631.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.274777507781982,
|
|
"epoch": 1.0874159462055715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004889665178278719,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.22480629831552507,
|
|
"num_tokens": 25945190.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.284109163284302,
|
|
"epoch": 1.0878962536023056,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004889559112069792,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.22814873605966568,
|
|
"num_tokens": 25956817.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.376457166671753,
|
|
"epoch": 1.0883765609990395,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004889452996186657,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.22788677662611007,
|
|
"num_tokens": 25968134.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.211644506454467,
|
|
"epoch": 1.0888568683957733,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004889346830631774,
|
|
"loss": 4.8761,
|
|
"mean_token_accuracy": 0.2291594311594963,
|
|
"num_tokens": 25981825.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.3677743434906,
|
|
"epoch": 1.0893371757925072,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000488924061540761,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.20639665126800538,
|
|
"num_tokens": 25993962.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.250808143615723,
|
|
"epoch": 1.089817483189241,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004889134350516633,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.23112435042858123,
|
|
"num_tokens": 26005705.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.225830125808716,
|
|
"epoch": 1.090297790585975,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004889028035961308,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.22975675612688065,
|
|
"num_tokens": 26017111.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.309533739089966,
|
|
"epoch": 1.0907780979827089,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004888921671744103,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.22030390948057174,
|
|
"num_tokens": 26028097.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.2683014392852785,
|
|
"epoch": 1.0912584053794427,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004888815257867488,
|
|
"loss": 4.8921,
|
|
"mean_token_accuracy": 0.2270355209708214,
|
|
"num_tokens": 26039281.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.30238709449768,
|
|
"epoch": 1.0917387127761768,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004888708794333934,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.214099483191967,
|
|
"num_tokens": 26051133.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.254332494735718,
|
|
"epoch": 1.0922190201729107,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004888602281145913,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.22377143204212188,
|
|
"num_tokens": 26062220.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.25627908706665,
|
|
"epoch": 1.0926993275696446,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004888495718305897,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.2350233718752861,
|
|
"num_tokens": 26072556.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.331442594528198,
|
|
"epoch": 1.0931796349663785,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000488838910581636,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.21914745271205902,
|
|
"num_tokens": 26084218.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.401429319381714,
|
|
"epoch": 1.0936599423631124,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004888282443679777,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.21373916566371917,
|
|
"num_tokens": 26096272.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.293875312805175,
|
|
"epoch": 1.0941402497598463,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004888175731898627,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.2266232892870903,
|
|
"num_tokens": 26109247.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.263606977462769,
|
|
"epoch": 1.0946205571565801,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004888068970475384,
|
|
"loss": 4.8944,
|
|
"mean_token_accuracy": 0.22127517461776733,
|
|
"num_tokens": 26121340.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.284204959869385,
|
|
"epoch": 1.0951008645533142,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004887962159412529,
|
|
"loss": 4.9177,
|
|
"mean_token_accuracy": 0.2198970928788185,
|
|
"num_tokens": 26133135.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.250123500823975,
|
|
"epoch": 1.0955811719500481,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004887855298712541,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.2283838599920273,
|
|
"num_tokens": 26145324.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.1924458026885985,
|
|
"epoch": 1.096061479346782,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048877483883779,
|
|
"loss": 4.8366,
|
|
"mean_token_accuracy": 0.232439087331295,
|
|
"num_tokens": 26156739.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.284620332717895,
|
|
"epoch": 1.0965417867435159,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004887641428411091,
|
|
"loss": 4.922,
|
|
"mean_token_accuracy": 0.22266011834144592,
|
|
"num_tokens": 26169543.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.291568088531494,
|
|
"epoch": 1.0970220941402498,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004887534418814595,
|
|
"loss": 4.9099,
|
|
"mean_token_accuracy": 0.2259551227092743,
|
|
"num_tokens": 26181317.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.333689260482788,
|
|
"epoch": 1.0975024015369836,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004887427359590897,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.22025445401668547,
|
|
"num_tokens": 26193402.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.235490179061889,
|
|
"epoch": 1.0979827089337175,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004887320250742482,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.22831207364797593,
|
|
"num_tokens": 26204660.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.345036363601684,
|
|
"epoch": 1.0984630163304514,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004887213092271838,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.22482469230890273,
|
|
"num_tokens": 26215593.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.210754632949829,
|
|
"epoch": 1.0989433237271853,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004887105884181451,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.2314085140824318,
|
|
"num_tokens": 26227481.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.298476886749268,
|
|
"epoch": 1.0994236311239194,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004886998626473813,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.2163267195224762,
|
|
"num_tokens": 26238260.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.325344753265381,
|
|
"epoch": 1.0999039385206533,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004886891319151411,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.22192018926143647,
|
|
"num_tokens": 26249749.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.3324202537536625,
|
|
"epoch": 1.1003842459173871,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004886783962216738,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.22930229008197783,
|
|
"num_tokens": 26260639.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.2848546504974365,
|
|
"epoch": 1.100864553314121,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004886676555672287,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.22212115973234176,
|
|
"num_tokens": 26271797.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.309595680236816,
|
|
"epoch": 1.101344860710855,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004886569099520551,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.21452850252389907,
|
|
"num_tokens": 26283298.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.221762990951538,
|
|
"epoch": 1.1018251681075888,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004886461593764024,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.23223839998245238,
|
|
"num_tokens": 26293632.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.297098875045776,
|
|
"epoch": 1.1023054755043227,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004886354038405204,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.2147509604692459,
|
|
"num_tokens": 26307053.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.263954162597656,
|
|
"epoch": 1.1027857829010568,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004886246433446586,
|
|
"loss": 4.8337,
|
|
"mean_token_accuracy": 0.234157557785511,
|
|
"num_tokens": 26317136.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.261523866653443,
|
|
"epoch": 1.1032660902977907,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004886138778890669,
|
|
"loss": 4.9225,
|
|
"mean_token_accuracy": 0.22860513925552367,
|
|
"num_tokens": 26328865.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.27056303024292,
|
|
"epoch": 1.1037463976945245,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004886031074739953,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.22938338667154312,
|
|
"num_tokens": 26341010.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.3497730731964115,
|
|
"epoch": 1.1042267050912584,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004885923320996938,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.22074739187955855,
|
|
"num_tokens": 26352203.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.345974493026733,
|
|
"epoch": 1.1047070124879923,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004885815517664127,
|
|
"loss": 4.9437,
|
|
"mean_token_accuracy": 0.2226704552769661,
|
|
"num_tokens": 26363096.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.20188536643982,
|
|
"epoch": 1.1051873198847262,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000488570766474402,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.2332399994134903,
|
|
"num_tokens": 26374776.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.252371501922608,
|
|
"epoch": 1.10566762728146,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004885599762239124,
|
|
"loss": 4.9413,
|
|
"mean_token_accuracy": 0.22429201751947403,
|
|
"num_tokens": 26386654.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.257208442687988,
|
|
"epoch": 1.106147934678194,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004885491810151943,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.22466953992843627,
|
|
"num_tokens": 26400022.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.249144744873047,
|
|
"epoch": 1.106628242074928,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004885383808484982,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.22867700904607774,
|
|
"num_tokens": 26412308.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.339946460723877,
|
|
"epoch": 1.107108549471662,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004885275757240751,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.2093404471874237,
|
|
"num_tokens": 26424506.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.308559083938599,
|
|
"epoch": 1.1075888568683958,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004885167656421757,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.2279639348387718,
|
|
"num_tokens": 26435020.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.160638904571533,
|
|
"epoch": 1.1080691642651297,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000488505950603051,
|
|
"loss": 4.8255,
|
|
"mean_token_accuracy": 0.23112286627292633,
|
|
"num_tokens": 26447952.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.263839530944824,
|
|
"epoch": 1.1085494716618636,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000488495130606952,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.2231008976697922,
|
|
"num_tokens": 26460001.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.266804313659668,
|
|
"epoch": 1.1090297790585975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004884843056541302,
|
|
"loss": 4.8758,
|
|
"mean_token_accuracy": 0.2282893553376198,
|
|
"num_tokens": 26472139.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.254396438598633,
|
|
"epoch": 1.1095100864553313,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004884734757448367,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.22577227056026458,
|
|
"num_tokens": 26483855.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.3095542907714846,
|
|
"epoch": 1.1099903938520654,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000488462640879323,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.21780347526073457,
|
|
"num_tokens": 26496529.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.304741287231446,
|
|
"epoch": 1.1104707012487993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004884518010578405,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.2261032685637474,
|
|
"num_tokens": 26506663.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.306883907318115,
|
|
"epoch": 1.1109510086455332,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004884409562806411,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.21742438524961472,
|
|
"num_tokens": 26519091.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.287644004821777,
|
|
"epoch": 1.111431316042267,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004884301065479765,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.22612448632717133,
|
|
"num_tokens": 26530145.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.3014226913452145,
|
|
"epoch": 1.111911623439001,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004884192518600986,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.2259310245513916,
|
|
"num_tokens": 26541228.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.305756092071533,
|
|
"epoch": 1.1123919308357348,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004884083922172593,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.2242702767252922,
|
|
"num_tokens": 26551359.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.194130945205688,
|
|
"epoch": 1.1128722382324687,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004883975276197108,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.22318680435419083,
|
|
"num_tokens": 26562911.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.350737237930298,
|
|
"epoch": 1.1133525456292026,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883866580677055,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.2287845328450203,
|
|
"num_tokens": 26573198.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.300978660583496,
|
|
"epoch": 1.1138328530259365,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004883757835614956,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.2226686418056488,
|
|
"num_tokens": 26584932.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.3802323818206785,
|
|
"epoch": 1.1143131604226706,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004883649041013335,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.21441729962825776,
|
|
"num_tokens": 26596042.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.324697113037109,
|
|
"epoch": 1.1147934678194045,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000488354019687472,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.21586629897356033,
|
|
"num_tokens": 26607359.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.336730861663819,
|
|
"epoch": 1.1152737752161384,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004883431303201636,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.2256915330886841,
|
|
"num_tokens": 26617095.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.238125371932983,
|
|
"epoch": 1.1157540826128722,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004883322359996613,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.22074692994356154,
|
|
"num_tokens": 26628450.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.267247819900513,
|
|
"epoch": 1.1162343900096061,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004883213367262179,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.22716759741306305,
|
|
"num_tokens": 26639428.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.221054220199585,
|
|
"epoch": 1.11671469740634,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004883104325000866,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.226392462849617,
|
|
"num_tokens": 26650730.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.261678218841553,
|
|
"epoch": 1.1171950048030739,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004882995233215203,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.22781110554933548,
|
|
"num_tokens": 26661745.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.219639301300049,
|
|
"epoch": 1.117675312199808,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004882886091907726,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.23578773438930511,
|
|
"num_tokens": 26672976.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.323981761932373,
|
|
"epoch": 1.1181556195965419,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048827769010809666,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.21722061783075333,
|
|
"num_tokens": 26683503.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.2824342250823975,
|
|
"epoch": 1.1186359269932757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048826676607374606,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.2207248628139496,
|
|
"num_tokens": 26695160.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.222529792785645,
|
|
"epoch": 1.1191162343900096,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048825583708797434,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.22609965950250627,
|
|
"num_tokens": 26706514.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.205767583847046,
|
|
"epoch": 1.1195965417867435,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004882449031510354,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.23533940613269805,
|
|
"num_tokens": 26717268.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.393366193771362,
|
|
"epoch": 1.1200768491834774,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000488233964263183,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.21961141228675843,
|
|
"num_tokens": 26728821.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.37230076789856,
|
|
"epoch": 1.1205571565802113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048822302042467115,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.21768180131912232,
|
|
"num_tokens": 26740476.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.317116355895996,
|
|
"epoch": 1.1210374639769451,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004882120716357539,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.21823584884405137,
|
|
"num_tokens": 26751289.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.252418565750122,
|
|
"epoch": 1.1215177713736793,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004882011178966854,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.22957109063863754,
|
|
"num_tokens": 26762115.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.248479509353638,
|
|
"epoch": 1.1219980787704131,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004881901592077201,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.22818623781204223,
|
|
"num_tokens": 26772837.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.347883605957032,
|
|
"epoch": 1.122478386167147,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004881791955691123,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.22577099800109862,
|
|
"num_tokens": 26783721.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.263661336898804,
|
|
"epoch": 1.122958693563881,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048816822698111655,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.23205357939004898,
|
|
"num_tokens": 26794320.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.318215990066529,
|
|
"epoch": 1.1234390009606148,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048815725344398766,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.2154138281941414,
|
|
"num_tokens": 26807053.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.404174184799194,
|
|
"epoch": 1.1239193083573487,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048814627495798017,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.21833395063877106,
|
|
"num_tokens": 26817245.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.278433418273925,
|
|
"epoch": 1.1243996157540825,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004881352915233492,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.21832550019025804,
|
|
"num_tokens": 26829498.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.17567892074585,
|
|
"epoch": 1.1248799231508164,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048812430314034956,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.23114259541034698,
|
|
"num_tokens": 26840534.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.330444431304931,
|
|
"epoch": 1.1253602305475505,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004881133098092365,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.21893862187862395,
|
|
"num_tokens": 26851305.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.261358785629272,
|
|
"epoch": 1.1258405379442844,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004881023115302652,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.2254275858402252,
|
|
"num_tokens": 26862620.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.296838045120239,
|
|
"epoch": 1.1263208453410183,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000488091308303691,
|
|
"loss": 4.9334,
|
|
"mean_token_accuracy": 0.222735396027565,
|
|
"num_tokens": 26874108.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.322463846206665,
|
|
"epoch": 1.1268011527377522,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004880803001297694,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.22394784390926362,
|
|
"num_tokens": 26886523.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.2631556510925295,
|
|
"epoch": 1.127281460134486,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004880692870087559,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.23387356996536254,
|
|
"num_tokens": 26897316.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.23564658164978,
|
|
"epoch": 1.12776176753122,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048805826894090626,
|
|
"loss": 4.8977,
|
|
"mean_token_accuracy": 0.22059985250234604,
|
|
"num_tokens": 26909807.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.330638408660889,
|
|
"epoch": 1.1282420749279538,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048804724592647626,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.2176713839173317,
|
|
"num_tokens": 26922054.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.2835084915161135,
|
|
"epoch": 1.1287223823246877,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004880362179657218,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.22437111884355546,
|
|
"num_tokens": 26933838.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.271953439712524,
|
|
"epoch": 1.1292026897214218,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048802518505889904,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.22372469305992126,
|
|
"num_tokens": 26945396.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.322554016113282,
|
|
"epoch": 1.1296829971181557,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048801414720626404,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.21679863333702087,
|
|
"num_tokens": 26957809.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.326206970214844,
|
|
"epoch": 1.1301633045148896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048800310440807294,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.23308510780334474,
|
|
"num_tokens": 26969024.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.225106430053711,
|
|
"epoch": 1.1306436119116234,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004879920566645823,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.22595815658569335,
|
|
"num_tokens": 26980689.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.32217173576355,
|
|
"epoch": 1.1311239193083573,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004879810039760486,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.21771504431962968,
|
|
"num_tokens": 26992115.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.348143291473389,
|
|
"epoch": 1.1316042267050912,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004879699463427284,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.22278164327144623,
|
|
"num_tokens": 27003042.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.2671184062957765,
|
|
"epoch": 1.132084534101825,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004879588837648785,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.23316011130809783,
|
|
"num_tokens": 27013863.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.168650960922241,
|
|
"epoch": 1.1325648414985592,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048794781624275554,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.23176731616258622,
|
|
"num_tokens": 27024423.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.24285135269165,
|
|
"epoch": 1.133045148895293,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048793674377661664,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.2196636125445366,
|
|
"num_tokens": 27035460.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.276094532012939,
|
|
"epoch": 1.133525456292027,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048792566636671886,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.22262306809425353,
|
|
"num_tokens": 27046731.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.280252265930176,
|
|
"epoch": 1.1340057636887608,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004879145840133194,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.22826443910598754,
|
|
"num_tokens": 27057758.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.377760028839111,
|
|
"epoch": 1.1344860710854947,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004879034967166755,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.21985043585300446,
|
|
"num_tokens": 27068055.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.267134714126587,
|
|
"epoch": 1.1349663784822286,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004878924044770446,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.22107535004615783,
|
|
"num_tokens": 27078602.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.239167499542236,
|
|
"epoch": 1.1354466858789625,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004878813072946843,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.21947692185640336,
|
|
"num_tokens": 27089944.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.248386573791504,
|
|
"epoch": 1.1359269932756964,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048787020516985203,
|
|
"loss": 4.8695,
|
|
"mean_token_accuracy": 0.23418137729167937,
|
|
"num_tokens": 27100486.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.292231273651123,
|
|
"epoch": 1.1364073006724302,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048785909810280576,
|
|
"loss": 4.9348,
|
|
"mean_token_accuracy": 0.22394795566797257,
|
|
"num_tokens": 27111435.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.309876537322998,
|
|
"epoch": 1.1368876080691643,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004878479860938033,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.22473978400230407,
|
|
"num_tokens": 27123482.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.272254467010498,
|
|
"epoch": 1.1373679154658982,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048783686914310266,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.22432289719581605,
|
|
"num_tokens": 27135009.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.272644329071045,
|
|
"epoch": 1.137848222862632,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004878257472509619,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.23252134621143342,
|
|
"num_tokens": 27145230.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.260117912292481,
|
|
"epoch": 1.138328530259366,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004878146204176392,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.22533958107233049,
|
|
"num_tokens": 27156490.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.279542064666748,
|
|
"epoch": 1.1388088376560999,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000487803488643393,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.23250271379947662,
|
|
"num_tokens": 27166727.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.233031797409057,
|
|
"epoch": 1.1392891450528337,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048779235192848166,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.22842863947153091,
|
|
"num_tokens": 27177969.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.297597980499267,
|
|
"epoch": 1.1397694524495678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004877812102731638,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.2235347256064415,
|
|
"num_tokens": 27189637.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.379896450042724,
|
|
"epoch": 1.1402497598463017,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048777006367769804,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.22346871346235275,
|
|
"num_tokens": 27201124.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.323694324493408,
|
|
"epoch": 1.1407300672430356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004877589121423432,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.2247152492403984,
|
|
"num_tokens": 27212399.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.274643898010254,
|
|
"epoch": 1.1412103746397695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004877477556673582,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.22820097357034683,
|
|
"num_tokens": 27224469.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.308396482467652,
|
|
"epoch": 1.1416906820365034,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000487736594253002,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.22925153821706773,
|
|
"num_tokens": 27236026.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.243916320800781,
|
|
"epoch": 1.1421709894332372,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048772542789953384,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.22675956636667252,
|
|
"num_tokens": 27248332.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.233785581588745,
|
|
"epoch": 1.1426512968299711,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048771425660721284,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.22579319328069686,
|
|
"num_tokens": 27258701.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.268739366531372,
|
|
"epoch": 1.143131604226705,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048770308037629853,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.22018825113773347,
|
|
"num_tokens": 27269808.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.305982875823974,
|
|
"epoch": 1.143611911623439,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004876918992070502,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.22035384327173232,
|
|
"num_tokens": 27282440.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.383598804473877,
|
|
"epoch": 1.144092219020173,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004876807130997276,
|
|
"loss": 5.0031,
|
|
"mean_token_accuracy": 0.22794283479452132,
|
|
"num_tokens": 27294430.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.333565044403076,
|
|
"epoch": 1.1445725264169069,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004876695220545903,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.22716333717107773,
|
|
"num_tokens": 27305896.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.39122200012207,
|
|
"epoch": 1.1450528338136408,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048765832607189824,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.21848920434713365,
|
|
"num_tokens": 27318195.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.23537540435791,
|
|
"epoch": 1.1455331412103746,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048764712515191136,
|
|
"loss": 4.8839,
|
|
"mean_token_accuracy": 0.21925975531339645,
|
|
"num_tokens": 27329055.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.2235136985778805,
|
|
"epoch": 1.1460134486071085,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048763591929488966,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.2313270390033722,
|
|
"num_tokens": 27340296.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.296753978729248,
|
|
"epoch": 1.1464937560038424,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004876247085010933,
|
|
"loss": 4.9244,
|
|
"mean_token_accuracy": 0.22054026126861573,
|
|
"num_tokens": 27350995.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.30924162864685,
|
|
"epoch": 1.1469740634005763,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048761349277078253,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.22072670012712478,
|
|
"num_tokens": 27362463.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.286093235015869,
|
|
"epoch": 1.1474543707973104,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048760227210421775,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.22891708761453627,
|
|
"num_tokens": 27373579.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.242615842819214,
|
|
"epoch": 1.1479346781940443,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004875910465016596,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.23427345007658004,
|
|
"num_tokens": 27383813.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.286447191238404,
|
|
"epoch": 1.1484149855907781,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004875798159633686,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.21635657995939256,
|
|
"num_tokens": 27395651.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.309388637542725,
|
|
"epoch": 1.148895292987512,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004875685804896055,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.22336858361959458,
|
|
"num_tokens": 27407827.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.292154169082641,
|
|
"epoch": 1.149375600384246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004875573400806312,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.22190959006547928,
|
|
"num_tokens": 27418777.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.349992942810059,
|
|
"epoch": 1.1498559077809798,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048754609473670654,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.21579217165708542,
|
|
"num_tokens": 27429626.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.359822463989258,
|
|
"epoch": 1.1503362151777137,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004875348444580927,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.2140723615884781,
|
|
"num_tokens": 27442304.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.296966552734375,
|
|
"epoch": 1.1508165225744476,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000487523589245051,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.23015321046113968,
|
|
"num_tokens": 27454421.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.233119487762451,
|
|
"epoch": 1.1512968299711814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004875123290978425,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.2346567317843437,
|
|
"num_tokens": 27465220.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.2676084518432615,
|
|
"epoch": 1.1517771373679155,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048750106401672876,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.2209341809153557,
|
|
"num_tokens": 27476542.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.208718776702881,
|
|
"epoch": 1.1522574447646494,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048748979400197134,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.23239563256502152,
|
|
"num_tokens": 27487721.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.283078336715699,
|
|
"epoch": 1.1527377521613833,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048747851905383183,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.2305010125041008,
|
|
"num_tokens": 27498982.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1527377521613833,
|
|
"eval_entropy": 5.076282615838314,
|
|
"eval_loss": 4.989743709564209,
|
|
"eval_mean_token_accuracy": 0.23013732650352217,
|
|
"eval_num_tokens": 27498982.0,
|
|
"eval_runtime": 20.3582,
|
|
"eval_samples_per_second": 1611.88,
|
|
"eval_steps_per_second": 201.491,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.213899278640747,
|
|
"epoch": 1.1532180595581172,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004874672391725721,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.22866705656051636,
|
|
"num_tokens": 27509863.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.243181896209717,
|
|
"epoch": 1.153698366954851,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004874559543584539,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.2223299562931061,
|
|
"num_tokens": 27521061.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.255204582214356,
|
|
"epoch": 1.154178674351585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004874446646117394,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.2245883971452713,
|
|
"num_tokens": 27532187.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.292505550384521,
|
|
"epoch": 1.154658981748319,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004874333699326906,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.22449182718992233,
|
|
"num_tokens": 27543371.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.253701829910279,
|
|
"epoch": 1.155139289145053,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004874220703215697,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.22171628773212432,
|
|
"num_tokens": 27554423.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.236413192749024,
|
|
"epoch": 1.1556195965417868,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004874107657786391,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.22681025564670562,
|
|
"num_tokens": 27566397.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.3486207008361815,
|
|
"epoch": 1.1560999039385207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048739945630416124,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.22516235560178757,
|
|
"num_tokens": 27578668.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.24963960647583,
|
|
"epoch": 1.1565802113352546,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004873881418983987,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.2148892477154732,
|
|
"num_tokens": 27589345.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.179498720169067,
|
|
"epoch": 1.1570605187319885,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004873768225616141,
|
|
"loss": 4.8204,
|
|
"mean_token_accuracy": 0.23276507705450059,
|
|
"num_tokens": 27600482.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.330718469619751,
|
|
"epoch": 1.1575408261287223,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048736549829407047,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.22195883393287658,
|
|
"num_tokens": 27611543.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.320622491836548,
|
|
"epoch": 1.1580211335254562,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004873541690960305,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.230392524600029,
|
|
"num_tokens": 27623503.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.212500286102295,
|
|
"epoch": 1.15850144092219,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004873428349677573,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.23469651639461517,
|
|
"num_tokens": 27633593.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.279120683670044,
|
|
"epoch": 1.1589817483189242,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000487331495909514,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.21967076063156127,
|
|
"num_tokens": 27646339.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.16450047492981,
|
|
"epoch": 1.159462055715658,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048732015192156383,
|
|
"loss": 4.7026,
|
|
"mean_token_accuracy": 0.24802426397800445,
|
|
"num_tokens": 27657314.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.257600784301758,
|
|
"epoch": 1.159942363112392,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048730880300417015,
|
|
"loss": 4.9236,
|
|
"mean_token_accuracy": 0.22343200743198394,
|
|
"num_tokens": 27668680.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.288353300094604,
|
|
"epoch": 1.1604226705091258,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048729744915759657,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.22471121102571487,
|
|
"num_tokens": 27679628.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.308005094528198,
|
|
"epoch": 1.1609029779058597,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048728609038210655,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.225208181142807,
|
|
"num_tokens": 27691205.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.28764967918396,
|
|
"epoch": 1.1613832853025936,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048727472667796395,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.22570321708917618,
|
|
"num_tokens": 27702903.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.326485919952392,
|
|
"epoch": 1.1618635926993275,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004872633580454325,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.20930682867765427,
|
|
"num_tokens": 27716554.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.317094373703003,
|
|
"epoch": 1.1623439000960616,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048725198448477616,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.22881208807229997,
|
|
"num_tokens": 27727931.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.301674461364746,
|
|
"epoch": 1.1628242074927955,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048724060599625893,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.2247401401400566,
|
|
"num_tokens": 27739483.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.292816925048828,
|
|
"epoch": 1.1633045148895294,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048722922258014506,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.22169628143310546,
|
|
"num_tokens": 27751157.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.383207941055298,
|
|
"epoch": 1.1637848222862632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004872178342366989,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.21847013533115386,
|
|
"num_tokens": 27762190.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.241438102722168,
|
|
"epoch": 1.1642651296829971,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048720644096618475,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.22622582763433458,
|
|
"num_tokens": 27773684.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.339538621902466,
|
|
"epoch": 1.164745437079731,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004871950427688672,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.2144733414053917,
|
|
"num_tokens": 27785388.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.24886121749878,
|
|
"epoch": 1.1652257444764649,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048718363964501087,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.23086258471012117,
|
|
"num_tokens": 27797603.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.333011484146118,
|
|
"epoch": 1.1657060518731988,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004871722315948805,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.222240874171257,
|
|
"num_tokens": 27809444.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.373708343505859,
|
|
"epoch": 1.1661863592699326,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004871608186187408,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.22020337134599685,
|
|
"num_tokens": 27820213.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.271370935440063,
|
|
"epoch": 1.1666666666666667,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048714940071685703,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.22825344502925873,
|
|
"num_tokens": 27831564.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.319097328186035,
|
|
"epoch": 1.1671469740634006,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048713797788949405,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.21939121037721634,
|
|
"num_tokens": 27843686.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.369612360000611,
|
|
"epoch": 1.1676272814601345,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048712655013691714,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.2161249354481697,
|
|
"num_tokens": 27855428.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.3798620223999025,
|
|
"epoch": 1.1681075888568684,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048711511745939165,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.21654373556375503,
|
|
"num_tokens": 27866733.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.297148704528809,
|
|
"epoch": 1.1685878962536023,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000487103679857183,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.21982619166374207,
|
|
"num_tokens": 27878639.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.239616775512696,
|
|
"epoch": 1.1690682036503361,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004870922373305567,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.22240009903907776,
|
|
"num_tokens": 27892139.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.389735889434815,
|
|
"epoch": 1.1695485110470702,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048708078987977837,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.22253280282020568,
|
|
"num_tokens": 27904395.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.341794395446778,
|
|
"epoch": 1.1700288184438041,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048706933750511394,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.22119931429624556,
|
|
"num_tokens": 27916444.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.265074825286865,
|
|
"epoch": 1.170509125840538,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004870578802068292,
|
|
"loss": 4.9292,
|
|
"mean_token_accuracy": 0.2259729653596878,
|
|
"num_tokens": 27926914.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.269755220413208,
|
|
"epoch": 1.170989433237272,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048704641798519006,
|
|
"loss": 4.8411,
|
|
"mean_token_accuracy": 0.22487289011478423,
|
|
"num_tokens": 27938203.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.325486040115356,
|
|
"epoch": 1.1714697406340058,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048703495084046286,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.22593795508146286,
|
|
"num_tokens": 27950463.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.302979564666748,
|
|
"epoch": 1.1719500480307397,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004870234787729137,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.22107742130756378,
|
|
"num_tokens": 27962312.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.258091735839844,
|
|
"epoch": 1.1724303554274735,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004870120017828089,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.23015029430389405,
|
|
"num_tokens": 27973723.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.24245982170105,
|
|
"epoch": 1.1729106628242074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000487000519870415,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.2364684149622917,
|
|
"num_tokens": 27983816.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.193110656738281,
|
|
"epoch": 1.1733909702209413,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004869890330359986,
|
|
"loss": 4.8957,
|
|
"mean_token_accuracy": 0.23184577822685243,
|
|
"num_tokens": 27996516.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.2932945728302006,
|
|
"epoch": 1.1738712776176754,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004869775412798262,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.22416026890277863,
|
|
"num_tokens": 28008256.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.231776571273803,
|
|
"epoch": 1.1743515850144093,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048696604460216476,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.24224432557821274,
|
|
"num_tokens": 28018882.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.242003965377807,
|
|
"epoch": 1.1748318924111432,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048695454300328123,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.2250194013118744,
|
|
"num_tokens": 28030399.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.279533338546753,
|
|
"epoch": 1.175312199807877,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048694303648344256,
|
|
"loss": 4.9318,
|
|
"mean_token_accuracy": 0.22823032289743422,
|
|
"num_tokens": 28041621.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.289956521987915,
|
|
"epoch": 1.175792507204611,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048693152504291595,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.22168980091810225,
|
|
"num_tokens": 28053198.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.265848016738891,
|
|
"epoch": 1.1762728146013448,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004869200086819686,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.22646988481283187,
|
|
"num_tokens": 28064095.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.271948337554932,
|
|
"epoch": 1.1767531219980787,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048690848740086796,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.21718837320804596,
|
|
"num_tokens": 28075665.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.300185012817383,
|
|
"epoch": 1.1772334293948128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004868969611998814,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.2224125862121582,
|
|
"num_tokens": 28089166.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.399428844451904,
|
|
"epoch": 1.1777137367915467,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004868854300792767,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.21735192835330963,
|
|
"num_tokens": 28101379.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.3120828628540036,
|
|
"epoch": 1.1781940441882806,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048687389403932144,
|
|
"loss": 4.9027,
|
|
"mean_token_accuracy": 0.22682823240756989,
|
|
"num_tokens": 28112836.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.32960262298584,
|
|
"epoch": 1.1786743515850144,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004868623530802835,
|
|
"loss": 5.0055,
|
|
"mean_token_accuracy": 0.2179756298661232,
|
|
"num_tokens": 28125039.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.274281787872314,
|
|
"epoch": 1.1791546589817483,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048685080720243086,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.2315664306282997,
|
|
"num_tokens": 28137504.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.286910057067871,
|
|
"epoch": 1.1796349663784822,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004868392564060315,
|
|
"loss": 4.9097,
|
|
"mean_token_accuracy": 0.22913093566894532,
|
|
"num_tokens": 28149483.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.288751888275146,
|
|
"epoch": 1.180115273775216,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004868277006913537,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.2262890800833702,
|
|
"num_tokens": 28161001.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.31149525642395,
|
|
"epoch": 1.18059558117195,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004868161400586656,
|
|
"loss": 4.9341,
|
|
"mean_token_accuracy": 0.22621139287948608,
|
|
"num_tokens": 28171146.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.355176401138306,
|
|
"epoch": 1.1810758885686838,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004868045745082357,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.21873114854097367,
|
|
"num_tokens": 28182870.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.249316930770874,
|
|
"epoch": 1.181556195965418,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004867930040403326,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.2236865520477295,
|
|
"num_tokens": 28194457.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.3589221954345705,
|
|
"epoch": 1.1820365033621518,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048678142865522475,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.2197428822517395,
|
|
"num_tokens": 28205818.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.273658227920532,
|
|
"epoch": 1.1825168107588857,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000486769848353181,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.22610000371932984,
|
|
"num_tokens": 28216124.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.2789984226226805,
|
|
"epoch": 1.1829971181556196,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048675826313447027,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.22373877763748168,
|
|
"num_tokens": 28227485.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.345300340652466,
|
|
"epoch": 1.1834774255523535,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048674667299936135,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.22025788873434066,
|
|
"num_tokens": 28239007.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.341910743713379,
|
|
"epoch": 1.1839577329490873,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048673507794812356,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.22071691304445268,
|
|
"num_tokens": 28250926.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.3584901809692385,
|
|
"epoch": 1.1844380403458212,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004867234779810259,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.22352295368909836,
|
|
"num_tokens": 28263182.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.211591005325317,
|
|
"epoch": 1.1849183477425553,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004867118730983378,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.23005927503108978,
|
|
"num_tokens": 28274666.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.1788191318511965,
|
|
"epoch": 1.1853986551392892,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004867002633003286,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.24038515985012054,
|
|
"num_tokens": 28286007.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.2520256519317625,
|
|
"epoch": 1.185878962536023,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000486688648587268,
|
|
"loss": 4.8623,
|
|
"mean_token_accuracy": 0.23420607149600983,
|
|
"num_tokens": 28298262.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.21573839187622,
|
|
"epoch": 1.186359269932757,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004866770289594256,
|
|
"loss": 4.8479,
|
|
"mean_token_accuracy": 0.22856395244598388,
|
|
"num_tokens": 28309428.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.301443386077881,
|
|
"epoch": 1.1868395773294909,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048666540441707107,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.22390749752521516,
|
|
"num_tokens": 28319609.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.334644365310669,
|
|
"epoch": 1.1873198847262247,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004866537749604744,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.21985554546117783,
|
|
"num_tokens": 28330526.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.280503654479981,
|
|
"epoch": 1.1878001921229586,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048664214058990546,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.2225042000412941,
|
|
"num_tokens": 28343919.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.371648359298706,
|
|
"epoch": 1.1882804995196925,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004866305013056346,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.22465581595897674,
|
|
"num_tokens": 28354850.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.212606477737427,
|
|
"epoch": 1.1887608069164266,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004866188571079318,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.23031488806009293,
|
|
"num_tokens": 28365699.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.158883333206177,
|
|
"epoch": 1.1892411143131605,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004866072079970676,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.2380594551563263,
|
|
"num_tokens": 28377053.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.331990432739258,
|
|
"epoch": 1.1897214217098944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048659555397331236,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.22227679938077927,
|
|
"num_tokens": 28387505.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.257408905029297,
|
|
"epoch": 1.1902017291066282,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004865838950369366,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.22374467849731444,
|
|
"num_tokens": 28399308.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.216291046142578,
|
|
"epoch": 1.1906820365033621,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048657223118821116,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.22908505648374558,
|
|
"num_tokens": 28410860.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.15766396522522,
|
|
"epoch": 1.191162343900096,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048656056242740665,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.23348231762647628,
|
|
"num_tokens": 28421867.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.288563013076782,
|
|
"epoch": 1.19164265129683,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004865488887547942,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.2269439399242401,
|
|
"num_tokens": 28433375.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.315909290313721,
|
|
"epoch": 1.192122958693564,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004865372101706446,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.22878504246473313,
|
|
"num_tokens": 28445242.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.22556209564209,
|
|
"epoch": 1.1926032660902979,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004865255266752292,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.23005042523145675,
|
|
"num_tokens": 28455904.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.292299699783325,
|
|
"epoch": 1.1930835734870318,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004865138382688191,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.22179051488637924,
|
|
"num_tokens": 28465768.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.302860164642334,
|
|
"epoch": 1.1935638808837656,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004865021449516859,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.22680420130491258,
|
|
"num_tokens": 28476489.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.288759469985962,
|
|
"epoch": 1.1940441882804995,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004864904467241008,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.234687939286232,
|
|
"num_tokens": 28487684.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.285887813568115,
|
|
"epoch": 1.1945244956772334,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048647874358633556,
|
|
"loss": 4.9022,
|
|
"mean_token_accuracy": 0.22325137555599212,
|
|
"num_tokens": 28499083.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.241272687911987,
|
|
"epoch": 1.1950048030739673,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048646703553866183,
|
|
"loss": 4.9114,
|
|
"mean_token_accuracy": 0.22717530131340027,
|
|
"num_tokens": 28510057.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.221782588958741,
|
|
"epoch": 1.1954851104707012,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004864553225813515,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.23339149802923204,
|
|
"num_tokens": 28522787.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.343481349945068,
|
|
"epoch": 1.195965417867435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004864436047146765,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.22414992600679398,
|
|
"num_tokens": 28534353.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.384238195419312,
|
|
"epoch": 1.1964457252641691,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048643188193890874,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.2151029348373413,
|
|
"num_tokens": 28546079.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.337256193161011,
|
|
"epoch": 1.196926032660903,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004864201542543206,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.21865832656621934,
|
|
"num_tokens": 28557637.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.251881504058838,
|
|
"epoch": 1.197406340057637,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004864084216611843,
|
|
"loss": 4.8898,
|
|
"mean_token_accuracy": 0.23184243589639664,
|
|
"num_tokens": 28568809.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.2851276874542235,
|
|
"epoch": 1.1978866474543708,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048639668415977207,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.22349860966205598,
|
|
"num_tokens": 28579766.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.300716781616211,
|
|
"epoch": 1.1983669548511047,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048638494175035665,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.23186599910259248,
|
|
"num_tokens": 28590898.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.235792636871338,
|
|
"epoch": 1.1988472622478386,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004863731944332105,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.22557783871889114,
|
|
"num_tokens": 28603380.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.321315908432007,
|
|
"epoch": 1.1993275696445724,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004863614422086065,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.2225848525762558,
|
|
"num_tokens": 28615509.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.322009468078614,
|
|
"epoch": 1.1998078770413065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004863496850768174,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.2238227054476738,
|
|
"num_tokens": 28627353.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.2483748435974125,
|
|
"epoch": 1.2002881844380404,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004863379230381162,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.23517177850008011,
|
|
"num_tokens": 28638217.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.265489625930786,
|
|
"epoch": 1.2007684918347743,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000486326156092776,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.22992444336414336,
|
|
"num_tokens": 28648862.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.261841821670532,
|
|
"epoch": 1.2012487992315082,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048631438424106985,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.2268499657511711,
|
|
"num_tokens": 28661561.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.313421440124512,
|
|
"epoch": 1.201729106628242,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048630260748327124,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.22231673449277878,
|
|
"num_tokens": 28674851.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.299883651733398,
|
|
"epoch": 1.202209414024976,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048629082581965355,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.22303642332553864,
|
|
"num_tokens": 28688444.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.353349494934082,
|
|
"epoch": 1.2026897214217098,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048627903925049033,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.21868470907211304,
|
|
"num_tokens": 28699374.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.26991639137268,
|
|
"epoch": 1.2031700288184437,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048626724777605507,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.22409470230340958,
|
|
"num_tokens": 28711283.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.343924045562744,
|
|
"epoch": 1.2036503362151778,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004862554513966217,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.222480645775795,
|
|
"num_tokens": 28723445.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.242320108413696,
|
|
"epoch": 1.2041306436119117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048624365011246405,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.23059036433696747,
|
|
"num_tokens": 28734505.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.197605895996094,
|
|
"epoch": 1.2046109510086456,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004862318439238561,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.2306837856769562,
|
|
"num_tokens": 28745476.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.278162908554077,
|
|
"epoch": 1.2050912584053795,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000486220032831072,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.23113964945077897,
|
|
"num_tokens": 28755645.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.267625570297241,
|
|
"epoch": 1.2055715658021133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004862082168343859,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.22473337650299072,
|
|
"num_tokens": 28767911.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.283082818984985,
|
|
"epoch": 1.2060518731988472,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004861963959340722,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.22639374285936356,
|
|
"num_tokens": 28779418.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.3485908031463625,
|
|
"epoch": 1.206532180595581,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004861845701304053,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.21961624026298524,
|
|
"num_tokens": 28790857.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.3545318126678465,
|
|
"epoch": 1.2070124879923152,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048617273942365977,
|
|
"loss": 4.9579,
|
|
"mean_token_accuracy": 0.22158015966415406,
|
|
"num_tokens": 28802975.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.300499439239502,
|
|
"epoch": 1.207492795389049,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004861609038141103,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.22851590663194657,
|
|
"num_tokens": 28813874.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.270928573608399,
|
|
"epoch": 1.207973102785783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048614906330203165,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.22868123948574065,
|
|
"num_tokens": 28826278.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.334063482284546,
|
|
"epoch": 1.2084534101825168,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004861372178876987,
|
|
"loss": 4.947,
|
|
"mean_token_accuracy": 0.22115338742733,
|
|
"num_tokens": 28838607.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.248928546905518,
|
|
"epoch": 1.2089337175792507,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048612536757138653,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2320932850241661,
|
|
"num_tokens": 28849801.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.18966064453125,
|
|
"epoch": 1.2094140249759846,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004861135123533702,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.23669253140687943,
|
|
"num_tokens": 28861312.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.252087783813477,
|
|
"epoch": 1.2098943323727185,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048610165223392503,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.22257398217916488,
|
|
"num_tokens": 28872337.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.289003229141235,
|
|
"epoch": 1.2103746397694524,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004860897872133263,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.2340528815984726,
|
|
"num_tokens": 28883263.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.283442544937134,
|
|
"epoch": 1.2108549471661862,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004860779172918496,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.22458644658327104,
|
|
"num_tokens": 28896166.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.323458290100097,
|
|
"epoch": 1.2113352545629203,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004860660424697704,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.22197462916374205,
|
|
"num_tokens": 28906928.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.383277416229248,
|
|
"epoch": 1.2118155619596542,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048605416274736434,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.21394694447517396,
|
|
"num_tokens": 28918328.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.301858425140381,
|
|
"epoch": 1.2122958693563881,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048604227812490744,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.22388734370470048,
|
|
"num_tokens": 28930327.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.2491201877594,
|
|
"epoch": 1.212776176753122,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048603038860267546,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.22794556766748428,
|
|
"num_tokens": 28942166.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.199049282073974,
|
|
"epoch": 1.2132564841498559,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004860184941809445,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.2401387169957161,
|
|
"num_tokens": 28953159.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.235630846023559,
|
|
"epoch": 1.2137367915465898,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048600659485999073,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.23363138288259505,
|
|
"num_tokens": 28963897.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.22575535774231,
|
|
"epoch": 1.2142170989433236,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048599469064009027,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.2316145196557045,
|
|
"num_tokens": 28974452.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.200207328796386,
|
|
"epoch": 1.2146974063400577,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048598278152151974,
|
|
"loss": 4.7842,
|
|
"mean_token_accuracy": 0.23332896679639817,
|
|
"num_tokens": 28984664.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.298865079879761,
|
|
"epoch": 1.2151777137367916,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004859708675045555,
|
|
"loss": 4.8647,
|
|
"mean_token_accuracy": 0.23237190395593643,
|
|
"num_tokens": 28994992.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.362056922912598,
|
|
"epoch": 1.2156580211335255,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004859589485894741,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.22350963354110717,
|
|
"num_tokens": 29006190.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.277804136276245,
|
|
"epoch": 1.2161383285302594,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004859470247765524,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.22440502494573594,
|
|
"num_tokens": 29017987.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.2218598365783695,
|
|
"epoch": 1.2166186359269933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004859350960660671,
|
|
"loss": 4.9025,
|
|
"mean_token_accuracy": 0.2233032375574112,
|
|
"num_tokens": 29030012.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.321821641921997,
|
|
"epoch": 1.2170989433237271,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004859231624582953,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.22126200050115585,
|
|
"num_tokens": 29041684.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.318899774551392,
|
|
"epoch": 1.217579250720461,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048591122395351394,
|
|
"loss": 4.8331,
|
|
"mean_token_accuracy": 0.2271633192896843,
|
|
"num_tokens": 29052525.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.2532970905303955,
|
|
"epoch": 1.218059558117195,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004858992805520003,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.2300228148698807,
|
|
"num_tokens": 29063471.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.204842472076416,
|
|
"epoch": 1.218539865513929,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048588733225403153,
|
|
"loss": 4.7993,
|
|
"mean_token_accuracy": 0.23498221784830092,
|
|
"num_tokens": 29074616.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.269283866882324,
|
|
"epoch": 1.219020172910663,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004858753790598851,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.2252691552042961,
|
|
"num_tokens": 29086603.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.2978297710418705,
|
|
"epoch": 1.2195004803073968,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004858634209698386,
|
|
"loss": 4.8779,
|
|
"mean_token_accuracy": 0.23235439658164977,
|
|
"num_tokens": 29097232.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.376942491531372,
|
|
"epoch": 1.2199807877041307,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048585145798416956,
|
|
"loss": 4.9831,
|
|
"mean_token_accuracy": 0.21972853541374207,
|
|
"num_tokens": 29107453.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.222160196304321,
|
|
"epoch": 1.2204610951008645,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004858394901031558,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.2268979713320732,
|
|
"num_tokens": 29120255.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.3283775806427,
|
|
"epoch": 1.2209414024975984,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004858275173270751,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.2257829412817955,
|
|
"num_tokens": 29130892.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.346088075637818,
|
|
"epoch": 1.2214217098943323,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048581553965620553,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.22143454551696778,
|
|
"num_tokens": 29142613.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.251632976531982,
|
|
"epoch": 1.2219020172910664,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048580355709082506,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.22718705534934996,
|
|
"num_tokens": 29153045.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.193819236755371,
|
|
"epoch": 1.2223823246878003,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000485791569631212,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.23124794512987137,
|
|
"num_tokens": 29163767.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.291526794433594,
|
|
"epoch": 1.2228626320845342,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004857795772776446,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.22369253784418106,
|
|
"num_tokens": 29174277.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.3211160659790036,
|
|
"epoch": 1.223342939481268,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048576758003040127,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.21929248422384262,
|
|
"num_tokens": 29186078.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.230485582351685,
|
|
"epoch": 1.223823246878002,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048575557788976066,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.23409243375062944,
|
|
"num_tokens": 29198056.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.382903814315796,
|
|
"epoch": 1.2243035542747358,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004857435708560013,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.21207209080457687,
|
|
"num_tokens": 29209892.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.349674081802368,
|
|
"epoch": 1.2247838616714697,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048573155892940204,
|
|
"loss": 4.9074,
|
|
"mean_token_accuracy": 0.227152718603611,
|
|
"num_tokens": 29220813.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.306207752227783,
|
|
"epoch": 1.2252641690682036,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048571954211024164,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.22248944789171218,
|
|
"num_tokens": 29232807.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.31163854598999,
|
|
"epoch": 1.2257444764649374,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048570752039879924,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.22574216425418853,
|
|
"num_tokens": 29243721.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.30392279624939,
|
|
"epoch": 1.2262247838616716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004856954937953539,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.2228822559118271,
|
|
"num_tokens": 29255783.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.256290674209595,
|
|
"epoch": 1.2267050912584054,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004856834623001848,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.23350512683391572,
|
|
"num_tokens": 29266857.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.205719423294068,
|
|
"epoch": 1.2271853986551393,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004856714259135713,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.24134122133255004,
|
|
"num_tokens": 29278479.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.328455257415771,
|
|
"epoch": 1.2276657060518732,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004856593846357929,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.22884824126958847,
|
|
"num_tokens": 29289369.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.245373630523682,
|
|
"epoch": 1.228146013448607,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004856473384671291,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.22057788968086242,
|
|
"num_tokens": 29301015.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.312074422836304,
|
|
"epoch": 1.228626320845341,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048563528740785955,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.21944900453090668,
|
|
"num_tokens": 29312638.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.312940692901611,
|
|
"epoch": 1.2291066282420748,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048562323145826414,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.22726546227931976,
|
|
"num_tokens": 29323540.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.282015132904053,
|
|
"epoch": 1.229586935638809,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004856111706186227,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.21805706918239592,
|
|
"num_tokens": 29334287.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.30173659324646,
|
|
"epoch": 1.2300672430355428,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048559910488921534,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.22153738886117935,
|
|
"num_tokens": 29345278.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.366576910018921,
|
|
"epoch": 1.2305475504322767,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000485587034270322,
|
|
"loss": 4.9322,
|
|
"mean_token_accuracy": 0.22082512974739074,
|
|
"num_tokens": 29357297.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.275426006317138,
|
|
"epoch": 1.2310278578290106,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000485574958762223,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.23419896513223648,
|
|
"num_tokens": 29368513.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.287274885177612,
|
|
"epoch": 1.2315081652257445,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048556287836519886,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.22199588567018508,
|
|
"num_tokens": 29379227.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.22232756614685,
|
|
"epoch": 1.2319884726224783,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004855507930795299,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.22781666219234467,
|
|
"num_tokens": 29390048.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.284283447265625,
|
|
"epoch": 1.2324687800192122,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048553870290549665,
|
|
"loss": 4.898,
|
|
"mean_token_accuracy": 0.22314652055501938,
|
|
"num_tokens": 29401252.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.285875034332276,
|
|
"epoch": 1.232949087415946,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048552660784338,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.22878161519765855,
|
|
"num_tokens": 29413122.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.425276803970337,
|
|
"epoch": 1.23342939481268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004855145078934606,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.22571081072092056,
|
|
"num_tokens": 29423240.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.282816314697266,
|
|
"epoch": 1.233909702209414,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004855024030560195,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.22660202234983445,
|
|
"num_tokens": 29433818.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.313459825515747,
|
|
"epoch": 1.234390009606148,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004854902933313376,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.22076904475688935,
|
|
"num_tokens": 29446927.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.318238115310669,
|
|
"epoch": 1.2348703170028819,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048547817871969607,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.2231932431459427,
|
|
"num_tokens": 29458092.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.3200963020324705,
|
|
"epoch": 1.2353506243996157,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048546605922137633,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.21735387444496154,
|
|
"num_tokens": 29470395.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.345174026489258,
|
|
"epoch": 1.2358309317963496,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004854539348366596,
|
|
"loss": 4.9468,
|
|
"mean_token_accuracy": 0.22376212924718858,
|
|
"num_tokens": 29481177.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.28560996055603,
|
|
"epoch": 1.2363112391930835,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004854418055658274,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.2268490746617317,
|
|
"num_tokens": 29492305.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.31044373512268,
|
|
"epoch": 1.2367915465898176,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048542967140916134,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.23124985098838807,
|
|
"num_tokens": 29503237.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.29931263923645,
|
|
"epoch": 1.2372718539865515,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004854175323669432,
|
|
"loss": 4.8865,
|
|
"mean_token_accuracy": 0.22539192736148833,
|
|
"num_tokens": 29514195.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.329322814941406,
|
|
"epoch": 1.2377521613832854,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004854053884394547,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.2145614057779312,
|
|
"num_tokens": 29526110.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.275633764266968,
|
|
"epoch": 1.2382324687800192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048539323962697796,
|
|
"loss": 4.8801,
|
|
"mean_token_accuracy": 0.22505635023117065,
|
|
"num_tokens": 29536912.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.3349686622619625,
|
|
"epoch": 1.2387127761767531,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004853810859297949,
|
|
"loss": 4.8914,
|
|
"mean_token_accuracy": 0.22245031148195266,
|
|
"num_tokens": 29548070.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.279468107223511,
|
|
"epoch": 1.239193083573487,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048536892734818773,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.217719267308712,
|
|
"num_tokens": 29560713.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.27452597618103,
|
|
"epoch": 1.239673390970221,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004853567638824387,
|
|
"loss": 4.8589,
|
|
"mean_token_accuracy": 0.23524908125400543,
|
|
"num_tokens": 29571269.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.339184904098511,
|
|
"epoch": 1.2401536983669548,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048534459553283026,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.22903675734996795,
|
|
"num_tokens": 29584024.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.206672286987304,
|
|
"epoch": 1.2406340057636887,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004853324222996449,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.23775954842567443,
|
|
"num_tokens": 29595679.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.305984544754028,
|
|
"epoch": 1.2411143131604228,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048532024418316525,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.23070094138383865,
|
|
"num_tokens": 29607316.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.281985712051392,
|
|
"epoch": 1.2415946205571566,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004853080611836741,
|
|
"loss": 4.8891,
|
|
"mean_token_accuracy": 0.2320896402001381,
|
|
"num_tokens": 29618929.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.348261404037475,
|
|
"epoch": 1.2420749279538905,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048529587330145427,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.2256532773375511,
|
|
"num_tokens": 29630253.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.245777320861817,
|
|
"epoch": 1.2425552353506244,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048528368053678863,
|
|
"loss": 4.8949,
|
|
"mean_token_accuracy": 0.22698078453540801,
|
|
"num_tokens": 29641676.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.2509020328521725,
|
|
"epoch": 1.2430355427473583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004852714828899604,
|
|
"loss": 4.9221,
|
|
"mean_token_accuracy": 0.22819210588932037,
|
|
"num_tokens": 29651942.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.374736738204956,
|
|
"epoch": 1.2435158501440922,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048525928036125264,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.22148187160491944,
|
|
"num_tokens": 29663094.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.2889985084533695,
|
|
"epoch": 1.243996157540826,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048524707295094884,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.22593451887369156,
|
|
"num_tokens": 29675412.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.251107311248779,
|
|
"epoch": 1.2444764649375601,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004852348606593322,
|
|
"loss": 4.8952,
|
|
"mean_token_accuracy": 0.2193370595574379,
|
|
"num_tokens": 29686684.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.242860746383667,
|
|
"epoch": 1.244956772334294,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048522264348668646,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.23706025034189224,
|
|
"num_tokens": 29697387.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.3084986209869385,
|
|
"epoch": 1.245437079731028,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004852104214332951,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.2404892012476921,
|
|
"num_tokens": 29708677.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.311293888092041,
|
|
"epoch": 1.2459173871277618,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048519819449944205,
|
|
"loss": 4.9622,
|
|
"mean_token_accuracy": 0.22139002978801728,
|
|
"num_tokens": 29720430.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.243887615203858,
|
|
"epoch": 1.2463976945244957,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000485185962685411,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.23532560616731643,
|
|
"num_tokens": 29731370.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.365581893920899,
|
|
"epoch": 1.2468780019212296,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000485173725991486,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.2150997191667557,
|
|
"num_tokens": 29743399.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.3384401321411135,
|
|
"epoch": 1.2473583093179634,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048516148441795124,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.21933296024799348,
|
|
"num_tokens": 29755693.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.315793895721436,
|
|
"epoch": 1.2478386167146973,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004851492379650908,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.22667403072118758,
|
|
"num_tokens": 29766576.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.229128837585449,
|
|
"epoch": 1.2483189241114312,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004851369866331891,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.22003341019153594,
|
|
"num_tokens": 29779255.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.237980651855469,
|
|
"epoch": 1.2487992315081653,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004851247304225306,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.23527223914861678,
|
|
"num_tokens": 29790172.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.340753126144409,
|
|
"epoch": 1.2492795389048992,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004851124693333997,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.2177285522222519,
|
|
"num_tokens": 29801206.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.375913858413696,
|
|
"epoch": 1.249759846301633,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004851002033660812,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.21840065568685532,
|
|
"num_tokens": 29813917.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.238556337356568,
|
|
"epoch": 1.250240153698367,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048508793252085994,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.23273527771234512,
|
|
"num_tokens": 29826036.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.1948158740997314,
|
|
"epoch": 1.2507204610951008,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004850756567980206,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.24163396656513214,
|
|
"num_tokens": 29837901.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.182002925872803,
|
|
"epoch": 1.2512007684918347,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048506337619784836,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.23296924084424972,
|
|
"num_tokens": 29850074.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.285552263259888,
|
|
"epoch": 1.2516810758885688,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004850510907206283,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.2238919422030449,
|
|
"num_tokens": 29862447.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.2805461406707765,
|
|
"epoch": 1.2521613832853027,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048503880036664555,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.22840482592582703,
|
|
"num_tokens": 29873483.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.2354694366455075,
|
|
"epoch": 1.2526416906820366,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004850265051361857,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.2327910393476486,
|
|
"num_tokens": 29884807.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.273411273956299,
|
|
"epoch": 1.2531219980787704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004850142050295339,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.2224018543958664,
|
|
"num_tokens": 29895994.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.28048791885376,
|
|
"epoch": 1.2536023054755043,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048500190004697595,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.22533302903175353,
|
|
"num_tokens": 29907534.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.3137696266174315,
|
|
"epoch": 1.2540826128722382,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004849895901887974,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.22645546793937682,
|
|
"num_tokens": 29919747.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.273074293136597,
|
|
"epoch": 1.254562920268972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004849772754552842,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.22883890122175216,
|
|
"num_tokens": 29930254.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.357173585891724,
|
|
"epoch": 1.255043227665706,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048496495584672214,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.22011245489120485,
|
|
"num_tokens": 29941232.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.305529594421387,
|
|
"epoch": 1.2555235350624399,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048495263136339725,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.23015487641096116,
|
|
"num_tokens": 29952452.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.30009880065918,
|
|
"epoch": 1.2560038424591737,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004849403020055956,
|
|
"loss": 4.8884,
|
|
"mean_token_accuracy": 0.2317175954580307,
|
|
"num_tokens": 29963583.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.234221172332764,
|
|
"epoch": 1.2564841498559078,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048492796777360373,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.23276158720254897,
|
|
"num_tokens": 29975186.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.242563486099243,
|
|
"epoch": 1.2569644572526417,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048491562866770767,
|
|
"loss": 4.8476,
|
|
"mean_token_accuracy": 0.23539069145917893,
|
|
"num_tokens": 29987474.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.259023284912109,
|
|
"epoch": 1.2574447646493756,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048490328468819404,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.23443285673856734,
|
|
"num_tokens": 29999254.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.303188180923462,
|
|
"epoch": 1.2579250720461095,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048489093583534945,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.2249145656824112,
|
|
"num_tokens": 30009901.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.319523525238037,
|
|
"epoch": 1.2584053794428434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004848785821094606,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.22429210394620896,
|
|
"num_tokens": 30022424.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.2345349311828615,
|
|
"epoch": 1.2588856868395775,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004848662235108142,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.2255250483751297,
|
|
"num_tokens": 30034209.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.272771883010864,
|
|
"epoch": 1.2593659942363113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004848538600396973,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.23225222676992416,
|
|
"num_tokens": 30044885.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.377711772918701,
|
|
"epoch": 1.2598463016330452,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048484149169639694,
|
|
"loss": 4.922,
|
|
"mean_token_accuracy": 0.2228950172662735,
|
|
"num_tokens": 30056592.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.384818077087402,
|
|
"epoch": 1.260326609029779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004848291184812003,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.21530148088932038,
|
|
"num_tokens": 30068423.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.299792146682739,
|
|
"epoch": 1.260806916426513,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004848167403943945,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.22784140557050706,
|
|
"num_tokens": 30079132.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.202923345565796,
|
|
"epoch": 1.2612872238232469,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048480435743626703,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.23620920479297638,
|
|
"num_tokens": 30090335.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.275820064544678,
|
|
"epoch": 1.2617675312199808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004847919696071054,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.22161888778209687,
|
|
"num_tokens": 30101781.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.265617752075196,
|
|
"epoch": 1.2622478386167146,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048477957690719716,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.23945854157209395,
|
|
"num_tokens": 30112486.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.287116956710816,
|
|
"epoch": 1.2627281460134485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004847671793368301,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.22346707433462143,
|
|
"num_tokens": 30123664.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.347845792770386,
|
|
"epoch": 1.2632084534101824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000484754776896292,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.22723597139120102,
|
|
"num_tokens": 30134139.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.2529387950897215,
|
|
"epoch": 1.2636887608069165,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004847423695858708,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.22333753108978271,
|
|
"num_tokens": 30146127.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.302427434921265,
|
|
"epoch": 1.2641690682036504,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048472995740585456,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.2239130347967148,
|
|
"num_tokens": 30158177.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.306107139587402,
|
|
"epoch": 1.2646493756003843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004847175403565316,
|
|
"loss": 4.8885,
|
|
"mean_token_accuracy": 0.22423329949378967,
|
|
"num_tokens": 30168930.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.339647531509399,
|
|
"epoch": 1.2651296829971181,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048470511843818996,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.22271023392677308,
|
|
"num_tokens": 30181206.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.322815322875977,
|
|
"epoch": 1.265609990393852,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004846926916511182,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.23166753351688385,
|
|
"num_tokens": 30193093.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.232468891143799,
|
|
"epoch": 1.266090297790586,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004846802599956048,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.23463916182518005,
|
|
"num_tokens": 30204864.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.3086216926574705,
|
|
"epoch": 1.26657060518732,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048466782347193847,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.22571448981761932,
|
|
"num_tokens": 30216312.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.351695489883423,
|
|
"epoch": 1.267050912584054,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048465538208040775,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.22061448246240617,
|
|
"num_tokens": 30227824.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.333390188217163,
|
|
"epoch": 1.2675312199807878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048464293582130166,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.22237409502267838,
|
|
"num_tokens": 30239065.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.261845541000366,
|
|
"epoch": 1.2680115273775217,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004846304846949091,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.22935133874416352,
|
|
"num_tokens": 30250684.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.27158374786377,
|
|
"epoch": 1.2684918347742555,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048461802870151916,
|
|
"loss": 4.8917,
|
|
"mean_token_accuracy": 0.2273133158683777,
|
|
"num_tokens": 30261376.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.277223825454712,
|
|
"epoch": 1.2689721421709894,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048460556784142106,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.23242881149053574,
|
|
"num_tokens": 30272441.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.249832010269165,
|
|
"epoch": 1.2694524495677233,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048459310211490406,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.23380652964115142,
|
|
"num_tokens": 30284446.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.340443801879883,
|
|
"epoch": 1.2699327569644572,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845806315222576,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.2242629885673523,
|
|
"num_tokens": 30295666.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.314307689666748,
|
|
"epoch": 1.270413064361191,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004845681560637711,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.22809236645698547,
|
|
"num_tokens": 30307663.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.326168584823608,
|
|
"epoch": 1.270893371757925,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004845556757397344,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.2191484674811363,
|
|
"num_tokens": 30318914.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.301120662689209,
|
|
"epoch": 1.271373679154659,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004845431905504372,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.2195732444524765,
|
|
"num_tokens": 30331499.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.348009395599365,
|
|
"epoch": 1.271853986551393,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048453070049616926,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.22559115141630173,
|
|
"num_tokens": 30342186.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.350795125961303,
|
|
"epoch": 1.2723342939481268,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048451820557722064,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.2216058626770973,
|
|
"num_tokens": 30353423.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.266600799560547,
|
|
"epoch": 1.2728146013448607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004845057057938815,
|
|
"loss": 4.856,
|
|
"mean_token_accuracy": 0.22971896827220917,
|
|
"num_tokens": 30365008.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.1968999862670895,
|
|
"epoch": 1.2732949087415946,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048449320114644185,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.24132516533136367,
|
|
"num_tokens": 30376589.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.2440104484558105,
|
|
"epoch": 1.2737752161383284,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004844806916351922,
|
|
"loss": 4.8758,
|
|
"mean_token_accuracy": 0.22862728089094161,
|
|
"num_tokens": 30388228.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.254297971725464,
|
|
"epoch": 1.2742555235350626,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004844681772604229,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.22595674246549607,
|
|
"num_tokens": 30400225.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.300699615478516,
|
|
"epoch": 1.2747358309317964,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048445565802242454,
|
|
"loss": 4.8836,
|
|
"mean_token_accuracy": 0.22263522148132325,
|
|
"num_tokens": 30411913.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.302100372314453,
|
|
"epoch": 1.2752161383285303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004844431339214878,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.22886559516191482,
|
|
"num_tokens": 30423891.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.340325546264649,
|
|
"epoch": 1.2756964457252642,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004844306049579034,
|
|
"loss": 4.9074,
|
|
"mean_token_accuracy": 0.2293411061167717,
|
|
"num_tokens": 30434144.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.244186305999756,
|
|
"epoch": 1.276176753121998,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048441807113196216,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.22604585587978362,
|
|
"num_tokens": 30446628.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.322153759002686,
|
|
"epoch": 1.276657060518732,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048440553244395517,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.2282743126153946,
|
|
"num_tokens": 30456885.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.345173978805542,
|
|
"epoch": 1.2771373679154658,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048439298889417357,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.2185268297791481,
|
|
"num_tokens": 30468642.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.317099285125733,
|
|
"epoch": 1.2776176753121997,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048438044048290847,
|
|
"loss": 4.8779,
|
|
"mean_token_accuracy": 0.21479855328798295,
|
|
"num_tokens": 30480393.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.266658306121826,
|
|
"epoch": 1.2780979827089336,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048436788721045135,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.2307826280593872,
|
|
"num_tokens": 30491918.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.291443109512329,
|
|
"epoch": 1.2785782901056677,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004843553290770935,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.23445792496204376,
|
|
"num_tokens": 30502250.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.238134336471558,
|
|
"epoch": 1.2790585975024016,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004843427660831266,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.22540532499551774,
|
|
"num_tokens": 30514499.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.26519742012024,
|
|
"epoch": 1.2795389048991355,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048433019822884235,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.2248773232102394,
|
|
"num_tokens": 30525133.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.219779586791992,
|
|
"epoch": 1.2800192122958693,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004843176255145325,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.23180866837501526,
|
|
"num_tokens": 30535778.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.279614639282227,
|
|
"epoch": 1.2804995196926032,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004843050479404888,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.2401960790157318,
|
|
"num_tokens": 30547711.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.199344158172607,
|
|
"epoch": 1.280979827089337,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048429246550700343,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.2323608934879303,
|
|
"num_tokens": 30558719.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.229083061218262,
|
|
"epoch": 1.2814601344860712,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004842798782143686,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.22547318041324615,
|
|
"num_tokens": 30570173.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.297634267807007,
|
|
"epoch": 1.281940441882805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048426728606287627,
|
|
"loss": 4.8719,
|
|
"mean_token_accuracy": 0.2311459943652153,
|
|
"num_tokens": 30580438.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.304043340682983,
|
|
"epoch": 1.282420749279539,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004842546890528191,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.22381553798913956,
|
|
"num_tokens": 30592191.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.259458732604981,
|
|
"epoch": 1.2829010566762729,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004842420871844893,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.22496811747550965,
|
|
"num_tokens": 30604041.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.211715936660767,
|
|
"epoch": 1.2833813640730067,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004842294804581796,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.23580067306756974,
|
|
"num_tokens": 30616087.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.2846394062042235,
|
|
"epoch": 1.2838616714697406,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048421686887418266,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.22688255757093428,
|
|
"num_tokens": 30627150.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.299831581115723,
|
|
"epoch": 1.2843419788664745,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004842042524327912,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.22966404259204865,
|
|
"num_tokens": 30638627.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.313389301300049,
|
|
"epoch": 1.2848222862632084,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004841916311342983,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.22523440420627594,
|
|
"num_tokens": 30649257.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.270278835296631,
|
|
"epoch": 1.2853025936599423,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004841790049789969,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.2321015179157257,
|
|
"num_tokens": 30659765.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.262380743026734,
|
|
"epoch": 1.2857829010566761,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048416637396718004,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.219100883603096,
|
|
"num_tokens": 30672921.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.297061395645142,
|
|
"epoch": 1.2862632084534102,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004841537380991411,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.23165907263755797,
|
|
"num_tokens": 30684994.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.321485996246338,
|
|
"epoch": 1.2867435158501441,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048414109737517346,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.22365331947803496,
|
|
"num_tokens": 30698094.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.31019778251648,
|
|
"epoch": 1.287223823246878,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004841284517955706,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.227160482108593,
|
|
"num_tokens": 30710716.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.280695867538452,
|
|
"epoch": 1.2877041306436119,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000484115801360626,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.2304807722568512,
|
|
"num_tokens": 30721910.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.259746122360229,
|
|
"epoch": 1.2881844380403458,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004841031460706335,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.23149482011795045,
|
|
"num_tokens": 30734445.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.287132930755615,
|
|
"epoch": 1.2886647454370797,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048409048592588683,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.23715678304433824,
|
|
"num_tokens": 30745131.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.276015138626098,
|
|
"epoch": 1.2891450528338138,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004840778209266799,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.23173314779996873,
|
|
"num_tokens": 30757714.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.173889636993408,
|
|
"epoch": 1.2896253602305476,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048406515107330685,
|
|
"loss": 4.844,
|
|
"mean_token_accuracy": 0.2381197839975357,
|
|
"num_tokens": 30768585.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.286986207962036,
|
|
"epoch": 1.2901056676272815,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048405247636606173,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.23146469444036483,
|
|
"num_tokens": 30779866.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.3030962467193605,
|
|
"epoch": 1.2905859750240154,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048403979680523894,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.22890648990869522,
|
|
"num_tokens": 30791252.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.326808214187622,
|
|
"epoch": 1.2910662824207493,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004840271123911328,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.23737964630126954,
|
|
"num_tokens": 30802938.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.337230777740478,
|
|
"epoch": 1.2915465898174832,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004840144231240377,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.2127877190709114,
|
|
"num_tokens": 30816382.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.314842176437378,
|
|
"epoch": 1.292026897214217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004840017290042484,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.23337081521749498,
|
|
"num_tokens": 30826402.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.2790008068084715,
|
|
"epoch": 1.292507204610951,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048398903003205957,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.2297771990299225,
|
|
"num_tokens": 30837862.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.248302555084228,
|
|
"epoch": 1.2929875120076848,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048397632620776604,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.2291993245482445,
|
|
"num_tokens": 30848351.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.222362852096557,
|
|
"epoch": 1.293467819404419,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048396361753166276,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.23203548341989516,
|
|
"num_tokens": 30858854.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.2282768249511715,
|
|
"epoch": 1.2939481268011528,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048395090400404466,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.22279109954833984,
|
|
"num_tokens": 30869977.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.376765489578247,
|
|
"epoch": 1.2944284341978867,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048393818562520715,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.22715052515268325,
|
|
"num_tokens": 30881620.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.321596288681031,
|
|
"epoch": 1.2949087415946205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048392546239544535,
|
|
"loss": 4.943,
|
|
"mean_token_accuracy": 0.2184120535850525,
|
|
"num_tokens": 30893575.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.250306749343872,
|
|
"epoch": 1.2953890489913544,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004839127343150547,
|
|
"loss": 4.8561,
|
|
"mean_token_accuracy": 0.2308366373181343,
|
|
"num_tokens": 30904489.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.333672332763672,
|
|
"epoch": 1.2958693563880883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004839000013843307,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.2268122836947441,
|
|
"num_tokens": 30915513.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.3217870712280275,
|
|
"epoch": 1.2963496637848224,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048388726360356894,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.23192450255155564,
|
|
"num_tokens": 30927633.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.3775605201721195,
|
|
"epoch": 1.2968299711815563,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004838745209730653,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.21707165241241455,
|
|
"num_tokens": 30938937.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.282814836502075,
|
|
"epoch": 1.2973102785782902,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048386177349311535,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.2259071424603462,
|
|
"num_tokens": 30950847.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.295459985733032,
|
|
"epoch": 1.297790585975024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004838490211640153,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.2285751760005951,
|
|
"num_tokens": 30962583.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.317586517333984,
|
|
"epoch": 1.298270893371758,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004838362639860611,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.22235753238201142,
|
|
"num_tokens": 30973487.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.197871398925781,
|
|
"epoch": 1.2987512007684918,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000483823501959549,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.2369787111878395,
|
|
"num_tokens": 30985176.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.293571090698242,
|
|
"epoch": 1.2992315081652257,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048381073508477527,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.22215368449687958,
|
|
"num_tokens": 30997239.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.361584329605103,
|
|
"epoch": 1.2997118155619596,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048379796336203625,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.21852207630872728,
|
|
"num_tokens": 31009381.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.284013795852661,
|
|
"epoch": 1.3001921229586935,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004837851867916286,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.2334059953689575,
|
|
"num_tokens": 31020728.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.289690780639648,
|
|
"epoch": 1.3006724303554273,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004837724053738488,
|
|
"loss": 4.9454,
|
|
"mean_token_accuracy": 0.2304823637008667,
|
|
"num_tokens": 31032933.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.299079895019531,
|
|
"epoch": 1.3011527377521614,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048375961910899373,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.22634686380624772,
|
|
"num_tokens": 31044919.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.34165506362915,
|
|
"epoch": 1.3016330451488953,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004837468279973602,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.22299737483263016,
|
|
"num_tokens": 31057140.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.271787500381469,
|
|
"epoch": 1.3021133525456292,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004837340320392451,
|
|
"loss": 4.816,
|
|
"mean_token_accuracy": 0.2292573407292366,
|
|
"num_tokens": 31068035.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.270804452896118,
|
|
"epoch": 1.302593659942363,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048372123123494563,
|
|
"loss": 4.9025,
|
|
"mean_token_accuracy": 0.22387927621603013,
|
|
"num_tokens": 31079819.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.2087853908538815,
|
|
"epoch": 1.303073967339097,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000483708425584759,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.2341977521777153,
|
|
"num_tokens": 31091272.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.307672309875488,
|
|
"epoch": 1.3035542747358309,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004836956150889825,
|
|
"loss": 4.9094,
|
|
"mean_token_accuracy": 0.22462717443704605,
|
|
"num_tokens": 31101513.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.342522621154785,
|
|
"epoch": 1.304034582132565,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004836827997479134,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.21842339485883713,
|
|
"num_tokens": 31112937.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.306411504745483,
|
|
"epoch": 1.3045148895292988,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004836699795618494,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.2270845115184784,
|
|
"num_tokens": 31123445.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.29972276687622,
|
|
"epoch": 1.3049951969260327,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004836571545310881,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.2297523647546768,
|
|
"num_tokens": 31135016.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.241649198532104,
|
|
"epoch": 1.3054755043227666,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048364432465592723,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.226303893327713,
|
|
"num_tokens": 31146772.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.268217515945435,
|
|
"epoch": 1.3059558117195005,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004836314899366647,
|
|
"loss": 4.812,
|
|
"mean_token_accuracy": 0.23610137552022933,
|
|
"num_tokens": 31157977.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.220667171478271,
|
|
"epoch": 1.3064361191162344,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048361865037359846,
|
|
"loss": 4.8325,
|
|
"mean_token_accuracy": 0.23478028923273087,
|
|
"num_tokens": 31170693.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.271761894226074,
|
|
"epoch": 1.3069164265129682,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048360580596702664,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.23004645109176636,
|
|
"num_tokens": 31181276.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.363384819030761,
|
|
"epoch": 1.3073967339097021,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048359295671724744,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.21954558193683624,
|
|
"num_tokens": 31192740.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.29459547996521,
|
|
"epoch": 1.307877041306436,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004835801026245592,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.22213852852582933,
|
|
"num_tokens": 31204075.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.327059888839722,
|
|
"epoch": 1.30835734870317,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048356724368926035,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.21406137496232985,
|
|
"num_tokens": 31215590.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.327007579803467,
|
|
"epoch": 1.308837656099904,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048355437991164937,
|
|
"loss": 4.9509,
|
|
"mean_token_accuracy": 0.21829143017530442,
|
|
"num_tokens": 31228427.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.337122821807862,
|
|
"epoch": 1.3093179634966379,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000483541511292025,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.22587185353040695,
|
|
"num_tokens": 31240348.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.353642702102661,
|
|
"epoch": 1.3097982708933718,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048352863783068594,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.22507394701242447,
|
|
"num_tokens": 31253028.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.38724799156189,
|
|
"epoch": 1.3102785782901056,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048351575952793117,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.2247902736067772,
|
|
"num_tokens": 31265242.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.285993576049805,
|
|
"epoch": 1.3107588856868395,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004835028763840595,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.2245868742465973,
|
|
"num_tokens": 31277248.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.326944875717163,
|
|
"epoch": 1.3112391930835736,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004834899883993703,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.2178810030221939,
|
|
"num_tokens": 31289631.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.203888845443726,
|
|
"epoch": 1.3117195004803075,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048347709557416263,
|
|
"loss": 4.7819,
|
|
"mean_token_accuracy": 0.24139073938131334,
|
|
"num_tokens": 31301006.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.368936777114868,
|
|
"epoch": 1.3121998078770414,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004834641979087359,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.22103772908449174,
|
|
"num_tokens": 31312621.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.330341863632202,
|
|
"epoch": 1.3126801152737753,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004834512954033894,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.22278797328472139,
|
|
"num_tokens": 31324173.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.287948322296143,
|
|
"epoch": 1.3131604226705091,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048343838805842284,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.22552861869335175,
|
|
"num_tokens": 31336872.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.332477140426636,
|
|
"epoch": 1.313640730067243,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048342547587413583,
|
|
"loss": 4.9261,
|
|
"mean_token_accuracy": 0.22281795889139175,
|
|
"num_tokens": 31348760.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.327580833435059,
|
|
"epoch": 1.314121037463977,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004834125588508282,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.22789753824472428,
|
|
"num_tokens": 31360591.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.410232830047607,
|
|
"epoch": 1.3146013448607108,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004833996369887998,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.22477337568998337,
|
|
"num_tokens": 31372273.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.284677648544312,
|
|
"epoch": 1.3150816522574447,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048338671028835063,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.2286585658788681,
|
|
"num_tokens": 31382569.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.3640632152557375,
|
|
"epoch": 1.3155619596541785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048337377874978086,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.21975779831409453,
|
|
"num_tokens": 31393913.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.260070943832398,
|
|
"epoch": 1.3160422670509127,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048336084237339067,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.23087886571884156,
|
|
"num_tokens": 31405645.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.211161804199219,
|
|
"epoch": 1.3165225744476465,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004833479011594804,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.234009812772274,
|
|
"num_tokens": 31418728.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.237175178527832,
|
|
"epoch": 1.3170028818443804,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048333495510835057,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.23652959018945693,
|
|
"num_tokens": 31430226.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.279783868789673,
|
|
"epoch": 1.3174831892411143,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048332200422030163,
|
|
"loss": 4.8364,
|
|
"mean_token_accuracy": 0.23543841540813445,
|
|
"num_tokens": 31441751.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.234709882736206,
|
|
"epoch": 1.3179634966378482,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004833090484956345,
|
|
"loss": 4.9053,
|
|
"mean_token_accuracy": 0.22799936681985855,
|
|
"num_tokens": 31455413.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.261393308639526,
|
|
"epoch": 1.318443804034582,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048329608793464966,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.24311941266059875,
|
|
"num_tokens": 31466486.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.264467716217041,
|
|
"epoch": 1.3189241114313162,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004832831225376482,
|
|
"loss": 4.8884,
|
|
"mean_token_accuracy": 0.23037912398576738,
|
|
"num_tokens": 31477048.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.319593095779419,
|
|
"epoch": 1.31940441882805,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004832701523049312,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.2244417369365692,
|
|
"num_tokens": 31488015.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.267164087295532,
|
|
"epoch": 1.319884726224784,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004832571772367997,
|
|
"loss": 4.8255,
|
|
"mean_token_accuracy": 0.2342330813407898,
|
|
"num_tokens": 31499735.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.164936256408692,
|
|
"epoch": 1.3203650336215178,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048324419733355485,
|
|
"loss": 4.6819,
|
|
"mean_token_accuracy": 0.2358386591076851,
|
|
"num_tokens": 31511970.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.302882194519043,
|
|
"epoch": 1.3208453410182517,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048323121259549805,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.23052025884389876,
|
|
"num_tokens": 31522780.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.313451433181763,
|
|
"epoch": 1.3213256484149856,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048321822302293095,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.22662624418735505,
|
|
"num_tokens": 31535578.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.372038650512695,
|
|
"epoch": 1.3218059558117194,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004832052286161549,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.2184154897928238,
|
|
"num_tokens": 31546623.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.358031511306763,
|
|
"epoch": 1.3222862632084533,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048319222937547176,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.2195260539650917,
|
|
"num_tokens": 31559334.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.32586989402771,
|
|
"epoch": 1.3227665706051872,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048317922530118323,
|
|
"loss": 4.8537,
|
|
"mean_token_accuracy": 0.23372365534305573,
|
|
"num_tokens": 31570431.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.255680942535401,
|
|
"epoch": 1.3232468780019213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004831662163935912,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.23567444384098052,
|
|
"num_tokens": 31580314.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.24572434425354,
|
|
"epoch": 1.3237271853986552,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048315320265299784,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.23685482144355774,
|
|
"num_tokens": 31592071.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.361861276626587,
|
|
"epoch": 1.324207492795389,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048314018407970516,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.22194671928882598,
|
|
"num_tokens": 31603143.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.35422191619873,
|
|
"epoch": 1.324687800192123,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048312716067401535,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.22264783680438996,
|
|
"num_tokens": 31613979.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.283797931671143,
|
|
"epoch": 1.3251681075888568,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000483114132436231,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.2307205855846405,
|
|
"num_tokens": 31625206.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.340966081619262,
|
|
"epoch": 1.3256484149855907,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004831010993666545,
|
|
"loss": 4.9479,
|
|
"mean_token_accuracy": 0.2321000173687935,
|
|
"num_tokens": 31637709.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.294027042388916,
|
|
"epoch": 1.3261287223823248,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004830880614655884,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.22225373834371567,
|
|
"num_tokens": 31648754.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.236833763122559,
|
|
"epoch": 1.3266090297790587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048307501873333527,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.23637470602989197,
|
|
"num_tokens": 31660177.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.30433464050293,
|
|
"epoch": 1.3270893371757926,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004830619711701982,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.2224350556731224,
|
|
"num_tokens": 31671467.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.341637182235718,
|
|
"epoch": 1.3275696445725265,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004830489187764799,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.23051448166370392,
|
|
"num_tokens": 31683073.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.25308747291565,
|
|
"epoch": 1.3280499519692603,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004830358615524835,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.22969947904348373,
|
|
"num_tokens": 31694661.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.193709850311279,
|
|
"epoch": 1.3285302593659942,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048302279949851215,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.22478851526975632,
|
|
"num_tokens": 31706904.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.25140609741211,
|
|
"epoch": 1.329010566762728,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048300973261486906,
|
|
"loss": 4.8413,
|
|
"mean_token_accuracy": 0.23144730180501938,
|
|
"num_tokens": 31718087.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.249017143249512,
|
|
"epoch": 1.329490874159462,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004829966609018577,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.23781906217336654,
|
|
"num_tokens": 31728960.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.323820400238037,
|
|
"epoch": 1.3299711815561959,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048298358435978146,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.22524954080581666,
|
|
"num_tokens": 31741461.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.213440656661987,
|
|
"epoch": 1.3304514889529298,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048297050298894394,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.22599694579839708,
|
|
"num_tokens": 31753582.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.239785003662109,
|
|
"epoch": 1.3309317963496639,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004829574167896489,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.23112653940916061,
|
|
"num_tokens": 31764354.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.27246356010437,
|
|
"epoch": 1.3314121037463977,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048294432576220027,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.22293347865343094,
|
|
"num_tokens": 31775860.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.288629484176636,
|
|
"epoch": 1.3318924111431316,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004829312299069017,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.23204280585050582,
|
|
"num_tokens": 31787606.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.28007869720459,
|
|
"epoch": 1.3323727185398655,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048291812922405755,
|
|
"loss": 4.8607,
|
|
"mean_token_accuracy": 0.22758687734603883,
|
|
"num_tokens": 31798601.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.261399841308593,
|
|
"epoch": 1.3328530259365994,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004829050237139717,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.23489607721567154,
|
|
"num_tokens": 31809843.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.311271667480469,
|
|
"epoch": 1.3333333333333333,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004828919133769486,
|
|
"loss": 4.9234,
|
|
"mean_token_accuracy": 0.22307837009429932,
|
|
"num_tokens": 31821309.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.319310188293457,
|
|
"epoch": 1.3338136407300674,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004828787982132926,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.23160814344882966,
|
|
"num_tokens": 31832215.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.2452006340026855,
|
|
"epoch": 1.3342939481268012,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048286567822330815,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.23767984062433242,
|
|
"num_tokens": 31843254.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.190567255020142,
|
|
"epoch": 1.3347742555235351,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004828525534072999,
|
|
"loss": 4.8255,
|
|
"mean_token_accuracy": 0.2275513619184494,
|
|
"num_tokens": 31855678.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.322296762466431,
|
|
"epoch": 1.335254562920269,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048283942376557254,
|
|
"loss": 4.916,
|
|
"mean_token_accuracy": 0.22968599796295167,
|
|
"num_tokens": 31867264.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.260318470001221,
|
|
"epoch": 1.3357348703170029,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048282628929843097,
|
|
"loss": 4.7981,
|
|
"mean_token_accuracy": 0.23529295474290848,
|
|
"num_tokens": 31878908.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.272362279891968,
|
|
"epoch": 1.3362151777137368,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048281315000617996,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.2268168330192566,
|
|
"num_tokens": 31890299.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.256171751022339,
|
|
"epoch": 1.3366954851104706,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004828000058891248,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.233488766849041,
|
|
"num_tokens": 31901279.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.31510066986084,
|
|
"epoch": 1.3371757925072045,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004827868569475706,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.23226404637098313,
|
|
"num_tokens": 31912851.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.256809377670288,
|
|
"epoch": 1.3376560999039384,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048277370318182243,
|
|
"loss": 4.8349,
|
|
"mean_token_accuracy": 0.23580387085676194,
|
|
"num_tokens": 31923479.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.285678434371948,
|
|
"epoch": 1.3381364073006723,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048276054459218596,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.22871267646551133,
|
|
"num_tokens": 31935035.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.353064393997192,
|
|
"epoch": 1.3386167146974064,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048274738117896643,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.221511635184288,
|
|
"num_tokens": 31946140.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.308857202529907,
|
|
"epoch": 1.3390970220941403,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048273421294246966,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.22493131458759308,
|
|
"num_tokens": 31957315.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.24450364112854,
|
|
"epoch": 1.3395773294908742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048272103988300134,
|
|
"loss": 4.806,
|
|
"mean_token_accuracy": 0.23285052478313445,
|
|
"num_tokens": 31967773.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.33428544998169,
|
|
"epoch": 1.340057636887608,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004827078620008672,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.22046296745538713,
|
|
"num_tokens": 31980112.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.28593602180481,
|
|
"epoch": 1.340537944284342,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048269467929637337,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.2386722296476364,
|
|
"num_tokens": 31991655.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.228332281112671,
|
|
"epoch": 1.341018251681076,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048268149176982576,
|
|
"loss": 4.8296,
|
|
"mean_token_accuracy": 0.23890599459409714,
|
|
"num_tokens": 32003551.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.1912168025970455,
|
|
"epoch": 1.34149855907781,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048266829942153055,
|
|
"loss": 4.763,
|
|
"mean_token_accuracy": 0.2331228017807007,
|
|
"num_tokens": 32015096.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.277292680740357,
|
|
"epoch": 1.3419788664745438,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048265510225179413,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.22532890737056732,
|
|
"num_tokens": 32026219.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.284398078918457,
|
|
"epoch": 1.3424591738712777,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004826419002609229,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.22561265230178834,
|
|
"num_tokens": 32037301.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.241148519515991,
|
|
"epoch": 1.3429394812680115,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048262869344922326,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.23676882535219193,
|
|
"num_tokens": 32048707.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.370438766479492,
|
|
"epoch": 1.3434197886647454,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048261548181700186,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.22086658775806428,
|
|
"num_tokens": 32061008.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.2228881359100345,
|
|
"epoch": 1.3439000960614793,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004826022653645655,
|
|
"loss": 4.7656,
|
|
"mean_token_accuracy": 0.24620358198881148,
|
|
"num_tokens": 32071360.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.228779888153076,
|
|
"epoch": 1.3443804034582132,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000482589044092221,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.22839943021535875,
|
|
"num_tokens": 32083441.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.24906735420227,
|
|
"epoch": 1.344860710854947,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048257581800027527,
|
|
"loss": 4.8805,
|
|
"mean_token_accuracy": 0.22779346704483033,
|
|
"num_tokens": 32094773.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.23834457397461,
|
|
"epoch": 1.345341018251681,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004825625870890354,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.22961954027414322,
|
|
"num_tokens": 32107076.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.42303466796875,
|
|
"epoch": 1.345821325648415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004825493513588086,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.21108204275369644,
|
|
"num_tokens": 32118781.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.282232856750488,
|
|
"epoch": 1.346301633045149,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048253611080990226,
|
|
"loss": 4.8224,
|
|
"mean_token_accuracy": 0.23346803337335587,
|
|
"num_tokens": 32130181.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.283539056777954,
|
|
"epoch": 1.3467819404418828,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004825228654426236,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.23185106217861176,
|
|
"num_tokens": 32142576.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.24665412902832,
|
|
"epoch": 1.3472622478386167,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004825096152572803,
|
|
"loss": 4.8521,
|
|
"mean_token_accuracy": 0.23700545281171798,
|
|
"num_tokens": 32152413.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.22188892364502,
|
|
"epoch": 1.3477425552353506,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048249636025417974,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.228569296002388,
|
|
"num_tokens": 32163539.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.266401100158691,
|
|
"epoch": 1.3482228626320845,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048248310043362997,
|
|
"loss": 4.8471,
|
|
"mean_token_accuracy": 0.22841058820486068,
|
|
"num_tokens": 32174662.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.2411253452301025,
|
|
"epoch": 1.3487031700288186,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004824698357959386,
|
|
"loss": 4.8467,
|
|
"mean_token_accuracy": 0.22844584435224533,
|
|
"num_tokens": 32185950.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.341646528244018,
|
|
"epoch": 1.3491834774255524,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048245656634141385,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.2313084602355957,
|
|
"num_tokens": 32198076.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.2999636173248295,
|
|
"epoch": 1.3496637848222863,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048244329207036354,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.22688691467046737,
|
|
"num_tokens": 32208739.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.35469913482666,
|
|
"epoch": 1.3501440922190202,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048243001298309604,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.2186221569776535,
|
|
"num_tokens": 32221494.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.275912857055664,
|
|
"epoch": 1.350624399615754,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048241672907991954,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.22838854193687438,
|
|
"num_tokens": 32232991.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.302502822875977,
|
|
"epoch": 1.351104707012488,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004824034403611424,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.2239799067378044,
|
|
"num_tokens": 32244022.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.252355098724365,
|
|
"epoch": 1.3515850144092219,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004823901468270733,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.22486374527215958,
|
|
"num_tokens": 32255779.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.2357605457305905,
|
|
"epoch": 1.3520653218059557,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004823768484780209,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.23418948650360108,
|
|
"num_tokens": 32267505.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.273962688446045,
|
|
"epoch": 1.3525456292026896,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048236354531429375,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.23144857585430145,
|
|
"num_tokens": 32278675.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.259935617446899,
|
|
"epoch": 1.3530259365994235,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004823502373362009,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.22919583022594453,
|
|
"num_tokens": 32289372.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.304187870025634,
|
|
"epoch": 1.3535062439961576,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004823369245440512,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.22650113999843596,
|
|
"num_tokens": 32301281.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.313820552825928,
|
|
"epoch": 1.3539865513928915,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048232360693815387,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.23197641223669052,
|
|
"num_tokens": 32312204.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.270289754867553,
|
|
"epoch": 1.3544668587896254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048231028451881786,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.2287669762969017,
|
|
"num_tokens": 32323607.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.303109502792358,
|
|
"epoch": 1.3549471661863592,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004822969572863527,
|
|
"loss": 4.8711,
|
|
"mean_token_accuracy": 0.23928057551383972,
|
|
"num_tokens": 32334864.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.243580484390259,
|
|
"epoch": 1.3554274735830931,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048228362524106776,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.22393329292535782,
|
|
"num_tokens": 32345664.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.282011461257935,
|
|
"epoch": 1.3559077809798272,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048227028838327253,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.2405575007200241,
|
|
"num_tokens": 32355727.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.249009323120117,
|
|
"epoch": 1.356388088376561,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048225694671327665,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.2395205169916153,
|
|
"num_tokens": 32367132.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.2512105941772464,
|
|
"epoch": 1.356868395773295,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004822436002313899,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.24117519557476044,
|
|
"num_tokens": 32377599.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.339269208908081,
|
|
"epoch": 1.3573487031700289,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004822302489379222,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.21826828718185426,
|
|
"num_tokens": 32389659.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.2715959548950195,
|
|
"epoch": 1.3578290105667628,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048221689283318335,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.23138606548309326,
|
|
"num_tokens": 32400573.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.322536945343018,
|
|
"epoch": 1.3583093179634966,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004822035319174837,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.23157959282398224,
|
|
"num_tokens": 32411009.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.248195028305053,
|
|
"epoch": 1.3587896253602305,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004821901661911332,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.23302590250968933,
|
|
"num_tokens": 32422489.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.233991384506226,
|
|
"epoch": 1.3592699327569644,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004821767956544423,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.23541870713233948,
|
|
"num_tokens": 32432613.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.251161766052246,
|
|
"epoch": 1.3597502401536983,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004821634203077214,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.2325788766145706,
|
|
"num_tokens": 32444556.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.285679197311401,
|
|
"epoch": 1.3602305475504322,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000482150040151281,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.23650093823671342,
|
|
"num_tokens": 32455143.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.255841493606567,
|
|
"epoch": 1.3607108549471663,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004821366551854318,
|
|
"loss": 4.8893,
|
|
"mean_token_accuracy": 0.23019080758094787,
|
|
"num_tokens": 32466966.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.214169502258301,
|
|
"epoch": 1.3611911623439001,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004821232654104845,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.2381372943520546,
|
|
"num_tokens": 32479435.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.244314765930175,
|
|
"epoch": 1.361671469740634,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048210987082675005,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.234271539747715,
|
|
"num_tokens": 32490923.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.368768405914307,
|
|
"epoch": 1.362151777137368,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048209647143453946,
|
|
"loss": 4.9001,
|
|
"mean_token_accuracy": 0.23635877817869186,
|
|
"num_tokens": 32500939.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.229743242263794,
|
|
"epoch": 1.3626320845341018,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048208306723416356,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.2387525513768196,
|
|
"num_tokens": 32513260.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.331829309463501,
|
|
"epoch": 1.3631123919308357,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004820696582259339,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.224588979780674,
|
|
"num_tokens": 32524813.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.309105300903321,
|
|
"epoch": 1.3635926993275698,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004820562444101616,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.22189621925354003,
|
|
"num_tokens": 32536904.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.231140422821045,
|
|
"epoch": 1.3640730067243036,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004820428257871581,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.23138538599014283,
|
|
"num_tokens": 32547419.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.203041315078735,
|
|
"epoch": 1.3645533141210375,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004820294023572351,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.24022648483514786,
|
|
"num_tokens": 32558644.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.265234804153442,
|
|
"epoch": 1.3650336215177714,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000482015974120704,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.23820355534553528,
|
|
"num_tokens": 32569629.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.226956415176391,
|
|
"epoch": 1.3655139289145053,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048200254107787677,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.22867552042007447,
|
|
"num_tokens": 32581850.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.3824375629425045,
|
|
"epoch": 1.3659942363112392,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048198910322906516,
|
|
"loss": 4.9551,
|
|
"mean_token_accuracy": 0.21849586814641953,
|
|
"num_tokens": 32592478.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.408511924743652,
|
|
"epoch": 1.366474543707973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048197566057458125,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.21260084211826324,
|
|
"num_tokens": 32603099.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.392895936965942,
|
|
"epoch": 1.366954851104707,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000481962213114737,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.21556312441825867,
|
|
"num_tokens": 32613415.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.267104625701904,
|
|
"epoch": 1.3674351585014408,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004819487608498448,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.2290557712316513,
|
|
"num_tokens": 32625348.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.250453996658325,
|
|
"epoch": 1.3679154658981747,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048193530378021687,
|
|
"loss": 4.8113,
|
|
"mean_token_accuracy": 0.2318305104970932,
|
|
"num_tokens": 32636878.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.3228535652160645,
|
|
"epoch": 1.3683957732949088,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048192184190616567,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.22265833467245102,
|
|
"num_tokens": 32647808.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.5003479480743405,
|
|
"epoch": 1.3688760806916427,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004819083752280037,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21311703473329544,
|
|
"num_tokens": 32659425.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.288406276702881,
|
|
"epoch": 1.3693563880883766,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048189490374604373,
|
|
"loss": 4.8679,
|
|
"mean_token_accuracy": 0.22975482791662216,
|
|
"num_tokens": 32671797.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.231360292434692,
|
|
"epoch": 1.3698366954851104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004818814274605983,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.2294129267334938,
|
|
"num_tokens": 32683506.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.332203388214111,
|
|
"epoch": 1.3703170028818443,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004818679463719805,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.2167862817645073,
|
|
"num_tokens": 32695047.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.269526195526123,
|
|
"epoch": 1.3707973102785782,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004818544604805033,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.23465178310871124,
|
|
"num_tokens": 32705433.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.297580051422119,
|
|
"epoch": 1.3712776176753123,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004818409697864798,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.22133130431175232,
|
|
"num_tokens": 32717315.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.269482278823853,
|
|
"epoch": 1.3717579250720462,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048182747429022303,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.23813296407461165,
|
|
"num_tokens": 32728817.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.328981876373291,
|
|
"epoch": 1.37223823246878,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004818139739920465,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.2252840906381607,
|
|
"num_tokens": 32741030.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.351285409927368,
|
|
"epoch": 1.372718539865514,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004818004688922637,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.2197895273566246,
|
|
"num_tokens": 32752212.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.295556545257568,
|
|
"epoch": 1.3731988472622478,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000481786958991188,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.22555726021528244,
|
|
"num_tokens": 32764581.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.283309364318848,
|
|
"epoch": 1.3736791546589817,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048177344428913316,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.22425589710474014,
|
|
"num_tokens": 32775992.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.305206060409546,
|
|
"epoch": 1.3741594620557156,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048175992478641293,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.22635285407304764,
|
|
"num_tokens": 32787164.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.2151288986206055,
|
|
"epoch": 1.3746397694524495,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004817464004833412,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.2408003106713295,
|
|
"num_tokens": 32798190.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.249113273620606,
|
|
"epoch": 1.3751200768491834,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048173287138023204,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.23890016674995423,
|
|
"num_tokens": 32809559.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.323111534118652,
|
|
"epoch": 1.3756003842459175,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004817193374773993,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.2213254004716873,
|
|
"num_tokens": 32820799.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.268077230453491,
|
|
"epoch": 1.3760806916426513,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048170579877515753,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.22888128012418746,
|
|
"num_tokens": 32833971.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.229554939270019,
|
|
"epoch": 1.3765609990393852,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004816922552738209,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.2335382580757141,
|
|
"num_tokens": 32845237.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.329076862335205,
|
|
"epoch": 1.377041306436119,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048167870697370373,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.22476319819688798,
|
|
"num_tokens": 32857960.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.23589015007019,
|
|
"epoch": 1.377521613832853,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004816651538751207,
|
|
"loss": 4.7823,
|
|
"mean_token_accuracy": 0.23540939539670944,
|
|
"num_tokens": 32868801.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.286581754684448,
|
|
"epoch": 1.3780019212295869,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048165159597838664,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.2290355980396271,
|
|
"num_tokens": 32880544.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.409329843521118,
|
|
"epoch": 1.378482228626321,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000481638033283816,
|
|
"loss": 4.9382,
|
|
"mean_token_accuracy": 0.2205681622028351,
|
|
"num_tokens": 32892179.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.386000394821167,
|
|
"epoch": 1.3789625360230549,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048162446579172387,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.23125014454126358,
|
|
"num_tokens": 32903854.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.308592844009399,
|
|
"epoch": 1.3794428434197887,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004816108935024252,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.2281137615442276,
|
|
"num_tokens": 32914731.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.206430101394654,
|
|
"epoch": 1.3799231508165226,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048159731641623507,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.2290823221206665,
|
|
"num_tokens": 32925894.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.232677555084228,
|
|
"epoch": 1.3804034582132565,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004815837345334687,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.23096399307250975,
|
|
"num_tokens": 32937463.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.378424978256225,
|
|
"epoch": 1.3808837656099904,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004815701478544415,
|
|
"loss": 4.9307,
|
|
"mean_token_accuracy": 0.2221388950943947,
|
|
"num_tokens": 32949635.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.304316759109497,
|
|
"epoch": 1.3813640730067243,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048155655637946876,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.23021723330020905,
|
|
"num_tokens": 32961043.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.321470022201538,
|
|
"epoch": 1.3818443804034581,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004815429601088662,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.23187019675970078,
|
|
"num_tokens": 32972218.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.270710515975952,
|
|
"epoch": 1.382324687800192,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004815293590429494,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.23584538251161574,
|
|
"num_tokens": 32983157.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.3315651416778564,
|
|
"epoch": 1.382804995196926,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048151575318203417,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.23347924202680587,
|
|
"num_tokens": 32994524.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.324014663696289,
|
|
"epoch": 1.38328530259366,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048150214252643637,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.22477815449237823,
|
|
"num_tokens": 33006477.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.335023832321167,
|
|
"epoch": 1.3837656099903939,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000481488527076472,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.2292187288403511,
|
|
"num_tokens": 33018067.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.3557960987091064,
|
|
"epoch": 1.3842459173871278,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004814749068324571,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.22997545450925827,
|
|
"num_tokens": 33031927.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.308238077163696,
|
|
"epoch": 1.3847262247838616,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048146128179470804,
|
|
"loss": 4.9313,
|
|
"mean_token_accuracy": 0.228590290248394,
|
|
"num_tokens": 33042516.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.271084594726562,
|
|
"epoch": 1.3852065321805955,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004814476519635411,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.23446821868419648,
|
|
"num_tokens": 33054931.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.385772228240967,
|
|
"epoch": 1.3856868395773294,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048143401733927274,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.21871936768293382,
|
|
"num_tokens": 33067333.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.312605333328247,
|
|
"epoch": 1.3861671469740635,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048142037792221943,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.23323214203119277,
|
|
"num_tokens": 33078469.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.3099383354187015,
|
|
"epoch": 1.3866474543707974,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004814067337126978,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.22582686841487884,
|
|
"num_tokens": 33089993.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.325845670700073,
|
|
"epoch": 1.3871277617675313,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004813930847110248,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.219264480471611,
|
|
"num_tokens": 33101837.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.319591045379639,
|
|
"epoch": 1.3876080691642652,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004813794309175173,
|
|
"loss": 4.8588,
|
|
"mean_token_accuracy": 0.23033579736948012,
|
|
"num_tokens": 33113036.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.250951480865479,
|
|
"epoch": 1.388088376560999,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048136577233249205,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.23147183656692505,
|
|
"num_tokens": 33124826.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.204612398147583,
|
|
"epoch": 1.388568683957733,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004813521089562666,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.24077195227146148,
|
|
"num_tokens": 33135878.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.259447956085205,
|
|
"epoch": 1.3890489913544668,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004813384407891577,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.23157328516244888,
|
|
"num_tokens": 33146938.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.288221979141236,
|
|
"epoch": 1.3895292987512007,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000481324767831483,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.22329280227422715,
|
|
"num_tokens": 33159223.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.291362524032593,
|
|
"epoch": 1.3900096061479346,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004813110900835598,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.2236812010407448,
|
|
"num_tokens": 33170235.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.280011463165283,
|
|
"epoch": 1.3904899135446687,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004812974075457058,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.23473982959985734,
|
|
"num_tokens": 33181193.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.291380786895752,
|
|
"epoch": 1.3909702209414025,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048128372021823845,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.22656660825014113,
|
|
"num_tokens": 33192505.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.276843643188476,
|
|
"epoch": 1.3914505283381364,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048127002810147574,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.2300192356109619,
|
|
"num_tokens": 33204113.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.4321756839752195,
|
|
"epoch": 1.3919308357348703,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004812563311957355,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.21253889948129653,
|
|
"num_tokens": 33216175.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.34905776977539,
|
|
"epoch": 1.3924111431316042,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004812426295013356,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.2308240920305252,
|
|
"num_tokens": 33226916.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.307059335708618,
|
|
"epoch": 1.392891450528338,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048122892301859433,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.22785025984048843,
|
|
"num_tokens": 33238020.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.299710845947265,
|
|
"epoch": 1.3933717579250722,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048121521174782983,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.23315846771001816,
|
|
"num_tokens": 33248343.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.374834394454956,
|
|
"epoch": 1.393852065321806,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048120149568936044,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.22798160910606385,
|
|
"num_tokens": 33259206.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.276068830490113,
|
|
"epoch": 1.39433237271854,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004811877748435046,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.22525516599416734,
|
|
"num_tokens": 33271020.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.260751438140869,
|
|
"epoch": 1.3948126801152738,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004811740492105809,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.2402859941124916,
|
|
"num_tokens": 33282603.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.36489462852478,
|
|
"epoch": 1.3952929875120077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000481160318790908,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.2292606070637703,
|
|
"num_tokens": 33292877.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.393796396255493,
|
|
"epoch": 1.3957732949087416,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048114658358480467,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.21945453435182571,
|
|
"num_tokens": 33304835.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.410309362411499,
|
|
"epoch": 1.3962536023054755,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048113284359258977,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.2272926762700081,
|
|
"num_tokens": 33315028.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.249249505996704,
|
|
"epoch": 1.3967339097022093,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048111909881458234,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.23231498748064042,
|
|
"num_tokens": 33325321.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.30019063949585,
|
|
"epoch": 1.3972142170989432,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048110534925110146,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.22677967101335525,
|
|
"num_tokens": 33337677.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.299238204956055,
|
|
"epoch": 1.397694524495677,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004810915949024664,
|
|
"loss": 4.8415,
|
|
"mean_token_accuracy": 0.2303346425294876,
|
|
"num_tokens": 33347613.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.285510540008545,
|
|
"epoch": 1.3981748318924112,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004810778357689965,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.23075131177902222,
|
|
"num_tokens": 33358912.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.333116865158081,
|
|
"epoch": 1.398655139289145,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048106407185101116,
|
|
"loss": 4.9817,
|
|
"mean_token_accuracy": 0.2257014513015747,
|
|
"num_tokens": 33371635.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.302935981750489,
|
|
"epoch": 1.399135446685879,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048105030314883,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.2440153792500496,
|
|
"num_tokens": 33383521.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.24767746925354,
|
|
"epoch": 1.3996157540826129,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004810365296627725,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.2288927659392357,
|
|
"num_tokens": 33395297.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.202698516845703,
|
|
"epoch": 1.4000960614793467,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004810227513931587,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.24412582218647003,
|
|
"num_tokens": 33407168.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.262039375305176,
|
|
"epoch": 1.4005763688760806,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004810089683403084,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.23078029304742814,
|
|
"num_tokens": 33418568.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.280432033538818,
|
|
"epoch": 1.4010566762728147,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004809951805045415,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.22067529559135438,
|
|
"num_tokens": 33428822.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.213821792602539,
|
|
"epoch": 1.4015369836695486,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048098138788617815,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.24073369354009627,
|
|
"num_tokens": 33441547.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.293232440948486,
|
|
"epoch": 1.4020172910662825,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004809675904855387,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.23399228900671004,
|
|
"num_tokens": 33452445.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.246175765991211,
|
|
"epoch": 1.4024975984630164,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048095378830294343,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.23206302672624587,
|
|
"num_tokens": 33463845.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.307990598678589,
|
|
"epoch": 1.4029779058597502,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048093998133871276,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.23472516983747482,
|
|
"num_tokens": 33474950.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.233728361129761,
|
|
"epoch": 1.4034582132564841,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004809261695931671,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.23447295576333999,
|
|
"num_tokens": 33486225.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.294132423400879,
|
|
"epoch": 1.403938520653218,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004809123530666273,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.2306529849767685,
|
|
"num_tokens": 33498125.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.213075256347656,
|
|
"epoch": 1.4044188280499519,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004808985317594142,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.23970939368009567,
|
|
"num_tokens": 33508731.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.277259397506714,
|
|
"epoch": 1.4048991354466858,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048088470567184854,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.2394686833024025,
|
|
"num_tokens": 33520356.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.321457719802856,
|
|
"epoch": 1.4053794428434199,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048087087480425133,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.2303534984588623,
|
|
"num_tokens": 33533179.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.169512033462524,
|
|
"epoch": 1.4058597502401537,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004808570391569437,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.2326017439365387,
|
|
"num_tokens": 33544700.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.357865905761718,
|
|
"epoch": 1.4063400576368876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048084319873024694,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.2234628140926361,
|
|
"num_tokens": 33558781.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.319727611541748,
|
|
"epoch": 1.4068203650336215,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004808293535244823,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.2345006972551346,
|
|
"num_tokens": 33569508.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.316493129730224,
|
|
"epoch": 1.4073006724303554,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004808155035399712,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.23127016574144363,
|
|
"num_tokens": 33580977.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.277981519699097,
|
|
"epoch": 1.4077809798270893,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004808016487770354,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.23048563599586486,
|
|
"num_tokens": 33593757.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.361047220230103,
|
|
"epoch": 1.4082612872238234,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048078778923599637,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.22015651762485505,
|
|
"num_tokens": 33604903.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.271301364898681,
|
|
"epoch": 1.4087415946205573,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048077392491717593,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.23945565968751908,
|
|
"num_tokens": 33616976.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.337930965423584,
|
|
"epoch": 1.4092219020172911,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048076005582089597,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.23259798735380172,
|
|
"num_tokens": 33627654.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.261020040512085,
|
|
"epoch": 1.409702209414025,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048074618194747845,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.2359254851937294,
|
|
"num_tokens": 33638377.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.298476982116699,
|
|
"epoch": 1.410182516810759,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004807323032972456,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.22941923886537552,
|
|
"num_tokens": 33650959.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.353920125961304,
|
|
"epoch": 1.4106628242074928,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004807184198705196,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.21783974319696425,
|
|
"num_tokens": 33663069.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.270303058624267,
|
|
"epoch": 1.4111431316042267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004807045316676226,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.2251239836215973,
|
|
"num_tokens": 33674868.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.248739194869995,
|
|
"epoch": 1.4116234390009605,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004806906386888773,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.22903505116701126,
|
|
"num_tokens": 33685482.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.291160202026367,
|
|
"epoch": 1.4121037463976944,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048067674093460607,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.22898110002279282,
|
|
"num_tokens": 33697518.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.321464538574219,
|
|
"epoch": 1.4125840537944283,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048066283840513175,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.22844946533441543,
|
|
"num_tokens": 33708827.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.28525185585022,
|
|
"epoch": 1.4130643611911624,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004806489311007769,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.22561291307210923,
|
|
"num_tokens": 33719452.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.329116916656494,
|
|
"epoch": 1.4135446685878963,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048063501902186463,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.2308429256081581,
|
|
"num_tokens": 33730630.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.26832857131958,
|
|
"epoch": 1.4140249759846302,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048062110216871775,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.239089173078537,
|
|
"num_tokens": 33742696.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.291332197189331,
|
|
"epoch": 1.414505283381364,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048060718054165945,
|
|
"loss": 4.8587,
|
|
"mean_token_accuracy": 0.23524873852729797,
|
|
"num_tokens": 33753818.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.381168031692505,
|
|
"epoch": 1.414985590778098,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000480593254141013,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.22263559252023696,
|
|
"num_tokens": 33766847.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.331195878982544,
|
|
"epoch": 1.4154658981748318,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048057932296710165,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.22950732856988906,
|
|
"num_tokens": 33777070.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.307909345626831,
|
|
"epoch": 1.415946205571566,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004805653870202489,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.2352450504899025,
|
|
"num_tokens": 33788826.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.248942041397095,
|
|
"epoch": 1.4164265129682998,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048055144630077825,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.23205181658267976,
|
|
"num_tokens": 33801564.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.303957557678222,
|
|
"epoch": 1.4169068203650337,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048053750080901336,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.23239743560552598,
|
|
"num_tokens": 33813389.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.262201452255249,
|
|
"epoch": 1.4173871277617676,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048052355054527794,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.22541129291057588,
|
|
"num_tokens": 33824585.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.35182294845581,
|
|
"epoch": 1.4178674351585014,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048050959550989606,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.22750388085842133,
|
|
"num_tokens": 33837995.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.288938522338867,
|
|
"epoch": 1.4183477425552353,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004804956357031916,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.23956688195466996,
|
|
"num_tokens": 33848849.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.267833042144775,
|
|
"epoch": 1.4188280499519692,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048048167112548873,
|
|
"loss": 4.8284,
|
|
"mean_token_accuracy": 0.2378850519657135,
|
|
"num_tokens": 33859711.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.32486138343811,
|
|
"epoch": 1.419308357348703,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048046770177711157,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.22436279207468032,
|
|
"num_tokens": 33872613.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.225239229202271,
|
|
"epoch": 1.419788664745437,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004804537276583844,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.23746151030063628,
|
|
"num_tokens": 33883759.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.295125484466553,
|
|
"epoch": 1.420268972142171,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004804397487696319,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.23527446240186692,
|
|
"num_tokens": 33894448.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.376807498931885,
|
|
"epoch": 1.420749279538905,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004804257651111783,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.22703338414430618,
|
|
"num_tokens": 33906976.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.313551425933838,
|
|
"epoch": 1.4212295869356388,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048041177668334853,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.22828034162521363,
|
|
"num_tokens": 33919384.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.272687864303589,
|
|
"epoch": 1.4217098943323727,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004803977834864672,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.23434606492519378,
|
|
"num_tokens": 33931080.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.266438245773315,
|
|
"epoch": 1.4221902017291066,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048038378552085927,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.2319291651248932,
|
|
"num_tokens": 33943021.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.305624151229859,
|
|
"epoch": 1.4226705091258405,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048036978278684974,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.23084961175918578,
|
|
"num_tokens": 33953609.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.309899854660034,
|
|
"epoch": 1.4231508165225746,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004803557752847636,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.22725344598293304,
|
|
"num_tokens": 33966985.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.322706127166748,
|
|
"epoch": 1.4236311239193085,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048034176301492616,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.23540655970573426,
|
|
"num_tokens": 33976536.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.299081802368164,
|
|
"epoch": 1.4241114313160423,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004803277459776628,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.22966450899839402,
|
|
"num_tokens": 33988000.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.333430576324463,
|
|
"epoch": 1.4245917387127762,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048031372417329875,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.22813379913568496,
|
|
"num_tokens": 33998944.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.36594820022583,
|
|
"epoch": 1.42507204610951,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004802996976021598,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.23190574049949647,
|
|
"num_tokens": 34010440.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.329521512985229,
|
|
"epoch": 1.425552353506244,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048028566626457145,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.23077847063541412,
|
|
"num_tokens": 34023222.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.248945426940918,
|
|
"epoch": 1.4260326609029779,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048027163016085947,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.23556418418884278,
|
|
"num_tokens": 34035413.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.286364984512329,
|
|
"epoch": 1.4265129682997117,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048025758929134976,
|
|
"loss": 4.8736,
|
|
"mean_token_accuracy": 0.2299775391817093,
|
|
"num_tokens": 34046700.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.291650581359863,
|
|
"epoch": 1.4269932756964456,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004802435436563684,
|
|
"loss": 4.8672,
|
|
"mean_token_accuracy": 0.23308432549238206,
|
|
"num_tokens": 34058039.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.317603826522827,
|
|
"epoch": 1.4274735830931795,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048022949325624134,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.2259013369679451,
|
|
"num_tokens": 34069602.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.368908452987671,
|
|
"epoch": 1.4279538904899136,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048021543809129483,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.22293349355459213,
|
|
"num_tokens": 34080514.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.272464990615845,
|
|
"epoch": 1.4284341978866475,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004802013781618552,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.23298212438821791,
|
|
"num_tokens": 34091416.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.294010305404663,
|
|
"epoch": 1.4289145052833814,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048018731346824895,
|
|
"loss": 4.849,
|
|
"mean_token_accuracy": 0.2284226045012474,
|
|
"num_tokens": 34102153.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.345822334289551,
|
|
"epoch": 1.4293948126801153,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004801732440108026,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.2321384310722351,
|
|
"num_tokens": 34111917.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.325803661346436,
|
|
"epoch": 1.4298751200768491,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004801591697898427,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.22585595399141312,
|
|
"num_tokens": 34124038.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.363279819488525,
|
|
"epoch": 1.430355427473583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004801450908056961,
|
|
"loss": 4.9436,
|
|
"mean_token_accuracy": 0.2269161194562912,
|
|
"num_tokens": 34134503.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.225108098983765,
|
|
"epoch": 1.4308357348703171,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004801310070586896,
|
|
"loss": 4.7695,
|
|
"mean_token_accuracy": 0.23093787878751754,
|
|
"num_tokens": 34146145.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.2943947315216064,
|
|
"epoch": 1.431316042267051,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004801169185491503,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.23103205114603043,
|
|
"num_tokens": 34156672.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.317024374008179,
|
|
"epoch": 1.4317963496637849,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048010282527740516,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.21998953819274902,
|
|
"num_tokens": 34168817.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.30555214881897,
|
|
"epoch": 1.4322766570605188,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048008872724378146,
|
|
"loss": 4.8382,
|
|
"mean_token_accuracy": 0.2385418638586998,
|
|
"num_tokens": 34179804.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.435409021377564,
|
|
"epoch": 1.4327569644572526,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004800746244486065,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.21270764917135238,
|
|
"num_tokens": 34192293.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.374172687530518,
|
|
"epoch": 1.4332372718539865,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004800605168922077,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.22714117616415025,
|
|
"num_tokens": 34203331.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.3247278213500975,
|
|
"epoch": 1.4337175792507204,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048004640457491267,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.22871071249246597,
|
|
"num_tokens": 34213554.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.2559130668640135,
|
|
"epoch": 1.4341978866474543,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000480032287497049,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.23580200374126434,
|
|
"num_tokens": 34225824.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.281751441955566,
|
|
"epoch": 1.4346781940441882,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048001816565894427,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.2310378760099411,
|
|
"num_tokens": 34237479.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.309472942352295,
|
|
"epoch": 1.435158501440922,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004800040390609267,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.22416912466287614,
|
|
"num_tokens": 34248706.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.422905731201172,
|
|
"epoch": 1.4356388088376562,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047998990770332396,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.2292816236615181,
|
|
"num_tokens": 34258957.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.294883584976196,
|
|
"epoch": 1.43611911623439,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004799757715864643,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.22865601480007172,
|
|
"num_tokens": 34270635.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.349995422363281,
|
|
"epoch": 1.436599423631124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004799616307106759,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.23302433043718337,
|
|
"num_tokens": 34282491.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.308272457122802,
|
|
"epoch": 1.4370797310278578,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000479947485076287,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.23539260625839234,
|
|
"num_tokens": 34294666.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.274190950393677,
|
|
"epoch": 1.4375600384245917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047993333468362607,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.23427844941616058,
|
|
"num_tokens": 34305065.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.358624410629273,
|
|
"epoch": 1.4380403458213258,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047991917953302173,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.22201366424560548,
|
|
"num_tokens": 34315955.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.256867980957031,
|
|
"epoch": 1.4385206532180597,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047990501962480236,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.2338082119822502,
|
|
"num_tokens": 34327011.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.2386657238006595,
|
|
"epoch": 1.4390009606147935,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000479890854959297,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.23089877367019654,
|
|
"num_tokens": 34338011.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.272846841812134,
|
|
"epoch": 1.4394812680115274,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004798766855368344,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.2401675194501877,
|
|
"num_tokens": 34348957.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.254907321929932,
|
|
"epoch": 1.4399615754082613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047986251135774343,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.2315062865614891,
|
|
"num_tokens": 34359442.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.273412132263184,
|
|
"epoch": 1.4404418828049952,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004798483324223533,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.23255077004432678,
|
|
"num_tokens": 34371129.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.2647865295410154,
|
|
"epoch": 1.440922190201729,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004798341487309932,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.2353270560503006,
|
|
"num_tokens": 34381565.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.440922190201729,
|
|
"eval_entropy": 5.0992762972702925,
|
|
"eval_loss": 4.927521705627441,
|
|
"eval_mean_token_accuracy": 0.23593334462684373,
|
|
"eval_num_tokens": 34381565.0,
|
|
"eval_runtime": 20.5989,
|
|
"eval_samples_per_second": 1593.044,
|
|
"eval_steps_per_second": 199.137,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.312543869018555,
|
|
"epoch": 1.441402497598463,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047981996028399233,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.23783516734838486,
|
|
"num_tokens": 34392145.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.312717580795288,
|
|
"epoch": 1.4418828049951968,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004798057670816802,
|
|
"loss": 4.9382,
|
|
"mean_token_accuracy": 0.22248364090919495,
|
|
"num_tokens": 34403193.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.237011241912842,
|
|
"epoch": 1.4423631123919307,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004797915691243863,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.22698803544044494,
|
|
"num_tokens": 34414289.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.378029441833496,
|
|
"epoch": 1.4428434197886648,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004797773664124403,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.2238407775759697,
|
|
"num_tokens": 34424439.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.214139366149903,
|
|
"epoch": 1.4433237271853987,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047976315894617195,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.23276933431625366,
|
|
"num_tokens": 34437299.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.24204387664795,
|
|
"epoch": 1.4438040345821326,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000479748946725911,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.2460225224494934,
|
|
"num_tokens": 34448397.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.243703413009643,
|
|
"epoch": 1.4442843419788665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004797347297519875,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.23377222567796707,
|
|
"num_tokens": 34459389.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.330431127548218,
|
|
"epoch": 1.4447646493756003,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047972050802473154,
|
|
"loss": 4.8778,
|
|
"mean_token_accuracy": 0.23219251334667207,
|
|
"num_tokens": 34470610.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.185707044601441,
|
|
"epoch": 1.4452449567723342,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004797062815444733,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.23478201925754547,
|
|
"num_tokens": 34482100.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.251016569137573,
|
|
"epoch": 1.4457252641690683,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000479692050311543,
|
|
"loss": 4.8588,
|
|
"mean_token_accuracy": 0.2215760201215744,
|
|
"num_tokens": 34493086.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.22499361038208,
|
|
"epoch": 1.4462055715658022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004796778143262711,
|
|
"loss": 4.7766,
|
|
"mean_token_accuracy": 0.24327786564826964,
|
|
"num_tokens": 34505030.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.319513607025146,
|
|
"epoch": 1.446685878962536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004796635735889882,
|
|
"loss": 4.9507,
|
|
"mean_token_accuracy": 0.22045567333698274,
|
|
"num_tokens": 34516790.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.3796735286712645,
|
|
"epoch": 1.44716618635927,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047964932810002476,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.22323225140571595,
|
|
"num_tokens": 34530333.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.296913385391235,
|
|
"epoch": 1.4476464937560038,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004796350778597117,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.2378691926598549,
|
|
"num_tokens": 34540945.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.362420177459716,
|
|
"epoch": 1.4481268011527377,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004796208228683796,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.2292117014527321,
|
|
"num_tokens": 34551449.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.277546501159668,
|
|
"epoch": 1.4486071085494716,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047960656312635977,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.2274739071726799,
|
|
"num_tokens": 34562841.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.284660959243775,
|
|
"epoch": 1.4490874159462055,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004795922986339831,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.23250235766172409,
|
|
"num_tokens": 34574408.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.337628316879273,
|
|
"epoch": 1.4495677233429394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047957802939158057,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.23142256140708922,
|
|
"num_tokens": 34586243.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.311780023574829,
|
|
"epoch": 1.4500480307396733,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004795637553994838,
|
|
"loss": 4.8597,
|
|
"mean_token_accuracy": 0.2327668085694313,
|
|
"num_tokens": 34596631.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.275566530227661,
|
|
"epoch": 1.4505283381364074,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047954947665802404,
|
|
"loss": 4.8139,
|
|
"mean_token_accuracy": 0.23989165127277373,
|
|
"num_tokens": 34607952.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.229511642456055,
|
|
"epoch": 1.4510086455331412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004795351931675329,
|
|
"loss": 4.7617,
|
|
"mean_token_accuracy": 0.24085824936628342,
|
|
"num_tokens": 34618355.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.249600791931153,
|
|
"epoch": 1.4514889529298751,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004795209049283419,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.23053434640169143,
|
|
"num_tokens": 34629402.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.3902629852294925,
|
|
"epoch": 1.451969260326609,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795066119407827,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.22719368189573289,
|
|
"num_tokens": 34642523.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.244619226455688,
|
|
"epoch": 1.4524495677233429,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004794923142051873,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.24192884415388108,
|
|
"num_tokens": 34653714.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.20252571105957,
|
|
"epoch": 1.452929875120077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047947801172188755,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.231999933719635,
|
|
"num_tokens": 34664899.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.349028205871582,
|
|
"epoch": 1.4534101825168109,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004794637044912155,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.22824462950229646,
|
|
"num_tokens": 34674888.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.2613725662231445,
|
|
"epoch": 1.4538904899135447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004794493925135034,
|
|
"loss": 4.7747,
|
|
"mean_token_accuracy": 0.24439068883657455,
|
|
"num_tokens": 34686446.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.326886320114136,
|
|
"epoch": 1.4543707973102786,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047943507578908357,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.2326458215713501,
|
|
"num_tokens": 34697592.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.295575094223023,
|
|
"epoch": 1.4548511047070125,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004794207543182883,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.22895009070634842,
|
|
"num_tokens": 34709305.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.3281543254852295,
|
|
"epoch": 1.4553314121037464,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047940642810145005,
|
|
"loss": 4.9061,
|
|
"mean_token_accuracy": 0.22993949800729752,
|
|
"num_tokens": 34721606.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.2910112857818605,
|
|
"epoch": 1.4558117195004803,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047939209713890156,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.23535388708114624,
|
|
"num_tokens": 34732125.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.238086414337158,
|
|
"epoch": 1.4562920268972142,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047937776143097547,
|
|
"loss": 4.8325,
|
|
"mean_token_accuracy": 0.22951911836862565,
|
|
"num_tokens": 34743317.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.2394784450531,
|
|
"epoch": 1.456772334293948,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004793634209780047,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.22641302943229674,
|
|
"num_tokens": 34754546.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.289898300170899,
|
|
"epoch": 1.457252641690682,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004793490757803221,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.23605655431747435,
|
|
"num_tokens": 34766027.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.31829309463501,
|
|
"epoch": 1.457732949087416,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047933472583826063,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.22983877807855607,
|
|
"num_tokens": 34777750.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.3111754894256595,
|
|
"epoch": 1.45821325648415,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004793203711521537,
|
|
"loss": 4.8888,
|
|
"mean_token_accuracy": 0.2342851623892784,
|
|
"num_tokens": 34788924.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.301740121841431,
|
|
"epoch": 1.4586935638808838,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047930601172233446,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.23600803017616273,
|
|
"num_tokens": 34800153.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.269999551773071,
|
|
"epoch": 1.4591738712776177,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047929164754913624,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.22790223956108094,
|
|
"num_tokens": 34811597.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.276542234420776,
|
|
"epoch": 1.4596541786743515,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004792772786328926,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.24159185886383056,
|
|
"num_tokens": 34822661.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.38875789642334,
|
|
"epoch": 1.4601344860710854,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047926290497393714,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.2268211916089058,
|
|
"num_tokens": 34833554.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.2933214664459225,
|
|
"epoch": 1.4606147934678195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004792485265726036,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.23481793105602264,
|
|
"num_tokens": 34846060.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.300823307037353,
|
|
"epoch": 1.4610951008645534,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004792341434292257,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.23330025523900985,
|
|
"num_tokens": 34857324.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.271159029006958,
|
|
"epoch": 1.4615754082612873,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004792197555441374,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.24566709995269775,
|
|
"num_tokens": 34869317.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.269768381118775,
|
|
"epoch": 1.4620557156580212,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004792053629176729,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.23217301368713378,
|
|
"num_tokens": 34880961.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.275739526748657,
|
|
"epoch": 1.462536023054755,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004791909655501662,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.23509399294853212,
|
|
"num_tokens": 34893518.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.324521923065186,
|
|
"epoch": 1.463016330451489,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004791765634419516,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2323857679963112,
|
|
"num_tokens": 34906201.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.308222341537475,
|
|
"epoch": 1.4634966378482228,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047916215659336343,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.23363053500652314,
|
|
"num_tokens": 34916841.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.3378394603729244,
|
|
"epoch": 1.4639769452449567,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004791477450047363,
|
|
"loss": 4.9423,
|
|
"mean_token_accuracy": 0.22186322808265685,
|
|
"num_tokens": 34928081.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.301794338226318,
|
|
"epoch": 1.4644572526416906,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047913332867640464,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.23227926194667817,
|
|
"num_tokens": 34939072.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.306238079071045,
|
|
"epoch": 1.4649375600384245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004791189076087033,
|
|
"loss": 4.8672,
|
|
"mean_token_accuracy": 0.2278971180319786,
|
|
"num_tokens": 34950898.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.397992134094238,
|
|
"epoch": 1.4654178674351586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047910448180196703,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.22830625474452973,
|
|
"num_tokens": 34961560.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.304385757446289,
|
|
"epoch": 1.4658981748318924,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004790900512565307,
|
|
"loss": 4.8864,
|
|
"mean_token_accuracy": 0.2351197451353073,
|
|
"num_tokens": 34973604.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.3087160110473635,
|
|
"epoch": 1.4663784822286263,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004790756159727294,
|
|
"loss": 4.9276,
|
|
"mean_token_accuracy": 0.22352074682712555,
|
|
"num_tokens": 34985369.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.414991283416748,
|
|
"epoch": 1.4668587896253602,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047906117595089835,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.22142387926578522,
|
|
"num_tokens": 34996746.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.292376327514648,
|
|
"epoch": 1.467339097022094,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004790467311913727,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.23350519835948944,
|
|
"num_tokens": 35008032.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.27772216796875,
|
|
"epoch": 1.4678194044188282,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004790322816944879,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.22990301847457886,
|
|
"num_tokens": 35019423.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.270286130905151,
|
|
"epoch": 1.468299711815562,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004790178274605793,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.24085628241300583,
|
|
"num_tokens": 35029985.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.378909969329834,
|
|
"epoch": 1.468780019212296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047900336848998254,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.23323570489883422,
|
|
"num_tokens": 35040580.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.323962259292602,
|
|
"epoch": 1.4692603266090298,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004789889047830334,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.23529486805200578,
|
|
"num_tokens": 35051414.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.27393798828125,
|
|
"epoch": 1.4697406340057637,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047897443634006766,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.2337924376130104,
|
|
"num_tokens": 35062483.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.312983608245849,
|
|
"epoch": 1.4702209414024976,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004789599631614211,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.2336376816034317,
|
|
"num_tokens": 35073536.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.330859184265137,
|
|
"epoch": 1.4707012487992315,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004789454852474298,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.22664361745119094,
|
|
"num_tokens": 35085636.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.291753768920898,
|
|
"epoch": 1.4711815561959654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004789310025984299,
|
|
"loss": 4.8283,
|
|
"mean_token_accuracy": 0.2277284875512123,
|
|
"num_tokens": 35096660.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.321732044219971,
|
|
"epoch": 1.4716618635926992,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047891651521475776,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.2253354609012604,
|
|
"num_tokens": 35109657.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.300340270996093,
|
|
"epoch": 1.4721421709894331,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047890202309674963,
|
|
"loss": 4.7867,
|
|
"mean_token_accuracy": 0.2289949893951416,
|
|
"num_tokens": 35120399.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.264930057525635,
|
|
"epoch": 1.4726224783861672,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047888752624474195,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.23857136964797973,
|
|
"num_tokens": 35130105.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.216929006576538,
|
|
"epoch": 1.473102785782901,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004788730246590714,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.23731542527675628,
|
|
"num_tokens": 35142547.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.249352693557739,
|
|
"epoch": 1.473583093179635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047885851834007456,
|
|
"loss": 4.7533,
|
|
"mean_token_accuracy": 0.2403828889131546,
|
|
"num_tokens": 35154603.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.284165716171264,
|
|
"epoch": 1.4740634005763689,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047884400728808824,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.23530466854572296,
|
|
"num_tokens": 35165727.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.257764101028442,
|
|
"epoch": 1.4745437079731027,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004788294915034494,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.22907171547412872,
|
|
"num_tokens": 35177642.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.268581485748291,
|
|
"epoch": 1.4750240153698366,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000478814970986495,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.2390742376446724,
|
|
"num_tokens": 35189377.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.287290859222412,
|
|
"epoch": 1.4755043227665707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047880044573756213,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.23268509209156035,
|
|
"num_tokens": 35201244.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.29988842010498,
|
|
"epoch": 1.4759846301633046,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047878591575698816,
|
|
"loss": 4.8398,
|
|
"mean_token_accuracy": 0.24167200475931166,
|
|
"num_tokens": 35212491.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.24768033027649,
|
|
"epoch": 1.4764649375600385,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004787713810451103,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.23075882643461226,
|
|
"num_tokens": 35225552.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.2463240146636965,
|
|
"epoch": 1.4769452449567724,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047875684160226606,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.23798478692770003,
|
|
"num_tokens": 35237961.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.267462253570557,
|
|
"epoch": 1.4774255523535063,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000478742297428793,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.23253741413354873,
|
|
"num_tokens": 35249502.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.3194215297698975,
|
|
"epoch": 1.4779058597502401,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047872774852502877,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.23033515959978104,
|
|
"num_tokens": 35262978.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.361565732955933,
|
|
"epoch": 1.478386167146974,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004787131948913112,
|
|
"loss": 4.9513,
|
|
"mean_token_accuracy": 0.23036439269781112,
|
|
"num_tokens": 35273289.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.320690774917603,
|
|
"epoch": 1.478866474543708,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047869863652797806,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.2283661261200905,
|
|
"num_tokens": 35283827.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.349998712539673,
|
|
"epoch": 1.4793467819404418,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004786840734353675,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.23321111500263214,
|
|
"num_tokens": 35293264.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.275122022628784,
|
|
"epoch": 1.4798270893371757,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047866950561381756,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.2333392471075058,
|
|
"num_tokens": 35304380.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.239330291748047,
|
|
"epoch": 1.4803073967339098,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004786549330636665,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.23879213333129884,
|
|
"num_tokens": 35316805.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.266374683380127,
|
|
"epoch": 1.4807877041306436,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047864035578525256,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.22830595672130585,
|
|
"num_tokens": 35328645.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.2660058498382565,
|
|
"epoch": 1.4812680115273775,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004786257737789143,
|
|
"loss": 4.8434,
|
|
"mean_token_accuracy": 0.23213723301887512,
|
|
"num_tokens": 35339983.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.387819242477417,
|
|
"epoch": 1.4817483189241114,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004786111870449902,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.22103267312049865,
|
|
"num_tokens": 35350720.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.329033708572387,
|
|
"epoch": 1.4822286263208453,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047859659558381894,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.22708055824041368,
|
|
"num_tokens": 35361435.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.295695877075195,
|
|
"epoch": 1.4827089337175792,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047858199939573935,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.22537657916545867,
|
|
"num_tokens": 35372829.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.326714420318604,
|
|
"epoch": 1.4831892411143133,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047856739848109014,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.23137360960245132,
|
|
"num_tokens": 35383270.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.403406429290771,
|
|
"epoch": 1.4836695485110472,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047855279284021046,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.22417293936014177,
|
|
"num_tokens": 35396308.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.2896710395812985,
|
|
"epoch": 1.484149855907781,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047853818247343933,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.23580022752285004,
|
|
"num_tokens": 35408944.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.332905006408692,
|
|
"epoch": 1.484630163304515,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047852356738111606,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.2209497570991516,
|
|
"num_tokens": 35422227.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.334182167053223,
|
|
"epoch": 1.4851104707012488,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004785089475635799,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.22398222237825394,
|
|
"num_tokens": 35434110.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.327423143386841,
|
|
"epoch": 1.4855907780979827,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047849432302117024,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.23519299924373627,
|
|
"num_tokens": 35445194.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.376470947265625,
|
|
"epoch": 1.4860710854947166,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047847969375422656,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.23571797758340834,
|
|
"num_tokens": 35455953.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.287313175201416,
|
|
"epoch": 1.4865513928914504,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004784650597630887,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.2374580219388008,
|
|
"num_tokens": 35466932.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.242569398880005,
|
|
"epoch": 1.4870317002881843,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047845042104809635,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.23464161902666092,
|
|
"num_tokens": 35477755.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.249139308929443,
|
|
"epoch": 1.4875120076849184,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004784357776095892,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.23817242234945296,
|
|
"num_tokens": 35489913.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.303370618820191,
|
|
"epoch": 1.4879923150816523,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004784211294479075,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.2331164747476578,
|
|
"num_tokens": 35500314.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.396001195907592,
|
|
"epoch": 1.4884726224783862,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004784064765633912,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.2187351331114769,
|
|
"num_tokens": 35514717.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.292451238632202,
|
|
"epoch": 1.48895292987512,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047839181895638057,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.2333967238664627,
|
|
"num_tokens": 35526122.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.272830963134766,
|
|
"epoch": 1.489433237271854,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047837715662721575,
|
|
"loss": 4.8722,
|
|
"mean_token_accuracy": 0.22474659830331803,
|
|
"num_tokens": 35538270.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.387707614898682,
|
|
"epoch": 1.4899135446685878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004783624895762372,
|
|
"loss": 4.9448,
|
|
"mean_token_accuracy": 0.22472756952047349,
|
|
"num_tokens": 35549598.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.34476375579834,
|
|
"epoch": 1.490393852065322,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047834781780378563,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.23243311941623687,
|
|
"num_tokens": 35559623.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.295139312744141,
|
|
"epoch": 1.4908741594620558,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004783331413102015,
|
|
"loss": 4.8376,
|
|
"mean_token_accuracy": 0.2336409792304039,
|
|
"num_tokens": 35571578.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.300051736831665,
|
|
"epoch": 1.4913544668587897,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047831846009582557,
|
|
"loss": 4.9048,
|
|
"mean_token_accuracy": 0.2279307633638382,
|
|
"num_tokens": 35583570.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.318568134307862,
|
|
"epoch": 1.4918347742555236,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004783037741609988,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.22934223264455794,
|
|
"num_tokens": 35595360.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.2764698505401615,
|
|
"epoch": 1.4923150816522575,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004782890835060621,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.2300932824611664,
|
|
"num_tokens": 35607326.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.356933164596557,
|
|
"epoch": 1.4927953890489913,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004782743881313564,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.22920414805412292,
|
|
"num_tokens": 35618504.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.277383708953858,
|
|
"epoch": 1.4932756964457252,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047825968803722315,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.23649007827043533,
|
|
"num_tokens": 35631111.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.299050569534302,
|
|
"epoch": 1.493756003842459,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004782449832240035,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.2329176887869835,
|
|
"num_tokens": 35643434.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.381638622283935,
|
|
"epoch": 1.494236311239193,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004782302736920387,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.22687426209449768,
|
|
"num_tokens": 35654531.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.321961069107056,
|
|
"epoch": 1.4947166186359269,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004782155594416705,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.2344045966863632,
|
|
"num_tokens": 35665488.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.314302206039429,
|
|
"epoch": 1.495196926032661,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047820084047324045,
|
|
"loss": 4.9117,
|
|
"mean_token_accuracy": 0.2227581948041916,
|
|
"num_tokens": 35677110.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.374086046218872,
|
|
"epoch": 1.4956772334293948,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047818611678709027,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.22745931446552276,
|
|
"num_tokens": 35688694.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.287300109863281,
|
|
"epoch": 1.4961575408261287,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004781713883835618,
|
|
"loss": 4.8537,
|
|
"mean_token_accuracy": 0.23311122357845307,
|
|
"num_tokens": 35699497.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.367317247390747,
|
|
"epoch": 1.4966378482228626,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047815665526299695,
|
|
"loss": 4.8894,
|
|
"mean_token_accuracy": 0.23066503703594207,
|
|
"num_tokens": 35711034.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.27130389213562,
|
|
"epoch": 1.4971181556195965,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004781419174257378,
|
|
"loss": 4.8227,
|
|
"mean_token_accuracy": 0.23645153939723967,
|
|
"num_tokens": 35721804.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.242462778091431,
|
|
"epoch": 1.4975984630163304,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004781271748721266,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.23825213313102722,
|
|
"num_tokens": 35732897.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.156380558013916,
|
|
"epoch": 1.4980787704130645,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004781124276025055,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.24663252681493758,
|
|
"num_tokens": 35743792.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.319638061523437,
|
|
"epoch": 1.4985590778097984,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000478097675617217,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.22521654069423674,
|
|
"num_tokens": 35754659.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.357067680358886,
|
|
"epoch": 1.4990393852065322,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047808291891660357,
|
|
"loss": 4.878,
|
|
"mean_token_accuracy": 0.23699617236852646,
|
|
"num_tokens": 35766269.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.324287033081054,
|
|
"epoch": 1.4995196926032661,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047806815750100774,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.23178330063819885,
|
|
"num_tokens": 35777634.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.316570281982422,
|
|
"epoch": 1.5,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004780533913707723,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.23129383027553557,
|
|
"num_tokens": 35788689.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.299579238891601,
|
|
"epoch": 1.5004803073967339,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047803862052624006,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.23791473954916,
|
|
"num_tokens": 35799365.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.257741022109985,
|
|
"epoch": 1.5009606147934678,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047802384496775397,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.2374805063009262,
|
|
"num_tokens": 35810682.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.3094367504119875,
|
|
"epoch": 1.5014409221902016,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004780090646956571,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.22757837176322937,
|
|
"num_tokens": 35822193.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.266992998123169,
|
|
"epoch": 1.5019212295869355,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047799427971029245,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.23070555925369263,
|
|
"num_tokens": 35835486.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.33390736579895,
|
|
"epoch": 1.5024015369836694,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004779794900120034,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.22841998636722566,
|
|
"num_tokens": 35846245.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.3570763111114506,
|
|
"epoch": 1.5028818443804035,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004779646956011334,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.23079439699649812,
|
|
"num_tokens": 35857914.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.355497360229492,
|
|
"epoch": 1.5033621517771374,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047794989647802574,
|
|
"loss": 4.8796,
|
|
"mean_token_accuracy": 0.22647291123867036,
|
|
"num_tokens": 35870235.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.317256498336792,
|
|
"epoch": 1.5038424591738713,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047793509264302424,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.22313896119594573,
|
|
"num_tokens": 35882154.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.2858642578125,
|
|
"epoch": 1.5043227665706052,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047792028409647237,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.24137395322322847,
|
|
"num_tokens": 35894192.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.33257646560669,
|
|
"epoch": 1.5048030739673393,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047790547083871414,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.2290818676352501,
|
|
"num_tokens": 35906017.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.343887805938721,
|
|
"epoch": 1.5052833813640731,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047789065287009335,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.22418413907289506,
|
|
"num_tokens": 35917671.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.191481494903565,
|
|
"epoch": 1.505763688760807,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004778758301909542,
|
|
"loss": 4.7986,
|
|
"mean_token_accuracy": 0.2381480425596237,
|
|
"num_tokens": 35928421.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.36408543586731,
|
|
"epoch": 1.506243996157541,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004778610028016405,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.22347050309181213,
|
|
"num_tokens": 35939689.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.3692827224731445,
|
|
"epoch": 1.5067243035542748,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004778461707024967,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.2264258787035942,
|
|
"num_tokens": 35952342.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.458053398132324,
|
|
"epoch": 1.5072046109510087,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004778313338938672,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.21351457238197327,
|
|
"num_tokens": 35964726.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.335521936416626,
|
|
"epoch": 1.5076849183477425,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047781649237609643,
|
|
"loss": 4.8355,
|
|
"mean_token_accuracy": 0.24036585539579391,
|
|
"num_tokens": 35976932.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.208167934417725,
|
|
"epoch": 1.5081652257444764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004778016461495289,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.23511285930871964,
|
|
"num_tokens": 35988371.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.216825675964356,
|
|
"epoch": 1.5086455331412103,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004777867952145094,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.24414088129997252,
|
|
"num_tokens": 36001310.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.391431856155395,
|
|
"epoch": 1.5091258405379442,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004777719395713826,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.21931854486465455,
|
|
"num_tokens": 36011975.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.321526765823364,
|
|
"epoch": 1.509606147934678,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047775707922049354,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.22342558354139327,
|
|
"num_tokens": 36024987.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.2979155540466305,
|
|
"epoch": 1.510086455331412,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004777422141621871,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.23239705413579942,
|
|
"num_tokens": 36036003.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.350589323043823,
|
|
"epoch": 1.510566762728146,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004777273443968085,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.2262003943324089,
|
|
"num_tokens": 36047948.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.275156879425049,
|
|
"epoch": 1.51104707012488,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004777124699247029,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.2388824388384819,
|
|
"num_tokens": 36059197.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.38087043762207,
|
|
"epoch": 1.5115273775216138,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004776975907462157,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.22684673815965653,
|
|
"num_tokens": 36072167.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.431838655471802,
|
|
"epoch": 1.5120076849183477,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004776827068616924,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.22165147066116334,
|
|
"num_tokens": 36083805.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.252172660827637,
|
|
"epoch": 1.5124879923150818,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004776678182714785,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.2385775163769722,
|
|
"num_tokens": 36095450.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.255028104782104,
|
|
"epoch": 1.5129682997118157,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047765292497591955,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.24202008843421935,
|
|
"num_tokens": 36106319.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.2359575748443605,
|
|
"epoch": 1.5134486071085496,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047763802697536146,
|
|
"loss": 4.6848,
|
|
"mean_token_accuracy": 0.24708511978387832,
|
|
"num_tokens": 36117015.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.273720836639404,
|
|
"epoch": 1.5139289145052834,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047762312427015015,
|
|
"loss": 4.8587,
|
|
"mean_token_accuracy": 0.22630208283662795,
|
|
"num_tokens": 36127308.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.225775289535522,
|
|
"epoch": 1.5144092219020173,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047760821686063153,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.23904190361499786,
|
|
"num_tokens": 36139811.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.364750528335572,
|
|
"epoch": 1.5148895292987512,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047759330474715173,
|
|
"loss": 4.8874,
|
|
"mean_token_accuracy": 0.22948714792728425,
|
|
"num_tokens": 36151330.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.271615886688233,
|
|
"epoch": 1.515369836695485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047757838793005704,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.2311893329024315,
|
|
"num_tokens": 36162436.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.400334405899048,
|
|
"epoch": 1.515850144092219,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047756346640969366,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.2131258189678192,
|
|
"num_tokens": 36175642.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.273558902740478,
|
|
"epoch": 1.5163304514889528,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047754854018640803,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.23493409603834153,
|
|
"num_tokens": 36186925.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.289919662475586,
|
|
"epoch": 1.5168107588856867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047753360926054684,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.2228931650519371,
|
|
"num_tokens": 36199280.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.2627030372619625,
|
|
"epoch": 1.5172910662824206,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047751867363245653,
|
|
"loss": 4.7888,
|
|
"mean_token_accuracy": 0.23883871883153915,
|
|
"num_tokens": 36210276.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.3797026634216305,
|
|
"epoch": 1.5177713736791547,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004775037333024841,
|
|
"loss": 4.8797,
|
|
"mean_token_accuracy": 0.23246933817863463,
|
|
"num_tokens": 36221211.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.241886377334595,
|
|
"epoch": 1.5182516810758886,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004774887882709762,
|
|
"loss": 4.7466,
|
|
"mean_token_accuracy": 0.23952676206827164,
|
|
"num_tokens": 36233465.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.24563627243042,
|
|
"epoch": 1.5187319884726225,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047747383853827995,
|
|
"loss": 4.8053,
|
|
"mean_token_accuracy": 0.236426705121994,
|
|
"num_tokens": 36245594.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.3441102504730225,
|
|
"epoch": 1.5192122958693564,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004774588841047424,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.22616782188415527,
|
|
"num_tokens": 36257776.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.303483724594116,
|
|
"epoch": 1.5196926032660905,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004774439249707108,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.22480264604091643,
|
|
"num_tokens": 36269056.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.278879642486572,
|
|
"epoch": 1.5201729106628243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004774289611365323,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.2290485143661499,
|
|
"num_tokens": 36280700.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.333908176422119,
|
|
"epoch": 1.5206532180595582,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047741399260255434,
|
|
"loss": 4.8996,
|
|
"mean_token_accuracy": 0.22798043936491014,
|
|
"num_tokens": 36291708.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.303629779815674,
|
|
"epoch": 1.521133525456292,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047739901936912467,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.23165204823017121,
|
|
"num_tokens": 36303830.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.271772480010986,
|
|
"epoch": 1.521613832853026,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004773840414365907,
|
|
"loss": 4.8347,
|
|
"mean_token_accuracy": 0.22957141250371932,
|
|
"num_tokens": 36316514.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.370714378356934,
|
|
"epoch": 1.5220941402497599,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047736905880530026,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.22955637127161027,
|
|
"num_tokens": 36328234.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.288986301422119,
|
|
"epoch": 1.5225744476464937,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004773540714756012,
|
|
"loss": 4.8433,
|
|
"mean_token_accuracy": 0.2366768941283226,
|
|
"num_tokens": 36340383.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.271821308135986,
|
|
"epoch": 1.5230547550432276,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047733907944784144,
|
|
"loss": 4.8249,
|
|
"mean_token_accuracy": 0.2349734425544739,
|
|
"num_tokens": 36351970.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.2607330799102785,
|
|
"epoch": 1.5235350624399615,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004773240827223691,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.23831689357757568,
|
|
"num_tokens": 36363163.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.334766054153443,
|
|
"epoch": 1.5240153698366954,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004773090812995323,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.22810457795858383,
|
|
"num_tokens": 36375079.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.348368072509766,
|
|
"epoch": 1.5244956772334293,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047729407517967945,
|
|
"loss": 4.8165,
|
|
"mean_token_accuracy": 0.23758147954940795,
|
|
"num_tokens": 36386402.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.230117130279541,
|
|
"epoch": 1.5249759846301632,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047727906436315884,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.24143534451723098,
|
|
"num_tokens": 36397973.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.297537469863892,
|
|
"epoch": 1.5254562920268973,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047726404885031895,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.22421104907989503,
|
|
"num_tokens": 36409941.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.371477460861206,
|
|
"epoch": 1.5259365994236311,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047724902864150845,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.23122090697288514,
|
|
"num_tokens": 36420609.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.31944465637207,
|
|
"epoch": 1.526416906820365,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047723400373707607,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.24054422229528427,
|
|
"num_tokens": 36430854.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.194965505599976,
|
|
"epoch": 1.526897214217099,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004772189741373707,
|
|
"loss": 4.7579,
|
|
"mean_token_accuracy": 0.23692538142204284,
|
|
"num_tokens": 36442225.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.43298373222351,
|
|
"epoch": 1.527377521613833,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047720393984274117,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.22856481820344926,
|
|
"num_tokens": 36454488.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.330136919021607,
|
|
"epoch": 1.5278578290105669,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047718890085353654,
|
|
"loss": 4.8024,
|
|
"mean_token_accuracy": 0.23705534636974335,
|
|
"num_tokens": 36466197.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.3460160255432125,
|
|
"epoch": 1.5283381364073008,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000477173857170106,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.2262958511710167,
|
|
"num_tokens": 36478159.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.321772193908691,
|
|
"epoch": 1.5288184438040346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047715880879279894,
|
|
"loss": 4.9639,
|
|
"mean_token_accuracy": 0.22722824066877365,
|
|
"num_tokens": 36489621.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.338768339157104,
|
|
"epoch": 1.5292987512007685,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004771437557219646,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.22727920711040497,
|
|
"num_tokens": 36500629.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.356277894973755,
|
|
"epoch": 1.5297790585975024,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004771286979579524,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.23016535341739655,
|
|
"num_tokens": 36512110.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.273930883407592,
|
|
"epoch": 1.5302593659942363,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004771136355011121,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.24108897447586058,
|
|
"num_tokens": 36522499.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.303047180175781,
|
|
"epoch": 1.5307396733909702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047709856835179333,
|
|
"loss": 4.8952,
|
|
"mean_token_accuracy": 0.22442609518766404,
|
|
"num_tokens": 36533465.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.270796537399292,
|
|
"epoch": 1.531219980787704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047708349651034586,
|
|
"loss": 4.8345,
|
|
"mean_token_accuracy": 0.2303313910961151,
|
|
"num_tokens": 36545213.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.2370500564575195,
|
|
"epoch": 1.531700288184438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047706841997711974,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.2420397311449051,
|
|
"num_tokens": 36555656.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.291012573242187,
|
|
"epoch": 1.5321805955811718,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047705333875246495,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.22359175831079484,
|
|
"num_tokens": 36568027.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.264713096618652,
|
|
"epoch": 1.532660902977906,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047703825283673153,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.23256594240665435,
|
|
"num_tokens": 36579434.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.290767335891724,
|
|
"epoch": 1.5331412103746398,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004770231622302699,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.229158653318882,
|
|
"num_tokens": 36591068.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.30859489440918,
|
|
"epoch": 1.5336215177713737,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047700806693343016,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.23279626667499542,
|
|
"num_tokens": 36603013.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.361087894439697,
|
|
"epoch": 1.5341018251681076,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047699296694656316,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.22024546265602113,
|
|
"num_tokens": 36614565.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.264503288269043,
|
|
"epoch": 1.5345821325648417,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004769778622700192,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.2348505437374115,
|
|
"num_tokens": 36625685.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.199333524703979,
|
|
"epoch": 1.5350624399615755,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047696275290414885,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.23305382281541825,
|
|
"num_tokens": 36637278.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.251479816436768,
|
|
"epoch": 1.5355427473583094,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047694763884930324,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.227245931327343,
|
|
"num_tokens": 36649527.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.354219818115235,
|
|
"epoch": 1.5360230547550433,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047693252010583314,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.22815122753381728,
|
|
"num_tokens": 36660653.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.281329202651977,
|
|
"epoch": 1.5365033621517772,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004769173966740895,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.23592999577522278,
|
|
"num_tokens": 36672340.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.356746625900269,
|
|
"epoch": 1.536983669548511,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047690226855442346,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.22091226279735565,
|
|
"num_tokens": 36684468.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.307340955734253,
|
|
"epoch": 1.537463976945245,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004768871357471863,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.22866492569446564,
|
|
"num_tokens": 36695921.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.214216995239258,
|
|
"epoch": 1.5379442843419788,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047687199825272936,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.23439928591251374,
|
|
"num_tokens": 36707029.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.1887187480926515,
|
|
"epoch": 1.5384245917387127,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047685685607140403,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.24190615713596345,
|
|
"num_tokens": 36717899.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.279611015319825,
|
|
"epoch": 1.5389048991354466,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047684170920356185,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.22544503211975098,
|
|
"num_tokens": 36728691.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.327029657363892,
|
|
"epoch": 1.5393852065321805,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004768265576495546,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.22451414912939072,
|
|
"num_tokens": 36741122.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.3372739315032955,
|
|
"epoch": 1.5398655139289144,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047681140140973396,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.2256816118955612,
|
|
"num_tokens": 36752841.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.339261674880982,
|
|
"epoch": 1.5403458213256485,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004767962404844517,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.2359511137008667,
|
|
"num_tokens": 36763030.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.347400808334351,
|
|
"epoch": 1.5408261287223823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047678107487406015,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.22411470115184784,
|
|
"num_tokens": 36774442.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.308273029327393,
|
|
"epoch": 1.5413064361191162,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047676590457891116,
|
|
"loss": 4.8646,
|
|
"mean_token_accuracy": 0.22941686511039733,
|
|
"num_tokens": 36785650.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.261161518096924,
|
|
"epoch": 1.54178674351585,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004767507295993569,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.2332385241985321,
|
|
"num_tokens": 36797021.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.301163291931152,
|
|
"epoch": 1.5422670509125842,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004767355499357498,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.23535131365060807,
|
|
"num_tokens": 36807593.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.222672986984253,
|
|
"epoch": 1.542747358309318,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004767203655884423,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.23263099640607834,
|
|
"num_tokens": 36820185.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.235772371292114,
|
|
"epoch": 1.543227665706052,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004767051765577869,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.23961517214775085,
|
|
"num_tokens": 36831350.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.236897373199463,
|
|
"epoch": 1.5437079731027858,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047668998284413624,
|
|
"loss": 4.7345,
|
|
"mean_token_accuracy": 0.24079789072275162,
|
|
"num_tokens": 36842475.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.289089345932007,
|
|
"epoch": 1.5441882804995197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047667478444784306,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.23937571942806243,
|
|
"num_tokens": 36853385.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.234102725982666,
|
|
"epoch": 1.5446685878962536,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004766595813692602,
|
|
"loss": 4.8364,
|
|
"mean_token_accuracy": 0.2300464019179344,
|
|
"num_tokens": 36866339.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.314409065246582,
|
|
"epoch": 1.5451488952929875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047664437360874076,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.22917718887329103,
|
|
"num_tokens": 36877943.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.348731136322021,
|
|
"epoch": 1.5456292026897214,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047662916116663766,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.23287905305624007,
|
|
"num_tokens": 36889343.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.35634970664978,
|
|
"epoch": 1.5461095100864553,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047661394404330417,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.2318858578801155,
|
|
"num_tokens": 36900727.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.255250120162964,
|
|
"epoch": 1.5465898174831891,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047659872223909357,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.24044122844934462,
|
|
"num_tokens": 36911959.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.2365213394165036,
|
|
"epoch": 1.547070124879923,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004765834957543592,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.24004640877246858,
|
|
"num_tokens": 36924964.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.337001895904541,
|
|
"epoch": 1.547550432276657,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047656826458945475,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.21880113929510117,
|
|
"num_tokens": 36937033.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.301459264755249,
|
|
"epoch": 1.548030739673391,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047655302874473365,
|
|
"loss": 4.8063,
|
|
"mean_token_accuracy": 0.2349682033061981,
|
|
"num_tokens": 36948745.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.260270595550537,
|
|
"epoch": 1.5485110470701249,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004765377882205498,
|
|
"loss": 4.7562,
|
|
"mean_token_accuracy": 0.24231980592012406,
|
|
"num_tokens": 36961210.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.295747852325439,
|
|
"epoch": 1.5489913544668588,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004765225430172568,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.2326668009161949,
|
|
"num_tokens": 36973720.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.331075620651245,
|
|
"epoch": 1.5494716618635929,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004765072931352089,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.2319372698664665,
|
|
"num_tokens": 36986899.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.2789037227630615,
|
|
"epoch": 1.5499519692603267,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047649203857476,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.22847786843776702,
|
|
"num_tokens": 36998324.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.333527946472168,
|
|
"epoch": 1.5504322766570606,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047647677933626423,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.24026728123426438,
|
|
"num_tokens": 37009779.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.312811231613159,
|
|
"epoch": 1.5509125840537945,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047646151542007583,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.23364238888025285,
|
|
"num_tokens": 37022473.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.3996435642242435,
|
|
"epoch": 1.5513928914505284,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004764462468265494,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.2251835435628891,
|
|
"num_tokens": 37033456.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.338018083572388,
|
|
"epoch": 1.5518731988472623,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047643097355603913,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.22524084895849228,
|
|
"num_tokens": 37044983.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.302085828781128,
|
|
"epoch": 1.5523535062439962,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004764156956088999,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.23481125235557557,
|
|
"num_tokens": 37055992.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.324284315109253,
|
|
"epoch": 1.55283381364073,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004764004129854863,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.242535363137722,
|
|
"num_tokens": 37068227.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.292761659622192,
|
|
"epoch": 1.553314121037464,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047638512568615307,
|
|
"loss": 4.8818,
|
|
"mean_token_accuracy": 0.2263217344880104,
|
|
"num_tokens": 37080221.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.312381267547607,
|
|
"epoch": 1.5537944284341978,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004763698337112553,
|
|
"loss": 4.8517,
|
|
"mean_token_accuracy": 0.23051768839359282,
|
|
"num_tokens": 37092223.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.359284687042236,
|
|
"epoch": 1.5542747358309317,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004763545370611479,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.22549313455820083,
|
|
"num_tokens": 37104169.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.333751153945923,
|
|
"epoch": 1.5547550432276656,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047633923573618605,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.23081786632537843,
|
|
"num_tokens": 37115784.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.238654518127442,
|
|
"epoch": 1.5552353506243997,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000476323929736725,
|
|
"loss": 4.751,
|
|
"mean_token_accuracy": 0.23736601769924165,
|
|
"num_tokens": 37128018.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.305949735641479,
|
|
"epoch": 1.5557156580211335,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047630861906312004,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.22531356662511826,
|
|
"num_tokens": 37139330.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.209201526641846,
|
|
"epoch": 1.5561959654178674,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004762933037157268,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.24468899071216582,
|
|
"num_tokens": 37151531.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.366598510742188,
|
|
"epoch": 1.5566762728146013,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047627798369490076,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.22821409553289412,
|
|
"num_tokens": 37162442.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.302083301544189,
|
|
"epoch": 1.5571565802113354,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047626265900099757,
|
|
"loss": 4.8503,
|
|
"mean_token_accuracy": 0.2346849963068962,
|
|
"num_tokens": 37173737.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.219818496704102,
|
|
"epoch": 1.5576368876080693,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047624732963437314,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.23141918033361436,
|
|
"num_tokens": 37185983.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.340652894973755,
|
|
"epoch": 1.5581171950048032,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047623199559538324,
|
|
"loss": 4.9305,
|
|
"mean_token_accuracy": 0.22142349183559418,
|
|
"num_tokens": 37197119.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.477076292037964,
|
|
"epoch": 1.558597502401537,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000476216656884384,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.22583778500556945,
|
|
"num_tokens": 37209516.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.247388601303101,
|
|
"epoch": 1.559077809798271,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047620131350173135,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.23434314578771592,
|
|
"num_tokens": 37220559.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.333163833618164,
|
|
"epoch": 1.5595581171950048,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004761859654477817,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.23237013965845107,
|
|
"num_tokens": 37232232.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.245142841339112,
|
|
"epoch": 1.5600384245917387,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004761706127228914,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.23963506817817687,
|
|
"num_tokens": 37242819.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.33214373588562,
|
|
"epoch": 1.5605187319884726,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004761552553274168,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.23247638195753098,
|
|
"num_tokens": 37254940.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.336606502532959,
|
|
"epoch": 1.5609990393852065,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004761398932617144,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.22583602517843246,
|
|
"num_tokens": 37266220.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.348699522018433,
|
|
"epoch": 1.5614793467819403,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000476124526526141,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.2301702544093132,
|
|
"num_tokens": 37278136.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.339818811416626,
|
|
"epoch": 1.5619596541786742,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047610915512105327,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.22906616926193238,
|
|
"num_tokens": 37290358.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.402225399017334,
|
|
"epoch": 1.562439961575408,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004760937790468082,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.23538867831230165,
|
|
"num_tokens": 37300719.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.297584533691406,
|
|
"epoch": 1.5629202689721422,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004760783983037627,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.22721051424741745,
|
|
"num_tokens": 37311917.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.2691301822662355,
|
|
"epoch": 1.563400576368876,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004760630128922738,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.23727723062038422,
|
|
"num_tokens": 37325076.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.3392256736755375,
|
|
"epoch": 1.56388088376561,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004760476228126989,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.22878246009349823,
|
|
"num_tokens": 37336064.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.343370580673218,
|
|
"epoch": 1.5643611911623438,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004760322280653951,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.22716845124959945,
|
|
"num_tokens": 37347343.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.289535188674927,
|
|
"epoch": 1.564841498559078,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004760168286507199,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.24112166166305543,
|
|
"num_tokens": 37359067.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.334271240234375,
|
|
"epoch": 1.5653218059558118,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047600142456903085,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.23381167203187941,
|
|
"num_tokens": 37369811.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.227087020874023,
|
|
"epoch": 1.5658021133525457,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047598601582068555,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.24656683206558228,
|
|
"num_tokens": 37380944.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.314517402648926,
|
|
"epoch": 1.5662824207492796,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004759706024060418,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.22082749307155608,
|
|
"num_tokens": 37392099.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.26843638420105,
|
|
"epoch": 1.5667627281460135,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004759551843254575,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.23598048239946365,
|
|
"num_tokens": 37404254.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.273187971115112,
|
|
"epoch": 1.5672430355427474,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047593976157929034,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.24033963978290557,
|
|
"num_tokens": 37416112.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.2655823707580565,
|
|
"epoch": 1.5677233429394812,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004759243341678987,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.23352222740650178,
|
|
"num_tokens": 37428350.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.317991590499878,
|
|
"epoch": 1.5682036503362151,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004759089020916407,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.2387154296040535,
|
|
"num_tokens": 37440059.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.341684484481812,
|
|
"epoch": 1.568683957732949,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047589346535087444,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.22758761793375015,
|
|
"num_tokens": 37450880.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.286712741851806,
|
|
"epoch": 1.5691642651296829,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004758780239459586,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.2397177889943123,
|
|
"num_tokens": 37463484.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.332979297637939,
|
|
"epoch": 1.5696445725264168,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004758625778772514,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.23183574080467223,
|
|
"num_tokens": 37474952.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.339502906799316,
|
|
"epoch": 1.5701248799231509,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047584712714511166,
|
|
"loss": 4.9394,
|
|
"mean_token_accuracy": 0.2297532543540001,
|
|
"num_tokens": 37486858.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.30346188545227,
|
|
"epoch": 1.5706051873198847,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047583167174989797,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.23483210057020187,
|
|
"num_tokens": 37497852.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.32085280418396,
|
|
"epoch": 1.5710854947166186,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004758162116919692,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.22637958824634552,
|
|
"num_tokens": 37509051.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.36832971572876,
|
|
"epoch": 1.5715658021133525,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047580074697168434,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.23157298266887666,
|
|
"num_tokens": 37520415.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.3283697128295895,
|
|
"epoch": 1.5720461095100866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047578527758940236,
|
|
"loss": 4.8861,
|
|
"mean_token_accuracy": 0.23128714114427568,
|
|
"num_tokens": 37532087.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.352901601791382,
|
|
"epoch": 1.5725264169068205,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004757698035454825,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.22897535860538482,
|
|
"num_tokens": 37545219.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.326916027069092,
|
|
"epoch": 1.5730067243035544,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004757543248402839,
|
|
"loss": 4.8376,
|
|
"mean_token_accuracy": 0.23443261831998824,
|
|
"num_tokens": 37558138.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.251363277435303,
|
|
"epoch": 1.5734870317002883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047573884147416597,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.2360203042626381,
|
|
"num_tokens": 37568975.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.266435194015503,
|
|
"epoch": 1.5739673390970221,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004757233534474883,
|
|
"loss": 4.7644,
|
|
"mean_token_accuracy": 0.2396928310394287,
|
|
"num_tokens": 37580774.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.241900968551636,
|
|
"epoch": 1.574447646493756,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004757078607606103,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.2357242465019226,
|
|
"num_tokens": 37592858.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.319639730453491,
|
|
"epoch": 1.57492795389049,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004756923634138918,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.2295179009437561,
|
|
"num_tokens": 37604005.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.283957672119141,
|
|
"epoch": 1.5754082612872238,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047567686140769264,
|
|
"loss": 4.8316,
|
|
"mean_token_accuracy": 0.23492261320352553,
|
|
"num_tokens": 37614629.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.297015380859375,
|
|
"epoch": 1.5758885686839577,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047566135474237247,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.23638565540313722,
|
|
"num_tokens": 37626118.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.37575044631958,
|
|
"epoch": 1.5763688760806915,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047564584341829166,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.2213865950703621,
|
|
"num_tokens": 37638514.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.3610011577606205,
|
|
"epoch": 1.5768491834774254,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047563032743581,
|
|
"loss": 4.9377,
|
|
"mean_token_accuracy": 0.22104863226413726,
|
|
"num_tokens": 37649602.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.351442527770996,
|
|
"epoch": 1.5773294908741593,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047561480679528804,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.22902305871248246,
|
|
"num_tokens": 37661428.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.331100702285767,
|
|
"epoch": 1.5778097982708934,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004755992814970859,
|
|
"loss": 4.8894,
|
|
"mean_token_accuracy": 0.22980098575353622,
|
|
"num_tokens": 37673608.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.3866595268249515,
|
|
"epoch": 1.5782901056676273,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000475583751541564,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.22546689808368683,
|
|
"num_tokens": 37684957.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.2722372055053714,
|
|
"epoch": 1.5787704130643612,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047556821692908315,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.22878494262695312,
|
|
"num_tokens": 37697773.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.312799024581909,
|
|
"epoch": 1.579250720461095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004755526776600038,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.23138943463563919,
|
|
"num_tokens": 37708315.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.317187738418579,
|
|
"epoch": 1.5797310278578292,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047553713373468684,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.23269630074501038,
|
|
"num_tokens": 37720440.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.189525890350342,
|
|
"epoch": 1.580211335254563,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047552158515349306,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.2381934031844139,
|
|
"num_tokens": 37732332.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.2922650337219235,
|
|
"epoch": 1.580691642651297,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047550603191678356,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.23072789758443832,
|
|
"num_tokens": 37744770.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.275371313095093,
|
|
"epoch": 1.5811719500480308,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004754904740249194,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.24127918630838394,
|
|
"num_tokens": 37755958.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.290296506881714,
|
|
"epoch": 1.5816522574447647,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047547491147826156,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.23691444993019103,
|
|
"num_tokens": 37767182.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.339468955993652,
|
|
"epoch": 1.5821325648414986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004754593442771718,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.22870736420154572,
|
|
"num_tokens": 37778299.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.395206356048584,
|
|
"epoch": 1.5826128722382324,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047544377242201115,
|
|
"loss": 4.9274,
|
|
"mean_token_accuracy": 0.229831662774086,
|
|
"num_tokens": 37789879.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.362994194030762,
|
|
"epoch": 1.5830931796349663,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047542819591314136,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.2281927451491356,
|
|
"num_tokens": 37800726.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.332018566131592,
|
|
"epoch": 1.5835734870317002,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004754126147509241,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.22816014289855957,
|
|
"num_tokens": 37812298.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.226248645782471,
|
|
"epoch": 1.584053794428434,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047539702893572086,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.24084857404232024,
|
|
"num_tokens": 37824433.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.314221906661987,
|
|
"epoch": 1.584534101825168,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047538143846789376,
|
|
"loss": 4.8561,
|
|
"mean_token_accuracy": 0.23480234593153,
|
|
"num_tokens": 37835647.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.331889963150024,
|
|
"epoch": 1.585014409221902,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004753658433478047,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.23225387632846833,
|
|
"num_tokens": 37847721.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.282588148117066,
|
|
"epoch": 1.585494716618636,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047535024357581564,
|
|
"loss": 4.754,
|
|
"mean_token_accuracy": 0.23916036486625672,
|
|
"num_tokens": 37860111.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.289643287658691,
|
|
"epoch": 1.5859750240153698,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004753346391522889,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.22505705207586288,
|
|
"num_tokens": 37872321.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.366250658035279,
|
|
"epoch": 1.5864553314121037,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047531903007758667,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.22069799304008483,
|
|
"num_tokens": 37885195.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.3515894412994385,
|
|
"epoch": 1.5869356388088378,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004753034163520714,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.24019981026649476,
|
|
"num_tokens": 37895487.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.2470451354980465,
|
|
"epoch": 1.5874159462055717,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047528779797610557,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.23189063668251036,
|
|
"num_tokens": 37908344.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.300661373138428,
|
|
"epoch": 1.5878962536023056,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047527217495005184,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.23048147112131118,
|
|
"num_tokens": 37920220.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.260423040390014,
|
|
"epoch": 1.5883765609990395,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047525654727427285,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.24148745685815812,
|
|
"num_tokens": 37930874.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.27348108291626,
|
|
"epoch": 1.5888568683957733,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004752409149491315,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.234974704682827,
|
|
"num_tokens": 37942501.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.29255313873291,
|
|
"epoch": 1.5893371757925072,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047522527797499075,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.22974843233823777,
|
|
"num_tokens": 37954408.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.323912286758423,
|
|
"epoch": 1.589817483189241,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004752096363522135,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.22692240178585052,
|
|
"num_tokens": 37966088.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.343527603149414,
|
|
"epoch": 1.590297790585975,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047519399008116305,
|
|
"loss": 4.8691,
|
|
"mean_token_accuracy": 0.22495850771665574,
|
|
"num_tokens": 37977726.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.3275352954864506,
|
|
"epoch": 1.5907780979827089,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004751783391622026,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.22683385908603668,
|
|
"num_tokens": 37989024.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.3434919834136965,
|
|
"epoch": 1.5912584053794427,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004751626835956955,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.22882547974586487,
|
|
"num_tokens": 37999870.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.3383759498596195,
|
|
"epoch": 1.5917387127761766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004751470233820053,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.22726801335811614,
|
|
"num_tokens": 38010945.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.306109809875489,
|
|
"epoch": 1.5922190201729105,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004751313585214955,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.23694981932640075,
|
|
"num_tokens": 38021584.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.347380924224853,
|
|
"epoch": 1.5926993275696446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004751156890145298,
|
|
"loss": 4.9019,
|
|
"mean_token_accuracy": 0.2270787850022316,
|
|
"num_tokens": 38034407.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.377411890029907,
|
|
"epoch": 1.5931796349663785,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000475100014861472,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.2247257724404335,
|
|
"num_tokens": 38047061.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.435389375686645,
|
|
"epoch": 1.5936599423631124,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004750843360626861,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.22950884699821472,
|
|
"num_tokens": 38059168.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.353190898895264,
|
|
"epoch": 1.5941402497598463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004750686526185359,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.23673021793365479,
|
|
"num_tokens": 38070514.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.417277097702026,
|
|
"epoch": 1.5946205571565804,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047505296452938584,
|
|
"loss": 4.9403,
|
|
"mean_token_accuracy": 0.2302867814898491,
|
|
"num_tokens": 38081995.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.252400970458984,
|
|
"epoch": 1.5951008645533142,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047503727179559995,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.23869915753602983,
|
|
"num_tokens": 38094371.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.225997066497802,
|
|
"epoch": 1.5955811719500481,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047502157441754256,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.23816260695457458,
|
|
"num_tokens": 38106340.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.368935251235962,
|
|
"epoch": 1.596061479346782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004750058723955781,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.22963007688522338,
|
|
"num_tokens": 38117641.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.344534635543823,
|
|
"epoch": 1.5965417867435159,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004749901657300713,
|
|
"loss": 4.8312,
|
|
"mean_token_accuracy": 0.2329192653298378,
|
|
"num_tokens": 38129628.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.258495187759399,
|
|
"epoch": 1.5970220941402498,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047497445442138667,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.23259969055652618,
|
|
"num_tokens": 38140843.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.261810922622681,
|
|
"epoch": 1.5975024015369836,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047495873846988896,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.24192758798599243,
|
|
"num_tokens": 38152666.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.245664644241333,
|
|
"epoch": 1.5979827089337175,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004749430178759431,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.2384336084127426,
|
|
"num_tokens": 38164102.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.267911672592163,
|
|
"epoch": 1.5984630163304514,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047492729263991413,
|
|
"loss": 4.831,
|
|
"mean_token_accuracy": 0.23965033888816833,
|
|
"num_tokens": 38175211.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.284036016464233,
|
|
"epoch": 1.5989433237271853,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047491156276216695,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.2368493303656578,
|
|
"num_tokens": 38186968.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.318513345718384,
|
|
"epoch": 1.5994236311239192,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047489582824306704,
|
|
"loss": 4.8521,
|
|
"mean_token_accuracy": 0.22962785363197327,
|
|
"num_tokens": 38198740.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.295208835601807,
|
|
"epoch": 1.5999039385206533,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047488008908297955,
|
|
"loss": 4.7738,
|
|
"mean_token_accuracy": 0.2427997186779976,
|
|
"num_tokens": 38209110.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.239831590652466,
|
|
"epoch": 1.6003842459173871,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004748643452822699,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.24023987203836442,
|
|
"num_tokens": 38221840.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.360884094238282,
|
|
"epoch": 1.600864553314121,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004748485968413036,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.23239922970533372,
|
|
"num_tokens": 38232752.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.315357637405396,
|
|
"epoch": 1.601344860710855,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047483284376044634,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.22994168549776078,
|
|
"num_tokens": 38243394.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.326709985733032,
|
|
"epoch": 1.601825168107589,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004748170860400638,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.23443675339221953,
|
|
"num_tokens": 38254317.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.299792528152466,
|
|
"epoch": 1.602305475504323,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047480132368052185,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.2406340017914772,
|
|
"num_tokens": 38266886.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.360891199111938,
|
|
"epoch": 1.6027857829010568,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047478555668218643,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.22567255944013595,
|
|
"num_tokens": 38279975.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.382356834411621,
|
|
"epoch": 1.6032660902977907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004747697850454237,
|
|
"loss": 4.9302,
|
|
"mean_token_accuracy": 0.2224809542298317,
|
|
"num_tokens": 38290237.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.360258436203003,
|
|
"epoch": 1.6037463976945245,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004747540087705997,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.24065618515014647,
|
|
"num_tokens": 38300833.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.2291895866394045,
|
|
"epoch": 1.6042267050912584,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004747382278580808,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.24112123996019363,
|
|
"num_tokens": 38311926.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.327792453765869,
|
|
"epoch": 1.6047070124879923,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004747224423082333,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.22668983042240143,
|
|
"num_tokens": 38323053.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.364745140075684,
|
|
"epoch": 1.6051873198847262,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047470665212142384,
|
|
"loss": 4.9168,
|
|
"mean_token_accuracy": 0.22618085145950317,
|
|
"num_tokens": 38334959.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.4002423763275145,
|
|
"epoch": 1.60566762728146,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047469085729801887,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.22370482236146927,
|
|
"num_tokens": 38346402.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.343341445922851,
|
|
"epoch": 1.606147934678194,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047467505783838515,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.23184559792280196,
|
|
"num_tokens": 38358549.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.337767171859741,
|
|
"epoch": 1.6066282420749278,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004746592537428895,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.23056095242500305,
|
|
"num_tokens": 38370840.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.305025815963745,
|
|
"epoch": 1.6071085494716617,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047464344501189877,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.23262978941202164,
|
|
"num_tokens": 38382980.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.324799728393555,
|
|
"epoch": 1.6075888568683958,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047462763164578015,
|
|
"loss": 4.7783,
|
|
"mean_token_accuracy": 0.2456376314163208,
|
|
"num_tokens": 38393836.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.226725721359253,
|
|
"epoch": 1.6080691642651297,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004746118136449007,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.23900019079446794,
|
|
"num_tokens": 38405770.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.309355735778809,
|
|
"epoch": 1.6085494716618636,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004745959910096276,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.2239879474043846,
|
|
"num_tokens": 38418847.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.274864196777344,
|
|
"epoch": 1.6090297790585975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047458016374032837,
|
|
"loss": 4.7739,
|
|
"mean_token_accuracy": 0.2392196163535118,
|
|
"num_tokens": 38431532.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.399022054672241,
|
|
"epoch": 1.6095100864553316,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004745643318373703,
|
|
"loss": 4.986,
|
|
"mean_token_accuracy": 0.22532286047935485,
|
|
"num_tokens": 38442071.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.28731894493103,
|
|
"epoch": 1.6099903938520654,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047454849530112106,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.227568382024765,
|
|
"num_tokens": 38454979.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.261596536636352,
|
|
"epoch": 1.6104707012487993,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047453265413194826,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.24352045357227325,
|
|
"num_tokens": 38465579.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.2619805335998535,
|
|
"epoch": 1.6109510086455332,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047451680833021973,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.2330008015036583,
|
|
"num_tokens": 38477139.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.299579858779907,
|
|
"epoch": 1.611431316042267,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004745009578963034,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.24033277481794357,
|
|
"num_tokens": 38487638.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.165501976013184,
|
|
"epoch": 1.611911623439001,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047448510283056716,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.25157754570245744,
|
|
"num_tokens": 38498395.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.25656909942627,
|
|
"epoch": 1.6123919308357348,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047446924313337925,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.24205986857414247,
|
|
"num_tokens": 38509372.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.300742244720459,
|
|
"epoch": 1.6128722382324687,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047445337880510773,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.23664686530828477,
|
|
"num_tokens": 38520651.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.354139709472657,
|
|
"epoch": 1.6133525456292026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004744375098461211,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.226563960313797,
|
|
"num_tokens": 38531461.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.2627646923065186,
|
|
"epoch": 1.6138328530259365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004744216362567876,
|
|
"loss": 4.751,
|
|
"mean_token_accuracy": 0.24381977468729019,
|
|
"num_tokens": 38542707.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.304841136932373,
|
|
"epoch": 1.6143131604226704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047440575803747595,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.23932840377092363,
|
|
"num_tokens": 38553664.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.325404834747315,
|
|
"epoch": 1.6147934678194045,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047438987518855463,
|
|
"loss": 4.8418,
|
|
"mean_token_accuracy": 0.23073465675115584,
|
|
"num_tokens": 38564891.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.266715574264526,
|
|
"epoch": 1.6152737752161384,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004743739877103926,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.23276718705892563,
|
|
"num_tokens": 38576535.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.305066251754761,
|
|
"epoch": 1.6157540826128722,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004743580956033585,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.22737281918525695,
|
|
"num_tokens": 38588160.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.263997983932495,
|
|
"epoch": 1.6162343900096061,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047434219886782135,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.23453417867422105,
|
|
"num_tokens": 38599281.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.290989017486572,
|
|
"epoch": 1.6167146974063402,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004743262975041504,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.23277923911809922,
|
|
"num_tokens": 38611823.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.269582223892212,
|
|
"epoch": 1.617195004803074,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004743103915127146,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.2309708774089813,
|
|
"num_tokens": 38623181.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.3073522567749025,
|
|
"epoch": 1.617675312199808,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047429448089388336,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.22666438221931456,
|
|
"num_tokens": 38633149.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.298036527633667,
|
|
"epoch": 1.6181556195965419,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047427856564802605,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.22765953540802003,
|
|
"num_tokens": 38644204.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.35086088180542,
|
|
"epoch": 1.6186359269932757,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004742626457755122,
|
|
"loss": 4.8161,
|
|
"mean_token_accuracy": 0.24016182273626327,
|
|
"num_tokens": 38655287.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.246470785140991,
|
|
"epoch": 1.6191162343900096,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004742467212767114,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.2372668653726578,
|
|
"num_tokens": 38665732.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.354928350448608,
|
|
"epoch": 1.6195965417867435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004742307921519933,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.218870809674263,
|
|
"num_tokens": 38677289.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.3073149681091305,
|
|
"epoch": 1.6200768491834774,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047421485840172794,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.23764281421899797,
|
|
"num_tokens": 38689581.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.3484625816345215,
|
|
"epoch": 1.6205571565802113,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004741989200262851,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.22625012546777726,
|
|
"num_tokens": 38701327.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.3086882591247555,
|
|
"epoch": 1.6210374639769451,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004741829770260347,
|
|
"loss": 4.8804,
|
|
"mean_token_accuracy": 0.22986028492450714,
|
|
"num_tokens": 38713431.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.352789688110351,
|
|
"epoch": 1.621517771373679,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047416702940134714,
|
|
"loss": 4.8865,
|
|
"mean_token_accuracy": 0.2300675168633461,
|
|
"num_tokens": 38724091.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.319310426712036,
|
|
"epoch": 1.621998078770413,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047415107715259255,
|
|
"loss": 4.937,
|
|
"mean_token_accuracy": 0.2251893937587738,
|
|
"num_tokens": 38736219.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.252118158340454,
|
|
"epoch": 1.622478386167147,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047413512028014125,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.235407455265522,
|
|
"num_tokens": 38747512.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.347729635238648,
|
|
"epoch": 1.622958693563881,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004741191587843638,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.22380358278751372,
|
|
"num_tokens": 38758777.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.365285968780517,
|
|
"epoch": 1.6234390009606148,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004741031926656308,
|
|
"loss": 4.8767,
|
|
"mean_token_accuracy": 0.23481245189905167,
|
|
"num_tokens": 38770094.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.380953025817871,
|
|
"epoch": 1.6239193083573487,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004740872219243128,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.23925554901361465,
|
|
"num_tokens": 38781419.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.268444919586182,
|
|
"epoch": 1.6243996157540828,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004740712465607807,
|
|
"loss": 4.8237,
|
|
"mean_token_accuracy": 0.2344905376434326,
|
|
"num_tokens": 38794303.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.290090036392212,
|
|
"epoch": 1.6248799231508166,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004740552665754054,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.2343149170279503,
|
|
"num_tokens": 38805387.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.33501672744751,
|
|
"epoch": 1.6253602305475505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047403928196855776,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.2352287322282791,
|
|
"num_tokens": 38815307.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.3194352149963375,
|
|
"epoch": 1.6258405379442844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047402329274060916,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.23970703780651093,
|
|
"num_tokens": 38826585.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.260755634307861,
|
|
"epoch": 1.6263208453410183,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004740072988919306,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.24324409961700438,
|
|
"num_tokens": 38838406.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.3037803173065186,
|
|
"epoch": 1.6268011527377522,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004739913004228936,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.23730110377073288,
|
|
"num_tokens": 38849952.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.336380386352539,
|
|
"epoch": 1.627281460134486,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004739752973338694,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.22621188908815384,
|
|
"num_tokens": 38862761.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.313996267318726,
|
|
"epoch": 1.62776176753122,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047395928962522965,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.23149055391550064,
|
|
"num_tokens": 38874422.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.342024946212769,
|
|
"epoch": 1.6282420749279538,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047394327729734595,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.23020818829536438,
|
|
"num_tokens": 38885751.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.267931413650513,
|
|
"epoch": 1.6287223823246877,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004739272603505901,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.2412410706281662,
|
|
"num_tokens": 38897539.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.377118539810181,
|
|
"epoch": 1.6292026897214216,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000473911238785334,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.23108118623495102,
|
|
"num_tokens": 38908439.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.285419607162476,
|
|
"epoch": 1.6296829971181557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004738952126019496,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.22893782556056977,
|
|
"num_tokens": 38920881.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.310050058364868,
|
|
"epoch": 1.6301633045148896,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004738791818008089,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.23699779510498048,
|
|
"num_tokens": 38932097.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.412273597717285,
|
|
"epoch": 1.6306436119116234,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004738631463822841,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.22397930026054383,
|
|
"num_tokens": 38945122.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.28420934677124,
|
|
"epoch": 1.6311239193083573,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047384710634674766,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.2358503147959709,
|
|
"num_tokens": 38956136.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.371091508865357,
|
|
"epoch": 1.6316042267050914,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047383106169457184,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.23138389140367507,
|
|
"num_tokens": 38968650.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.2687334537506105,
|
|
"epoch": 1.6320845341018253,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004738150124261292,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.23893579989671707,
|
|
"num_tokens": 38979834.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.250964546203614,
|
|
"epoch": 1.6325648414985592,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047379895854179226,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.2407167762517929,
|
|
"num_tokens": 38991548.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.298982810974121,
|
|
"epoch": 1.633045148895293,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004737829000419338,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.23524673730134965,
|
|
"num_tokens": 39003344.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.327221536636353,
|
|
"epoch": 1.633525456292027,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047376683692692666,
|
|
"loss": 4.8526,
|
|
"mean_token_accuracy": 0.23715859055519103,
|
|
"num_tokens": 39015278.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.308913660049439,
|
|
"epoch": 1.6340057636887608,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004737507691971439,
|
|
"loss": 4.8139,
|
|
"mean_token_accuracy": 0.23246520906686782,
|
|
"num_tokens": 39027634.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.333699321746826,
|
|
"epoch": 1.6344860710854947,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047373469685295833,
|
|
"loss": 4.9255,
|
|
"mean_token_accuracy": 0.23339595943689345,
|
|
"num_tokens": 39038226.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.331917428970337,
|
|
"epoch": 1.6349663784822286,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047371861989474326,
|
|
"loss": 4.9008,
|
|
"mean_token_accuracy": 0.22952217608690262,
|
|
"num_tokens": 39050627.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.365664911270142,
|
|
"epoch": 1.6354466858789625,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004737025383228719,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.22988363355398178,
|
|
"num_tokens": 39061734.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.315570640563965,
|
|
"epoch": 1.6359269932756964,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047368645213771764,
|
|
"loss": 4.8906,
|
|
"mean_token_accuracy": 0.22240833044052125,
|
|
"num_tokens": 39074288.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.299259185791016,
|
|
"epoch": 1.6364073006724302,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000473670361339654,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.22274006456136702,
|
|
"num_tokens": 39084967.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.340850067138672,
|
|
"epoch": 1.6368876080691641,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004736542659290544,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.24465329200029373,
|
|
"num_tokens": 39095093.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.364175462722779,
|
|
"epoch": 1.6373679154658982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004736381659062927,
|
|
"loss": 4.8805,
|
|
"mean_token_accuracy": 0.23888119161128998,
|
|
"num_tokens": 39106952.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.258432006835937,
|
|
"epoch": 1.637848222862632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047362206127174255,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.2290976583957672,
|
|
"num_tokens": 39117682.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.380591344833374,
|
|
"epoch": 1.638328530259366,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047360595202577786,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.22346789240837098,
|
|
"num_tokens": 39129767.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.25060453414917,
|
|
"epoch": 1.6388088376560999,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047358983816877284,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.23524311631917955,
|
|
"num_tokens": 39140906.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.362659502029419,
|
|
"epoch": 1.639289145052834,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004735737197011015,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.22921187430620193,
|
|
"num_tokens": 39151884.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.270849943161011,
|
|
"epoch": 1.6397694524495678,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047355759662313793,
|
|
"loss": 4.7903,
|
|
"mean_token_accuracy": 0.23549116551876068,
|
|
"num_tokens": 39162986.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.28433928489685,
|
|
"epoch": 1.6402497598463017,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004735414689352566,
|
|
"loss": 4.8758,
|
|
"mean_token_accuracy": 0.23579030781984328,
|
|
"num_tokens": 39174280.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.334679079055786,
|
|
"epoch": 1.6407300672430356,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004735253366378318,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.2367052435874939,
|
|
"num_tokens": 39185499.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.279481649398804,
|
|
"epoch": 1.6412103746397695,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004735091997312383,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.23685247898101808,
|
|
"num_tokens": 39196322.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.2726024150848385,
|
|
"epoch": 1.6416906820365034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047349305821585067,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.23765674233436584,
|
|
"num_tokens": 39207332.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.378822469711304,
|
|
"epoch": 1.6421709894332372,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004734769120920435,
|
|
"loss": 4.8929,
|
|
"mean_token_accuracy": 0.23013981580734252,
|
|
"num_tokens": 39217305.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.319589424133301,
|
|
"epoch": 1.6426512968299711,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004734607613601919,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.23646987229585648,
|
|
"num_tokens": 39228895.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.30557017326355,
|
|
"epoch": 1.643131604226705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047344460602067077,
|
|
"loss": 4.8464,
|
|
"mean_token_accuracy": 0.23459748327732086,
|
|
"num_tokens": 39240859.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.257879543304443,
|
|
"epoch": 1.643611911623439,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000473428446073855,
|
|
"loss": 4.7466,
|
|
"mean_token_accuracy": 0.24393977969884872,
|
|
"num_tokens": 39251556.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.259178018569946,
|
|
"epoch": 1.6440922190201728,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047341228152012003,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.23913211822509767,
|
|
"num_tokens": 39263919.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.3462896823883055,
|
|
"epoch": 1.6445725264169067,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000473396112359841,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.228570456802845,
|
|
"num_tokens": 39276873.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.288535642623901,
|
|
"epoch": 1.6450528338136408,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047337993859339334,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.24578937739133835,
|
|
"num_tokens": 39288912.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.258509349822998,
|
|
"epoch": 1.6455331412103746,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047336376022115255,
|
|
"loss": 4.8113,
|
|
"mean_token_accuracy": 0.23630768060684204,
|
|
"num_tokens": 39301115.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.331364250183105,
|
|
"epoch": 1.6460134486071085,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047334757724349437,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.22679813355207443,
|
|
"num_tokens": 39313535.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.351892900466919,
|
|
"epoch": 1.6464937560038426,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004733313896607943,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.2308068886399269,
|
|
"num_tokens": 39325289.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.295709800720215,
|
|
"epoch": 1.6469740634005765,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004733151974734284,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.23476625233888626,
|
|
"num_tokens": 39337382.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.301625156402588,
|
|
"epoch": 1.6474543707973104,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047329900068177245,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.23196763396263123,
|
|
"num_tokens": 39348548.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.2968034744262695,
|
|
"epoch": 1.6479346781940443,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047328279928620244,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.23528865575790406,
|
|
"num_tokens": 39359788.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.342213821411133,
|
|
"epoch": 1.6484149855907781,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004732665932870947,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.23749008178710937,
|
|
"num_tokens": 39370533.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.348770666122436,
|
|
"epoch": 1.648895292987512,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047325038268482544,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.22980386763811111,
|
|
"num_tokens": 39381157.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.342569732666016,
|
|
"epoch": 1.649375600384246,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004732341674797709,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.23309521824121476,
|
|
"num_tokens": 39391280.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.21559362411499,
|
|
"epoch": 1.6498559077809798,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047321794767230766,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.23503521978855133,
|
|
"num_tokens": 39402097.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.355506420135498,
|
|
"epoch": 1.6503362151777137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047320172326281224,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.23342329561710357,
|
|
"num_tokens": 39414590.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.312139320373535,
|
|
"epoch": 1.6508165225744476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047318549425166134,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.23576575964689256,
|
|
"num_tokens": 39425933.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.283951663970948,
|
|
"epoch": 1.6512968299711814,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004731692606392318,
|
|
"loss": 4.8274,
|
|
"mean_token_accuracy": 0.2386905610561371,
|
|
"num_tokens": 39437059.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.32426438331604,
|
|
"epoch": 1.6517771373679153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004731530224259004,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.23583868145942688,
|
|
"num_tokens": 39449582.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.4207579612731935,
|
|
"epoch": 1.6522574447646494,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004731367796120442,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.2304081439971924,
|
|
"num_tokens": 39461147.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.3806235790252686,
|
|
"epoch": 1.6527377521613833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004731205321980404,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.22450334578752518,
|
|
"num_tokens": 39471881.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.250331926345825,
|
|
"epoch": 1.6532180595581172,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047310428018426616,
|
|
"loss": 4.8708,
|
|
"mean_token_accuracy": 0.23063654750585555,
|
|
"num_tokens": 39483632.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.2999039649963375,
|
|
"epoch": 1.653698366954851,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004730880235710987,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.2301526501774788,
|
|
"num_tokens": 39495587.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.335765027999878,
|
|
"epoch": 1.6541786743515852,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004730717623589155,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.2261074036359787,
|
|
"num_tokens": 39505503.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.3444005966186525,
|
|
"epoch": 1.654658981748319,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004730554965480942,
|
|
"loss": 4.8298,
|
|
"mean_token_accuracy": 0.23526241183280944,
|
|
"num_tokens": 39516681.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.275598526000977,
|
|
"epoch": 1.655139289145053,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004730392261390124,
|
|
"loss": 4.788,
|
|
"mean_token_accuracy": 0.23677062392234802,
|
|
"num_tokens": 39528451.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.295856237411499,
|
|
"epoch": 1.6556195965417868,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004730229511320478,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.2292807549238205,
|
|
"num_tokens": 39540306.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.301976680755615,
|
|
"epoch": 1.6560999039385207,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047300667152757827,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.23696596175432205,
|
|
"num_tokens": 39551260.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.339865827560425,
|
|
"epoch": 1.6565802113352546,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047299038732598184,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.2275793209671974,
|
|
"num_tokens": 39562991.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.263572692871094,
|
|
"epoch": 1.6570605187319885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047297409852763644,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.24136826694011687,
|
|
"num_tokens": 39574629.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.320040035247803,
|
|
"epoch": 1.6575408261287223,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004729578051329204,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.22859242409467698,
|
|
"num_tokens": 39585599.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.331939268112182,
|
|
"epoch": 1.6580211335254562,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047294150714221185,
|
|
"loss": 4.8324,
|
|
"mean_token_accuracy": 0.23592211902141572,
|
|
"num_tokens": 39597225.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.355507707595825,
|
|
"epoch": 1.65850144092219,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004729252045558894,
|
|
"loss": 4.8703,
|
|
"mean_token_accuracy": 0.23339155316352844,
|
|
"num_tokens": 39609296.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.278488206863403,
|
|
"epoch": 1.658981748318924,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047290889737433133,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.24432171434164046,
|
|
"num_tokens": 39619369.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.291545581817627,
|
|
"epoch": 1.6594620557156579,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047289258559791633,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.23812910467386245,
|
|
"num_tokens": 39630438.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.299667119979858,
|
|
"epoch": 1.659942363112392,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047287626922702317,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.23257336616516114,
|
|
"num_tokens": 39643339.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.329848337173462,
|
|
"epoch": 1.6604226705091258,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047285994826203054,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.23836521357297896,
|
|
"num_tokens": 39654495.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.276008653640747,
|
|
"epoch": 1.6609029779058597,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004728436227033175,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.23726756721735,
|
|
"num_tokens": 39665870.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.24581356048584,
|
|
"epoch": 1.6613832853025938,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047282729255126294,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.23655612617731095,
|
|
"num_tokens": 39676761.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.333010196685791,
|
|
"epoch": 1.6618635926993277,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004728109578062461,
|
|
"loss": 4.8298,
|
|
"mean_token_accuracy": 0.23347929120063782,
|
|
"num_tokens": 39687515.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.2653340816497805,
|
|
"epoch": 1.6623439000960616,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047279461846864626,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.24276616424322128,
|
|
"num_tokens": 39699599.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.291073274612427,
|
|
"epoch": 1.6628242074927955,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047277827453884265,
|
|
"loss": 4.7954,
|
|
"mean_token_accuracy": 0.24815717935562134,
|
|
"num_tokens": 39710122.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.369096422195435,
|
|
"epoch": 1.6633045148895294,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047276192601721477,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.22848236411809922,
|
|
"num_tokens": 39722884.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.257306957244873,
|
|
"epoch": 1.6637848222862632,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004727455729041422,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.2400132641196251,
|
|
"num_tokens": 39734464.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.300629949569702,
|
|
"epoch": 1.6642651296829971,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047272921520000465,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.23532968312501906,
|
|
"num_tokens": 39745948.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.321057271957398,
|
|
"epoch": 1.664745437079731,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004727128529051819,
|
|
"loss": 4.8249,
|
|
"mean_token_accuracy": 0.2302912399172783,
|
|
"num_tokens": 39757024.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.269631671905517,
|
|
"epoch": 1.6652257444764649,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004726964860200537,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.23901496529579164,
|
|
"num_tokens": 39767205.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.3055158138275145,
|
|
"epoch": 1.6657060518731988,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004726801145450002,
|
|
"loss": 4.8412,
|
|
"mean_token_accuracy": 0.23198553174734116,
|
|
"num_tokens": 39779543.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.272429990768432,
|
|
"epoch": 1.6661863592699326,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004726637384804014,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.24141939878463745,
|
|
"num_tokens": 39790827.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.200071477890015,
|
|
"epoch": 1.6666666666666665,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004726473578266375,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.23998078405857087,
|
|
"num_tokens": 39801995.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.279646158218384,
|
|
"epoch": 1.6671469740634006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047263097258408893,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.23790742009878157,
|
|
"num_tokens": 39813319.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.337472915649414,
|
|
"epoch": 1.6676272814601345,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004726145827531359,
|
|
"loss": 4.7956,
|
|
"mean_token_accuracy": 0.24129658937454224,
|
|
"num_tokens": 39824178.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.285546159744262,
|
|
"epoch": 1.6681075888568684,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047259818833415916,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.23100116103887558,
|
|
"num_tokens": 39835452.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.199541759490967,
|
|
"epoch": 1.6685878962536023,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047258178932753917,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.2307039976119995,
|
|
"num_tokens": 39848083.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.349788665771484,
|
|
"epoch": 1.6690682036503364,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047256538573365675,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.23148238509893418,
|
|
"num_tokens": 39859132.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.321217489242554,
|
|
"epoch": 1.6695485110470702,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004725489775528928,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.2345855191349983,
|
|
"num_tokens": 39870237.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.230425548553467,
|
|
"epoch": 1.6700288184438041,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047253256478562805,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.2344790056347847,
|
|
"num_tokens": 39883009.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.270969724655151,
|
|
"epoch": 1.670509125840538,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047251614743224374,
|
|
"loss": 4.838,
|
|
"mean_token_accuracy": 0.23384612649679185,
|
|
"num_tokens": 39894444.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.361810255050659,
|
|
"epoch": 1.670989433237272,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047249972549312107,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.22805399894714357,
|
|
"num_tokens": 39905312.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.34267144203186,
|
|
"epoch": 1.6714697406340058,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004724832989686411,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.23449280112981796,
|
|
"num_tokens": 39916724.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.318605184555054,
|
|
"epoch": 1.6719500480307397,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047246686785918545,
|
|
"loss": 4.8563,
|
|
"mean_token_accuracy": 0.23809899240732194,
|
|
"num_tokens": 39928919.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.354156064987182,
|
|
"epoch": 1.6724303554274735,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047245043216513546,
|
|
"loss": 4.9431,
|
|
"mean_token_accuracy": 0.2233753725886345,
|
|
"num_tokens": 39940301.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.312848138809204,
|
|
"epoch": 1.6729106628242074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004724339918868727,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.2359646365046501,
|
|
"num_tokens": 39951269.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.383089637756347,
|
|
"epoch": 1.6733909702209413,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000472417547024779,
|
|
"loss": 4.8796,
|
|
"mean_token_accuracy": 0.2384801834821701,
|
|
"num_tokens": 39963057.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.406864213943481,
|
|
"epoch": 1.6738712776176752,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047240109757923593,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.23091021925210953,
|
|
"num_tokens": 39973876.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.396348142623902,
|
|
"epoch": 1.674351585014409,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004723846435506256,
|
|
"loss": 4.8714,
|
|
"mean_token_accuracy": 0.23132962584495545,
|
|
"num_tokens": 39984477.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.316521549224854,
|
|
"epoch": 1.6748318924111432,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047236818493932994,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.23416852056980134,
|
|
"num_tokens": 39996266.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.328397941589356,
|
|
"epoch": 1.675312199807877,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004723517217457311,
|
|
"loss": 4.8944,
|
|
"mean_token_accuracy": 0.2304820939898491,
|
|
"num_tokens": 40008618.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.289344930648804,
|
|
"epoch": 1.675792507204611,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004723352539702113,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.2346118375658989,
|
|
"num_tokens": 40020290.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.296611166000366,
|
|
"epoch": 1.6762728146013448,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004723187816131529,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.2373323544859886,
|
|
"num_tokens": 40031167.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.296824502944946,
|
|
"epoch": 1.676753121998079,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004723023046749383,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.24056745916604996,
|
|
"num_tokens": 40043278.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.300357627868652,
|
|
"epoch": 1.6772334293948128,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047228582315595,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.2378392532467842,
|
|
"num_tokens": 40055022.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.304041624069214,
|
|
"epoch": 1.6777137367915467,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004722693370565708,
|
|
"loss": 4.8664,
|
|
"mean_token_accuracy": 0.23486433923244476,
|
|
"num_tokens": 40066556.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.421879386901855,
|
|
"epoch": 1.6781940441882806,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047225284637718323,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.2249600276350975,
|
|
"num_tokens": 40078015.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.282445859909058,
|
|
"epoch": 1.6786743515850144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004722363511181703,
|
|
"loss": 4.8211,
|
|
"mean_token_accuracy": 0.2313766822218895,
|
|
"num_tokens": 40090061.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.334756469726562,
|
|
"epoch": 1.6791546589817483,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000472219851279915,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.2297206774353981,
|
|
"num_tokens": 40102569.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.338450908660889,
|
|
"epoch": 1.6796349663784822,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004722033468628004,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.2331488013267517,
|
|
"num_tokens": 40114883.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.287060642242432,
|
|
"epoch": 1.680115273775216,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004721868378672098,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.24692731946706772,
|
|
"num_tokens": 40126337.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.259734201431274,
|
|
"epoch": 1.68059558117195,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004721703242935261,
|
|
"loss": 4.7982,
|
|
"mean_token_accuracy": 0.24350020587444304,
|
|
"num_tokens": 40137438.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.312447786331177,
|
|
"epoch": 1.6810758885686838,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004721538061421331,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.23646066933870316,
|
|
"num_tokens": 40148061.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.363009738922119,
|
|
"epoch": 1.6815561959654177,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047213728341341407,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.23209244459867479,
|
|
"num_tokens": 40159118.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.288822507858276,
|
|
"epoch": 1.6820365033621518,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004721207561077527,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.236354798078537,
|
|
"num_tokens": 40170027.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.23339433670044,
|
|
"epoch": 1.6825168107588857,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004721042242255327,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.23289799690246582,
|
|
"num_tokens": 40181819.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.357213544845581,
|
|
"epoch": 1.6829971181556196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047208768776713805,
|
|
"loss": 4.7287,
|
|
"mean_token_accuracy": 0.24112251698970794,
|
|
"num_tokens": 40191870.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.295327377319336,
|
|
"epoch": 1.6834774255523535,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004720711467329523,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.23327968865633011,
|
|
"num_tokens": 40203191.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.393956518173217,
|
|
"epoch": 1.6839577329490876,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004720546011233599,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.22205229997634887,
|
|
"num_tokens": 40214217.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.3250403881073,
|
|
"epoch": 1.6844380403458215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004720380509387446,
|
|
"loss": 4.8458,
|
|
"mean_token_accuracy": 0.23746116310358048,
|
|
"num_tokens": 40225711.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.428515195846558,
|
|
"epoch": 1.6849183477425553,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000472021496179491,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.2206125169992447,
|
|
"num_tokens": 40235748.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.37783465385437,
|
|
"epoch": 1.6853986551392892,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047200493684598316,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.22122507840394973,
|
|
"num_tokens": 40246090.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.32340087890625,
|
|
"epoch": 1.685878962536023,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047198837293860573,
|
|
"loss": 4.8878,
|
|
"mean_token_accuracy": 0.2313563346862793,
|
|
"num_tokens": 40257709.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.345572233200073,
|
|
"epoch": 1.686359269932757,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004719718044577432,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.23155910074710845,
|
|
"num_tokens": 40268670.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.285569763183593,
|
|
"epoch": 1.6868395773294909,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047195523140378034,
|
|
"loss": 4.759,
|
|
"mean_token_accuracy": 0.24224598556756974,
|
|
"num_tokens": 40279289.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.375236082077026,
|
|
"epoch": 1.6873198847262247,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047193865377710177,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.2248787686228752,
|
|
"num_tokens": 40289953.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.374778747558594,
|
|
"epoch": 1.6878001921229586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047192207157809246,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.22854468822479249,
|
|
"num_tokens": 40302180.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.300807332992553,
|
|
"epoch": 1.6882804995196925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047190548480713736,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.23899870961904526,
|
|
"num_tokens": 40312556.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.325531101226806,
|
|
"epoch": 1.6887608069164264,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047188889346462163,
|
|
"loss": 4.8637,
|
|
"mean_token_accuracy": 0.2330825924873352,
|
|
"num_tokens": 40323213.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.336818504333496,
|
|
"epoch": 1.6892411143131603,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047187229755093037,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.22609812915325164,
|
|
"num_tokens": 40334567.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.347298526763916,
|
|
"epoch": 1.6897214217098944,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000471855697066449,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.22936315834522247,
|
|
"num_tokens": 40345606.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.352277565002441,
|
|
"epoch": 1.6902017291066282,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047183909201156297,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.23507800251245498,
|
|
"num_tokens": 40356366.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.26538405418396,
|
|
"epoch": 1.6906820365033621,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004718224823866576,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.24038785248994826,
|
|
"num_tokens": 40367451.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.209910488128662,
|
|
"epoch": 1.691162343900096,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004718058681921186,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.2449033424258232,
|
|
"num_tokens": 40379377.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.294075155258179,
|
|
"epoch": 1.6916426512968301,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047178924942833185,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.23504394590854644,
|
|
"num_tokens": 40390615.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.358276987075806,
|
|
"epoch": 1.692122958693564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004717726260956831,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.22745494693517684,
|
|
"num_tokens": 40402475.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.339623546600341,
|
|
"epoch": 1.6926032660902979,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004717559981945581,
|
|
"loss": 4.884,
|
|
"mean_token_accuracy": 0.22328956574201583,
|
|
"num_tokens": 40414311.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.277577352523804,
|
|
"epoch": 1.6930835734870318,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004717393657253432,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.2391604080796242,
|
|
"num_tokens": 40425859.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.370849895477295,
|
|
"epoch": 1.6935638808837656,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004717227286884243,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.22401827275753022,
|
|
"num_tokens": 40436679.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.371461391448975,
|
|
"epoch": 1.6940441882804995,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004717060870841879,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.22141451984643937,
|
|
"num_tokens": 40446985.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.298881959915161,
|
|
"epoch": 1.6945244956772334,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004716894409130202,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.23311383575201033,
|
|
"num_tokens": 40458777.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.353746795654297,
|
|
"epoch": 1.6950048030739673,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004716727901753078,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.2220725655555725,
|
|
"num_tokens": 40469493.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.322965335845947,
|
|
"epoch": 1.6954851104707012,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004716561348714371,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.23430486470460893,
|
|
"num_tokens": 40480889.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.3235808372497555,
|
|
"epoch": 1.695965417867435,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047163947500179494,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.2291315406560898,
|
|
"num_tokens": 40491630.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.430650329589843,
|
|
"epoch": 1.696445725264169,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004716228105667681,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.2152542993426323,
|
|
"num_tokens": 40503204.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.296370172500611,
|
|
"epoch": 1.696926032660903,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004716061415667435,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.23445128053426742,
|
|
"num_tokens": 40513917.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.360758304595947,
|
|
"epoch": 1.697406340057637,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000471589468002108,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.22705449610948564,
|
|
"num_tokens": 40526501.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.290028285980225,
|
|
"epoch": 1.6978866474543708,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004715727898732488,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.23773220777511597,
|
|
"num_tokens": 40536641.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.324151563644409,
|
|
"epoch": 1.6983669548511047,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047155610718055315,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.2345806285738945,
|
|
"num_tokens": 40547497.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.305400419235229,
|
|
"epoch": 1.6988472622478388,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047153941992440833,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.23231041580438613,
|
|
"num_tokens": 40559212.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.274342584609985,
|
|
"epoch": 1.6993275696445727,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004715227281052018,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.23710446208715438,
|
|
"num_tokens": 40571692.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.2967053890228275,
|
|
"epoch": 1.6998078770413065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004715060317233211,
|
|
"loss": 4.8314,
|
|
"mean_token_accuracy": 0.2319769188761711,
|
|
"num_tokens": 40583751.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.366555309295654,
|
|
"epoch": 1.7002881844380404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004714893307791538,
|
|
"loss": 4.8349,
|
|
"mean_token_accuracy": 0.23159306347370148,
|
|
"num_tokens": 40594782.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.3152172565460205,
|
|
"epoch": 1.7007684918347743,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047147262527308766,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.2357310563325882,
|
|
"num_tokens": 40604583.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.274031639099121,
|
|
"epoch": 1.7012487992315082,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004714559152055106,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.22664034068584443,
|
|
"num_tokens": 40617957.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.328817892074585,
|
|
"epoch": 1.701729106628242,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004714392005768106,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.23254188746213914,
|
|
"num_tokens": 40628016.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.412788724899292,
|
|
"epoch": 1.702209414024976,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004714224813873756,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.2292790189385414,
|
|
"num_tokens": 40639339.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.3787822246551515,
|
|
"epoch": 1.7026897214217098,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047140575763759393,
|
|
"loss": 4.9151,
|
|
"mean_token_accuracy": 0.2305568650364876,
|
|
"num_tokens": 40651634.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.372726583480835,
|
|
"epoch": 1.7031700288184437,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047138902932785363,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.23058863878250122,
|
|
"num_tokens": 40662742.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.365936946868897,
|
|
"epoch": 1.7036503362151776,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047137229645854333,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.22971679270267487,
|
|
"num_tokens": 40673586.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.301830673217774,
|
|
"epoch": 1.7041306436119115,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004713555590300513,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.23757684975862503,
|
|
"num_tokens": 40684238.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.3698255062103275,
|
|
"epoch": 1.7046109510086456,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004713388170427664,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.2268364682793617,
|
|
"num_tokens": 40696154.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.340982103347779,
|
|
"epoch": 1.7050912584053795,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004713220704970771,
|
|
"loss": 4.8464,
|
|
"mean_token_accuracy": 0.2326067715883255,
|
|
"num_tokens": 40708328.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.410878467559814,
|
|
"epoch": 1.7055715658021133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047130531939337236,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.22764498889446258,
|
|
"num_tokens": 40719067.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.211362838745117,
|
|
"epoch": 1.7060518731988472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047128856373204086,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.25235945731401443,
|
|
"num_tokens": 40730638.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.320070505142212,
|
|
"epoch": 1.7065321805955813,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047127180351347184,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.23468254655599594,
|
|
"num_tokens": 40743245.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.39382700920105,
|
|
"epoch": 1.7070124879923152,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004712550387380544,
|
|
"loss": 4.8463,
|
|
"mean_token_accuracy": 0.23245684951543807,
|
|
"num_tokens": 40753769.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.30980281829834,
|
|
"epoch": 1.707492795389049,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004712382694061776,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.23621623069047928,
|
|
"num_tokens": 40765470.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.341102552413941,
|
|
"epoch": 1.707973102785783,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047122149551823096,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.22604156136512757,
|
|
"num_tokens": 40776427.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.293577051162719,
|
|
"epoch": 1.7084534101825168,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004712047170746039,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.22916379272937776,
|
|
"num_tokens": 40788707.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.432657670974732,
|
|
"epoch": 1.7089337175792507,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047118793407568586,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.22362485229969026,
|
|
"num_tokens": 40800092.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.283945608139038,
|
|
"epoch": 1.7094140249759846,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047117114652186657,
|
|
"loss": 4.7739,
|
|
"mean_token_accuracy": 0.24215201586484908,
|
|
"num_tokens": 40811389.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.300406885147095,
|
|
"epoch": 1.7098943323727185,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047115435441353573,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.23158869743347169,
|
|
"num_tokens": 40821438.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.293314409255982,
|
|
"epoch": 1.7103746397694524,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047113755775108333,
|
|
"loss": 4.8063,
|
|
"mean_token_accuracy": 0.23431237936019897,
|
|
"num_tokens": 40833335.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.452017736434937,
|
|
"epoch": 1.7108549471661862,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047112075653489913,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.22811897993087768,
|
|
"num_tokens": 40844090.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.33890929222107,
|
|
"epoch": 1.7113352545629201,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004711039507653734,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.23028045296669006,
|
|
"num_tokens": 40855176.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.299865484237671,
|
|
"epoch": 1.7118155619596542,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004710871404428961,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.2293744221329689,
|
|
"num_tokens": 40866190.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.320199060440063,
|
|
"epoch": 1.7122958693563881,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047107032556785786,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.23105816096067427,
|
|
"num_tokens": 40876273.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.265713453292847,
|
|
"epoch": 1.712776176753122,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047105350614064874,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.24215801805257797,
|
|
"num_tokens": 40887843.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.332673025131226,
|
|
"epoch": 1.7132564841498559,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047103668216165944,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.23663513064384462,
|
|
"num_tokens": 40898648.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.249697971343994,
|
|
"epoch": 1.71373679154659,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047101985363128045,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.2370961308479309,
|
|
"num_tokens": 40910817.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.333352279663086,
|
|
"epoch": 1.7142170989433239,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047100302054990255,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.23611992299556733,
|
|
"num_tokens": 40922520.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.325203800201416,
|
|
"epoch": 1.7146974063400577,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004709861829179165,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.23326247781515122,
|
|
"num_tokens": 40934188.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.355665588378907,
|
|
"epoch": 1.7151777137367916,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047096934073571325,
|
|
"loss": 4.8804,
|
|
"mean_token_accuracy": 0.23150865584611893,
|
|
"num_tokens": 40944520.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.386121463775635,
|
|
"epoch": 1.7156580211335255,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047095249400368384,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.22216322124004365,
|
|
"num_tokens": 40955874.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.289990520477295,
|
|
"epoch": 1.7161383285302594,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047093564272221927,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.23259228467941284,
|
|
"num_tokens": 40966697.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.2582660675048825,
|
|
"epoch": 1.7166186359269933,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047091878689171105,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.23319696485996247,
|
|
"num_tokens": 40978107.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.359699296951294,
|
|
"epoch": 1.7170989433237271,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004709019265125502,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.23546558171510695,
|
|
"num_tokens": 40991535.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.400731182098388,
|
|
"epoch": 1.717579250720461,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047088506158512837,
|
|
"loss": 4.87,
|
|
"mean_token_accuracy": 0.22968026101589203,
|
|
"num_tokens": 41001333.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.248492479324341,
|
|
"epoch": 1.718059558117195,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047086819210983714,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.23710882365703584,
|
|
"num_tokens": 41012854.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.275948238372803,
|
|
"epoch": 1.7185398655139288,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047085131808706813,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.24112180173397063,
|
|
"num_tokens": 41024041.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.351696109771728,
|
|
"epoch": 1.7190201729106627,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004708344395172129,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.23446576595306395,
|
|
"num_tokens": 41034788.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.368868970870972,
|
|
"epoch": 1.7195004803073968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004708175564006636,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.24357000589370728,
|
|
"num_tokens": 41046513.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.386513566970825,
|
|
"epoch": 1.7199807877041307,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004708006687378121,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.22210543006658554,
|
|
"num_tokens": 41059054.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.333546590805054,
|
|
"epoch": 1.7204610951008645,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004707837765290505,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.2326895922422409,
|
|
"num_tokens": 41070171.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.282652282714844,
|
|
"epoch": 1.7209414024975984,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004707668797747709,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.23269082307815553,
|
|
"num_tokens": 41080963.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.320404577255249,
|
|
"epoch": 1.7214217098943325,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004707499784753657,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.23227480053901672,
|
|
"num_tokens": 41092658.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.344872903823853,
|
|
"epoch": 1.7219020172910664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004707330726312273,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.2263922333717346,
|
|
"num_tokens": 41104521.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.339590167999267,
|
|
"epoch": 1.7223823246878003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047071616224274803,
|
|
"loss": 4.8269,
|
|
"mean_token_accuracy": 0.23808463364839555,
|
|
"num_tokens": 41116420.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.323220682144165,
|
|
"epoch": 1.7228626320845342,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004706992473103207,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.23438357710838317,
|
|
"num_tokens": 41127747.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.334920978546142,
|
|
"epoch": 1.723342939481268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047068232783433806,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.23581747263669967,
|
|
"num_tokens": 41138498.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.382309436798096,
|
|
"epoch": 1.723823246878002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004706654038151927,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.2313832312822342,
|
|
"num_tokens": 41149781.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.3551623821258545,
|
|
"epoch": 1.7243035542747358,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004706484752532777,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.23643603473901748,
|
|
"num_tokens": 41160421.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.283184337615967,
|
|
"epoch": 1.7247838616714697,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004706315421489861,
|
|
"loss": 4.7992,
|
|
"mean_token_accuracy": 0.24343128353357316,
|
|
"num_tokens": 41171192.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.297224378585815,
|
|
"epoch": 1.7252641690682036,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004706146045027109,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.23663620203733443,
|
|
"num_tokens": 41182396.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.402194976806641,
|
|
"epoch": 1.7257444764649374,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004705976623148455,
|
|
"loss": 4.9538,
|
|
"mean_token_accuracy": 0.21937407106161116,
|
|
"num_tokens": 41194939.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.337102365493775,
|
|
"epoch": 1.7262247838616713,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047058071558578324,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.22709277421236038,
|
|
"num_tokens": 41206670.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.3930981159210205,
|
|
"epoch": 1.7267050912584054,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004705637643159175,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.22125570327043534,
|
|
"num_tokens": 41220200.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.375378894805908,
|
|
"epoch": 1.7271853986551393,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047054680850564185,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.23934533298015595,
|
|
"num_tokens": 41231697.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.3446568012237545,
|
|
"epoch": 1.7276657060518732,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004705298481553499,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.23490726947784424,
|
|
"num_tokens": 41243835.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.3816304206848145,
|
|
"epoch": 1.728146013448607,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047051288326543553,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.23618047684431076,
|
|
"num_tokens": 41255147.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.442400884628296,
|
|
"epoch": 1.7286263208453412,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047049591383629247,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.21958484649658203,
|
|
"num_tokens": 41267863.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.397318506240845,
|
|
"epoch": 1.729106628242075,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047047893986831493,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.23012505173683168,
|
|
"num_tokens": 41278506.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.729106628242075,
|
|
"eval_entropy": 5.13264592225118,
|
|
"eval_loss": 4.885778427124023,
|
|
"eval_mean_token_accuracy": 0.24051083410126967,
|
|
"eval_num_tokens": 41278506.0,
|
|
"eval_runtime": 20.4361,
|
|
"eval_samples_per_second": 1605.736,
|
|
"eval_steps_per_second": 200.723,
|
|
"step": 18000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 104090,
|
|
"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": 9365090288209920.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|