6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.3369461447745269,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.69199733734131,
|
||
|
|
"epoch": 0.0005615769079575448,
|
||
|
|
"grad_norm": 14.125,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.84,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 11659.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.691959762573243,
|
||
|
|
"epoch": 0.0011231538159150896,
|
||
|
|
"grad_norm": 14.875,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7444,
|
||
|
|
"mean_token_accuracy": 7.587253348901868e-05,
|
||
|
|
"num_tokens": 21794.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.691159057617188,
|
||
|
|
"epoch": 0.0016847307238726343,
|
||
|
|
"grad_norm": 10.5625,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.4856,
|
||
|
|
"mean_token_accuracy": 0.01876390671823174,
|
||
|
|
"num_tokens": 33206.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.683279323577882,
|
||
|
|
"epoch": 0.0022463076318301792,
|
||
|
|
"grad_norm": 6.25,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.1599,
|
||
|
|
"mean_token_accuracy": 0.034115538187325004,
|
||
|
|
"num_tokens": 44487.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.643766784667969,
|
||
|
|
"epoch": 0.002807884539787724,
|
||
|
|
"grad_norm": 4.09375,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 9.8718,
|
||
|
|
"mean_token_accuracy": 0.04097060300409794,
|
||
|
|
"num_tokens": 56062.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.59372034072876,
|
||
|
|
"epoch": 0.0033694614477452686,
|
||
|
|
"grad_norm": 3.21875,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 9.6884,
|
||
|
|
"mean_token_accuracy": 0.0397952314466238,
|
||
|
|
"num_tokens": 67453.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.589542388916016,
|
||
|
|
"epoch": 0.003931038355702813,
|
||
|
|
"grad_norm": 2.71875,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 9.6654,
|
||
|
|
"mean_token_accuracy": 0.040205162949860096,
|
||
|
|
"num_tokens": 78527.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.591767120361329,
|
||
|
|
"epoch": 0.0044926152636603585,
|
||
|
|
"grad_norm": 2.578125,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 9.5713,
|
||
|
|
"mean_token_accuracy": 0.04592900909483433,
|
||
|
|
"num_tokens": 89267.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.579859638214112,
|
||
|
|
"epoch": 0.005054192171617903,
|
||
|
|
"grad_norm": 2.609375,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.5319,
|
||
|
|
"mean_token_accuracy": 0.04604604430496693,
|
||
|
|
"num_tokens": 102035.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.586153793334962,
|
||
|
|
"epoch": 0.005615769079575448,
|
||
|
|
"grad_norm": 2.671875,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.4905,
|
||
|
|
"mean_token_accuracy": 0.04422647394239902,
|
||
|
|
"num_tokens": 112734.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.576881599426269,
|
||
|
|
"epoch": 0.006177345987532993,
|
||
|
|
"grad_norm": 2.390625,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.4077,
|
||
|
|
"mean_token_accuracy": 0.03770475871860981,
|
||
|
|
"num_tokens": 123854.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.551261711120606,
|
||
|
|
"epoch": 0.006738922895490537,
|
||
|
|
"grad_norm": 2.484375,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.3296,
|
||
|
|
"mean_token_accuracy": 0.04481921121478081,
|
||
|
|
"num_tokens": 133444.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.531212902069091,
|
||
|
|
"epoch": 0.007300499803448083,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.2183,
|
||
|
|
"mean_token_accuracy": 0.05932291820645332,
|
||
|
|
"num_tokens": 144678.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.393140697479248,
|
||
|
|
"epoch": 0.007862076711405626,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.1453,
|
||
|
|
"mean_token_accuracy": 0.056172562018036845,
|
||
|
|
"num_tokens": 155866.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.388829708099365,
|
||
|
|
"epoch": 0.008423653619363172,
|
||
|
|
"grad_norm": 2.421875,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.0724,
|
||
|
|
"mean_token_accuracy": 0.06042071580886841,
|
||
|
|
"num_tokens": 166965.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.462674045562744,
|
||
|
|
"epoch": 0.008985230527320717,
|
||
|
|
"grad_norm": 2.296875,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 8.9521,
|
||
|
|
"mean_token_accuracy": 0.0692318245768547,
|
||
|
|
"num_tokens": 177423.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.331163120269775,
|
||
|
|
"epoch": 0.00954680743527826,
|
||
|
|
"grad_norm": 2.3125,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 8.8328,
|
||
|
|
"mean_token_accuracy": 0.07574180811643601,
|
||
|
|
"num_tokens": 188687.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.222314929962158,
|
||
|
|
"epoch": 0.010108384343235806,
|
||
|
|
"grad_norm": 2.21875,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 8.7904,
|
||
|
|
"mean_token_accuracy": 0.07162599004805088,
|
||
|
|
"num_tokens": 200173.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.237919807434082,
|
||
|
|
"epoch": 0.010669961251193351,
|
||
|
|
"grad_norm": 2.234375,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 8.6616,
|
||
|
|
"mean_token_accuracy": 0.07694140449166298,
|
||
|
|
"num_tokens": 210877.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.136093044281006,
|
||
|
|
"epoch": 0.011231538159150897,
|
||
|
|
"grad_norm": 2.234375,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 8.5155,
|
||
|
|
"mean_token_accuracy": 0.0797793373465538,
|
||
|
|
"num_tokens": 221770.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.076034641265869,
|
||
|
|
"epoch": 0.01179311506710844,
|
||
|
|
"grad_norm": 2.1875,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.4363,
|
||
|
|
"mean_token_accuracy": 0.08221952021121978,
|
||
|
|
"num_tokens": 232140.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.958266925811767,
|
||
|
|
"epoch": 0.012354691975065986,
|
||
|
|
"grad_norm": 2.0,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.3904,
|
||
|
|
"mean_token_accuracy": 0.07742410823702812,
|
||
|
|
"num_tokens": 244186.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.92665433883667,
|
||
|
|
"epoch": 0.012916268883023531,
|
||
|
|
"grad_norm": 1.9453125,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.1995,
|
||
|
|
"mean_token_accuracy": 0.08315626531839371,
|
||
|
|
"num_tokens": 254805.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.761961746215821,
|
||
|
|
"epoch": 0.013477845790981074,
|
||
|
|
"grad_norm": 2.0625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.0418,
|
||
|
|
"mean_token_accuracy": 0.09004319682717324,
|
||
|
|
"num_tokens": 265055.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.711062622070312,
|
||
|
|
"epoch": 0.01403942269893862,
|
||
|
|
"grad_norm": 1.7890625,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 7.9103,
|
||
|
|
"mean_token_accuracy": 0.08997093960642814,
|
||
|
|
"num_tokens": 275850.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.528320026397704,
|
||
|
|
"epoch": 0.014600999606896165,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 7.8455,
|
||
|
|
"mean_token_accuracy": 0.08536324948072434,
|
||
|
|
"num_tokens": 286802.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.43552894592285,
|
||
|
|
"epoch": 0.015162576514853709,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 7.8037,
|
||
|
|
"mean_token_accuracy": 0.08595463857054711,
|
||
|
|
"num_tokens": 297070.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.212979316711426,
|
||
|
|
"epoch": 0.015724153422811252,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 7.6719,
|
||
|
|
"mean_token_accuracy": 0.08102959841489792,
|
||
|
|
"num_tokens": 309617.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.98444652557373,
|
||
|
|
"epoch": 0.0162857303307688,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 7.5759,
|
||
|
|
"mean_token_accuracy": 0.0875118389725685,
|
||
|
|
"num_tokens": 321310.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.683964824676513,
|
||
|
|
"epoch": 0.016847307238726343,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 7.4529,
|
||
|
|
"mean_token_accuracy": 0.09075084403157234,
|
||
|
|
"num_tokens": 332243.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.567935752868653,
|
||
|
|
"epoch": 0.017408884146683887,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 7.3707,
|
||
|
|
"mean_token_accuracy": 0.09007078930735588,
|
||
|
|
"num_tokens": 342847.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.343489074707032,
|
||
|
|
"epoch": 0.017970461054641434,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.2838,
|
||
|
|
"mean_token_accuracy": 0.09157189652323723,
|
||
|
|
"num_tokens": 353570.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.204969120025634,
|
||
|
|
"epoch": 0.018532037962598977,
|
||
|
|
"grad_norm": 1.6484375,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.2465,
|
||
|
|
"mean_token_accuracy": 0.09896112084388733,
|
||
|
|
"num_tokens": 364330.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.996236562728882,
|
||
|
|
"epoch": 0.01909361487055652,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.2602,
|
||
|
|
"mean_token_accuracy": 0.09376133009791374,
|
||
|
|
"num_tokens": 374930.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.048484230041504,
|
||
|
|
"epoch": 0.019655191778514068,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.2096,
|
||
|
|
"mean_token_accuracy": 0.09344206750392914,
|
||
|
|
"num_tokens": 384690.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.837320470809937,
|
||
|
|
"epoch": 0.020216768686471612,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.1975,
|
||
|
|
"mean_token_accuracy": 0.0976659506559372,
|
||
|
|
"num_tokens": 395753.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.850379133224488,
|
||
|
|
"epoch": 0.020778345594429155,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.1482,
|
||
|
|
"mean_token_accuracy": 0.09964234381914139,
|
||
|
|
"num_tokens": 407049.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.762841367721558,
|
||
|
|
"epoch": 0.021339922502386702,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.1287,
|
||
|
|
"mean_token_accuracy": 0.10560355857014656,
|
||
|
|
"num_tokens": 417942.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.797861766815186,
|
||
|
|
"epoch": 0.021901499410344246,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.1548,
|
||
|
|
"mean_token_accuracy": 0.10006576329469681,
|
||
|
|
"num_tokens": 428151.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.798689174652099,
|
||
|
|
"epoch": 0.022463076318301793,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.2293,
|
||
|
|
"mean_token_accuracy": 0.09349132850766181,
|
||
|
|
"num_tokens": 439837.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.697256374359131,
|
||
|
|
"epoch": 0.023024653226259337,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.0368,
|
||
|
|
"mean_token_accuracy": 0.1030456155538559,
|
||
|
|
"num_tokens": 450357.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.727653217315674,
|
||
|
|
"epoch": 0.02358623013421688,
|
||
|
|
"grad_norm": 1.5859375,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.0594,
|
||
|
|
"mean_token_accuracy": 0.10246213376522065,
|
||
|
|
"num_tokens": 461174.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.568133020401001,
|
||
|
|
"epoch": 0.024147807042174427,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.1079,
|
||
|
|
"mean_token_accuracy": 0.10158494561910629,
|
||
|
|
"num_tokens": 472785.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.636423826217651,
|
||
|
|
"epoch": 0.02470938395013197,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.0786,
|
||
|
|
"mean_token_accuracy": 0.10676130950450897,
|
||
|
|
"num_tokens": 483248.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.532600831985474,
|
||
|
|
"epoch": 0.025270960858089515,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 6.9308,
|
||
|
|
"mean_token_accuracy": 0.10589632242918015,
|
||
|
|
"num_tokens": 494690.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.67465763092041,
|
||
|
|
"epoch": 0.025832537766047062,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.1502,
|
||
|
|
"mean_token_accuracy": 0.10144523307681083,
|
||
|
|
"num_tokens": 506192.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.504990577697754,
|
||
|
|
"epoch": 0.026394114674004605,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.0149,
|
||
|
|
"mean_token_accuracy": 0.10282881110906601,
|
||
|
|
"num_tokens": 517152.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.417121648788452,
|
||
|
|
"epoch": 0.02695569158196215,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 6.9465,
|
||
|
|
"mean_token_accuracy": 0.11191134601831436,
|
||
|
|
"num_tokens": 527836.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.521721506118775,
|
||
|
|
"epoch": 0.027517268489919696,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.074,
|
||
|
|
"mean_token_accuracy": 0.10694148242473603,
|
||
|
|
"num_tokens": 539491.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5123631954193115,
|
||
|
|
"epoch": 0.02807884539787724,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.0457,
|
||
|
|
"mean_token_accuracy": 0.10798109769821167,
|
||
|
|
"num_tokens": 550816.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.512091779708863,
|
||
|
|
"epoch": 0.028640422305834783,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.0864,
|
||
|
|
"mean_token_accuracy": 0.10389656201004982,
|
||
|
|
"num_tokens": 561566.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.469761371612549,
|
||
|
|
"epoch": 0.02920199921379233,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.0043,
|
||
|
|
"mean_token_accuracy": 0.10888160541653633,
|
||
|
|
"num_tokens": 573032.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.406926107406616,
|
||
|
|
"epoch": 0.029763576121749874,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 6.9295,
|
||
|
|
"mean_token_accuracy": 0.11083082705736161,
|
||
|
|
"num_tokens": 584140.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.479501533508301,
|
||
|
|
"epoch": 0.030325153029707418,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 6.9942,
|
||
|
|
"mean_token_accuracy": 0.11373844891786575,
|
||
|
|
"num_tokens": 595097.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.397661972045898,
|
||
|
|
"epoch": 0.030886729937664965,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.0078,
|
||
|
|
"mean_token_accuracy": 0.10632957443594933,
|
||
|
|
"num_tokens": 606797.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.419397830963135,
|
||
|
|
"epoch": 0.031448306845622505,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 6.9786,
|
||
|
|
"mean_token_accuracy": 0.10562919154763221,
|
||
|
|
"num_tokens": 618187.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.363228178024292,
|
||
|
|
"epoch": 0.032009883753580055,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 6.9095,
|
||
|
|
"mean_token_accuracy": 0.11332885026931763,
|
||
|
|
"num_tokens": 629829.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.330576467514038,
|
||
|
|
"epoch": 0.0325714606615376,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 6.9224,
|
||
|
|
"mean_token_accuracy": 0.11370442360639572,
|
||
|
|
"num_tokens": 640914.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.378089332580567,
|
||
|
|
"epoch": 0.03313303756949514,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 6.9324,
|
||
|
|
"mean_token_accuracy": 0.10816294327378273,
|
||
|
|
"num_tokens": 653057.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.25587100982666,
|
||
|
|
"epoch": 0.033694614477452686,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 6.8538,
|
||
|
|
"mean_token_accuracy": 0.11798578426241875,
|
||
|
|
"num_tokens": 663437.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.289643287658691,
|
||
|
|
"epoch": 0.03425619138541023,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 6.9274,
|
||
|
|
"mean_token_accuracy": 0.10952336639165879,
|
||
|
|
"num_tokens": 675416.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.191143465042114,
|
||
|
|
"epoch": 0.03481776829336777,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 6.7139,
|
||
|
|
"mean_token_accuracy": 0.11911309286952018,
|
||
|
|
"num_tokens": 686633.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.206870460510254,
|
||
|
|
"epoch": 0.035379345201325324,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 6.8231,
|
||
|
|
"mean_token_accuracy": 0.11704705879092217,
|
||
|
|
"num_tokens": 698065.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.289987993240357,
|
||
|
|
"epoch": 0.03594092210928287,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 6.8248,
|
||
|
|
"mean_token_accuracy": 0.11439744681119919,
|
||
|
|
"num_tokens": 708652.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.232913827896118,
|
||
|
|
"epoch": 0.03650249901724041,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 6.9881,
|
||
|
|
"mean_token_accuracy": 0.10934536978602409,
|
||
|
|
"num_tokens": 720199.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.196808099746704,
|
||
|
|
"epoch": 0.037064075925197955,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 6.9619,
|
||
|
|
"mean_token_accuracy": 0.10815565586090088,
|
||
|
|
"num_tokens": 732964.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.188594055175781,
|
||
|
|
"epoch": 0.0376256528331555,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 6.7203,
|
||
|
|
"mean_token_accuracy": 0.11759673580527305,
|
||
|
|
"num_tokens": 743528.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216085720062256,
|
||
|
|
"epoch": 0.03818722974111304,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 6.7942,
|
||
|
|
"mean_token_accuracy": 0.11542778238654136,
|
||
|
|
"num_tokens": 754365.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.035056495666504,
|
||
|
|
"epoch": 0.03874880664907059,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 6.7182,
|
||
|
|
"mean_token_accuracy": 0.11288121640682221,
|
||
|
|
"num_tokens": 766094.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.112251138687133,
|
||
|
|
"epoch": 0.039310383557028136,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 6.7712,
|
||
|
|
"mean_token_accuracy": 0.11812571287155152,
|
||
|
|
"num_tokens": 777275.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1510889530181885,
|
||
|
|
"epoch": 0.03987196046498568,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 6.844,
|
||
|
|
"mean_token_accuracy": 0.1156160980463028,
|
||
|
|
"num_tokens": 789436.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.172001838684082,
|
||
|
|
"epoch": 0.040433537372943223,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 6.8679,
|
||
|
|
"mean_token_accuracy": 0.11365923285484314,
|
||
|
|
"num_tokens": 800164.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.032376146316528,
|
||
|
|
"epoch": 0.04099511428090077,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 6.73,
|
||
|
|
"mean_token_accuracy": 0.1194022923707962,
|
||
|
|
"num_tokens": 811797.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.035384750366211,
|
||
|
|
"epoch": 0.04155669118885831,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 6.744,
|
||
|
|
"mean_token_accuracy": 0.12005754113197327,
|
||
|
|
"num_tokens": 824158.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.067680978775025,
|
||
|
|
"epoch": 0.04211826809681586,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.7441,
|
||
|
|
"mean_token_accuracy": 0.12421485558152198,
|
||
|
|
"num_tokens": 835803.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.172079133987427,
|
||
|
|
"epoch": 0.042679845004773405,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 6.8204,
|
||
|
|
"mean_token_accuracy": 0.11587870791554451,
|
||
|
|
"num_tokens": 848106.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.041548442840576,
|
||
|
|
"epoch": 0.04324142191273095,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 6.7849,
|
||
|
|
"mean_token_accuracy": 0.11313552036881447,
|
||
|
|
"num_tokens": 859101.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.045945501327514,
|
||
|
|
"epoch": 0.04380299882068849,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.6582,
|
||
|
|
"mean_token_accuracy": 0.12235154137015343,
|
||
|
|
"num_tokens": 870309.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.961396837234497,
|
||
|
|
"epoch": 0.044364575728646036,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 6.7449,
|
||
|
|
"mean_token_accuracy": 0.11937168762087821,
|
||
|
|
"num_tokens": 881515.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.038133382797241,
|
||
|
|
"epoch": 0.044926152636603586,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.7085,
|
||
|
|
"mean_token_accuracy": 0.12275884225964546,
|
||
|
|
"num_tokens": 892129.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.987507295608521,
|
||
|
|
"epoch": 0.04548772954456113,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 6.7253,
|
||
|
|
"mean_token_accuracy": 0.11545129716396332,
|
||
|
|
"num_tokens": 903186.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.024265384674072,
|
||
|
|
"epoch": 0.046049306452518673,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.6962,
|
||
|
|
"mean_token_accuracy": 0.12458662018179893,
|
||
|
|
"num_tokens": 913471.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.011588430404663,
|
||
|
|
"epoch": 0.04661088336047622,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.6937,
|
||
|
|
"mean_token_accuracy": 0.11497079506516457,
|
||
|
|
"num_tokens": 924283.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.955825996398926,
|
||
|
|
"epoch": 0.04717246026843376,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.7257,
|
||
|
|
"mean_token_accuracy": 0.12139789834618568,
|
||
|
|
"num_tokens": 934975.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.922592639923096,
|
||
|
|
"epoch": 0.047734037176391304,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.6052,
|
||
|
|
"mean_token_accuracy": 0.12621162980794906,
|
||
|
|
"num_tokens": 945587.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.930565118789673,
|
||
|
|
"epoch": 0.048295614084348855,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.6627,
|
||
|
|
"mean_token_accuracy": 0.11665054634213448,
|
||
|
|
"num_tokens": 955935.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9625404357910154,
|
||
|
|
"epoch": 0.0488571909923064,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.6217,
|
||
|
|
"mean_token_accuracy": 0.12234737649559975,
|
||
|
|
"num_tokens": 967960.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.918611526489258,
|
||
|
|
"epoch": 0.04941876790026394,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.6711,
|
||
|
|
"mean_token_accuracy": 0.12240631505846977,
|
||
|
|
"num_tokens": 979680.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.917942047119141,
|
||
|
|
"epoch": 0.049980344808221486,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.7478,
|
||
|
|
"mean_token_accuracy": 0.12340849041938781,
|
||
|
|
"num_tokens": 990600.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.053799295425415,
|
||
|
|
"epoch": 0.05054192171617903,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.7757,
|
||
|
|
"mean_token_accuracy": 0.12520086020231247,
|
||
|
|
"num_tokens": 1002331.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.887303018569947,
|
||
|
|
"epoch": 0.05110349862413657,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.5812,
|
||
|
|
"mean_token_accuracy": 0.12343053072690964,
|
||
|
|
"num_tokens": 1013473.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.888548421859741,
|
||
|
|
"epoch": 0.051665075532094124,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.6644,
|
||
|
|
"mean_token_accuracy": 0.12126656621694565,
|
||
|
|
"num_tokens": 1024434.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.952251386642456,
|
||
|
|
"epoch": 0.05222665244005167,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.6902,
|
||
|
|
"mean_token_accuracy": 0.11487246379256248,
|
||
|
|
"num_tokens": 1035452.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.930226802825928,
|
||
|
|
"epoch": 0.05278822934800921,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.563,
|
||
|
|
"mean_token_accuracy": 0.12226332053542137,
|
||
|
|
"num_tokens": 1046213.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.727850151062012,
|
||
|
|
"epoch": 0.053349806255966754,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.5962,
|
||
|
|
"mean_token_accuracy": 0.12299741804599762,
|
||
|
|
"num_tokens": 1057469.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.949178981781006,
|
||
|
|
"epoch": 0.0539113831639243,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.7449,
|
||
|
|
"mean_token_accuracy": 0.11885052472352982,
|
||
|
|
"num_tokens": 1069543.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.829960346221924,
|
||
|
|
"epoch": 0.05447296007188184,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.6032,
|
||
|
|
"mean_token_accuracy": 0.12388219833374023,
|
||
|
|
"num_tokens": 1080476.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.998953199386596,
|
||
|
|
"epoch": 0.05503453697983939,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.7311,
|
||
|
|
"mean_token_accuracy": 0.12146280780434608,
|
||
|
|
"num_tokens": 1091700.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7566276550292965,
|
||
|
|
"epoch": 0.055596113887796936,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.623,
|
||
|
|
"mean_token_accuracy": 0.12116920575499535,
|
||
|
|
"num_tokens": 1103056.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9239182472229,
|
||
|
|
"epoch": 0.05615769079575448,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.6717,
|
||
|
|
"mean_token_accuracy": 0.12681836783885955,
|
||
|
|
"num_tokens": 1114836.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.807825708389283,
|
||
|
|
"epoch": 0.05671926770371202,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.5797,
|
||
|
|
"mean_token_accuracy": 0.12368799895048141,
|
||
|
|
"num_tokens": 1125993.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.843410921096802,
|
||
|
|
"epoch": 0.05728084461166957,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.6499,
|
||
|
|
"mean_token_accuracy": 0.12425459921360016,
|
||
|
|
"num_tokens": 1136719.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.831955003738403,
|
||
|
|
"epoch": 0.05784242151962711,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.5187,
|
||
|
|
"mean_token_accuracy": 0.12717537805438042,
|
||
|
|
"num_tokens": 1146947.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8093184471130375,
|
||
|
|
"epoch": 0.05840399842758466,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.6549,
|
||
|
|
"mean_token_accuracy": 0.1217711940407753,
|
||
|
|
"num_tokens": 1157974.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.776603937149048,
|
||
|
|
"epoch": 0.058965575335542204,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.5957,
|
||
|
|
"mean_token_accuracy": 0.12135538086295128,
|
||
|
|
"num_tokens": 1168573.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.728848695755005,
|
||
|
|
"epoch": 0.05952715224349975,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.4734,
|
||
|
|
"mean_token_accuracy": 0.1271596685051918,
|
||
|
|
"num_tokens": 1178446.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.797522687911988,
|
||
|
|
"epoch": 0.06008872915145729,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.5178,
|
||
|
|
"mean_token_accuracy": 0.12605770081281661,
|
||
|
|
"num_tokens": 1190558.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.782135057449341,
|
||
|
|
"epoch": 0.060650306059414835,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.684,
|
||
|
|
"mean_token_accuracy": 0.12132162749767303,
|
||
|
|
"num_tokens": 1201929.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.717436075210571,
|
||
|
|
"epoch": 0.06121188296737238,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.5219,
|
||
|
|
"mean_token_accuracy": 0.12698362171649932,
|
||
|
|
"num_tokens": 1213155.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.891464042663574,
|
||
|
|
"epoch": 0.06177345987532993,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.5834,
|
||
|
|
"mean_token_accuracy": 0.12621916830539703,
|
||
|
|
"num_tokens": 1223961.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.545057249069214,
|
||
|
|
"epoch": 0.06233503678328747,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.4808,
|
||
|
|
"mean_token_accuracy": 0.12663164362311363,
|
||
|
|
"num_tokens": 1233888.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.767652130126953,
|
||
|
|
"epoch": 0.06289661369124501,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.5989,
|
||
|
|
"mean_token_accuracy": 0.11711542010307312,
|
||
|
|
"num_tokens": 1244405.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754672956466675,
|
||
|
|
"epoch": 0.06345819059920256,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.5399,
|
||
|
|
"mean_token_accuracy": 0.12238047644495964,
|
||
|
|
"num_tokens": 1257099.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.819364261627197,
|
||
|
|
"epoch": 0.06401976750716011,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.6517,
|
||
|
|
"mean_token_accuracy": 0.12521917819976808,
|
||
|
|
"num_tokens": 1267965.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.710899448394775,
|
||
|
|
"epoch": 0.06458134441511765,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.5609,
|
||
|
|
"mean_token_accuracy": 0.1245420053601265,
|
||
|
|
"num_tokens": 1280075.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.763568544387818,
|
||
|
|
"epoch": 0.0651429213230752,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.558,
|
||
|
|
"mean_token_accuracy": 0.1273508958518505,
|
||
|
|
"num_tokens": 1290574.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.691582345962525,
|
||
|
|
"epoch": 0.06570449823103273,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.5351,
|
||
|
|
"mean_token_accuracy": 0.13094205483794213,
|
||
|
|
"num_tokens": 1302680.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.729927682876587,
|
||
|
|
"epoch": 0.06626607513899029,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.5249,
|
||
|
|
"mean_token_accuracy": 0.12820309847593309,
|
||
|
|
"num_tokens": 1314577.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.720426177978515,
|
||
|
|
"epoch": 0.06682765204694784,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.6534,
|
||
|
|
"mean_token_accuracy": 0.127957072108984,
|
||
|
|
"num_tokens": 1326560.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889089202880859,
|
||
|
|
"epoch": 0.06738922895490537,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.7183,
|
||
|
|
"mean_token_accuracy": 0.11803506314754486,
|
||
|
|
"num_tokens": 1339105.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515667247772217,
|
||
|
|
"epoch": 0.06795080586286292,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.3725,
|
||
|
|
"mean_token_accuracy": 0.13529646024107933,
|
||
|
|
"num_tokens": 1349914.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7512102127075195,
|
||
|
|
"epoch": 0.06851238277082046,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.6063,
|
||
|
|
"mean_token_accuracy": 0.12086223512887954,
|
||
|
|
"num_tokens": 1361700.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.72710428237915,
|
||
|
|
"epoch": 0.06907395967877801,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.6141,
|
||
|
|
"mean_token_accuracy": 0.12547043561935425,
|
||
|
|
"num_tokens": 1373103.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.627476501464844,
|
||
|
|
"epoch": 0.06963553658673555,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.4321,
|
||
|
|
"mean_token_accuracy": 0.13028801828622819,
|
||
|
|
"num_tokens": 1383742.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.588920402526855,
|
||
|
|
"epoch": 0.0701971134946931,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.5754,
|
||
|
|
"mean_token_accuracy": 0.12626228407025336,
|
||
|
|
"num_tokens": 1396656.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6745930194854735,
|
||
|
|
"epoch": 0.07075869040265065,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.4518,
|
||
|
|
"mean_token_accuracy": 0.14176289066672326,
|
||
|
|
"num_tokens": 1406709.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6905371189117435,
|
||
|
|
"epoch": 0.07132026731060818,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.4806,
|
||
|
|
"mean_token_accuracy": 0.1374201662838459,
|
||
|
|
"num_tokens": 1417793.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.665899324417114,
|
||
|
|
"epoch": 0.07188184421856574,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.5627,
|
||
|
|
"mean_token_accuracy": 0.13078077808022498,
|
||
|
|
"num_tokens": 1429093.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.610226154327393,
|
||
|
|
"epoch": 0.07244342112652327,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.492,
|
||
|
|
"mean_token_accuracy": 0.13368908688426018,
|
||
|
|
"num_tokens": 1440907.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.695104122161865,
|
||
|
|
"epoch": 0.07300499803448082,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.5606,
|
||
|
|
"mean_token_accuracy": 0.12654911056160928,
|
||
|
|
"num_tokens": 1452089.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7353943347930905,
|
||
|
|
"epoch": 0.07356657494243837,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.5794,
|
||
|
|
"mean_token_accuracy": 0.12776191011071206,
|
||
|
|
"num_tokens": 1464378.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.62319712638855,
|
||
|
|
"epoch": 0.07412815185039591,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.5055,
|
||
|
|
"mean_token_accuracy": 0.13134382292628288,
|
||
|
|
"num_tokens": 1476678.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5715944290161135,
|
||
|
|
"epoch": 0.07468972875835346,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.3478,
|
||
|
|
"mean_token_accuracy": 0.1335635580122471,
|
||
|
|
"num_tokens": 1486808.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.715902948379517,
|
||
|
|
"epoch": 0.075251305666311,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.6385,
|
||
|
|
"mean_token_accuracy": 0.1281900115311146,
|
||
|
|
"num_tokens": 1499281.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594720935821533,
|
||
|
|
"epoch": 0.07581288257426855,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.5429,
|
||
|
|
"mean_token_accuracy": 0.12866927832365035,
|
||
|
|
"num_tokens": 1510202.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.640082120895386,
|
||
|
|
"epoch": 0.07637445948222608,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.4175,
|
||
|
|
"mean_token_accuracy": 0.13352399095892906,
|
||
|
|
"num_tokens": 1521492.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.529734992980957,
|
||
|
|
"epoch": 0.07693603639018363,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.4224,
|
||
|
|
"mean_token_accuracy": 0.1373117059469223,
|
||
|
|
"num_tokens": 1532856.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563913011550904,
|
||
|
|
"epoch": 0.07749761329814119,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.4298,
|
||
|
|
"mean_token_accuracy": 0.13284594789147378,
|
||
|
|
"num_tokens": 1543408.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5086448192596436,
|
||
|
|
"epoch": 0.07805919020609872,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.4744,
|
||
|
|
"mean_token_accuracy": 0.1292234666645527,
|
||
|
|
"num_tokens": 1555474.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.665031242370605,
|
||
|
|
"epoch": 0.07862076711405627,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.5664,
|
||
|
|
"mean_token_accuracy": 0.1303274817764759,
|
||
|
|
"num_tokens": 1567484.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.562999153137207,
|
||
|
|
"epoch": 0.07918234402201381,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.3967,
|
||
|
|
"mean_token_accuracy": 0.13949733674526216,
|
||
|
|
"num_tokens": 1578204.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.614490175247193,
|
||
|
|
"epoch": 0.07974392092997136,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.3833,
|
||
|
|
"mean_token_accuracy": 0.1383664131164551,
|
||
|
|
"num_tokens": 1589012.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.435742950439453,
|
||
|
|
"epoch": 0.08030549783792891,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.3943,
|
||
|
|
"mean_token_accuracy": 0.1336691454052925,
|
||
|
|
"num_tokens": 1601099.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609636449813843,
|
||
|
|
"epoch": 0.08086707474588645,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.572,
|
||
|
|
"mean_token_accuracy": 0.12780067026615144,
|
||
|
|
"num_tokens": 1612814.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.573339128494263,
|
||
|
|
"epoch": 0.081428651653844,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.4532,
|
||
|
|
"mean_token_accuracy": 0.13029669150710105,
|
||
|
|
"num_tokens": 1624953.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.592752456665039,
|
||
|
|
"epoch": 0.08199022856180153,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.4967,
|
||
|
|
"mean_token_accuracy": 0.12852037101984023,
|
||
|
|
"num_tokens": 1635673.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.508557653427124,
|
||
|
|
"epoch": 0.08255180546975908,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.3898,
|
||
|
|
"mean_token_accuracy": 0.13426842764019967,
|
||
|
|
"num_tokens": 1647282.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.531473875045776,
|
||
|
|
"epoch": 0.08311338237771662,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.4091,
|
||
|
|
"mean_token_accuracy": 0.13616270646452905,
|
||
|
|
"num_tokens": 1658426.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.508967781066895,
|
||
|
|
"epoch": 0.08367495928567417,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.4464,
|
||
|
|
"mean_token_accuracy": 0.13434510231018065,
|
||
|
|
"num_tokens": 1669958.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.531551885604858,
|
||
|
|
"epoch": 0.08423653619363172,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.496,
|
||
|
|
"mean_token_accuracy": 0.1306629441678524,
|
||
|
|
"num_tokens": 1682409.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5382561683654785,
|
||
|
|
"epoch": 0.08479811310158926,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.4142,
|
||
|
|
"mean_token_accuracy": 0.1416614383459091,
|
||
|
|
"num_tokens": 1692409.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.598318290710449,
|
||
|
|
"epoch": 0.08535969000954681,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.5122,
|
||
|
|
"mean_token_accuracy": 0.1292322888970375,
|
||
|
|
"num_tokens": 1705018.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.487031126022339,
|
||
|
|
"epoch": 0.08592126691750435,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.4388,
|
||
|
|
"mean_token_accuracy": 0.13245034515857695,
|
||
|
|
"num_tokens": 1715625.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.529515266418457,
|
||
|
|
"epoch": 0.0864828438254619,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.5178,
|
||
|
|
"mean_token_accuracy": 0.125034099817276,
|
||
|
|
"num_tokens": 1727045.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.638304615020752,
|
||
|
|
"epoch": 0.08704442073341945,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.5797,
|
||
|
|
"mean_token_accuracy": 0.13172487169504166,
|
||
|
|
"num_tokens": 1737374.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.570305490493775,
|
||
|
|
"epoch": 0.08760599764137698,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.5729,
|
||
|
|
"mean_token_accuracy": 0.1319825679063797,
|
||
|
|
"num_tokens": 1747788.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.380049180984497,
|
||
|
|
"epoch": 0.08816757454933453,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.2706,
|
||
|
|
"mean_token_accuracy": 0.14245652109384538,
|
||
|
|
"num_tokens": 1757769.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.499381113052368,
|
||
|
|
"epoch": 0.08872915145729207,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.3888,
|
||
|
|
"mean_token_accuracy": 0.12719078063964845,
|
||
|
|
"num_tokens": 1769246.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.573248052597046,
|
||
|
|
"epoch": 0.08929072836524962,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.5119,
|
||
|
|
"mean_token_accuracy": 0.131352935731411,
|
||
|
|
"num_tokens": 1781306.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.474650239944458,
|
||
|
|
"epoch": 0.08985230527320717,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.413,
|
||
|
|
"mean_token_accuracy": 0.13447367399930954,
|
||
|
|
"num_tokens": 1792888.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4736183166503904,
|
||
|
|
"epoch": 0.09041388218116471,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.4328,
|
||
|
|
"mean_token_accuracy": 0.13652909994125367,
|
||
|
|
"num_tokens": 1802938.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.540951681137085,
|
||
|
|
"epoch": 0.09097545908912226,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.4417,
|
||
|
|
"mean_token_accuracy": 0.13303363993763923,
|
||
|
|
"num_tokens": 1814738.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546661281585694,
|
||
|
|
"epoch": 0.0915370359970798,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.5162,
|
||
|
|
"mean_token_accuracy": 0.13302921801805495,
|
||
|
|
"num_tokens": 1825100.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.376165437698364,
|
||
|
|
"epoch": 0.09209861290503735,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.3468,
|
||
|
|
"mean_token_accuracy": 0.13940613865852355,
|
||
|
|
"num_tokens": 1835879.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.615822601318359,
|
||
|
|
"epoch": 0.09266018981299488,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.4934,
|
||
|
|
"mean_token_accuracy": 0.12611727342009543,
|
||
|
|
"num_tokens": 1848352.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488889122009278,
|
||
|
|
"epoch": 0.09322176672095243,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.4528,
|
||
|
|
"mean_token_accuracy": 0.13165955916047095,
|
||
|
|
"num_tokens": 1859687.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441867017745972,
|
||
|
|
"epoch": 0.09378334362890998,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.4471,
|
||
|
|
"mean_token_accuracy": 0.13207249566912652,
|
||
|
|
"num_tokens": 1871438.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.437953948974609,
|
||
|
|
"epoch": 0.09434492053686752,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.317,
|
||
|
|
"mean_token_accuracy": 0.1421381339430809,
|
||
|
|
"num_tokens": 1881519.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.583179473876953,
|
||
|
|
"epoch": 0.09490649744482507,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.5235,
|
||
|
|
"mean_token_accuracy": 0.1294063374400139,
|
||
|
|
"num_tokens": 1892428.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5530884742736815,
|
||
|
|
"epoch": 0.09546807435278261,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.3993,
|
||
|
|
"mean_token_accuracy": 0.13649718686938286,
|
||
|
|
"num_tokens": 1903760.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441016054153442,
|
||
|
|
"epoch": 0.09602965126074016,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.4656,
|
||
|
|
"mean_token_accuracy": 0.12715155258774757,
|
||
|
|
"num_tokens": 1915430.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446907186508179,
|
||
|
|
"epoch": 0.09659122816869771,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.4209,
|
||
|
|
"mean_token_accuracy": 0.1297461584210396,
|
||
|
|
"num_tokens": 1925709.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.458964443206787,
|
||
|
|
"epoch": 0.09715280507665525,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.4711,
|
||
|
|
"mean_token_accuracy": 0.13050815761089324,
|
||
|
|
"num_tokens": 1938148.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.31799168586731,
|
||
|
|
"epoch": 0.0977143819846128,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.3348,
|
||
|
|
"mean_token_accuracy": 0.138660329580307,
|
||
|
|
"num_tokens": 1949028.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.477993202209473,
|
||
|
|
"epoch": 0.09827595889257033,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.3788,
|
||
|
|
"mean_token_accuracy": 0.1366566650569439,
|
||
|
|
"num_tokens": 1960353.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.498833131790161,
|
||
|
|
"epoch": 0.09883753580052788,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.4888,
|
||
|
|
"mean_token_accuracy": 0.1329733595252037,
|
||
|
|
"num_tokens": 1972335.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.404474306106567,
|
||
|
|
"epoch": 0.09939911270848542,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.3449,
|
||
|
|
"mean_token_accuracy": 0.13555458709597587,
|
||
|
|
"num_tokens": 1982851.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407796001434326,
|
||
|
|
"epoch": 0.09996068961644297,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.3255,
|
||
|
|
"mean_token_accuracy": 0.13792148530483245,
|
||
|
|
"num_tokens": 1993931.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.429170560836792,
|
||
|
|
"epoch": 0.10052226652440052,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.4634,
|
||
|
|
"mean_token_accuracy": 0.13388581573963165,
|
||
|
|
"num_tokens": 2004838.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3420192241668705,
|
||
|
|
"epoch": 0.10108384343235806,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.2468,
|
||
|
|
"mean_token_accuracy": 0.1361763894557953,
|
||
|
|
"num_tokens": 2015620.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4620874404907225,
|
||
|
|
"epoch": 0.10164542034031561,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.3865,
|
||
|
|
"mean_token_accuracy": 0.13934891074895858,
|
||
|
|
"num_tokens": 2027489.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.273737144470215,
|
||
|
|
"epoch": 0.10220699724827315,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.2673,
|
||
|
|
"mean_token_accuracy": 0.14417464286088943,
|
||
|
|
"num_tokens": 2038475.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.300836038589478,
|
||
|
|
"epoch": 0.1027685741562307,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.2657,
|
||
|
|
"mean_token_accuracy": 0.1379096359014511,
|
||
|
|
"num_tokens": 2048938.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.325875759124756,
|
||
|
|
"epoch": 0.10333015106418825,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.3679,
|
||
|
|
"mean_token_accuracy": 0.1302135966718197,
|
||
|
|
"num_tokens": 2060372.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.354682302474975,
|
||
|
|
"epoch": 0.10389172797214578,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.3505,
|
||
|
|
"mean_token_accuracy": 0.13487576618790625,
|
||
|
|
"num_tokens": 2071558.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.366049098968506,
|
||
|
|
"epoch": 0.10445330488010333,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.3933,
|
||
|
|
"mean_token_accuracy": 0.13562066927552224,
|
||
|
|
"num_tokens": 2082350.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407677173614502,
|
||
|
|
"epoch": 0.10501488178806087,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.4426,
|
||
|
|
"mean_token_accuracy": 0.1333223059773445,
|
||
|
|
"num_tokens": 2093448.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.589928674697876,
|
||
|
|
"epoch": 0.10557645869601842,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.4712,
|
||
|
|
"mean_token_accuracy": 0.13386278226971626,
|
||
|
|
"num_tokens": 2104171.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.296870374679566,
|
||
|
|
"epoch": 0.10613803560397596,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.3689,
|
||
|
|
"mean_token_accuracy": 0.1341085195541382,
|
||
|
|
"num_tokens": 2114496.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.430097818374634,
|
||
|
|
"epoch": 0.10669961251193351,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.361,
|
||
|
|
"mean_token_accuracy": 0.13727748170495033,
|
||
|
|
"num_tokens": 2125930.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.391914176940918,
|
||
|
|
"epoch": 0.10726118941989106,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.2988,
|
||
|
|
"mean_token_accuracy": 0.14066791236400605,
|
||
|
|
"num_tokens": 2136452.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.334331274032593,
|
||
|
|
"epoch": 0.1078227663278486,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.423,
|
||
|
|
"mean_token_accuracy": 0.13491920307278632,
|
||
|
|
"num_tokens": 2148233.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278422260284424,
|
||
|
|
"epoch": 0.10838434323580615,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.1964,
|
||
|
|
"mean_token_accuracy": 0.1412498541176319,
|
||
|
|
"num_tokens": 2159475.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.32360987663269,
|
||
|
|
"epoch": 0.10894592014376368,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.3321,
|
||
|
|
"mean_token_accuracy": 0.13456659838557244,
|
||
|
|
"num_tokens": 2170042.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.306992149353027,
|
||
|
|
"epoch": 0.10950749705172123,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.3404,
|
||
|
|
"mean_token_accuracy": 0.13353059962391853,
|
||
|
|
"num_tokens": 2182234.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304850292205811,
|
||
|
|
"epoch": 0.11006907395967878,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.3209,
|
||
|
|
"mean_token_accuracy": 0.13740065470337867,
|
||
|
|
"num_tokens": 2192477.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2778017044067385,
|
||
|
|
"epoch": 0.11063065086763632,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.3165,
|
||
|
|
"mean_token_accuracy": 0.13349851667881013,
|
||
|
|
"num_tokens": 2203082.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.335120153427124,
|
||
|
|
"epoch": 0.11119222777559387,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.2766,
|
||
|
|
"mean_token_accuracy": 0.1371467188000679,
|
||
|
|
"num_tokens": 2213684.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.285449409484864,
|
||
|
|
"epoch": 0.11175380468355141,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.3063,
|
||
|
|
"mean_token_accuracy": 0.13364971727132796,
|
||
|
|
"num_tokens": 2225524.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.384835195541382,
|
||
|
|
"epoch": 0.11231538159150896,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.26,
|
||
|
|
"mean_token_accuracy": 0.13841750770807265,
|
||
|
|
"num_tokens": 2236004.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.345810842514038,
|
||
|
|
"epoch": 0.1128769584994665,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499999997707492,
|
||
|
|
"loss": 6.4186,
|
||
|
|
"mean_token_accuracy": 0.12697779908776283,
|
||
|
|
"num_tokens": 2247730.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.38932580947876,
|
||
|
|
"epoch": 0.11343853540742405,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999999883941787,
|
||
|
|
"loss": 6.3762,
|
||
|
|
"mean_token_accuracy": 0.1392652601003647,
|
||
|
|
"num_tokens": 2260132.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.30682406425476,
|
||
|
|
"epoch": 0.1140001123153816,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999999719167785,
|
||
|
|
"loss": 6.331,
|
||
|
|
"mean_token_accuracy": 0.1405606284737587,
|
||
|
|
"num_tokens": 2270060.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.300048065185547,
|
||
|
|
"epoch": 0.11456168922333913,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999999482752917,
|
||
|
|
"loss": 6.357,
|
||
|
|
"mean_token_accuracy": 0.13881335780024529,
|
||
|
|
"num_tokens": 2281568.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372472620010376,
|
||
|
|
"epoch": 0.11512326613129668,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999999174697195,
|
||
|
|
"loss": 6.3714,
|
||
|
|
"mean_token_accuracy": 0.13230287730693818,
|
||
|
|
"num_tokens": 2293325.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.375746154785157,
|
||
|
|
"epoch": 0.11568484303925422,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999998795000627,
|
||
|
|
"loss": 6.3781,
|
||
|
|
"mean_token_accuracy": 0.1413520097732544,
|
||
|
|
"num_tokens": 2304780.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2897717475891115,
|
||
|
|
"epoch": 0.11624641994721177,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999998343663223,
|
||
|
|
"loss": 6.2999,
|
||
|
|
"mean_token_accuracy": 0.1347263291478157,
|
||
|
|
"num_tokens": 2315999.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.392402696609497,
|
||
|
|
"epoch": 0.11680799685516932,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999997820685,
|
||
|
|
"loss": 6.459,
|
||
|
|
"mean_token_accuracy": 0.13655742704868318,
|
||
|
|
"num_tokens": 2326695.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.343186712265014,
|
||
|
|
"epoch": 0.11736957376312686,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999997226065974,
|
||
|
|
"loss": 6.2883,
|
||
|
|
"mean_token_accuracy": 0.14464715570211412,
|
||
|
|
"num_tokens": 2336925.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270289373397827,
|
||
|
|
"epoch": 0.11793115067108441,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999996559806163,
|
||
|
|
"loss": 6.1969,
|
||
|
|
"mean_token_accuracy": 0.14032867401838303,
|
||
|
|
"num_tokens": 2347431.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.202204418182373,
|
||
|
|
"epoch": 0.11849272757904195,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999995821905589,
|
||
|
|
"loss": 6.3097,
|
||
|
|
"mean_token_accuracy": 0.14124003648757935,
|
||
|
|
"num_tokens": 2359894.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.309885120391845,
|
||
|
|
"epoch": 0.1190543044869995,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999995012364276,
|
||
|
|
"loss": 6.3339,
|
||
|
|
"mean_token_accuracy": 0.1370592251420021,
|
||
|
|
"num_tokens": 2371181.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.306979990005493,
|
||
|
|
"epoch": 0.11961588139495703,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999994131182248,
|
||
|
|
"loss": 6.2286,
|
||
|
|
"mean_token_accuracy": 0.13838291838765143,
|
||
|
|
"num_tokens": 2381531.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.35607795715332,
|
||
|
|
"epoch": 0.12017745830291458,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999993178359535,
|
||
|
|
"loss": 6.355,
|
||
|
|
"mean_token_accuracy": 0.1394966445863247,
|
||
|
|
"num_tokens": 2391573.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.261186027526856,
|
||
|
|
"epoch": 0.12073903521087213,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999992153896166,
|
||
|
|
"loss": 6.3136,
|
||
|
|
"mean_token_accuracy": 0.139385873824358,
|
||
|
|
"num_tokens": 2402822.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.275346755981445,
|
||
|
|
"epoch": 0.12130061211882967,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999991057792175,
|
||
|
|
"loss": 6.239,
|
||
|
|
"mean_token_accuracy": 0.13587720692157745,
|
||
|
|
"num_tokens": 2414322.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.344015407562256,
|
||
|
|
"epoch": 0.12186218902678722,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999989890047596,
|
||
|
|
"loss": 6.4254,
|
||
|
|
"mean_token_accuracy": 0.14123198837041856,
|
||
|
|
"num_tokens": 2426560.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3500110626220705,
|
||
|
|
"epoch": 0.12242376593474476,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999988650662467,
|
||
|
|
"loss": 6.3292,
|
||
|
|
"mean_token_accuracy": 0.13752200379967688,
|
||
|
|
"num_tokens": 2437723.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181330251693725,
|
||
|
|
"epoch": 0.12298534284270231,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999987339636825,
|
||
|
|
"loss": 6.2744,
|
||
|
|
"mean_token_accuracy": 0.14474433213472365,
|
||
|
|
"num_tokens": 2448497.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24086971282959,
|
||
|
|
"epoch": 0.12354691975065986,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999985956970713,
|
||
|
|
"loss": 6.1501,
|
||
|
|
"mean_token_accuracy": 0.1460134916007519,
|
||
|
|
"num_tokens": 2459089.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.194115257263183,
|
||
|
|
"epoch": 0.1241084966586174,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999984502664178,
|
||
|
|
"loss": 6.2455,
|
||
|
|
"mean_token_accuracy": 0.1463638111948967,
|
||
|
|
"num_tokens": 2469882.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311574697494507,
|
||
|
|
"epoch": 0.12467007356657495,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999982976717261,
|
||
|
|
"loss": 6.2866,
|
||
|
|
"mean_token_accuracy": 0.14146196469664574,
|
||
|
|
"num_tokens": 2482120.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.229846334457397,
|
||
|
|
"epoch": 0.1252316504745325,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999981379130016,
|
||
|
|
"loss": 6.2776,
|
||
|
|
"mean_token_accuracy": 0.14120347276329995,
|
||
|
|
"num_tokens": 2492626.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.350741004943847,
|
||
|
|
"epoch": 0.12579322738249002,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000499997970990249,
|
||
|
|
"loss": 6.3394,
|
||
|
|
"mean_token_accuracy": 0.13675267696380616,
|
||
|
|
"num_tokens": 2506347.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1441210269927975,
|
||
|
|
"epoch": 0.12635480429044757,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999977969034737,
|
||
|
|
"loss": 6.2228,
|
||
|
|
"mean_token_accuracy": 0.14602547585964204,
|
||
|
|
"num_tokens": 2516584.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.257932376861572,
|
||
|
|
"epoch": 0.12691638119840512,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999976156526814,
|
||
|
|
"loss": 6.2654,
|
||
|
|
"mean_token_accuracy": 0.1448154129087925,
|
||
|
|
"num_tokens": 2526731.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25107250213623,
|
||
|
|
"epoch": 0.12747795810636267,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999974272378776,
|
||
|
|
"loss": 6.1746,
|
||
|
|
"mean_token_accuracy": 0.14796190187335015,
|
||
|
|
"num_tokens": 2537180.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.249812936782837,
|
||
|
|
"epoch": 0.12803953501432022,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999972316590685,
|
||
|
|
"loss": 6.2552,
|
||
|
|
"mean_token_accuracy": 0.14051769748330117,
|
||
|
|
"num_tokens": 2547617.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184178209304809,
|
||
|
|
"epoch": 0.12860111192227774,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999970289162604,
|
||
|
|
"loss": 6.1305,
|
||
|
|
"mean_token_accuracy": 0.1504683867096901,
|
||
|
|
"num_tokens": 2557743.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.158236503601074,
|
||
|
|
"epoch": 0.1291626888302353,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999968190094595,
|
||
|
|
"loss": 6.2303,
|
||
|
|
"mean_token_accuracy": 0.14085211753845214,
|
||
|
|
"num_tokens": 2568351.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255946779251099,
|
||
|
|
"epoch": 0.12972426573819285,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999966019386727,
|
||
|
|
"loss": 6.2956,
|
||
|
|
"mean_token_accuracy": 0.1466837540268898,
|
||
|
|
"num_tokens": 2579703.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278928565979004,
|
||
|
|
"epoch": 0.1302858426461504,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999963777039067,
|
||
|
|
"loss": 6.2721,
|
||
|
|
"mean_token_accuracy": 0.1395919069647789,
|
||
|
|
"num_tokens": 2591197.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.206645822525024,
|
||
|
|
"epoch": 0.13084741955410795,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499996146305169,
|
||
|
|
"loss": 6.2382,
|
||
|
|
"mean_token_accuracy": 0.138199520111084,
|
||
|
|
"num_tokens": 2601836.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.127915143966675,
|
||
|
|
"epoch": 0.13140899646206547,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999959077424665,
|
||
|
|
"loss": 6.1883,
|
||
|
|
"mean_token_accuracy": 0.1469881147146225,
|
||
|
|
"num_tokens": 2613513.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.19788556098938,
|
||
|
|
"epoch": 0.13197057337002302,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999956620158072,
|
||
|
|
"loss": 6.2278,
|
||
|
|
"mean_token_accuracy": 0.14186860024929046,
|
||
|
|
"num_tokens": 2625246.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174941778182983,
|
||
|
|
"epoch": 0.13253215027798057,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999954091251987,
|
||
|
|
"loss": 6.1827,
|
||
|
|
"mean_token_accuracy": 0.14362877011299133,
|
||
|
|
"num_tokens": 2636375.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.236839866638183,
|
||
|
|
"epoch": 0.13309372718593812,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999951490706491,
|
||
|
|
"loss": 6.2803,
|
||
|
|
"mean_token_accuracy": 0.14121622070670128,
|
||
|
|
"num_tokens": 2648586.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25318398475647,
|
||
|
|
"epoch": 0.13365530409389567,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999948818521667,
|
||
|
|
"loss": 6.2896,
|
||
|
|
"mean_token_accuracy": 0.14876099526882172,
|
||
|
|
"num_tokens": 2660847.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.262707948684692,
|
||
|
|
"epoch": 0.1342168810018532,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00049999460746976,
|
||
|
|
"loss": 6.1967,
|
||
|
|
"mean_token_accuracy": 0.1488579124212265,
|
||
|
|
"num_tokens": 2671160.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.28086223602295,
|
||
|
|
"epoch": 0.13477845790981074,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999943259234377,
|
||
|
|
"loss": 6.3232,
|
||
|
|
"mean_token_accuracy": 0.1395305424928665,
|
||
|
|
"num_tokens": 2681622.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096985816955566,
|
||
|
|
"epoch": 0.1353400348177683,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999940372132089,
|
||
|
|
"loss": 6.1266,
|
||
|
|
"mean_token_accuracy": 0.14814743399620056,
|
||
|
|
"num_tokens": 2691503.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2123407363891605,
|
||
|
|
"epoch": 0.13590161172572585,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999937413390826,
|
||
|
|
"loss": 6.2161,
|
||
|
|
"mean_token_accuracy": 0.14390229135751725,
|
||
|
|
"num_tokens": 2702207.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2210283279418945,
|
||
|
|
"epoch": 0.1364631886336834,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999934383010683,
|
||
|
|
"loss": 6.2273,
|
||
|
|
"mean_token_accuracy": 0.13937842920422555,
|
||
|
|
"num_tokens": 2713178.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2355101108551025,
|
||
|
|
"epoch": 0.13702476554164092,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999931280991757,
|
||
|
|
"loss": 6.2215,
|
||
|
|
"mean_token_accuracy": 0.15077248811721802,
|
||
|
|
"num_tokens": 2723717.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212197589874267,
|
||
|
|
"epoch": 0.13758634244959847,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999928107334146,
|
||
|
|
"loss": 6.3009,
|
||
|
|
"mean_token_accuracy": 0.14038375541567802,
|
||
|
|
"num_tokens": 2735669.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169046878814697,
|
||
|
|
"epoch": 0.13814791935755602,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999924862037952,
|
||
|
|
"loss": 6.1964,
|
||
|
|
"mean_token_accuracy": 0.14300856739282608,
|
||
|
|
"num_tokens": 2746087.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.144366025924683,
|
||
|
|
"epoch": 0.13870949626551357,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999921545103278,
|
||
|
|
"loss": 6.2061,
|
||
|
|
"mean_token_accuracy": 0.14115993231534957,
|
||
|
|
"num_tokens": 2757143.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.342315292358398,
|
||
|
|
"epoch": 0.1392710731734711,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999918156530229,
|
||
|
|
"loss": 6.3124,
|
||
|
|
"mean_token_accuracy": 0.14043705612421037,
|
||
|
|
"num_tokens": 2769340.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.167529439926147,
|
||
|
|
"epoch": 0.13983265008142864,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999914696318913,
|
||
|
|
"loss": 6.2324,
|
||
|
|
"mean_token_accuracy": 0.14253571182489394,
|
||
|
|
"num_tokens": 2779514.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.215117454528809,
|
||
|
|
"epoch": 0.1403942269893862,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999911164469441,
|
||
|
|
"loss": 6.1716,
|
||
|
|
"mean_token_accuracy": 0.14638045579195022,
|
||
|
|
"num_tokens": 2790801.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150897598266601,
|
||
|
|
"epoch": 0.14095580389734375,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999907560981925,
|
||
|
|
"loss": 6.1577,
|
||
|
|
"mean_token_accuracy": 0.1422869920730591,
|
||
|
|
"num_tokens": 2801082.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115649127960205,
|
||
|
|
"epoch": 0.1415173808053013,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999903885856479,
|
||
|
|
"loss": 6.1729,
|
||
|
|
"mean_token_accuracy": 0.14438655823469163,
|
||
|
|
"num_tokens": 2812719.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.191334629058838,
|
||
|
|
"epoch": 0.14207895771325882,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499990013909322,
|
||
|
|
"loss": 6.1778,
|
||
|
|
"mean_token_accuracy": 0.13971620053052902,
|
||
|
|
"num_tokens": 2823766.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134991407394409,
|
||
|
|
"epoch": 0.14264053462121637,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000499989632069227,
|
||
|
|
"loss": 6.2602,
|
||
|
|
"mean_token_accuracy": 0.14011294320225715,
|
||
|
|
"num_tokens": 2834801.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.191428804397583,
|
||
|
|
"epoch": 0.14320211152917392,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999892430653747,
|
||
|
|
"loss": 6.0776,
|
||
|
|
"mean_token_accuracy": 0.14458837285637854,
|
||
|
|
"num_tokens": 2845769.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094238376617431,
|
||
|
|
"epoch": 0.14376368843713147,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999888468977776,
|
||
|
|
"loss": 6.1127,
|
||
|
|
"mean_token_accuracy": 0.14914896190166474,
|
||
|
|
"num_tokens": 2856001.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171784067153931,
|
||
|
|
"epoch": 0.14432526534508902,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999884435664485,
|
||
|
|
"loss": 6.1584,
|
||
|
|
"mean_token_accuracy": 0.14499107077717782,
|
||
|
|
"num_tokens": 2867703.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036443662643433,
|
||
|
|
"epoch": 0.14488684225304654,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999880330714,
|
||
|
|
"loss": 6.1071,
|
||
|
|
"mean_token_accuracy": 0.14794510155916213,
|
||
|
|
"num_tokens": 2878671.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.188154554367065,
|
||
|
|
"epoch": 0.1454484191610041,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999876154126453,
|
||
|
|
"loss": 6.2189,
|
||
|
|
"mean_token_accuracy": 0.139739553630352,
|
||
|
|
"num_tokens": 2890137.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1498771667480465,
|
||
|
|
"epoch": 0.14600999606896164,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999871905901977,
|
||
|
|
"loss": 6.1234,
|
||
|
|
"mean_token_accuracy": 0.1464032292366028,
|
||
|
|
"num_tokens": 2900344.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0827178955078125,
|
||
|
|
"epoch": 0.1465715729769192,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999867586040706,
|
||
|
|
"loss": 6.1436,
|
||
|
|
"mean_token_accuracy": 0.1437415286898613,
|
||
|
|
"num_tokens": 2912270.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.200682878494263,
|
||
|
|
"epoch": 0.14713314988487675,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999863194542779,
|
||
|
|
"loss": 6.2118,
|
||
|
|
"mean_token_accuracy": 0.13623538836836815,
|
||
|
|
"num_tokens": 2924677.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.07335467338562,
|
||
|
|
"epoch": 0.14769472679283427,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999858731408336,
|
||
|
|
"loss": 6.1296,
|
||
|
|
"mean_token_accuracy": 0.14736221581697465,
|
||
|
|
"num_tokens": 2935794.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.175930118560791,
|
||
|
|
"epoch": 0.14825630370079182,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999854196637518,
|
||
|
|
"loss": 6.2555,
|
||
|
|
"mean_token_accuracy": 0.13842563405632974,
|
||
|
|
"num_tokens": 2945958.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238176393508911,
|
||
|
|
"epoch": 0.14881788060874937,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999849590230469,
|
||
|
|
"loss": 6.203,
|
||
|
|
"mean_token_accuracy": 0.14000826627016066,
|
||
|
|
"num_tokens": 2957536.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148218727111816,
|
||
|
|
"epoch": 0.14937945751670692,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999844912187336,
|
||
|
|
"loss": 6.1913,
|
||
|
|
"mean_token_accuracy": 0.14294830784201623,
|
||
|
|
"num_tokens": 2967787.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1945525169372555,
|
||
|
|
"epoch": 0.14994103442466447,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000499984016250827,
|
||
|
|
"loss": 6.2067,
|
||
|
|
"mean_token_accuracy": 0.13826904371380805,
|
||
|
|
"num_tokens": 2980522.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966804313659668,
|
||
|
|
"epoch": 0.150502611332622,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499983534119342,
|
||
|
|
"loss": 6.1388,
|
||
|
|
"mean_token_accuracy": 0.14656713455915452,
|
||
|
|
"num_tokens": 2990497.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.274156188964843,
|
||
|
|
"epoch": 0.15106418824057954,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004999830448242941,
|
||
|
|
"loss": 6.2332,
|
||
|
|
"mean_token_accuracy": 0.14296478927135467,
|
||
|
|
"num_tokens": 3002931.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141962671279908,
|
||
|
|
"epoch": 0.1516257651485371,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999825483656986,
|
||
|
|
"loss": 6.156,
|
||
|
|
"mean_token_accuracy": 0.1505702443420887,
|
||
|
|
"num_tokens": 3014137.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2523428440094,
|
||
|
|
"epoch": 0.15218734205649465,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999820447435716,
|
||
|
|
"loss": 6.3274,
|
||
|
|
"mean_token_accuracy": 0.13458315059542655,
|
||
|
|
"num_tokens": 3026145.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.138166666030884,
|
||
|
|
"epoch": 0.15274891896445217,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999815339579291,
|
||
|
|
"loss": 6.1712,
|
||
|
|
"mean_token_accuracy": 0.14355397075414658,
|
||
|
|
"num_tokens": 3037068.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16013355255127,
|
||
|
|
"epoch": 0.15331049587240972,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999810160087872,
|
||
|
|
"loss": 6.0994,
|
||
|
|
"mean_token_accuracy": 0.14831770956516266,
|
||
|
|
"num_tokens": 3047836.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.168116474151612,
|
||
|
|
"epoch": 0.15387207278036727,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999804908961626,
|
||
|
|
"loss": 6.2286,
|
||
|
|
"mean_token_accuracy": 0.1443933680653572,
|
||
|
|
"num_tokens": 3060309.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171547555923462,
|
||
|
|
"epoch": 0.15443364968832482,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999799586200719,
|
||
|
|
"loss": 6.2005,
|
||
|
|
"mean_token_accuracy": 0.14509918689727783,
|
||
|
|
"num_tokens": 3071789.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1539019584655765,
|
||
|
|
"epoch": 0.15499522659628237,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000499979419180532,
|
||
|
|
"loss": 6.1132,
|
||
|
|
"mean_token_accuracy": 0.1455280564725399,
|
||
|
|
"num_tokens": 3081756.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111848592758179,
|
||
|
|
"epoch": 0.1555568035042399,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999788725775601,
|
||
|
|
"loss": 6.2161,
|
||
|
|
"mean_token_accuracy": 0.14064385145902633,
|
||
|
|
"num_tokens": 3093456.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234532213211059,
|
||
|
|
"epoch": 0.15611838041219744,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999783188111737,
|
||
|
|
"loss": 6.1529,
|
||
|
|
"mean_token_accuracy": 0.15091142654418946,
|
||
|
|
"num_tokens": 3104565.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103633165359497,
|
||
|
|
"epoch": 0.156679957320155,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999777578813904,
|
||
|
|
"loss": 6.1579,
|
||
|
|
"mean_token_accuracy": 0.14539188742637635,
|
||
|
|
"num_tokens": 3115577.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.097013330459594,
|
||
|
|
"epoch": 0.15724153422811254,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499977189788228,
|
||
|
|
"loss": 6.0538,
|
||
|
|
"mean_token_accuracy": 0.1482097752392292,
|
||
|
|
"num_tokens": 3126019.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163146924972534,
|
||
|
|
"epoch": 0.1578031111360701,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999766145317046,
|
||
|
|
"loss": 6.2181,
|
||
|
|
"mean_token_accuracy": 0.13583666682243348,
|
||
|
|
"num_tokens": 3136191.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162729549407959,
|
||
|
|
"epoch": 0.15836468804402762,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999760321118385,
|
||
|
|
"loss": 6.0858,
|
||
|
|
"mean_token_accuracy": 0.14940220788121222,
|
||
|
|
"num_tokens": 3147737.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.025310707092285,
|
||
|
|
"epoch": 0.15892626495198517,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999754425286483,
|
||
|
|
"loss": 6.1533,
|
||
|
|
"mean_token_accuracy": 0.1457144483923912,
|
||
|
|
"num_tokens": 3158494.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.223312425613403,
|
||
|
|
"epoch": 0.15948784185994272,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999748457821529,
|
||
|
|
"loss": 6.1982,
|
||
|
|
"mean_token_accuracy": 0.14512955993413926,
|
||
|
|
"num_tokens": 3170550.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002134227752686,
|
||
|
|
"epoch": 0.16004941876790027,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.000499974241872371,
|
||
|
|
"loss": 6.173,
|
||
|
|
"mean_token_accuracy": 0.14995696693658828,
|
||
|
|
"num_tokens": 3182860.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.145843410491944,
|
||
|
|
"epoch": 0.16061099567585782,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999736307993221,
|
||
|
|
"loss": 6.1589,
|
||
|
|
"mean_token_accuracy": 0.1427552342414856,
|
||
|
|
"num_tokens": 3193807.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033665990829467,
|
||
|
|
"epoch": 0.16117257258381534,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999730125630255,
|
||
|
|
"loss": 6.0343,
|
||
|
|
"mean_token_accuracy": 0.14640598148107528,
|
||
|
|
"num_tokens": 3203959.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.114152240753174,
|
||
|
|
"epoch": 0.1617341494917729,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999723871635008,
|
||
|
|
"loss": 6.05,
|
||
|
|
"mean_token_accuracy": 0.15276473239064217,
|
||
|
|
"num_tokens": 3215416.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174462223052979,
|
||
|
|
"epoch": 0.16229572639973044,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999717546007681,
|
||
|
|
"loss": 6.1968,
|
||
|
|
"mean_token_accuracy": 0.13907519057393075,
|
||
|
|
"num_tokens": 3226938.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01826319694519,
|
||
|
|
"epoch": 0.162857303307688,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999711148748476,
|
||
|
|
"loss": 6.0076,
|
||
|
|
"mean_token_accuracy": 0.15116169303655624,
|
||
|
|
"num_tokens": 3238406.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0103428840637205,
|
||
|
|
"epoch": 0.16341888021564555,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999704679857594,
|
||
|
|
"loss": 6.0333,
|
||
|
|
"mean_token_accuracy": 0.1464739538729191,
|
||
|
|
"num_tokens": 3249695.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.189427709579467,
|
||
|
|
"epoch": 0.16398045712360307,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999698139335243,
|
||
|
|
"loss": 6.1762,
|
||
|
|
"mean_token_accuracy": 0.14912961125373841,
|
||
|
|
"num_tokens": 3259656.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0474467277526855,
|
||
|
|
"epoch": 0.16454203403156062,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999691527181632,
|
||
|
|
"loss": 6.0055,
|
||
|
|
"mean_token_accuracy": 0.15426421761512757,
|
||
|
|
"num_tokens": 3269712.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944938468933105,
|
||
|
|
"epoch": 0.16510361093951817,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999684843396968,
|
||
|
|
"loss": 6.0062,
|
||
|
|
"mean_token_accuracy": 0.15657223016023636,
|
||
|
|
"num_tokens": 3280343.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05485725402832,
|
||
|
|
"epoch": 0.16566518784747572,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999678087981467,
|
||
|
|
"loss": 6.0399,
|
||
|
|
"mean_token_accuracy": 0.15069780349731446,
|
||
|
|
"num_tokens": 3291649.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21270523071289,
|
||
|
|
"epoch": 0.16622676475543324,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999671260935343,
|
||
|
|
"loss": 6.2278,
|
||
|
|
"mean_token_accuracy": 0.1479203850030899,
|
||
|
|
"num_tokens": 3304190.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936612796783447,
|
||
|
|
"epoch": 0.1667883416633908,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999664362258814,
|
||
|
|
"loss": 5.9433,
|
||
|
|
"mean_token_accuracy": 0.1585344895720482,
|
||
|
|
"num_tokens": 3313966.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14134840965271,
|
||
|
|
"epoch": 0.16734991857134834,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999657391952099,
|
||
|
|
"loss": 6.2044,
|
||
|
|
"mean_token_accuracy": 0.14634429141879082,
|
||
|
|
"num_tokens": 3326017.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.099699068069458,
|
||
|
|
"epoch": 0.1679114954793059,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000499965035001542,
|
||
|
|
"loss": 6.0878,
|
||
|
|
"mean_token_accuracy": 0.1465717777609825,
|
||
|
|
"num_tokens": 3338264.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0834414005279545,
|
||
|
|
"epoch": 0.16847307238726345,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999643236449001,
|
||
|
|
"loss": 6.1281,
|
||
|
|
"mean_token_accuracy": 0.15561570674180986,
|
||
|
|
"num_tokens": 3348901.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.077313470840454,
|
||
|
|
"epoch": 0.16903464929522097,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999636051253069,
|
||
|
|
"loss": 6.0809,
|
||
|
|
"mean_token_accuracy": 0.15013315677642822,
|
||
|
|
"num_tokens": 3358441.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141596937179566,
|
||
|
|
"epoch": 0.16959622620317852,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999628794427854,
|
||
|
|
"loss": 6.1594,
|
||
|
|
"mean_token_accuracy": 0.1495223045349121,
|
||
|
|
"num_tokens": 3369334.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033642292022705,
|
||
|
|
"epoch": 0.17015780311113607,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999621465973583,
|
||
|
|
"loss": 6.1466,
|
||
|
|
"mean_token_accuracy": 0.1485290877521038,
|
||
|
|
"num_tokens": 3380698.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.292063999176025,
|
||
|
|
"epoch": 0.17071938001909362,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999614065890495,
|
||
|
|
"loss": 6.1537,
|
||
|
|
"mean_token_accuracy": 0.14258649721741676,
|
||
|
|
"num_tokens": 3391061.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.035744714736938,
|
||
|
|
"epoch": 0.17128095692705117,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999606594178821,
|
||
|
|
"loss": 6.206,
|
||
|
|
"mean_token_accuracy": 0.14634663388133048,
|
||
|
|
"num_tokens": 3403983.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211483716964722,
|
||
|
|
"epoch": 0.1718425338350087,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00049995990508388,
|
||
|
|
"loss": 6.137,
|
||
|
|
"mean_token_accuracy": 0.14936505407094955,
|
||
|
|
"num_tokens": 3413838.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965998554229737,
|
||
|
|
"epoch": 0.17240411074296624,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999591435870674,
|
||
|
|
"loss": 5.9669,
|
||
|
|
"mean_token_accuracy": 0.1488761007785797,
|
||
|
|
"num_tokens": 3423978.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.155382394790649,
|
||
|
|
"epoch": 0.1729656876509238,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999583749274684,
|
||
|
|
"loss": 6.1435,
|
||
|
|
"mean_token_accuracy": 0.15120792090892793,
|
||
|
|
"num_tokens": 3433416.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947936916351319,
|
||
|
|
"epoch": 0.17352726455888134,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999575991051074,
|
||
|
|
"loss": 5.9987,
|
||
|
|
"mean_token_accuracy": 0.15397366210818292,
|
||
|
|
"num_tokens": 3444983.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043239402770996,
|
||
|
|
"epoch": 0.1740888414668389,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999568161200093,
|
||
|
|
"loss": 5.9785,
|
||
|
|
"mean_token_accuracy": 0.15082329958677293,
|
||
|
|
"num_tokens": 3455808.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976273250579834,
|
||
|
|
"epoch": 0.17465041837479642,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999560259721989,
|
||
|
|
"loss": 6.1215,
|
||
|
|
"mean_token_accuracy": 0.14532301798462868,
|
||
|
|
"num_tokens": 3467503.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.260001564025879,
|
||
|
|
"epoch": 0.17521199528275397,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999552286617014,
|
||
|
|
"loss": 6.326,
|
||
|
|
"mean_token_accuracy": 0.1441342644393444,
|
||
|
|
"num_tokens": 3479941.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030442523956299,
|
||
|
|
"epoch": 0.17577357219071152,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999544241885421,
|
||
|
|
"loss": 6.0042,
|
||
|
|
"mean_token_accuracy": 0.15812455415725707,
|
||
|
|
"num_tokens": 3491069.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056136274337769,
|
||
|
|
"epoch": 0.17633514909866907,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999536125527467,
|
||
|
|
"loss": 6.1824,
|
||
|
|
"mean_token_accuracy": 0.14446716159582138,
|
||
|
|
"num_tokens": 3502065.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2176953792572025,
|
||
|
|
"epoch": 0.17689672600662662,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000499952793754341,
|
||
|
|
"loss": 6.1444,
|
||
|
|
"mean_token_accuracy": 0.15198023170232772,
|
||
|
|
"num_tokens": 3514228.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030651617050171,
|
||
|
|
"epoch": 0.17745830291458414,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999519677933512,
|
||
|
|
"loss": 6.0734,
|
||
|
|
"mean_token_accuracy": 0.1505001425743103,
|
||
|
|
"num_tokens": 3525801.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083348560333252,
|
||
|
|
"epoch": 0.1780198798225417,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999511346698035,
|
||
|
|
"loss": 6.0093,
|
||
|
|
"mean_token_accuracy": 0.14821343570947648,
|
||
|
|
"num_tokens": 3536431.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9785850048065186,
|
||
|
|
"epoch": 0.17858145673049924,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999502943837244,
|
||
|
|
"loss": 6.1211,
|
||
|
|
"mean_token_accuracy": 0.14956868812441826,
|
||
|
|
"num_tokens": 3549098.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.202871322631836,
|
||
|
|
"epoch": 0.1791430336384568,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999494469351406,
|
||
|
|
"loss": 6.0691,
|
||
|
|
"mean_token_accuracy": 0.1480709992349148,
|
||
|
|
"num_tokens": 3560532.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9555768966674805,
|
||
|
|
"epoch": 0.17970461054641435,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999485923240793,
|
||
|
|
"loss": 6.0849,
|
||
|
|
"mean_token_accuracy": 0.14840494394302367,
|
||
|
|
"num_tokens": 3572175.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.107180643081665,
|
||
|
|
"epoch": 0.18026618745437187,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999477305505675,
|
||
|
|
"loss": 6.0088,
|
||
|
|
"mean_token_accuracy": 0.16300127431750297,
|
||
|
|
"num_tokens": 3582862.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1141856670379635,
|
||
|
|
"epoch": 0.18082776436232942,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999468616146328,
|
||
|
|
"loss": 6.1825,
|
||
|
|
"mean_token_accuracy": 0.15161287486553193,
|
||
|
|
"num_tokens": 3594685.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.94605827331543,
|
||
|
|
"epoch": 0.18138934127028697,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999459855163026,
|
||
|
|
"loss": 5.972,
|
||
|
|
"mean_token_accuracy": 0.1625172182917595,
|
||
|
|
"num_tokens": 3604847.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103135251998902,
|
||
|
|
"epoch": 0.18195091817824452,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000499945102255605,
|
||
|
|
"loss": 6.054,
|
||
|
|
"mean_token_accuracy": 0.1522398680448532,
|
||
|
|
"num_tokens": 3615549.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004732656478882,
|
||
|
|
"epoch": 0.18251249508620204,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999442118325682,
|
||
|
|
"loss": 5.9889,
|
||
|
|
"mean_token_accuracy": 0.1601618841290474,
|
||
|
|
"num_tokens": 3626300.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001117134094239,
|
||
|
|
"epoch": 0.1830740719941596,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999433142472205,
|
||
|
|
"loss": 6.0022,
|
||
|
|
"mean_token_accuracy": 0.15320078432559966,
|
||
|
|
"num_tokens": 3637832.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.015522909164429,
|
||
|
|
"epoch": 0.18363564890211714,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999424094995902,
|
||
|
|
"loss": 6.0363,
|
||
|
|
"mean_token_accuracy": 0.14825773611664772,
|
||
|
|
"num_tokens": 3649179.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044634246826172,
|
||
|
|
"epoch": 0.1841972258100747,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999414975897066,
|
||
|
|
"loss": 6.0829,
|
||
|
|
"mean_token_accuracy": 0.14763242304325103,
|
||
|
|
"num_tokens": 3660011.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159467792510986,
|
||
|
|
"epoch": 0.18475880271803224,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999405785175983,
|
||
|
|
"loss": 6.1561,
|
||
|
|
"mean_token_accuracy": 0.14462535828351974,
|
||
|
|
"num_tokens": 3672791.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92794132232666,
|
||
|
|
"epoch": 0.18532037962598977,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999396522832949,
|
||
|
|
"loss": 5.9746,
|
||
|
|
"mean_token_accuracy": 0.14504419267177582,
|
||
|
|
"num_tokens": 3684709.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973066902160644,
|
||
|
|
"epoch": 0.18588195653394732,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999387188868256,
|
||
|
|
"loss": 5.9508,
|
||
|
|
"mean_token_accuracy": 0.15417686551809312,
|
||
|
|
"num_tokens": 3694675.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916463327407837,
|
||
|
|
"epoch": 0.18644353344190487,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999377783282203,
|
||
|
|
"loss": 5.9505,
|
||
|
|
"mean_token_accuracy": 0.14933737069368364,
|
||
|
|
"num_tokens": 3706384.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.128504753112793,
|
||
|
|
"epoch": 0.18700511034986242,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999368306075089,
|
||
|
|
"loss": 6.0327,
|
||
|
|
"mean_token_accuracy": 0.15195935666561128,
|
||
|
|
"num_tokens": 3717419.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989669895172119,
|
||
|
|
"epoch": 0.18756668725781997,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999358757247215,
|
||
|
|
"loss": 6.051,
|
||
|
|
"mean_token_accuracy": 0.152767513692379,
|
||
|
|
"num_tokens": 3727306.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.138838481903076,
|
||
|
|
"epoch": 0.1881282641657775,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999349136798886,
|
||
|
|
"loss": 6.1893,
|
||
|
|
"mean_token_accuracy": 0.14532702267169953,
|
||
|
|
"num_tokens": 3739476.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0092527866363525,
|
||
|
|
"epoch": 0.18868984107373504,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999339444730409,
|
||
|
|
"loss": 5.9494,
|
||
|
|
"mean_token_accuracy": 0.15688171833753586,
|
||
|
|
"num_tokens": 3751035.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019771957397461,
|
||
|
|
"epoch": 0.1892514179816926,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999329681042092,
|
||
|
|
"loss": 6.0386,
|
||
|
|
"mean_token_accuracy": 0.1538560003042221,
|
||
|
|
"num_tokens": 3762881.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984057855606079,
|
||
|
|
"epoch": 0.18981299488965014,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999319845734243,
|
||
|
|
"loss": 6.0553,
|
||
|
|
"mean_token_accuracy": 0.15006775856018068,
|
||
|
|
"num_tokens": 3774180.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.981182193756103,
|
||
|
|
"epoch": 0.1903745717976077,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999309938807181,
|
||
|
|
"loss": 6.0545,
|
||
|
|
"mean_token_accuracy": 0.1547319382429123,
|
||
|
|
"num_tokens": 3784864.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1529374599456785,
|
||
|
|
"epoch": 0.19093614870556522,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999299960261216,
|
||
|
|
"loss": 6.0276,
|
||
|
|
"mean_token_accuracy": 0.14776145964860915,
|
||
|
|
"num_tokens": 3797693.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001488113403321,
|
||
|
|
"epoch": 0.19149772561352277,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999289910096669,
|
||
|
|
"loss": 6.0625,
|
||
|
|
"mean_token_accuracy": 0.15112081915140152,
|
||
|
|
"num_tokens": 3809379.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932614946365357,
|
||
|
|
"epoch": 0.19205930252148032,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999279788313858,
|
||
|
|
"loss": 5.8953,
|
||
|
|
"mean_token_accuracy": 0.15991028100252153,
|
||
|
|
"num_tokens": 3819473.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.836278581619263,
|
||
|
|
"epoch": 0.19262087942943787,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999269594913107,
|
||
|
|
"loss": 5.8975,
|
||
|
|
"mean_token_accuracy": 0.15740557461977006,
|
||
|
|
"num_tokens": 3831037.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986707925796509,
|
||
|
|
"epoch": 0.19318245633739542,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999259329894739,
|
||
|
|
"loss": 6.0239,
|
||
|
|
"mean_token_accuracy": 0.15171116292476655,
|
||
|
|
"num_tokens": 3841767.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.904497194290161,
|
||
|
|
"epoch": 0.19374403324535294,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999248993259081,
|
||
|
|
"loss": 5.8524,
|
||
|
|
"mean_token_accuracy": 0.1618407890200615,
|
||
|
|
"num_tokens": 3851629.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943421697616577,
|
||
|
|
"epoch": 0.1943056101533105,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999238585006463,
|
||
|
|
"loss": 5.9368,
|
||
|
|
"mean_token_accuracy": 0.15554058328270912,
|
||
|
|
"num_tokens": 3863247.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010688257217407,
|
||
|
|
"epoch": 0.19486718706126804,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999228105137218,
|
||
|
|
"loss": 5.9323,
|
||
|
|
"mean_token_accuracy": 0.15478108823299408,
|
||
|
|
"num_tokens": 3873949.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9788285255432125,
|
||
|
|
"epoch": 0.1954287639692256,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999217553651676,
|
||
|
|
"loss": 6.0231,
|
||
|
|
"mean_token_accuracy": 0.1538798376917839,
|
||
|
|
"num_tokens": 3884992.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0841248512268065,
|
||
|
|
"epoch": 0.19599034087718312,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999206930550175,
|
||
|
|
"loss": 6.1552,
|
||
|
|
"mean_token_accuracy": 0.15780816972255707,
|
||
|
|
"num_tokens": 3897029.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975784158706665,
|
||
|
|
"epoch": 0.19655191778514067,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999196235833054,
|
||
|
|
"loss": 6.0106,
|
||
|
|
"mean_token_accuracy": 0.14999836683273315,
|
||
|
|
"num_tokens": 3909510.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004339599609375,
|
||
|
|
"epoch": 0.19711349469309822,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999185469500651,
|
||
|
|
"loss": 5.9054,
|
||
|
|
"mean_token_accuracy": 0.15378687232732774,
|
||
|
|
"num_tokens": 3920593.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044984769821167,
|
||
|
|
"epoch": 0.19767507160105577,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499917463155331,
|
||
|
|
"loss": 6.0444,
|
||
|
|
"mean_token_accuracy": 0.14715591371059417,
|
||
|
|
"num_tokens": 3932215.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002836465835571,
|
||
|
|
"epoch": 0.19823664850901332,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999163721991378,
|
||
|
|
"loss": 5.9946,
|
||
|
|
"mean_token_accuracy": 0.15849560648202896,
|
||
|
|
"num_tokens": 3943876.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.868329048156738,
|
||
|
|
"epoch": 0.19879822541697084,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00049991527408152,
|
||
|
|
"loss": 5.99,
|
||
|
|
"mean_token_accuracy": 0.15757318139076232,
|
||
|
|
"num_tokens": 3954533.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096402406692505,
|
||
|
|
"epoch": 0.1993598023249284,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999141688025127,
|
||
|
|
"loss": 6.0397,
|
||
|
|
"mean_token_accuracy": 0.1561959594488144,
|
||
|
|
"num_tokens": 3965722.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9315564155578615,
|
||
|
|
"epoch": 0.19992137923288594,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000499913056362151,
|
||
|
|
"loss": 5.9636,
|
||
|
|
"mean_token_accuracy": 0.15444938093423843,
|
||
|
|
"num_tokens": 3976737.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066930055618286,
|
||
|
|
"epoch": 0.2004829561408435,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999119367604703,
|
||
|
|
"loss": 6.0435,
|
||
|
|
"mean_token_accuracy": 0.15687376260757446,
|
||
|
|
"num_tokens": 3986102.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019561910629273,
|
||
|
|
"epoch": 0.20104453304880104,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999108099975064,
|
||
|
|
"loss": 6.0286,
|
||
|
|
"mean_token_accuracy": 0.15214875042438508,
|
||
|
|
"num_tokens": 3996534.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.899537181854248,
|
||
|
|
"epoch": 0.20160610995675857,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499909676073295,
|
||
|
|
"loss": 5.9332,
|
||
|
|
"mean_token_accuracy": 0.15285612195730208,
|
||
|
|
"num_tokens": 4006947.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956607484817505,
|
||
|
|
"epoch": 0.20216768686471612,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999085349878723,
|
||
|
|
"loss": 5.9775,
|
||
|
|
"mean_token_accuracy": 0.16392070800065994,
|
||
|
|
"num_tokens": 4017723.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945090866088867,
|
||
|
|
"epoch": 0.20272926377267367,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999073867412746,
|
||
|
|
"loss": 6.0448,
|
||
|
|
"mean_token_accuracy": 0.14959224089980125,
|
||
|
|
"num_tokens": 4028347.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973555707931519,
|
||
|
|
"epoch": 0.20329084068063122,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999062313335385,
|
||
|
|
"loss": 5.9107,
|
||
|
|
"mean_token_accuracy": 0.15792374908924103,
|
||
|
|
"num_tokens": 4039648.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.071758031845093,
|
||
|
|
"epoch": 0.20385241758858877,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999050687647008,
|
||
|
|
"loss": 5.9651,
|
||
|
|
"mean_token_accuracy": 0.15182322710752488,
|
||
|
|
"num_tokens": 4050786.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987163734436035,
|
||
|
|
"epoch": 0.2044139944965463,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999038990347984,
|
||
|
|
"loss": 6.0045,
|
||
|
|
"mean_token_accuracy": 0.15671864449977874,
|
||
|
|
"num_tokens": 4061184.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081359481811523,
|
||
|
|
"epoch": 0.20497557140450384,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999027221438688,
|
||
|
|
"loss": 6.1371,
|
||
|
|
"mean_token_accuracy": 0.15203218758106232,
|
||
|
|
"num_tokens": 4073607.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913217067718506,
|
||
|
|
"epoch": 0.2055371483124614,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499901538091949,
|
||
|
|
"loss": 5.9466,
|
||
|
|
"mean_token_accuracy": 0.15213279873132707,
|
||
|
|
"num_tokens": 4083924.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989058113098144,
|
||
|
|
"epoch": 0.20609872522041894,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999003468790773,
|
||
|
|
"loss": 5.9445,
|
||
|
|
"mean_token_accuracy": 0.1569296732544899,
|
||
|
|
"num_tokens": 4094083.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978657531738281,
|
||
|
|
"epoch": 0.2066603021283765,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998991485052911,
|
||
|
|
"loss": 5.977,
|
||
|
|
"mean_token_accuracy": 0.16102480739355088,
|
||
|
|
"num_tokens": 4105124.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.050256776809692,
|
||
|
|
"epoch": 0.20722187903633402,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000499897942970629,
|
||
|
|
"loss": 6.1242,
|
||
|
|
"mean_token_accuracy": 0.14630307406187057,
|
||
|
|
"num_tokens": 4116792.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.172934484481812,
|
||
|
|
"epoch": 0.20778345594429157,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000499896730275129,
|
||
|
|
"loss": 6.1203,
|
||
|
|
"mean_token_accuracy": 0.1498411238193512,
|
||
|
|
"num_tokens": 4127441.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002869939804077,
|
||
|
|
"epoch": 0.20834503285224912,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00049989551041883,
|
||
|
|
"loss": 6.122,
|
||
|
|
"mean_token_accuracy": 0.1481037177145481,
|
||
|
|
"num_tokens": 4138696.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970435333251953,
|
||
|
|
"epoch": 0.20890660976020667,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998942834017707,
|
||
|
|
"loss": 5.9747,
|
||
|
|
"mean_token_accuracy": 0.15272988379001617,
|
||
|
|
"num_tokens": 4151254.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9465700626373295,
|
||
|
|
"epoch": 0.2094681866681642,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998930492239901,
|
||
|
|
"loss": 5.9417,
|
||
|
|
"mean_token_accuracy": 0.1490399457514286,
|
||
|
|
"num_tokens": 4162046.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.929416513442993,
|
||
|
|
"epoch": 0.21002976357612174,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998918078855277,
|
||
|
|
"loss": 5.8995,
|
||
|
|
"mean_token_accuracy": 0.15742434859275817,
|
||
|
|
"num_tokens": 4172409.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.905488348007202,
|
||
|
|
"epoch": 0.2105913404840793,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998905593864227,
|
||
|
|
"loss": 6.0486,
|
||
|
|
"mean_token_accuracy": 0.15691976398229598,
|
||
|
|
"num_tokens": 4182949.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005948495864868,
|
||
|
|
"epoch": 0.21115291739203684,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998893037267153,
|
||
|
|
"loss": 6.0075,
|
||
|
|
"mean_token_accuracy": 0.15736858546733856,
|
||
|
|
"num_tokens": 4194164.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075479507446289,
|
||
|
|
"epoch": 0.2117144942999944,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998880409064452,
|
||
|
|
"loss": 5.9782,
|
||
|
|
"mean_token_accuracy": 0.15652812123298646,
|
||
|
|
"num_tokens": 4206056.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.917818641662597,
|
||
|
|
"epoch": 0.21227607120795192,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998867709256527,
|
||
|
|
"loss": 6.0464,
|
||
|
|
"mean_token_accuracy": 0.15186507552862166,
|
||
|
|
"num_tokens": 4216660.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961790704727173,
|
||
|
|
"epoch": 0.21283764811590947,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499885493784378,
|
||
|
|
"loss": 5.9216,
|
||
|
|
"mean_token_accuracy": 0.15845142155885697,
|
||
|
|
"num_tokens": 4228495.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986710071563721,
|
||
|
|
"epoch": 0.21339922502386702,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998842094826621,
|
||
|
|
"loss": 5.9148,
|
||
|
|
"mean_token_accuracy": 0.16144272834062576,
|
||
|
|
"num_tokens": 4238560.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073420858383178,
|
||
|
|
"epoch": 0.21396080193182457,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998829180205458,
|
||
|
|
"loss": 6.1462,
|
||
|
|
"mean_token_accuracy": 0.14855025336146355,
|
||
|
|
"num_tokens": 4250553.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998498582839966,
|
||
|
|
"epoch": 0.21452237883978212,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998816193980701,
|
||
|
|
"loss": 6.0515,
|
||
|
|
"mean_token_accuracy": 0.1510763570666313,
|
||
|
|
"num_tokens": 4262050.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14221158027649,
|
||
|
|
"epoch": 0.21508395574773964,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998803136152764,
|
||
|
|
"loss": 6.0223,
|
||
|
|
"mean_token_accuracy": 0.14946622550487518,
|
||
|
|
"num_tokens": 4273019.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92807354927063,
|
||
|
|
"epoch": 0.2156455326556972,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998790006722063,
|
||
|
|
"loss": 5.8816,
|
||
|
|
"mean_token_accuracy": 0.16204874515533446,
|
||
|
|
"num_tokens": 4283585.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8864278316497805,
|
||
|
|
"epoch": 0.21620710956365474,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998776805689016,
|
||
|
|
"loss": 5.9586,
|
||
|
|
"mean_token_accuracy": 0.15603998452425002,
|
||
|
|
"num_tokens": 4294905.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072697687149048,
|
||
|
|
"epoch": 0.2167686864716123,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998763533054045,
|
||
|
|
"loss": 6.0863,
|
||
|
|
"mean_token_accuracy": 0.1533777520060539,
|
||
|
|
"num_tokens": 4305926.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.925010728836059,
|
||
|
|
"epoch": 0.21733026337956984,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998750188817568,
|
||
|
|
"loss": 6.058,
|
||
|
|
"mean_token_accuracy": 0.150500325858593,
|
||
|
|
"num_tokens": 4318297.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986216497421265,
|
||
|
|
"epoch": 0.21789184028752737,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998736772980015,
|
||
|
|
"loss": 5.8775,
|
||
|
|
"mean_token_accuracy": 0.16325863003730773,
|
||
|
|
"num_tokens": 4328795.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.907973289489746,
|
||
|
|
"epoch": 0.21845341719548492,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000499872328554181,
|
||
|
|
"loss": 5.8886,
|
||
|
|
"mean_token_accuracy": 0.1554047629237175,
|
||
|
|
"num_tokens": 4340279.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.068842029571533,
|
||
|
|
"epoch": 0.21901499410344247,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998709726503383,
|
||
|
|
"loss": 6.0561,
|
||
|
|
"mean_token_accuracy": 0.1501077175140381,
|
||
|
|
"num_tokens": 4352157.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955055046081543,
|
||
|
|
"epoch": 0.21957657101140002,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998696095865168,
|
||
|
|
"loss": 5.897,
|
||
|
|
"mean_token_accuracy": 0.15995442271232604,
|
||
|
|
"num_tokens": 4361909.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.730102634429931,
|
||
|
|
"epoch": 0.22013814791935757,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998682393627595,
|
||
|
|
"loss": 5.8254,
|
||
|
|
"mean_token_accuracy": 0.15582716166973115,
|
||
|
|
"num_tokens": 4372177.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933818626403808,
|
||
|
|
"epoch": 0.2206997248273151,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998668619791104,
|
||
|
|
"loss": 5.8732,
|
||
|
|
"mean_token_accuracy": 0.1587201938033104,
|
||
|
|
"num_tokens": 4382872.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.905340623855591,
|
||
|
|
"epoch": 0.22126130173527264,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998654774356131,
|
||
|
|
"loss": 5.9699,
|
||
|
|
"mean_token_accuracy": 0.15593308657407762,
|
||
|
|
"num_tokens": 4393623.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.907887887954712,
|
||
|
|
"epoch": 0.2218228786432302,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998640857323118,
|
||
|
|
"loss": 5.91,
|
||
|
|
"mean_token_accuracy": 0.15534867942333222,
|
||
|
|
"num_tokens": 4404215.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064648962020874,
|
||
|
|
"epoch": 0.22238445555118774,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998626868692509,
|
||
|
|
"loss": 6.1578,
|
||
|
|
"mean_token_accuracy": 0.15266190096735954,
|
||
|
|
"num_tokens": 4415978.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978055763244629,
|
||
|
|
"epoch": 0.2229460324591453,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998612808464748,
|
||
|
|
"loss": 5.9185,
|
||
|
|
"mean_token_accuracy": 0.1604282557964325,
|
||
|
|
"num_tokens": 4427060.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944674348831176,
|
||
|
|
"epoch": 0.22350760936710282,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998598676640283,
|
||
|
|
"loss": 5.9861,
|
||
|
|
"mean_token_accuracy": 0.15214295759797097,
|
||
|
|
"num_tokens": 4438145.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08530912399292,
|
||
|
|
"epoch": 0.22406918627506037,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998584473219563,
|
||
|
|
"loss": 6.0554,
|
||
|
|
"mean_token_accuracy": 0.1587221294641495,
|
||
|
|
"num_tokens": 4449324.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.903869676589966,
|
||
|
|
"epoch": 0.22463076318301792,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998570198203043,
|
||
|
|
"loss": 5.7953,
|
||
|
|
"mean_token_accuracy": 0.1570117339491844,
|
||
|
|
"num_tokens": 4459728.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.88097767829895,
|
||
|
|
"epoch": 0.22519234009097547,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998555851591175,
|
||
|
|
"loss": 5.9978,
|
||
|
|
"mean_token_accuracy": 0.16080355495214463,
|
||
|
|
"num_tokens": 4471164.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0333850383758545,
|
||
|
|
"epoch": 0.225753916998933,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998541433384416,
|
||
|
|
"loss": 6.0504,
|
||
|
|
"mean_token_accuracy": 0.15572140067815782,
|
||
|
|
"num_tokens": 4483349.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0429106712341305,
|
||
|
|
"epoch": 0.22631549390689054,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998526943583226,
|
||
|
|
"loss": 6.0179,
|
||
|
|
"mean_token_accuracy": 0.15771206319332123,
|
||
|
|
"num_tokens": 4495311.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924639892578125,
|
||
|
|
"epoch": 0.2268770708148481,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998512382188066,
|
||
|
|
"loss": 5.9688,
|
||
|
|
"mean_token_accuracy": 0.15513758808374406,
|
||
|
|
"num_tokens": 4507017.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992367076873779,
|
||
|
|
"epoch": 0.22743864772280564,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998497749199401,
|
||
|
|
"loss": 5.9937,
|
||
|
|
"mean_token_accuracy": 0.1526365488767624,
|
||
|
|
"num_tokens": 4517746.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032519912719726,
|
||
|
|
"epoch": 0.2280002246307632,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998483044617694,
|
||
|
|
"loss": 6.0745,
|
||
|
|
"mean_token_accuracy": 0.14750580340623856,
|
||
|
|
"num_tokens": 4529149.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030290651321411,
|
||
|
|
"epoch": 0.22856180153872072,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998468268443416,
|
||
|
|
"loss": 5.9585,
|
||
|
|
"mean_token_accuracy": 0.15775412023067475,
|
||
|
|
"num_tokens": 4540630.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.819119691848755,
|
||
|
|
"epoch": 0.22912337844667827,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998453420677034,
|
||
|
|
"loss": 5.9021,
|
||
|
|
"mean_token_accuracy": 0.15414910539984703,
|
||
|
|
"num_tokens": 4552877.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0394634246826175,
|
||
|
|
"epoch": 0.22968495535463582,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998438501319025,
|
||
|
|
"loss": 5.9873,
|
||
|
|
"mean_token_accuracy": 0.16143840849399566,
|
||
|
|
"num_tokens": 4563634.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.893660259246826,
|
||
|
|
"epoch": 0.23024653226259337,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998423510369862,
|
||
|
|
"loss": 5.9216,
|
||
|
|
"mean_token_accuracy": 0.163277006149292,
|
||
|
|
"num_tokens": 4574007.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.921794652938843,
|
||
|
|
"epoch": 0.23080810917055092,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998408447830022,
|
||
|
|
"loss": 5.9302,
|
||
|
|
"mean_token_accuracy": 0.15314771682024003,
|
||
|
|
"num_tokens": 4584146.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937058544158935,
|
||
|
|
"epoch": 0.23136968607850844,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998393313699985,
|
||
|
|
"loss": 5.9442,
|
||
|
|
"mean_token_accuracy": 0.15111495107412337,
|
||
|
|
"num_tokens": 4594839.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123587226867675,
|
||
|
|
"epoch": 0.231931262986466,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998378107980233,
|
||
|
|
"loss": 6.1128,
|
||
|
|
"mean_token_accuracy": 0.14634541124105455,
|
||
|
|
"num_tokens": 4608229.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988157129287719,
|
||
|
|
"epoch": 0.23249283989442354,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998362830671249,
|
||
|
|
"loss": 5.9118,
|
||
|
|
"mean_token_accuracy": 0.15399982333183287,
|
||
|
|
"num_tokens": 4619206.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.830771350860596,
|
||
|
|
"epoch": 0.2330544168023811,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998347481773522,
|
||
|
|
"loss": 5.939,
|
||
|
|
"mean_token_accuracy": 0.16280597448349,
|
||
|
|
"num_tokens": 4628966.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.950791311264038,
|
||
|
|
"epoch": 0.23361599371033864,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998332061287538,
|
||
|
|
"loss": 5.8271,
|
||
|
|
"mean_token_accuracy": 0.15719278901815414,
|
||
|
|
"num_tokens": 4639935.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976275014877319,
|
||
|
|
"epoch": 0.23417757061829617,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499831656921379,
|
||
|
|
"loss": 6.065,
|
||
|
|
"mean_token_accuracy": 0.1518533706665039,
|
||
|
|
"num_tokens": 4651998.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062891149520874,
|
||
|
|
"epoch": 0.23473914752625372,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499830100555277,
|
||
|
|
"loss": 6.0584,
|
||
|
|
"mean_token_accuracy": 0.1517246574163437,
|
||
|
|
"num_tokens": 4664002.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9623480319976805,
|
||
|
|
"epoch": 0.23530072443421127,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998285370304974,
|
||
|
|
"loss": 5.9293,
|
||
|
|
"mean_token_accuracy": 0.15818354934453965,
|
||
|
|
"num_tokens": 4675343.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996997594833374,
|
||
|
|
"epoch": 0.23586230134216882,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00049982696634709,
|
||
|
|
"loss": 5.9848,
|
||
|
|
"mean_token_accuracy": 0.1616687372326851,
|
||
|
|
"num_tokens": 4686410.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936463117599487,
|
||
|
|
"epoch": 0.23642387825012637,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998253885051048,
|
||
|
|
"loss": 6.0201,
|
||
|
|
"mean_token_accuracy": 0.15326433777809143,
|
||
|
|
"num_tokens": 4697768.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100189256668091,
|
||
|
|
"epoch": 0.2369854551580839,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000499823803504592,
|
||
|
|
"loss": 6.0104,
|
||
|
|
"mean_token_accuracy": 0.15419370904564858,
|
||
|
|
"num_tokens": 4709933.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993178224563598,
|
||
|
|
"epoch": 0.23754703206604144,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998222113456022,
|
||
|
|
"loss": 6.0493,
|
||
|
|
"mean_token_accuracy": 0.1489183008670807,
|
||
|
|
"num_tokens": 4721385.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.890592288970947,
|
||
|
|
"epoch": 0.238108608973999,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998206120281858,
|
||
|
|
"loss": 5.8685,
|
||
|
|
"mean_token_accuracy": 0.1633332997560501,
|
||
|
|
"num_tokens": 4732562.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.884363508224487,
|
||
|
|
"epoch": 0.23867018588195654,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499819005552394,
|
||
|
|
"loss": 5.8792,
|
||
|
|
"mean_token_accuracy": 0.15853570103645326,
|
||
|
|
"num_tokens": 4742794.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.837559032440185,
|
||
|
|
"epoch": 0.23923176278991407,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004998173919182779,
|
||
|
|
"loss": 5.8616,
|
||
|
|
"mean_token_accuracy": 0.1604430302977562,
|
||
|
|
"num_tokens": 4754903.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9406506538391115,
|
||
|
|
"epoch": 0.23979333969787162,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499815771125889,
|
||
|
|
"loss": 5.8989,
|
||
|
|
"mean_token_accuracy": 0.15427519828081132,
|
||
|
|
"num_tokens": 4766165.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9188025951385494,
|
||
|
|
"epoch": 0.24035491660582917,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998141431752785,
|
||
|
|
"loss": 5.9184,
|
||
|
|
"mean_token_accuracy": 0.15893685966730117,
|
||
|
|
"num_tokens": 4776551.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034300327301025,
|
||
|
|
"epoch": 0.24091649351378672,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998125080664987,
|
||
|
|
"loss": 6.0939,
|
||
|
|
"mean_token_accuracy": 0.1525190368294716,
|
||
|
|
"num_tokens": 4788344.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9868241310119625,
|
||
|
|
"epoch": 0.24147807042174427,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998108657996012,
|
||
|
|
"loss": 5.8973,
|
||
|
|
"mean_token_accuracy": 0.15438547730445862,
|
||
|
|
"num_tokens": 4799314.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9253113746643065,
|
||
|
|
"epoch": 0.2420396473297018,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998092163746387,
|
||
|
|
"loss": 5.9349,
|
||
|
|
"mean_token_accuracy": 0.16056873500347138,
|
||
|
|
"num_tokens": 4809588.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8701903343200685,
|
||
|
|
"epoch": 0.24260122423765934,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998075597916636,
|
||
|
|
"loss": 5.7562,
|
||
|
|
"mean_token_accuracy": 0.16604280918836595,
|
||
|
|
"num_tokens": 4820076.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9389283657073975,
|
||
|
|
"epoch": 0.2431628011456169,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998058960507286,
|
||
|
|
"loss": 6.0367,
|
||
|
|
"mean_token_accuracy": 0.15002979561686516,
|
||
|
|
"num_tokens": 4831504.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881774282455444,
|
||
|
|
"epoch": 0.24372437805357444,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998042251518866,
|
||
|
|
"loss": 5.8802,
|
||
|
|
"mean_token_accuracy": 0.15729590505361557,
|
||
|
|
"num_tokens": 4842826.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8496815204620365,
|
||
|
|
"epoch": 0.244285954961532,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998025470951908,
|
||
|
|
"loss": 5.8537,
|
||
|
|
"mean_token_accuracy": 0.16225429326295854,
|
||
|
|
"num_tokens": 4853279.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.957265853881836,
|
||
|
|
"epoch": 0.24484753186948952,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998008618806949,
|
||
|
|
"loss": 5.9213,
|
||
|
|
"mean_token_accuracy": 0.16333475559949875,
|
||
|
|
"num_tokens": 4863332.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962638473510742,
|
||
|
|
"epoch": 0.24540910877744707,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997991695084523,
|
||
|
|
"loss": 6.0566,
|
||
|
|
"mean_token_accuracy": 0.14747042953968048,
|
||
|
|
"num_tokens": 4874217.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0260858058929445,
|
||
|
|
"epoch": 0.24597068568540462,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997974699785169,
|
||
|
|
"loss": 5.9064,
|
||
|
|
"mean_token_accuracy": 0.16339460611343384,
|
||
|
|
"num_tokens": 4885322.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.819237565994262,
|
||
|
|
"epoch": 0.24653226259336217,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997957632909429,
|
||
|
|
"loss": 5.8615,
|
||
|
|
"mean_token_accuracy": 0.15775319337844848,
|
||
|
|
"num_tokens": 4895546.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.086778259277343,
|
||
|
|
"epoch": 0.24709383950131972,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997940494457846,
|
||
|
|
"loss": 6.0564,
|
||
|
|
"mean_token_accuracy": 0.1528075724840164,
|
||
|
|
"num_tokens": 4906957.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024942302703858,
|
||
|
|
"epoch": 0.24765541640927724,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997923284430967,
|
||
|
|
"loss": 5.9929,
|
||
|
|
"mean_token_accuracy": 0.14885835349559784,
|
||
|
|
"num_tokens": 4917965.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.866191291809082,
|
||
|
|
"epoch": 0.2482169933172348,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997906002829338,
|
||
|
|
"loss": 5.8855,
|
||
|
|
"mean_token_accuracy": 0.16118354648351668,
|
||
|
|
"num_tokens": 4928585.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916089773178101,
|
||
|
|
"epoch": 0.24877857022519234,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499788864965351,
|
||
|
|
"loss": 5.8858,
|
||
|
|
"mean_token_accuracy": 0.15575789362192155,
|
||
|
|
"num_tokens": 4939818.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965532827377319,
|
||
|
|
"epoch": 0.2493401471331499,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997871224904036,
|
||
|
|
"loss": 5.98,
|
||
|
|
"mean_token_accuracy": 0.1508565679192543,
|
||
|
|
"num_tokens": 4951752.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.827750968933105,
|
||
|
|
"epoch": 0.24990172404110744,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997853728581468,
|
||
|
|
"loss": 5.8161,
|
||
|
|
"mean_token_accuracy": 0.1646944299340248,
|
||
|
|
"num_tokens": 4961846.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95909481048584,
|
||
|
|
"epoch": 0.250463300949065,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997836160686368,
|
||
|
|
"loss": 5.9583,
|
||
|
|
"mean_token_accuracy": 0.15396301597356796,
|
||
|
|
"num_tokens": 4973693.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956462955474853,
|
||
|
|
"epoch": 0.25102487785702254,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004997818521219291,
|
||
|
|
"loss": 5.8866,
|
||
|
|
"mean_token_accuracy": 0.1603934332728386,
|
||
|
|
"num_tokens": 4986156.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8751894474029545,
|
||
|
|
"epoch": 0.25158645476498004,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997800810180803,
|
||
|
|
"loss": 5.9669,
|
||
|
|
"mean_token_accuracy": 0.15617042332887648,
|
||
|
|
"num_tokens": 4997615.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96913776397705,
|
||
|
|
"epoch": 0.2521480316729376,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997783027571464,
|
||
|
|
"loss": 5.8901,
|
||
|
|
"mean_token_accuracy": 0.1606399178504944,
|
||
|
|
"num_tokens": 5007655.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.879551124572754,
|
||
|
|
"epoch": 0.25270960858089514,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997765173391841,
|
||
|
|
"loss": 5.9554,
|
||
|
|
"mean_token_accuracy": 0.1597429096698761,
|
||
|
|
"num_tokens": 5018933.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.037764549255371,
|
||
|
|
"epoch": 0.2532711854888527,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997747247642505,
|
||
|
|
"loss": 5.9753,
|
||
|
|
"mean_token_accuracy": 0.15459429025650023,
|
||
|
|
"num_tokens": 5030495.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.930814743041992,
|
||
|
|
"epoch": 0.25383276239681024,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997729250324023,
|
||
|
|
"loss": 6.0208,
|
||
|
|
"mean_token_accuracy": 0.152151720225811,
|
||
|
|
"num_tokens": 5041553.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959843635559082,
|
||
|
|
"epoch": 0.2543943393047678,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997711181436971,
|
||
|
|
"loss": 5.94,
|
||
|
|
"mean_token_accuracy": 0.15976212471723555,
|
||
|
|
"num_tokens": 5052312.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988469648361206,
|
||
|
|
"epoch": 0.25495591621272534,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997693040981922,
|
||
|
|
"loss": 6.1231,
|
||
|
|
"mean_token_accuracy": 0.1494268372654915,
|
||
|
|
"num_tokens": 5063445.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01909031867981,
|
||
|
|
"epoch": 0.2555174931206829,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004997674828959456,
|
||
|
|
"loss": 5.9016,
|
||
|
|
"mean_token_accuracy": 0.15913700312376022,
|
||
|
|
"num_tokens": 5073052.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.919397306442261,
|
||
|
|
"epoch": 0.25607907002864044,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997656545370151,
|
||
|
|
"loss": 5.9473,
|
||
|
|
"mean_token_accuracy": 0.15869781970977784,
|
||
|
|
"num_tokens": 5084174.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975394916534424,
|
||
|
|
"epoch": 0.256640646936598,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499763819021459,
|
||
|
|
"loss": 5.9366,
|
||
|
|
"mean_token_accuracy": 0.1589258521795273,
|
||
|
|
"num_tokens": 5094106.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002953243255615,
|
||
|
|
"epoch": 0.2572022238445555,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997619763493357,
|
||
|
|
"loss": 6.0269,
|
||
|
|
"mean_token_accuracy": 0.15607377290725707,
|
||
|
|
"num_tokens": 5106963.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8494157791137695,
|
||
|
|
"epoch": 0.25776380075251304,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000499760126520704,
|
||
|
|
"loss": 5.8168,
|
||
|
|
"mean_token_accuracy": 0.15646326541900635,
|
||
|
|
"num_tokens": 5119476.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044357061386108,
|
||
|
|
"epoch": 0.2583253776604706,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997582695356225,
|
||
|
|
"loss": 6.0626,
|
||
|
|
"mean_token_accuracy": 0.1513483703136444,
|
||
|
|
"num_tokens": 5132169.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.878989505767822,
|
||
|
|
"epoch": 0.25888695456842814,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997564053941507,
|
||
|
|
"loss": 5.9071,
|
||
|
|
"mean_token_accuracy": 0.15743234679102897,
|
||
|
|
"num_tokens": 5143354.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887942600250244,
|
||
|
|
"epoch": 0.2594485314763857,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997545340963478,
|
||
|
|
"loss": 5.9689,
|
||
|
|
"mean_token_accuracy": 0.15517181158065796,
|
||
|
|
"num_tokens": 5154624.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0336226463317875,
|
||
|
|
"epoch": 0.26001010838434324,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997526556422733,
|
||
|
|
"loss": 5.8721,
|
||
|
|
"mean_token_accuracy": 0.1567656323313713,
|
||
|
|
"num_tokens": 5165349.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.863103628158569,
|
||
|
|
"epoch": 0.2605716852923008,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004997507700319872,
|
||
|
|
"loss": 5.9555,
|
||
|
|
"mean_token_accuracy": 0.1557866856455803,
|
||
|
|
"num_tokens": 5175874.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922141408920288,
|
||
|
|
"epoch": 0.26113326220025834,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997488772655492,
|
||
|
|
"loss": 5.8352,
|
||
|
|
"mean_token_accuracy": 0.16336635500192642,
|
||
|
|
"num_tokens": 5186591.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.844820261001587,
|
||
|
|
"epoch": 0.2616948391082159,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004997469773430199,
|
||
|
|
"loss": 5.9473,
|
||
|
|
"mean_token_accuracy": 0.16148907244205474,
|
||
|
|
"num_tokens": 5197307.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.896266222000122,
|
||
|
|
"epoch": 0.2622564160161734,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004997450702644596,
|
||
|
|
"loss": 5.8953,
|
||
|
|
"mean_token_accuracy": 0.15877846628427505,
|
||
|
|
"num_tokens": 5209868.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924633741378784,
|
||
|
|
"epoch": 0.26281799292413094,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997431560299292,
|
||
|
|
"loss": 5.9231,
|
||
|
|
"mean_token_accuracy": 0.15989050269126892,
|
||
|
|
"num_tokens": 5220365.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944304752349853,
|
||
|
|
"epoch": 0.2633795698320885,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997412346394894,
|
||
|
|
"loss": 5.834,
|
||
|
|
"mean_token_accuracy": 0.15482053458690642,
|
||
|
|
"num_tokens": 5231575.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.866419935226441,
|
||
|
|
"epoch": 0.26394114674004604,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997393060932017,
|
||
|
|
"loss": 5.9167,
|
||
|
|
"mean_token_accuracy": 0.15795815736055374,
|
||
|
|
"num_tokens": 5241852.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962919664382935,
|
||
|
|
"epoch": 0.2645027236480036,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997373703911273,
|
||
|
|
"loss": 5.9739,
|
||
|
|
"mean_token_accuracy": 0.15711618214845657,
|
||
|
|
"num_tokens": 5254536.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002066612243652,
|
||
|
|
"epoch": 0.26506430055596114,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997354275333277,
|
||
|
|
"loss": 5.8842,
|
||
|
|
"mean_token_accuracy": 0.15617608428001403,
|
||
|
|
"num_tokens": 5264946.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.679558563232422,
|
||
|
|
"epoch": 0.2656258774639187,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499733477519865,
|
||
|
|
"loss": 5.7131,
|
||
|
|
"mean_token_accuracy": 0.15967741459608079,
|
||
|
|
"num_tokens": 5275527.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.902612113952637,
|
||
|
|
"epoch": 0.26618745437187624,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997315203508013,
|
||
|
|
"loss": 5.8837,
|
||
|
|
"mean_token_accuracy": 0.15513267517089843,
|
||
|
|
"num_tokens": 5285471.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.831973838806152,
|
||
|
|
"epoch": 0.2667490312798338,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997295560261988,
|
||
|
|
"loss": 5.8057,
|
||
|
|
"mean_token_accuracy": 0.15760743468999863,
|
||
|
|
"num_tokens": 5295743.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89382266998291,
|
||
|
|
"epoch": 0.26731060818779134,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00049972758454612,
|
||
|
|
"loss": 5.9519,
|
||
|
|
"mean_token_accuracy": 0.15221580266952514,
|
||
|
|
"num_tokens": 5307963.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93057165145874,
|
||
|
|
"epoch": 0.26787218509574884,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997256059106279,
|
||
|
|
"loss": 5.8382,
|
||
|
|
"mean_token_accuracy": 0.16068274080753325,
|
||
|
|
"num_tokens": 5318394.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959908103942871,
|
||
|
|
"epoch": 0.2684337620037064,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997236201197853,
|
||
|
|
"loss": 6.0647,
|
||
|
|
"mean_token_accuracy": 0.14594504833221436,
|
||
|
|
"num_tokens": 5331728.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980408430099487,
|
||
|
|
"epoch": 0.26899533891166394,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997216271736554,
|
||
|
|
"loss": 5.9376,
|
||
|
|
"mean_token_accuracy": 0.16780572682619094,
|
||
|
|
"num_tokens": 5342825.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926927518844605,
|
||
|
|
"epoch": 0.2695569158196215,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997196270723018,
|
||
|
|
"loss": 5.8545,
|
||
|
|
"mean_token_accuracy": 0.15406033545732498,
|
||
|
|
"num_tokens": 5354232.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.896172904968262,
|
||
|
|
"epoch": 0.27011849272757904,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004997176198157881,
|
||
|
|
"loss": 5.9378,
|
||
|
|
"mean_token_accuracy": 0.154250118881464,
|
||
|
|
"num_tokens": 5364807.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911499881744385,
|
||
|
|
"epoch": 0.2706800696355366,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997156054041781,
|
||
|
|
"loss": 5.9182,
|
||
|
|
"mean_token_accuracy": 0.15305136442184447,
|
||
|
|
"num_tokens": 5375593.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.901667356491089,
|
||
|
|
"epoch": 0.27124164654349414,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004997135838375362,
|
||
|
|
"loss": 5.8676,
|
||
|
|
"mean_token_accuracy": 0.1642325833439827,
|
||
|
|
"num_tokens": 5386740.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.836700773239135,
|
||
|
|
"epoch": 0.2718032234514517,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997115551159267,
|
||
|
|
"loss": 5.8519,
|
||
|
|
"mean_token_accuracy": 0.16053027510643006,
|
||
|
|
"num_tokens": 5397732.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038162803649902,
|
||
|
|
"epoch": 0.27236480035940924,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499709519239414,
|
||
|
|
"loss": 5.913,
|
||
|
|
"mean_token_accuracy": 0.15328923463821412,
|
||
|
|
"num_tokens": 5409392.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7375201225280765,
|
||
|
|
"epoch": 0.2729263772673668,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997074762080632,
|
||
|
|
"loss": 5.8808,
|
||
|
|
"mean_token_accuracy": 0.1645394131541252,
|
||
|
|
"num_tokens": 5420903.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848090887069702,
|
||
|
|
"epoch": 0.2734879541753243,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499705426021939,
|
||
|
|
"loss": 5.8194,
|
||
|
|
"mean_token_accuracy": 0.15687702000141143,
|
||
|
|
"num_tokens": 5432631.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.903999853134155,
|
||
|
|
"epoch": 0.27404953108328184,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499703368681107,
|
||
|
|
"loss": 5.7843,
|
||
|
|
"mean_token_accuracy": 0.16448869407176972,
|
||
|
|
"num_tokens": 5443463.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943267393112182,
|
||
|
|
"epoch": 0.2746111079912394,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004997013041856326,
|
||
|
|
"loss": 6.091,
|
||
|
|
"mean_token_accuracy": 0.1532382771372795,
|
||
|
|
"num_tokens": 5455903.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.921958017349243,
|
||
|
|
"epoch": 0.27517268489919694,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996992325355815,
|
||
|
|
"loss": 5.9191,
|
||
|
|
"mean_token_accuracy": 0.15618202090263367,
|
||
|
|
"num_tokens": 5467201.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.923684930801391,
|
||
|
|
"epoch": 0.2757342618071545,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004996971537310198,
|
||
|
|
"loss": 5.7993,
|
||
|
|
"mean_token_accuracy": 0.15881394743919372,
|
||
|
|
"num_tokens": 5478109.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954914569854736,
|
||
|
|
"epoch": 0.27629583871511204,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004996950677720133,
|
||
|
|
"loss": 5.9197,
|
||
|
|
"mean_token_accuracy": 0.15350393652915956,
|
||
|
|
"num_tokens": 5489621.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.837770414352417,
|
||
|
|
"epoch": 0.2768574156230696,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000499692974658629,
|
||
|
|
"loss": 5.8777,
|
||
|
|
"mean_token_accuracy": 0.16119124591350556,
|
||
|
|
"num_tokens": 5500606.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.917882061004638,
|
||
|
|
"epoch": 0.27741899253102714,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004996908743909331,
|
||
|
|
"loss": 5.8125,
|
||
|
|
"mean_token_accuracy": 0.1658737137913704,
|
||
|
|
"num_tokens": 5510768.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.814739227294922,
|
||
|
|
"epoch": 0.2779805694389847,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004996887669689926,
|
||
|
|
"loss": 5.8378,
|
||
|
|
"mean_token_accuracy": 0.1627394124865532,
|
||
|
|
"num_tokens": 5522210.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897688150405884,
|
||
|
|
"epoch": 0.2785421463469422,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996866523928747,
|
||
|
|
"loss": 5.957,
|
||
|
|
"mean_token_accuracy": 0.15570937544107438,
|
||
|
|
"num_tokens": 5533055.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033761405944825,
|
||
|
|
"epoch": 0.27910372325489974,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004996845306626467,
|
||
|
|
"loss": 5.9712,
|
||
|
|
"mean_token_accuracy": 0.1545345276594162,
|
||
|
|
"num_tokens": 5544345.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881541776657104,
|
||
|
|
"epoch": 0.2796653001628573,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996824017783759,
|
||
|
|
"loss": 5.8838,
|
||
|
|
"mean_token_accuracy": 0.1547561228275299,
|
||
|
|
"num_tokens": 5556734.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.915271615982055,
|
||
|
|
"epoch": 0.28022687707081484,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004996802657401304,
|
||
|
|
"loss": 5.9166,
|
||
|
|
"mean_token_accuracy": 0.15897395685315133,
|
||
|
|
"num_tokens": 5566874.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96377158164978,
|
||
|
|
"epoch": 0.2807884539787724,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996781225479781,
|
||
|
|
"loss": 5.9268,
|
||
|
|
"mean_token_accuracy": 0.15026624351739884,
|
||
|
|
"num_tokens": 5578812.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955607175827026,
|
||
|
|
"epoch": 0.28135003088672994,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004996759722019872,
|
||
|
|
"loss": 5.971,
|
||
|
|
"mean_token_accuracy": 0.1573779821395874,
|
||
|
|
"num_tokens": 5590021.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935986137390136,
|
||
|
|
"epoch": 0.2819116077946875,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004996738147022262,
|
||
|
|
"loss": 5.9927,
|
||
|
|
"mean_token_accuracy": 0.1486438363790512,
|
||
|
|
"num_tokens": 5600921.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9097339630126955,
|
||
|
|
"epoch": 0.28247318470264504,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004996716500487638,
|
||
|
|
"loss": 5.8868,
|
||
|
|
"mean_token_accuracy": 0.15973623543977739,
|
||
|
|
"num_tokens": 5610615.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.794392156600952,
|
||
|
|
"epoch": 0.2830347616106026,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499669478241669,
|
||
|
|
"loss": 5.8205,
|
||
|
|
"mean_token_accuracy": 0.159597747027874,
|
||
|
|
"num_tokens": 5621596.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034035968780517,
|
||
|
|
"epoch": 0.28359633851856014,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004996672992810108,
|
||
|
|
"loss": 5.8562,
|
||
|
|
"mean_token_accuracy": 0.16451989412307738,
|
||
|
|
"num_tokens": 5633047.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8009015083312985,
|
||
|
|
"epoch": 0.28415791542651764,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004996651131668587,
|
||
|
|
"loss": 5.8476,
|
||
|
|
"mean_token_accuracy": 0.15795179605484008,
|
||
|
|
"num_tokens": 5644970.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8380271911621096,
|
||
|
|
"epoch": 0.2847194923344752,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004996629198992823,
|
||
|
|
"loss": 5.9632,
|
||
|
|
"mean_token_accuracy": 0.15440421998500825,
|
||
|
|
"num_tokens": 5656631.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936119413375854,
|
||
|
|
"epoch": 0.28528106924243274,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004996607194783513,
|
||
|
|
"loss": 5.9161,
|
||
|
|
"mean_token_accuracy": 0.1549352765083313,
|
||
|
|
"num_tokens": 5668808.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.823132276535034,
|
||
|
|
"epoch": 0.2858426461503903,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004996585119041359,
|
||
|
|
"loss": 5.8602,
|
||
|
|
"mean_token_accuracy": 0.1564148411154747,
|
||
|
|
"num_tokens": 5679493.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.972305202484131,
|
||
|
|
"epoch": 0.28640422305834784,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004996562971767063,
|
||
|
|
"loss": 5.8787,
|
||
|
|
"mean_token_accuracy": 0.16313901394605637,
|
||
|
|
"num_tokens": 5689879.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.90954475402832,
|
||
|
|
"epoch": 0.2869657999663054,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499654075296133,
|
||
|
|
"loss": 5.9669,
|
||
|
|
"mean_token_accuracy": 0.15989068448543547,
|
||
|
|
"num_tokens": 5699934.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.840920352935791,
|
||
|
|
"epoch": 0.28752737687426294,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000499651846262487,
|
||
|
|
"loss": 5.8848,
|
||
|
|
"mean_token_accuracy": 0.16583120375871657,
|
||
|
|
"num_tokens": 5710171.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9403012752532955,
|
||
|
|
"epoch": 0.2880889537822205,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004996496100758389,
|
||
|
|
"loss": 5.8924,
|
||
|
|
"mean_token_accuracy": 0.15079000890254973,
|
||
|
|
"num_tokens": 5721190.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004739475250244,
|
||
|
|
"epoch": 0.28865053069017804,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004996473667362604,
|
||
|
|
"loss": 5.9997,
|
||
|
|
"mean_token_accuracy": 0.15434087961912155,
|
||
|
|
"num_tokens": 5733706.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.847912883758545,
|
||
|
|
"epoch": 0.28921210759813554,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996451162438224,
|
||
|
|
"loss": 5.9651,
|
||
|
|
"mean_token_accuracy": 0.16153858602046967,
|
||
|
|
"num_tokens": 5745712.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.814180088043213,
|
||
|
|
"epoch": 0.2897736845060931,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004996428585985967,
|
||
|
|
"loss": 5.7713,
|
||
|
|
"mean_token_accuracy": 0.17209184318780898,
|
||
|
|
"num_tokens": 5757915.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8850490093231205,
|
||
|
|
"epoch": 0.29033526141405064,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004996405938006553,
|
||
|
|
"loss": 5.9153,
|
||
|
|
"mean_token_accuracy": 0.162559674680233,
|
||
|
|
"num_tokens": 5768788.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.906909847259522,
|
||
|
|
"epoch": 0.2908968383220082,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996383218500703,
|
||
|
|
"loss": 5.8458,
|
||
|
|
"mean_token_accuracy": 0.15892737954854966,
|
||
|
|
"num_tokens": 5779806.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.798295259475708,
|
||
|
|
"epoch": 0.29145841522996574,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499636042746914,
|
||
|
|
"loss": 5.8139,
|
||
|
|
"mean_token_accuracy": 0.15552390217781067,
|
||
|
|
"num_tokens": 5790177.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888185977935791,
|
||
|
|
"epoch": 0.2920199921379233,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499633756491259,
|
||
|
|
"loss": 5.8386,
|
||
|
|
"mean_token_accuracy": 0.16393716782331466,
|
||
|
|
"num_tokens": 5800251.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911457777023315,
|
||
|
|
"epoch": 0.29258156904588084,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004996314630831781,
|
||
|
|
"loss": 5.9226,
|
||
|
|
"mean_token_accuracy": 0.16139961034059525,
|
||
|
|
"num_tokens": 5812210.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936538457870483,
|
||
|
|
"epoch": 0.2931431459538384,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004996291625227443,
|
||
|
|
"loss": 5.9052,
|
||
|
|
"mean_token_accuracy": 0.16226045042276382,
|
||
|
|
"num_tokens": 5823280.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9634246826171875,
|
||
|
|
"epoch": 0.29370472286179594,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004996268548100307,
|
||
|
|
"loss": 5.9836,
|
||
|
|
"mean_token_accuracy": 0.15235772579908372,
|
||
|
|
"num_tokens": 5835076.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.800026893615723,
|
||
|
|
"epoch": 0.2942662997697535,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499624539945111,
|
||
|
|
"loss": 5.7683,
|
||
|
|
"mean_token_accuracy": 0.16759044528007508,
|
||
|
|
"num_tokens": 5845376.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.827654123306274,
|
||
|
|
"epoch": 0.294827876677711,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004996222179280589,
|
||
|
|
"loss": 5.8235,
|
||
|
|
"mean_token_accuracy": 0.1543615683913231,
|
||
|
|
"num_tokens": 5857124.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.908602380752564,
|
||
|
|
"epoch": 0.29538945358566854,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004996198887589481,
|
||
|
|
"loss": 5.9194,
|
||
|
|
"mean_token_accuracy": 0.15195261538028718,
|
||
|
|
"num_tokens": 5868681.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.923360443115234,
|
||
|
|
"epoch": 0.2959510304936261,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004996175524378531,
|
||
|
|
"loss": 5.9016,
|
||
|
|
"mean_token_accuracy": 0.1616549476981163,
|
||
|
|
"num_tokens": 5880532.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887218236923218,
|
||
|
|
"epoch": 0.29651260740158364,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499615208964848,
|
||
|
|
"loss": 5.8615,
|
||
|
|
"mean_token_accuracy": 0.1611190915107727,
|
||
|
|
"num_tokens": 5891582.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891259670257568,
|
||
|
|
"epoch": 0.2970741843095412,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004996128583400077,
|
||
|
|
"loss": 5.8643,
|
||
|
|
"mean_token_accuracy": 0.15494512170553207,
|
||
|
|
"num_tokens": 5903543.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.823057651519775,
|
||
|
|
"epoch": 0.29763576121749874,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996105005634066,
|
||
|
|
"loss": 5.8263,
|
||
|
|
"mean_token_accuracy": 0.16598099768161773,
|
||
|
|
"num_tokens": 5913140.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.846201181411743,
|
||
|
|
"epoch": 0.2981973381254563,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004996081356351202,
|
||
|
|
"loss": 5.8013,
|
||
|
|
"mean_token_accuracy": 0.16204901039600372,
|
||
|
|
"num_tokens": 5924010.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89202766418457,
|
||
|
|
"epoch": 0.29875891503341384,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004996057635552237,
|
||
|
|
"loss": 6.0094,
|
||
|
|
"mean_token_accuracy": 0.1546384647488594,
|
||
|
|
"num_tokens": 5936246.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920505714416504,
|
||
|
|
"epoch": 0.2993204919413714,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004996033843237925,
|
||
|
|
"loss": 5.8988,
|
||
|
|
"mean_token_accuracy": 0.1529396116733551,
|
||
|
|
"num_tokens": 5947594.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.925133943557739,
|
||
|
|
"epoch": 0.29988206884932894,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004996009979409025,
|
||
|
|
"loss": 5.8325,
|
||
|
|
"mean_token_accuracy": 0.1516793191432953,
|
||
|
|
"num_tokens": 5957660.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.700359630584717,
|
||
|
|
"epoch": 0.30044364575728644,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004995986044066295,
|
||
|
|
"loss": 5.6562,
|
||
|
|
"mean_token_accuracy": 0.16879596710205078,
|
||
|
|
"num_tokens": 5968881.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.853354215621948,
|
||
|
|
"epoch": 0.301005222665244,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00049959620372105,
|
||
|
|
"loss": 5.827,
|
||
|
|
"mean_token_accuracy": 0.1607290267944336,
|
||
|
|
"num_tokens": 5980032.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.761854076385498,
|
||
|
|
"epoch": 0.30156679957320154,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004995937958842401,
|
||
|
|
"loss": 5.8271,
|
||
|
|
"mean_token_accuracy": 0.16057847291231156,
|
||
|
|
"num_tokens": 5991781.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.842853689193726,
|
||
|
|
"epoch": 0.3021283764811591,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004995913808962767,
|
||
|
|
"loss": 5.8726,
|
||
|
|
"mean_token_accuracy": 0.15679309368133545,
|
||
|
|
"num_tokens": 6002303.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955978202819824,
|
||
|
|
"epoch": 0.30268995338911664,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004995889587572366,
|
||
|
|
"loss": 5.9421,
|
||
|
|
"mean_token_accuracy": 0.16047051846981047,
|
||
|
|
"num_tokens": 6011523.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.921958112716675,
|
||
|
|
"epoch": 0.3032515302970742,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499586529467197,
|
||
|
|
"loss": 5.7573,
|
||
|
|
"mean_token_accuracy": 0.1624143198132515,
|
||
|
|
"num_tokens": 6022169.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.688100337982178,
|
||
|
|
"epoch": 0.30381310720503174,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0004995840930262351,
|
||
|
|
"loss": 5.8048,
|
||
|
|
"mean_token_accuracy": 0.1632087327539921,
|
||
|
|
"num_tokens": 6033393.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.892455244064331,
|
||
|
|
"epoch": 0.3043746841129893,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004995816494344287,
|
||
|
|
"loss": 5.8762,
|
||
|
|
"mean_token_accuracy": 0.15626945048570634,
|
||
|
|
"num_tokens": 6045365.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.877195835113525,
|
||
|
|
"epoch": 0.30493626102094684,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995791986918554,
|
||
|
|
"loss": 5.8954,
|
||
|
|
"mean_token_accuracy": 0.16077566295862197,
|
||
|
|
"num_tokens": 6057482.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.91087236404419,
|
||
|
|
"epoch": 0.30549783792890434,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004995767407985933,
|
||
|
|
"loss": 5.8045,
|
||
|
|
"mean_token_accuracy": 0.16352560371160507,
|
||
|
|
"num_tokens": 6068194.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8684210777282715,
|
||
|
|
"epoch": 0.3060594148368619,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004995742757547207,
|
||
|
|
"loss": 5.8676,
|
||
|
|
"mean_token_accuracy": 0.16073331981897354,
|
||
|
|
"num_tokens": 6080540.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.772074127197266,
|
||
|
|
"epoch": 0.30662099174481944,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000499571803560316,
|
||
|
|
"loss": 5.9062,
|
||
|
|
"mean_token_accuracy": 0.16154931038618087,
|
||
|
|
"num_tokens": 6092464.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9210954189300535,
|
||
|
|
"epoch": 0.307182568652777,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995693242154581,
|
||
|
|
"loss": 5.8483,
|
||
|
|
"mean_token_accuracy": 0.16159511357545853,
|
||
|
|
"num_tokens": 6103242.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8642387866973875,
|
||
|
|
"epoch": 0.30774414556073454,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004995668377202258,
|
||
|
|
"loss": 5.8995,
|
||
|
|
"mean_token_accuracy": 0.16059732884168626,
|
||
|
|
"num_tokens": 6116383.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8038359642028805,
|
||
|
|
"epoch": 0.3083057224686921,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995643440746982,
|
||
|
|
"loss": 5.6883,
|
||
|
|
"mean_token_accuracy": 0.17047392278909684,
|
||
|
|
"num_tokens": 6126883.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.845919179916382,
|
||
|
|
"epoch": 0.30886729937664964,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004995618432789548,
|
||
|
|
"loss": 5.8948,
|
||
|
|
"mean_token_accuracy": 0.15591834336519242,
|
||
|
|
"num_tokens": 6139613.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.912436485290527,
|
||
|
|
"epoch": 0.3094288762846072,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004995593353330753,
|
||
|
|
"loss": 5.9525,
|
||
|
|
"mean_token_accuracy": 0.15195179283618926,
|
||
|
|
"num_tokens": 6151950.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8443773746490475,
|
||
|
|
"epoch": 0.30999045319256474,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004995568202371393,
|
||
|
|
"loss": 5.7443,
|
||
|
|
"mean_token_accuracy": 0.16946211010217666,
|
||
|
|
"num_tokens": 6161563.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.733523893356323,
|
||
|
|
"epoch": 0.3105520301005223,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004995542979912272,
|
||
|
|
"loss": 5.7569,
|
||
|
|
"mean_token_accuracy": 0.16979626566171646,
|
||
|
|
"num_tokens": 6170966.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8455491065979,
|
||
|
|
"epoch": 0.3111136070084798,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004995517685954192,
|
||
|
|
"loss": 5.8253,
|
||
|
|
"mean_token_accuracy": 0.1628107637166977,
|
||
|
|
"num_tokens": 6182563.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.925236988067627,
|
||
|
|
"epoch": 0.31167518391643734,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004995492320497958,
|
||
|
|
"loss": 5.942,
|
||
|
|
"mean_token_accuracy": 0.15330271273851395,
|
||
|
|
"num_tokens": 6194495.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.890429449081421,
|
||
|
|
"epoch": 0.3122367608243949,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995466883544376,
|
||
|
|
"loss": 5.8378,
|
||
|
|
"mean_token_accuracy": 0.15787812322378159,
|
||
|
|
"num_tokens": 6206594.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.852018165588379,
|
||
|
|
"epoch": 0.31279833773235244,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004995441375094258,
|
||
|
|
"loss": 5.8674,
|
||
|
|
"mean_token_accuracy": 0.15727385357022286,
|
||
|
|
"num_tokens": 6218371.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92617712020874,
|
||
|
|
"epoch": 0.31335991464031,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004995415795148417,
|
||
|
|
"loss": 5.792,
|
||
|
|
"mean_token_accuracy": 0.16471333503723146,
|
||
|
|
"num_tokens": 6228723.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894465827941895,
|
||
|
|
"epoch": 0.31392149154826754,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004995390143707665,
|
||
|
|
"loss": 5.9859,
|
||
|
|
"mean_token_accuracy": 0.16086607724428176,
|
||
|
|
"num_tokens": 6240535.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.770377111434937,
|
||
|
|
"epoch": 0.3144830684562251,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004995364420772821,
|
||
|
|
"loss": 5.6795,
|
||
|
|
"mean_token_accuracy": 0.16809894442558287,
|
||
|
|
"num_tokens": 6250643.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.803590869903564,
|
||
|
|
"epoch": 0.31504464536418264,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004995338626344702,
|
||
|
|
"loss": 5.811,
|
||
|
|
"mean_token_accuracy": 0.15963360369205476,
|
||
|
|
"num_tokens": 6259569.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.849584341049194,
|
||
|
|
"epoch": 0.3156062222721402,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499531276042413,
|
||
|
|
"loss": 5.9635,
|
||
|
|
"mean_token_accuracy": 0.16318879276514053,
|
||
|
|
"num_tokens": 6271108.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959302282333374,
|
||
|
|
"epoch": 0.31616779918009774,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004995286823011929,
|
||
|
|
"loss": 5.7944,
|
||
|
|
"mean_token_accuracy": 0.1569117486476898,
|
||
|
|
"num_tokens": 6282352.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.800611162185669,
|
||
|
|
"epoch": 0.31672937608805524,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004995260814108926,
|
||
|
|
"loss": 5.9256,
|
||
|
|
"mean_token_accuracy": 0.15762576460838318,
|
||
|
|
"num_tokens": 6294946.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.787460851669311,
|
||
|
|
"epoch": 0.3172909529960128,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004995234733715947,
|
||
|
|
"loss": 5.7398,
|
||
|
|
"mean_token_accuracy": 0.1648264065384865,
|
||
|
|
"num_tokens": 6305552.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.852634286880493,
|
||
|
|
"epoch": 0.31785252990397034,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004995208581833824,
|
||
|
|
"loss": 5.7964,
|
||
|
|
"mean_token_accuracy": 0.17010432332754136,
|
||
|
|
"num_tokens": 6315815.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.810712432861328,
|
||
|
|
"epoch": 0.3184141068119279,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004995182358463388,
|
||
|
|
"loss": 5.8413,
|
||
|
|
"mean_token_accuracy": 0.16378075629472733,
|
||
|
|
"num_tokens": 6327384.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.902743816375732,
|
||
|
|
"epoch": 0.31897568371988544,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995156063605475,
|
||
|
|
"loss": 5.8133,
|
||
|
|
"mean_token_accuracy": 0.156479349732399,
|
||
|
|
"num_tokens": 6338083.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93860764503479,
|
||
|
|
"epoch": 0.319537260627843,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004995129697260922,
|
||
|
|
"loss": 5.8299,
|
||
|
|
"mean_token_accuracy": 0.16261689811944963,
|
||
|
|
"num_tokens": 6349058.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.752696514129639,
|
||
|
|
"epoch": 0.32009883753580054,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995103259430569,
|
||
|
|
"loss": 5.8305,
|
||
|
|
"mean_token_accuracy": 0.16424888297915458,
|
||
|
|
"num_tokens": 6359655.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962045001983642,
|
||
|
|
"epoch": 0.3206604144437581,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004995076750115258,
|
||
|
|
"loss": 5.9625,
|
||
|
|
"mean_token_accuracy": 0.1578860342502594,
|
||
|
|
"num_tokens": 6372088.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874738883972168,
|
||
|
|
"epoch": 0.32122199135171564,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004995050169315832,
|
||
|
|
"loss": 5.8723,
|
||
|
|
"mean_token_accuracy": 0.15489131957292557,
|
||
|
|
"num_tokens": 6382946.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.825060510635376,
|
||
|
|
"epoch": 0.32178356825967314,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004995023517033138,
|
||
|
|
"loss": 5.8555,
|
||
|
|
"mean_token_accuracy": 0.15830326005816459,
|
||
|
|
"num_tokens": 6392591.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.798574829101563,
|
||
|
|
"epoch": 0.3223451451676307,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004994996793268024,
|
||
|
|
"loss": 5.8013,
|
||
|
|
"mean_token_accuracy": 0.16411383152008058,
|
||
|
|
"num_tokens": 6403159.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.871509552001953,
|
||
|
|
"epoch": 0.32290672207558824,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004994969998021342,
|
||
|
|
"loss": 5.809,
|
||
|
|
"mean_token_accuracy": 0.16091817617416382,
|
||
|
|
"num_tokens": 6414232.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89113826751709,
|
||
|
|
"epoch": 0.3234682989835458,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004994943131293944,
|
||
|
|
"loss": 5.8018,
|
||
|
|
"mean_token_accuracy": 0.17012230753898622,
|
||
|
|
"num_tokens": 6425762.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.764307022094727,
|
||
|
|
"epoch": 0.32402987589150334,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004994916193086687,
|
||
|
|
"loss": 5.8535,
|
||
|
|
"mean_token_accuracy": 0.15552848875522612,
|
||
|
|
"num_tokens": 6439077.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911887264251709,
|
||
|
|
"epoch": 0.3245914527994609,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004994889183400428,
|
||
|
|
"loss": 5.9207,
|
||
|
|
"mean_token_accuracy": 0.15717577636241914,
|
||
|
|
"num_tokens": 6450425.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.864399003982544,
|
||
|
|
"epoch": 0.32515302970741844,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004994862102236025,
|
||
|
|
"loss": 5.8702,
|
||
|
|
"mean_token_accuracy": 0.15890682712197304,
|
||
|
|
"num_tokens": 6461347.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.929317331314087,
|
||
|
|
"epoch": 0.325714606615376,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004994834949594342,
|
||
|
|
"loss": 5.8569,
|
||
|
|
"mean_token_accuracy": 0.16072623133659364,
|
||
|
|
"num_tokens": 6472428.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.843264627456665,
|
||
|
|
"epoch": 0.32627618352333354,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004994807725476246,
|
||
|
|
"loss": 5.8215,
|
||
|
|
"mean_token_accuracy": 0.16909091621637345,
|
||
|
|
"num_tokens": 6483393.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.799573183059692,
|
||
|
|
"epoch": 0.3268377604312911,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004994780429882599,
|
||
|
|
"loss": 5.8063,
|
||
|
|
"mean_token_accuracy": 0.16213589757680893,
|
||
|
|
"num_tokens": 6493520.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.797100687026978,
|
||
|
|
"epoch": 0.3273993373392486,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004994753062814274,
|
||
|
|
"loss": 5.7443,
|
||
|
|
"mean_token_accuracy": 0.17201152443885803,
|
||
|
|
"num_tokens": 6505282.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936969232559204,
|
||
|
|
"epoch": 0.32796091424720614,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004994725624272139,
|
||
|
|
"loss": 5.9204,
|
||
|
|
"mean_token_accuracy": 0.16258904635906218,
|
||
|
|
"num_tokens": 6516808.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8536591053009035,
|
||
|
|
"epoch": 0.3285224911551637,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004994698114257071,
|
||
|
|
"loss": 5.8889,
|
||
|
|
"mean_token_accuracy": 0.15758193880319596,
|
||
|
|
"num_tokens": 6529184.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.807791328430175,
|
||
|
|
"epoch": 0.32908406806312124,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004994670532769944,
|
||
|
|
"loss": 5.714,
|
||
|
|
"mean_token_accuracy": 0.17135922312736512,
|
||
|
|
"num_tokens": 6539909.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.777865743637085,
|
||
|
|
"epoch": 0.3296456449710788,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004994642879811637,
|
||
|
|
"loss": 5.7794,
|
||
|
|
"mean_token_accuracy": 0.16615391075611113,
|
||
|
|
"num_tokens": 6550870.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.783542823791504,
|
||
|
|
"epoch": 0.33020722187903634,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499461515538303,
|
||
|
|
"loss": 5.8383,
|
||
|
|
"mean_token_accuracy": 0.1643565073609352,
|
||
|
|
"num_tokens": 6561784.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.812904691696167,
|
||
|
|
"epoch": 0.3307687987869939,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004994587359485006,
|
||
|
|
"loss": 5.7965,
|
||
|
|
"mean_token_accuracy": 0.16411405503749849,
|
||
|
|
"num_tokens": 6573422.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.899852323532104,
|
||
|
|
"epoch": 0.33133037569495144,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000499455949211845,
|
||
|
|
"loss": 5.8645,
|
||
|
|
"mean_token_accuracy": 0.16602167785167693,
|
||
|
|
"num_tokens": 6584565.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.879082441329956,
|
||
|
|
"epoch": 0.331891952602909,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004994531553284248,
|
||
|
|
"loss": 5.7735,
|
||
|
|
"mean_token_accuracy": 0.16534640789031982,
|
||
|
|
"num_tokens": 6594238.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.761241102218628,
|
||
|
|
"epoch": 0.3324535295108665,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004994503542983293,
|
||
|
|
"loss": 5.8393,
|
||
|
|
"mean_token_accuracy": 0.15874847620725632,
|
||
|
|
"num_tokens": 6606309.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942394256591797,
|
||
|
|
"epoch": 0.33301510641882404,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004994475461216472,
|
||
|
|
"loss": 5.9289,
|
||
|
|
"mean_token_accuracy": 0.15209423899650573,
|
||
|
|
"num_tokens": 6617916.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.823106193542481,
|
||
|
|
"epoch": 0.3335766833267816,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004994447307984684,
|
||
|
|
"loss": 5.7864,
|
||
|
|
"mean_token_accuracy": 0.1635408341884613,
|
||
|
|
"num_tokens": 6627951.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.82645468711853,
|
||
|
|
"epoch": 0.33413826023473914,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004994419083288823,
|
||
|
|
"loss": 5.8445,
|
||
|
|
"mean_token_accuracy": 0.16017935127019883,
|
||
|
|
"num_tokens": 6639285.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8130076885223385,
|
||
|
|
"epoch": 0.3346998371426967,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004994390787129787,
|
||
|
|
"loss": 5.7106,
|
||
|
|
"mean_token_accuracy": 0.16786744594573974,
|
||
|
|
"num_tokens": 6649973.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.691775798797607,
|
||
|
|
"epoch": 0.33526141405065424,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004994362419508478,
|
||
|
|
"loss": 5.7358,
|
||
|
|
"mean_token_accuracy": 0.16457985043525697,
|
||
|
|
"num_tokens": 6660625.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848007583618164,
|
||
|
|
"epoch": 0.3358229909586118,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00049943339804258,
|
||
|
|
"loss": 5.8188,
|
||
|
|
"mean_token_accuracy": 0.15529035329818724,
|
||
|
|
"num_tokens": 6673191.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920690488815308,
|
||
|
|
"epoch": 0.33638456786656934,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004994305469882657,
|
||
|
|
"loss": 5.8128,
|
||
|
|
"mean_token_accuracy": 0.16549630016088485,
|
||
|
|
"num_tokens": 6683993.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.748003721237183,
|
||
|
|
"epoch": 0.3369461447745269,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004994276887879957,
|
||
|
|
"loss": 5.8422,
|
||
|
|
"mean_token_accuracy": 0.16537389457225798,
|
||
|
|
"num_tokens": 6694881.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3369461447745269,
|
||
|
|
"eval_entropy": 5.695829511641964,
|
||
|
|
"eval_loss": 5.859601020812988,
|
||
|
|
"eval_mean_token_accuracy": 0.16699215644086057,
|
||
|
|
"eval_num_tokens": 6694881.0,
|
||
|
|
"eval_runtime": 23.9604,
|
||
|
|
"eval_samples_per_second": 1294.343,
|
||
|
|
"eval_steps_per_second": 161.809,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 89030,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 3000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1.0448431460352e+16,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|