6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.742382335662843,
|
||
|
|
"epoch": 0.00038902937171756465,
|
||
|
|
"grad_norm": 4.78125,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.7699,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 9243.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742357444763183,
|
||
|
|
"epoch": 0.0007780587434351293,
|
||
|
|
"grad_norm": 5.03125,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7654,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 18424.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74235429763794,
|
||
|
|
"epoch": 0.001167088115152694,
|
||
|
|
"grad_norm": 5.03125,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.729,
|
||
|
|
"mean_token_accuracy": 0.00010964912362396718,
|
||
|
|
"num_tokens": 27006.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742323112487792,
|
||
|
|
"epoch": 0.0015561174868702586,
|
||
|
|
"grad_norm": 4.65625,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.68,
|
||
|
|
"mean_token_accuracy": 0.00010695187374949455,
|
||
|
|
"num_tokens": 35577.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742191219329834,
|
||
|
|
"epoch": 0.0019451468585878235,
|
||
|
|
"grad_norm": 4.46875,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.5624,
|
||
|
|
"mean_token_accuracy": 0.001254092820454389,
|
||
|
|
"num_tokens": 43706.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.741874980926514,
|
||
|
|
"epoch": 0.002334176230305388,
|
||
|
|
"grad_norm": 4.25,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.4785,
|
||
|
|
"mean_token_accuracy": 0.01906490430701524,
|
||
|
|
"num_tokens": 52571.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.741138744354249,
|
||
|
|
"epoch": 0.0027232056020229526,
|
||
|
|
"grad_norm": 3.296875,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.3631,
|
||
|
|
"mean_token_accuracy": 0.04432072527706623,
|
||
|
|
"num_tokens": 61900.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.739378833770752,
|
||
|
|
"epoch": 0.0031122349737405172,
|
||
|
|
"grad_norm": 2.796875,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.2522,
|
||
|
|
"mean_token_accuracy": 0.043363864347338674,
|
||
|
|
"num_tokens": 71234.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.736563587188721,
|
||
|
|
"epoch": 0.003501264345458082,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.1123,
|
||
|
|
"mean_token_accuracy": 0.04502938166260719,
|
||
|
|
"num_tokens": 79610.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.733458709716796,
|
||
|
|
"epoch": 0.003890293717175647,
|
||
|
|
"grad_norm": 2.25,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 10.0005,
|
||
|
|
"mean_token_accuracy": 0.04512783698737621,
|
||
|
|
"num_tokens": 87527.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.731391525268554,
|
||
|
|
"epoch": 0.004279323088893211,
|
||
|
|
"grad_norm": 2.125,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.9758,
|
||
|
|
"mean_token_accuracy": 0.044215765222907065,
|
||
|
|
"num_tokens": 95512.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.728329372406005,
|
||
|
|
"epoch": 0.004668352460610776,
|
||
|
|
"grad_norm": 2.0,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.9107,
|
||
|
|
"mean_token_accuracy": 0.04661451056599617,
|
||
|
|
"num_tokens": 104395.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.723896598815918,
|
||
|
|
"epoch": 0.0050573818323283405,
|
||
|
|
"grad_norm": 2.03125,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.8199,
|
||
|
|
"mean_token_accuracy": 0.049337920546531674,
|
||
|
|
"num_tokens": 112562.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.719001293182373,
|
||
|
|
"epoch": 0.005446411204045905,
|
||
|
|
"grad_norm": 2.03125,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.7691,
|
||
|
|
"mean_token_accuracy": 0.04639301113784313,
|
||
|
|
"num_tokens": 121962.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.715445232391357,
|
||
|
|
"epoch": 0.00583544057576347,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.7611,
|
||
|
|
"mean_token_accuracy": 0.04579820521175861,
|
||
|
|
"num_tokens": 130714.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.711173343658448,
|
||
|
|
"epoch": 0.0062244699474810344,
|
||
|
|
"grad_norm": 1.8046875,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.665,
|
||
|
|
"mean_token_accuracy": 0.0456673588603735,
|
||
|
|
"num_tokens": 139674.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.70630578994751,
|
||
|
|
"epoch": 0.006613499319198599,
|
||
|
|
"grad_norm": 1.9453125,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.5765,
|
||
|
|
"mean_token_accuracy": 0.04949404634535313,
|
||
|
|
"num_tokens": 148654.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.698366928100587,
|
||
|
|
"epoch": 0.007002528690916164,
|
||
|
|
"grad_norm": 2.0,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.435,
|
||
|
|
"mean_token_accuracy": 0.05969774164259434,
|
||
|
|
"num_tokens": 156180.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.684116172790528,
|
||
|
|
"epoch": 0.007391558062633729,
|
||
|
|
"grad_norm": 1.875,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.4372,
|
||
|
|
"mean_token_accuracy": 0.06196932159364223,
|
||
|
|
"num_tokens": 165608.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.664545917510987,
|
||
|
|
"epoch": 0.007780587434351294,
|
||
|
|
"grad_norm": 1.8984375,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.3091,
|
||
|
|
"mean_token_accuracy": 0.06599215753376483,
|
||
|
|
"num_tokens": 173871.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.63426914215088,
|
||
|
|
"epoch": 0.008169616806068859,
|
||
|
|
"grad_norm": 1.796875,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.2262,
|
||
|
|
"mean_token_accuracy": 0.06208839267492294,
|
||
|
|
"num_tokens": 182356.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.588347434997559,
|
||
|
|
"epoch": 0.008558646177786422,
|
||
|
|
"grad_norm": 1.6484375,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.1345,
|
||
|
|
"mean_token_accuracy": 0.06493466645479203,
|
||
|
|
"num_tokens": 190361.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.534650707244873,
|
||
|
|
"epoch": 0.008947675549503988,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 9.0175,
|
||
|
|
"mean_token_accuracy": 0.06511155813932419,
|
||
|
|
"num_tokens": 199253.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.498821544647218,
|
||
|
|
"epoch": 0.009336704921221552,
|
||
|
|
"grad_norm": 1.75,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.9191,
|
||
|
|
"mean_token_accuracy": 0.06383187472820281,
|
||
|
|
"num_tokens": 208181.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.446215152740479,
|
||
|
|
"epoch": 0.009725734292939117,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.7921,
|
||
|
|
"mean_token_accuracy": 0.06596225276589393,
|
||
|
|
"num_tokens": 216898.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.361998558044434,
|
||
|
|
"epoch": 0.010114763664656681,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.6872,
|
||
|
|
"mean_token_accuracy": 0.06298739649355412,
|
||
|
|
"num_tokens": 226051.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.26733865737915,
|
||
|
|
"epoch": 0.010503793036374246,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.5991,
|
||
|
|
"mean_token_accuracy": 0.06326549835503101,
|
||
|
|
"num_tokens": 235018.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.166206169128419,
|
||
|
|
"epoch": 0.01089282240809181,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.4509,
|
||
|
|
"mean_token_accuracy": 0.06088712736964226,
|
||
|
|
"num_tokens": 244268.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.03088960647583,
|
||
|
|
"epoch": 0.011281851779809376,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.3425,
|
||
|
|
"mean_token_accuracy": 0.06427538841962814,
|
||
|
|
"num_tokens": 253545.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.861793708801269,
|
||
|
|
"epoch": 0.01167088115152694,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.1413,
|
||
|
|
"mean_token_accuracy": 0.07204292267560959,
|
||
|
|
"num_tokens": 261767.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.695942211151124,
|
||
|
|
"epoch": 0.012059910523244505,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.1018,
|
||
|
|
"mean_token_accuracy": 0.06669669337570668,
|
||
|
|
"num_tokens": 270372.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.514180374145507,
|
||
|
|
"epoch": 0.012448939894962069,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.0639,
|
||
|
|
"mean_token_accuracy": 0.06147677525877952,
|
||
|
|
"num_tokens": 279726.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.323209476470947,
|
||
|
|
"epoch": 0.012837969266679634,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.9873,
|
||
|
|
"mean_token_accuracy": 0.06152131669223308,
|
||
|
|
"num_tokens": 288955.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.155291080474854,
|
||
|
|
"epoch": 0.013226998638397198,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.8671,
|
||
|
|
"mean_token_accuracy": 0.06018271669745445,
|
||
|
|
"num_tokens": 297898.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.913286781311035,
|
||
|
|
"epoch": 0.013616028010114764,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.7877,
|
||
|
|
"mean_token_accuracy": 0.06726240292191506,
|
||
|
|
"num_tokens": 306189.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.70859899520874,
|
||
|
|
"epoch": 0.014005057381832327,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.7347,
|
||
|
|
"mean_token_accuracy": 0.06567795276641845,
|
||
|
|
"num_tokens": 314881.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.591675281524658,
|
||
|
|
"epoch": 0.014394086753549893,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.7148,
|
||
|
|
"mean_token_accuracy": 0.0621601328253746,
|
||
|
|
"num_tokens": 323357.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.47695083618164,
|
||
|
|
"epoch": 0.014783116125267459,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.7356,
|
||
|
|
"mean_token_accuracy": 0.06571447476744652,
|
||
|
|
"num_tokens": 331799.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.370344352722167,
|
||
|
|
"epoch": 0.015172145496985022,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.6118,
|
||
|
|
"mean_token_accuracy": 0.06905685365200043,
|
||
|
|
"num_tokens": 340320.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.324654674530029,
|
||
|
|
"epoch": 0.015561174868702588,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.6178,
|
||
|
|
"mean_token_accuracy": 0.06449079662561416,
|
||
|
|
"num_tokens": 348990.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.174854373931884,
|
||
|
|
"epoch": 0.01595020424042015,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.5827,
|
||
|
|
"mean_token_accuracy": 0.06486652344465256,
|
||
|
|
"num_tokens": 357661.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.168173027038574,
|
||
|
|
"epoch": 0.016339233612137717,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.5391,
|
||
|
|
"mean_token_accuracy": 0.07107783854007721,
|
||
|
|
"num_tokens": 366099.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.15952262878418,
|
||
|
|
"epoch": 0.016728262983855283,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.677,
|
||
|
|
"mean_token_accuracy": 0.06535900048911572,
|
||
|
|
"num_tokens": 374926.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.183490467071532,
|
||
|
|
"epoch": 0.017117292355572845,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.5935,
|
||
|
|
"mean_token_accuracy": 0.06671289913356304,
|
||
|
|
"num_tokens": 383846.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.149136352539063,
|
||
|
|
"epoch": 0.01750632172729041,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.5526,
|
||
|
|
"mean_token_accuracy": 0.07337053082883357,
|
||
|
|
"num_tokens": 393678.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.142791080474854,
|
||
|
|
"epoch": 0.017895351099007976,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.5805,
|
||
|
|
"mean_token_accuracy": 0.07247933149337768,
|
||
|
|
"num_tokens": 401866.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.138428115844727,
|
||
|
|
"epoch": 0.01828438047072554,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.5559,
|
||
|
|
"mean_token_accuracy": 0.07213828079402447,
|
||
|
|
"num_tokens": 411057.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.083276653289795,
|
||
|
|
"epoch": 0.018673409842443103,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.5199,
|
||
|
|
"mean_token_accuracy": 0.07377653121948242,
|
||
|
|
"num_tokens": 419083.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.081015300750732,
|
||
|
|
"epoch": 0.01906243921416067,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.423,
|
||
|
|
"mean_token_accuracy": 0.07348247244954109,
|
||
|
|
"num_tokens": 427503.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.99849009513855,
|
||
|
|
"epoch": 0.019451468585878234,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.5381,
|
||
|
|
"mean_token_accuracy": 0.07209133058786392,
|
||
|
|
"num_tokens": 435820.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.958733320236206,
|
||
|
|
"epoch": 0.0198404979575958,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.3981,
|
||
|
|
"mean_token_accuracy": 0.07939725071191787,
|
||
|
|
"num_tokens": 444692.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.023887872695923,
|
||
|
|
"epoch": 0.020229527329313362,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.4495,
|
||
|
|
"mean_token_accuracy": 0.07057543247938156,
|
||
|
|
"num_tokens": 453536.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.02216215133667,
|
||
|
|
"epoch": 0.020618556701030927,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.4635,
|
||
|
|
"mean_token_accuracy": 0.07652526497840881,
|
||
|
|
"num_tokens": 462264.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.021293640136719,
|
||
|
|
"epoch": 0.021007586072748493,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.5942,
|
||
|
|
"mean_token_accuracy": 0.07328042685985565,
|
||
|
|
"num_tokens": 471819.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.957899475097657,
|
||
|
|
"epoch": 0.02139661544446606,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.4982,
|
||
|
|
"mean_token_accuracy": 0.0714272040873766,
|
||
|
|
"num_tokens": 480878.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.055506563186645,
|
||
|
|
"epoch": 0.02178564481618362,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.4444,
|
||
|
|
"mean_token_accuracy": 0.08031182736158371,
|
||
|
|
"num_tokens": 489454.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.901804733276367,
|
||
|
|
"epoch": 0.022174674187901186,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.3353,
|
||
|
|
"mean_token_accuracy": 0.07537753507494926,
|
||
|
|
"num_tokens": 498378.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9674581527709964,
|
||
|
|
"epoch": 0.02256370355961875,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.558,
|
||
|
|
"mean_token_accuracy": 0.07206817306578159,
|
||
|
|
"num_tokens": 507638.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.018344259262085,
|
||
|
|
"epoch": 0.022952732931336317,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.4655,
|
||
|
|
"mean_token_accuracy": 0.08074412941932678,
|
||
|
|
"num_tokens": 517047.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.928561210632324,
|
||
|
|
"epoch": 0.02334176230305388,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.3931,
|
||
|
|
"mean_token_accuracy": 0.07988100573420524,
|
||
|
|
"num_tokens": 525287.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.889331293106079,
|
||
|
|
"epoch": 0.023730791674771445,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.3272,
|
||
|
|
"mean_token_accuracy": 0.07765846103429794,
|
||
|
|
"num_tokens": 533266.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.938522481918335,
|
||
|
|
"epoch": 0.02411982104648901,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.4553,
|
||
|
|
"mean_token_accuracy": 0.07832531034946441,
|
||
|
|
"num_tokens": 542448.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.876863288879394,
|
||
|
|
"epoch": 0.024508850418206576,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.3373,
|
||
|
|
"mean_token_accuracy": 0.07851743251085282,
|
||
|
|
"num_tokens": 550872.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.92165994644165,
|
||
|
|
"epoch": 0.024897879789924138,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.3913,
|
||
|
|
"mean_token_accuracy": 0.08598420470952987,
|
||
|
|
"num_tokens": 559616.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.843034791946411,
|
||
|
|
"epoch": 0.025286909161641703,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.3644,
|
||
|
|
"mean_token_accuracy": 0.0826579324901104,
|
||
|
|
"num_tokens": 568379.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.829864072799682,
|
||
|
|
"epoch": 0.02567593853335927,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.3671,
|
||
|
|
"mean_token_accuracy": 0.08075782656669617,
|
||
|
|
"num_tokens": 577288.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.871328210830688,
|
||
|
|
"epoch": 0.026064967905076834,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.3243,
|
||
|
|
"mean_token_accuracy": 0.08058057203888894,
|
||
|
|
"num_tokens": 587054.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.879428195953369,
|
||
|
|
"epoch": 0.026453997276794396,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.443,
|
||
|
|
"mean_token_accuracy": 0.0813908450305462,
|
||
|
|
"num_tokens": 595405.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.87817964553833,
|
||
|
|
"epoch": 0.026843026648511962,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.3017,
|
||
|
|
"mean_token_accuracy": 0.0837264135479927,
|
||
|
|
"num_tokens": 604095.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7519464015960695,
|
||
|
|
"epoch": 0.027232056020229527,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.3331,
|
||
|
|
"mean_token_accuracy": 0.08179512321949005,
|
||
|
|
"num_tokens": 613518.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8531310081481935,
|
||
|
|
"epoch": 0.027621085391947093,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.1945,
|
||
|
|
"mean_token_accuracy": 0.08306437954306603,
|
||
|
|
"num_tokens": 621212.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.758134984970093,
|
||
|
|
"epoch": 0.028010114763664655,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.2697,
|
||
|
|
"mean_token_accuracy": 0.08436251506209373,
|
||
|
|
"num_tokens": 629326.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.758914995193481,
|
||
|
|
"epoch": 0.02839914413538222,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.2792,
|
||
|
|
"mean_token_accuracy": 0.08306139633059502,
|
||
|
|
"num_tokens": 637034.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.723426389694214,
|
||
|
|
"epoch": 0.028788173507099786,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.1741,
|
||
|
|
"mean_token_accuracy": 0.08840271160006523,
|
||
|
|
"num_tokens": 645924.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.825829219818115,
|
||
|
|
"epoch": 0.02917720287881735,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.3813,
|
||
|
|
"mean_token_accuracy": 0.08644352033734322,
|
||
|
|
"num_tokens": 655020.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.784128332138062,
|
||
|
|
"epoch": 0.029566232250534917,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.2057,
|
||
|
|
"mean_token_accuracy": 0.08727380409836769,
|
||
|
|
"num_tokens": 663451.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.727108144760132,
|
||
|
|
"epoch": 0.02995526162225248,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.2834,
|
||
|
|
"mean_token_accuracy": 0.08695143982768058,
|
||
|
|
"num_tokens": 671973.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.712132835388184,
|
||
|
|
"epoch": 0.030344290993970045,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.1734,
|
||
|
|
"mean_token_accuracy": 0.08923292458057404,
|
||
|
|
"num_tokens": 680583.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.674439716339111,
|
||
|
|
"epoch": 0.03073332036568761,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.1871,
|
||
|
|
"mean_token_accuracy": 0.0865532897412777,
|
||
|
|
"num_tokens": 689000.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.765862512588501,
|
||
|
|
"epoch": 0.031122349737405176,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.1741,
|
||
|
|
"mean_token_accuracy": 0.08593220934271813,
|
||
|
|
"num_tokens": 698047.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.731269979476929,
|
||
|
|
"epoch": 0.03151137910912274,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.2962,
|
||
|
|
"mean_token_accuracy": 0.08466848209500313,
|
||
|
|
"num_tokens": 707192.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.695866537094116,
|
||
|
|
"epoch": 0.0319004084808403,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.1133,
|
||
|
|
"mean_token_accuracy": 0.09290924519300461,
|
||
|
|
"num_tokens": 715895.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.683174657821655,
|
||
|
|
"epoch": 0.03228943785255787,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.1955,
|
||
|
|
"mean_token_accuracy": 0.08894984126091003,
|
||
|
|
"num_tokens": 724891.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.715670108795166,
|
||
|
|
"epoch": 0.032678467224275434,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.2305,
|
||
|
|
"mean_token_accuracy": 0.08583205491304398,
|
||
|
|
"num_tokens": 733378.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.689523315429687,
|
||
|
|
"epoch": 0.033067496595993,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.2038,
|
||
|
|
"mean_token_accuracy": 0.08817718252539634,
|
||
|
|
"num_tokens": 741098.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.737551879882813,
|
||
|
|
"epoch": 0.033456525967710565,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.1523,
|
||
|
|
"mean_token_accuracy": 0.08939553946256637,
|
||
|
|
"num_tokens": 749902.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.571504878997803,
|
||
|
|
"epoch": 0.033845555339428124,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.1379,
|
||
|
|
"mean_token_accuracy": 0.09236362501978874,
|
||
|
|
"num_tokens": 758638.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.696662092208863,
|
||
|
|
"epoch": 0.03423458471114569,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 7.2068,
|
||
|
|
"mean_token_accuracy": 0.0883943185210228,
|
||
|
|
"num_tokens": 768170.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6304443836212155,
|
||
|
|
"epoch": 0.034623614082863255,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.0936,
|
||
|
|
"mean_token_accuracy": 0.09277842119336129,
|
||
|
|
"num_tokens": 776745.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6743035316467285,
|
||
|
|
"epoch": 0.03501264345458082,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.2093,
|
||
|
|
"mean_token_accuracy": 0.0887695960700512,
|
||
|
|
"num_tokens": 785030.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6144163608551025,
|
||
|
|
"epoch": 0.035401672826298386,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.171,
|
||
|
|
"mean_token_accuracy": 0.08834633827209473,
|
||
|
|
"num_tokens": 793543.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.52853422164917,
|
||
|
|
"epoch": 0.03579070219801595,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.0163,
|
||
|
|
"mean_token_accuracy": 0.09290485829114914,
|
||
|
|
"num_tokens": 802401.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.607344436645508,
|
||
|
|
"epoch": 0.03617973156973352,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.1277,
|
||
|
|
"mean_token_accuracy": 0.08786619827151299,
|
||
|
|
"num_tokens": 811625.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.560419654846191,
|
||
|
|
"epoch": 0.03656876094145108,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.0702,
|
||
|
|
"mean_token_accuracy": 0.0898631051182747,
|
||
|
|
"num_tokens": 820742.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.608465671539307,
|
||
|
|
"epoch": 0.03695779031316864,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.1654,
|
||
|
|
"mean_token_accuracy": 0.08933878615498543,
|
||
|
|
"num_tokens": 829580.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.560161828994751,
|
||
|
|
"epoch": 0.03734681968488621,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.0934,
|
||
|
|
"mean_token_accuracy": 0.09360112398862838,
|
||
|
|
"num_tokens": 838818.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.639765310287475,
|
||
|
|
"epoch": 0.03773584905660377,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 7.1163,
|
||
|
|
"mean_token_accuracy": 0.08306419998407363,
|
||
|
|
"num_tokens": 847804.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4112790584564205,
|
||
|
|
"epoch": 0.03812487842832134,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.8803,
|
||
|
|
"mean_token_accuracy": 0.10076504200696945,
|
||
|
|
"num_tokens": 856395.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.583081674575806,
|
||
|
|
"epoch": 0.0385139078000389,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 7.1207,
|
||
|
|
"mean_token_accuracy": 0.09502710178494453,
|
||
|
|
"num_tokens": 865219.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.43314561843872,
|
||
|
|
"epoch": 0.03890293717175647,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.9119,
|
||
|
|
"mean_token_accuracy": 0.09718281924724578,
|
||
|
|
"num_tokens": 873868.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.498023557662964,
|
||
|
|
"epoch": 0.039291966543474034,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.0232,
|
||
|
|
"mean_token_accuracy": 0.09345900416374206,
|
||
|
|
"num_tokens": 882698.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.469527721405029,
|
||
|
|
"epoch": 0.0396809959151916,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.9475,
|
||
|
|
"mean_token_accuracy": 0.0993176445364952,
|
||
|
|
"num_tokens": 891280.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.47659912109375,
|
||
|
|
"epoch": 0.04007002528690916,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.0011,
|
||
|
|
"mean_token_accuracy": 0.09124450460076332,
|
||
|
|
"num_tokens": 900044.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.436534833908081,
|
||
|
|
"epoch": 0.040459054658626724,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.9727,
|
||
|
|
"mean_token_accuracy": 0.0896801546216011,
|
||
|
|
"num_tokens": 909297.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.425080251693726,
|
||
|
|
"epoch": 0.04084808403034429,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.9447,
|
||
|
|
"mean_token_accuracy": 0.0947676196694374,
|
||
|
|
"num_tokens": 917514.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.387802982330323,
|
||
|
|
"epoch": 0.041237113402061855,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.9388,
|
||
|
|
"mean_token_accuracy": 0.09883696585893631,
|
||
|
|
"num_tokens": 925842.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.389920854568482,
|
||
|
|
"epoch": 0.04162614277377942,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 7.0398,
|
||
|
|
"mean_token_accuracy": 0.09228231534361839,
|
||
|
|
"num_tokens": 934676.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4626116275787355,
|
||
|
|
"epoch": 0.042015172145496986,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.9525,
|
||
|
|
"mean_token_accuracy": 0.09330017715692521,
|
||
|
|
"num_tokens": 943763.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.356891870498657,
|
||
|
|
"epoch": 0.04240420151721455,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.9442,
|
||
|
|
"mean_token_accuracy": 0.09821118861436844,
|
||
|
|
"num_tokens": 952721.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.440818834304809,
|
||
|
|
"epoch": 0.04279323088893212,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.9443,
|
||
|
|
"mean_token_accuracy": 0.10198782086372375,
|
||
|
|
"num_tokens": 960899.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.310132646560669,
|
||
|
|
"epoch": 0.04318226026064968,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.9242,
|
||
|
|
"mean_token_accuracy": 0.09831049591302872,
|
||
|
|
"num_tokens": 969362.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.41514139175415,
|
||
|
|
"epoch": 0.04357128963236724,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.9077,
|
||
|
|
"mean_token_accuracy": 0.10258749797940254,
|
||
|
|
"num_tokens": 978028.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3455198287963865,
|
||
|
|
"epoch": 0.04396031900408481,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.8935,
|
||
|
|
"mean_token_accuracy": 0.10291868522763252,
|
||
|
|
"num_tokens": 985709.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.418910646438599,
|
||
|
|
"epoch": 0.04434934837580237,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.976,
|
||
|
|
"mean_token_accuracy": 0.10187083706259728,
|
||
|
|
"num_tokens": 994769.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.401043939590454,
|
||
|
|
"epoch": 0.04473837774751994,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.962,
|
||
|
|
"mean_token_accuracy": 0.10199706852436066,
|
||
|
|
"num_tokens": 1003997.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.399074697494507,
|
||
|
|
"epoch": 0.0451274071192375,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.9466,
|
||
|
|
"mean_token_accuracy": 0.09917582347989082,
|
||
|
|
"num_tokens": 1012931.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.332787704467774,
|
||
|
|
"epoch": 0.04551643649095507,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.9555,
|
||
|
|
"mean_token_accuracy": 0.10086694583296776,
|
||
|
|
"num_tokens": 1021149.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.499734544754029,
|
||
|
|
"epoch": 0.045905465862672634,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.9548,
|
||
|
|
"mean_token_accuracy": 0.10112444758415222,
|
||
|
|
"num_tokens": 1029421.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.391014766693115,
|
||
|
|
"epoch": 0.0462944952343902,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 7.0459,
|
||
|
|
"mean_token_accuracy": 0.09981294050812721,
|
||
|
|
"num_tokens": 1037222.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.352716112136841,
|
||
|
|
"epoch": 0.04668352460610776,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.9734,
|
||
|
|
"mean_token_accuracy": 0.09807954430580139,
|
||
|
|
"num_tokens": 1046903.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.385373210906982,
|
||
|
|
"epoch": 0.047072553977825324,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 7.0123,
|
||
|
|
"mean_token_accuracy": 0.09519420191645622,
|
||
|
|
"num_tokens": 1055516.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.407522106170655,
|
||
|
|
"epoch": 0.04746158334954289,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.9265,
|
||
|
|
"mean_token_accuracy": 0.09930946677923203,
|
||
|
|
"num_tokens": 1063846.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.281380128860474,
|
||
|
|
"epoch": 0.047850612721260455,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.8993,
|
||
|
|
"mean_token_accuracy": 0.09943632334470749,
|
||
|
|
"num_tokens": 1072500.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.34805383682251,
|
||
|
|
"epoch": 0.04823964209297802,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.922,
|
||
|
|
"mean_token_accuracy": 0.09708855003118515,
|
||
|
|
"num_tokens": 1081399.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2534126281738285,
|
||
|
|
"epoch": 0.048628671464695586,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.8743,
|
||
|
|
"mean_token_accuracy": 0.1036634124815464,
|
||
|
|
"num_tokens": 1089666.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.336611223220825,
|
||
|
|
"epoch": 0.04901770083641315,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.7632,
|
||
|
|
"mean_token_accuracy": 0.10756223425269126,
|
||
|
|
"num_tokens": 1097496.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.240615320205689,
|
||
|
|
"epoch": 0.04940673020813072,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.8822,
|
||
|
|
"mean_token_accuracy": 0.10434303507208824,
|
||
|
|
"num_tokens": 1105840.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.313789176940918,
|
||
|
|
"epoch": 0.049795759579848276,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.9515,
|
||
|
|
"mean_token_accuracy": 0.0976039707660675,
|
||
|
|
"num_tokens": 1115507.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.261141300201416,
|
||
|
|
"epoch": 0.05018478895156584,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.8997,
|
||
|
|
"mean_token_accuracy": 0.09827139601111412,
|
||
|
|
"num_tokens": 1124820.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.230596017837525,
|
||
|
|
"epoch": 0.05057381832328341,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.7406,
|
||
|
|
"mean_token_accuracy": 0.10685393288731575,
|
||
|
|
"num_tokens": 1133641.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.177046489715576,
|
||
|
|
"epoch": 0.05096284769500097,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.792,
|
||
|
|
"mean_token_accuracy": 0.10451765954494477,
|
||
|
|
"num_tokens": 1142182.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.294152784347534,
|
||
|
|
"epoch": 0.05135187706671854,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.8672,
|
||
|
|
"mean_token_accuracy": 0.10539027452468872,
|
||
|
|
"num_tokens": 1150737.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.172728967666626,
|
||
|
|
"epoch": 0.0517409064384361,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.7309,
|
||
|
|
"mean_token_accuracy": 0.10050051435828208,
|
||
|
|
"num_tokens": 1158899.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.331276702880859,
|
||
|
|
"epoch": 0.05212993581015367,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.819,
|
||
|
|
"mean_token_accuracy": 0.10705862119793892,
|
||
|
|
"num_tokens": 1167397.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.248978996276856,
|
||
|
|
"epoch": 0.052518965181871234,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.8332,
|
||
|
|
"mean_token_accuracy": 0.10063659623265267,
|
||
|
|
"num_tokens": 1177044.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.085381174087525,
|
||
|
|
"epoch": 0.05290799455358879,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.693,
|
||
|
|
"mean_token_accuracy": 0.10786959677934646,
|
||
|
|
"num_tokens": 1185740.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.203679895401001,
|
||
|
|
"epoch": 0.05329702392530636,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.8372,
|
||
|
|
"mean_token_accuracy": 0.10230442136526108,
|
||
|
|
"num_tokens": 1194970.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.245568037033081,
|
||
|
|
"epoch": 0.053686053297023924,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.7921,
|
||
|
|
"mean_token_accuracy": 0.10874027833342552,
|
||
|
|
"num_tokens": 1203565.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.196403169631958,
|
||
|
|
"epoch": 0.05407508266874149,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.8265,
|
||
|
|
"mean_token_accuracy": 0.10126563459634781,
|
||
|
|
"num_tokens": 1213226.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.09236512184143,
|
||
|
|
"epoch": 0.054464112040459055,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.7432,
|
||
|
|
"mean_token_accuracy": 0.1003255195915699,
|
||
|
|
"num_tokens": 1221710.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216377449035645,
|
||
|
|
"epoch": 0.05485314141217662,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.8035,
|
||
|
|
"mean_token_accuracy": 0.09862821027636529,
|
||
|
|
"num_tokens": 1231125.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.237710189819336,
|
||
|
|
"epoch": 0.055242170783894186,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.7667,
|
||
|
|
"mean_token_accuracy": 0.10697240307927132,
|
||
|
|
"num_tokens": 1239521.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.097472429275513,
|
||
|
|
"epoch": 0.05563120015561175,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.6474,
|
||
|
|
"mean_token_accuracy": 0.11173419132828713,
|
||
|
|
"num_tokens": 1247363.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1145548820495605,
|
||
|
|
"epoch": 0.05602022952732931,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.7447,
|
||
|
|
"mean_token_accuracy": 0.10396054536104202,
|
||
|
|
"num_tokens": 1255395.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2065142631530765,
|
||
|
|
"epoch": 0.056409258899046875,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.813,
|
||
|
|
"mean_token_accuracy": 0.10091793909668922,
|
||
|
|
"num_tokens": 1264135.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.164863967895508,
|
||
|
|
"epoch": 0.05679828827076444,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.7421,
|
||
|
|
"mean_token_accuracy": 0.10169361084699631,
|
||
|
|
"num_tokens": 1272375.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1601451396942135,
|
||
|
|
"epoch": 0.057187317642482006,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.7901,
|
||
|
|
"mean_token_accuracy": 0.10103225708007812,
|
||
|
|
"num_tokens": 1280960.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.184061765670776,
|
||
|
|
"epoch": 0.05757634701419957,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.8209,
|
||
|
|
"mean_token_accuracy": 0.10675038620829583,
|
||
|
|
"num_tokens": 1289273.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.113188409805298,
|
||
|
|
"epoch": 0.05796537638591714,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.7247,
|
||
|
|
"mean_token_accuracy": 0.10347931683063508,
|
||
|
|
"num_tokens": 1297571.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.19926347732544,
|
||
|
|
"epoch": 0.0583544057576347,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.7715,
|
||
|
|
"mean_token_accuracy": 0.10671985670924186,
|
||
|
|
"num_tokens": 1305686.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.111810922622681,
|
||
|
|
"epoch": 0.05874343512935227,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.7894,
|
||
|
|
"mean_token_accuracy": 0.1026329904794693,
|
||
|
|
"num_tokens": 1314483.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.088590431213379,
|
||
|
|
"epoch": 0.059132464501069834,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.6599,
|
||
|
|
"mean_token_accuracy": 0.10411886721849442,
|
||
|
|
"num_tokens": 1323183.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.122695350646973,
|
||
|
|
"epoch": 0.05952149387278739,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.7836,
|
||
|
|
"mean_token_accuracy": 0.10542866066098214,
|
||
|
|
"num_tokens": 1331964.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.062607765197754,
|
||
|
|
"epoch": 0.05991052324450496,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.7312,
|
||
|
|
"mean_token_accuracy": 0.11025277003645897,
|
||
|
|
"num_tokens": 1340185.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.220061302185059,
|
||
|
|
"epoch": 0.060299552616222524,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.806,
|
||
|
|
"mean_token_accuracy": 0.10550950691103936,
|
||
|
|
"num_tokens": 1349522.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.170696592330932,
|
||
|
|
"epoch": 0.06068858198794009,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.7858,
|
||
|
|
"mean_token_accuracy": 0.10444560423493385,
|
||
|
|
"num_tokens": 1357893.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.994049072265625,
|
||
|
|
"epoch": 0.061077611359657655,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.6669,
|
||
|
|
"mean_token_accuracy": 0.1103596955537796,
|
||
|
|
"num_tokens": 1366685.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.130297327041626,
|
||
|
|
"epoch": 0.06146664073137522,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.6085,
|
||
|
|
"mean_token_accuracy": 0.10908645838499069,
|
||
|
|
"num_tokens": 1375245.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.040684175491333,
|
||
|
|
"epoch": 0.061855670103092786,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.7932,
|
||
|
|
"mean_token_accuracy": 0.10705054327845573,
|
||
|
|
"num_tokens": 1383724.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.209282732009887,
|
||
|
|
"epoch": 0.06224469947481035,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.7782,
|
||
|
|
"mean_token_accuracy": 0.10306280329823495,
|
||
|
|
"num_tokens": 1392455.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1856764793396,
|
||
|
|
"epoch": 0.06263372884652792,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.7794,
|
||
|
|
"mean_token_accuracy": 0.10756833851337433,
|
||
|
|
"num_tokens": 1401262.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.964628410339356,
|
||
|
|
"epoch": 0.06302275821824548,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.6675,
|
||
|
|
"mean_token_accuracy": 0.1083975151181221,
|
||
|
|
"num_tokens": 1409991.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.013374662399292,
|
||
|
|
"epoch": 0.06341178758996305,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.6617,
|
||
|
|
"mean_token_accuracy": 0.1109016127884388,
|
||
|
|
"num_tokens": 1418208.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.072976303100586,
|
||
|
|
"epoch": 0.0638008169616806,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.6608,
|
||
|
|
"mean_token_accuracy": 0.11023175194859505,
|
||
|
|
"num_tokens": 1426665.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.980063629150391,
|
||
|
|
"epoch": 0.06418984633339817,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.5932,
|
||
|
|
"mean_token_accuracy": 0.11027788445353508,
|
||
|
|
"num_tokens": 1435247.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.98336706161499,
|
||
|
|
"epoch": 0.06457887570511574,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.6365,
|
||
|
|
"mean_token_accuracy": 0.11016326993703843,
|
||
|
|
"num_tokens": 1443678.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.947188854217529,
|
||
|
|
"epoch": 0.0649679050768333,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.5746,
|
||
|
|
"mean_token_accuracy": 0.11637299805879593,
|
||
|
|
"num_tokens": 1451567.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.953899240493774,
|
||
|
|
"epoch": 0.06535693444855087,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.5881,
|
||
|
|
"mean_token_accuracy": 0.10969302877783775,
|
||
|
|
"num_tokens": 1460618.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.999412250518799,
|
||
|
|
"epoch": 0.06574596382026843,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.667,
|
||
|
|
"mean_token_accuracy": 0.11072178110480309,
|
||
|
|
"num_tokens": 1469821.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0580075740814205,
|
||
|
|
"epoch": 0.066134993191986,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.7378,
|
||
|
|
"mean_token_accuracy": 0.10718388482928276,
|
||
|
|
"num_tokens": 1477989.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.051467561721802,
|
||
|
|
"epoch": 0.06652402256370356,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.7462,
|
||
|
|
"mean_token_accuracy": 0.10824755355715751,
|
||
|
|
"num_tokens": 1486822.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.015081548690796,
|
||
|
|
"epoch": 0.06691305193542113,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.6159,
|
||
|
|
"mean_token_accuracy": 0.1050032138824463,
|
||
|
|
"num_tokens": 1496604.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.946830940246582,
|
||
|
|
"epoch": 0.06730208130713869,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.6411,
|
||
|
|
"mean_token_accuracy": 0.1079692468047142,
|
||
|
|
"num_tokens": 1504725.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.015288543701172,
|
||
|
|
"epoch": 0.06769111067885625,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.6492,
|
||
|
|
"mean_token_accuracy": 0.11273297667503357,
|
||
|
|
"num_tokens": 1513222.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.022673845291138,
|
||
|
|
"epoch": 0.06808014005057382,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.6131,
|
||
|
|
"mean_token_accuracy": 0.10831626504659653,
|
||
|
|
"num_tokens": 1522183.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.945608234405517,
|
||
|
|
"epoch": 0.06846916942229138,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.6553,
|
||
|
|
"mean_token_accuracy": 0.10740983784198761,
|
||
|
|
"num_tokens": 1531316.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046859550476074,
|
||
|
|
"epoch": 0.06885819879400895,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.7085,
|
||
|
|
"mean_token_accuracy": 0.10943676829338074,
|
||
|
|
"num_tokens": 1540053.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0075178146362305,
|
||
|
|
"epoch": 0.06924722816572651,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.5681,
|
||
|
|
"mean_token_accuracy": 0.11703129261732101,
|
||
|
|
"num_tokens": 1549391.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.040959405899048,
|
||
|
|
"epoch": 0.06963625753744408,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.6779,
|
||
|
|
"mean_token_accuracy": 0.11206066384911537,
|
||
|
|
"num_tokens": 1557364.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.902760457992554,
|
||
|
|
"epoch": 0.07002528690916164,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.5277,
|
||
|
|
"mean_token_accuracy": 0.10990011170506478,
|
||
|
|
"num_tokens": 1567011.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839785480499268,
|
||
|
|
"epoch": 0.0704143162808792,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.6347,
|
||
|
|
"mean_token_accuracy": 0.10979588106274604,
|
||
|
|
"num_tokens": 1575441.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.96569299697876,
|
||
|
|
"epoch": 0.07080334565259677,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.5902,
|
||
|
|
"mean_token_accuracy": 0.11274805590510369,
|
||
|
|
"num_tokens": 1583757.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.020220041275024,
|
||
|
|
"epoch": 0.07119237502431433,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.6305,
|
||
|
|
"mean_token_accuracy": 0.11361563205718994,
|
||
|
|
"num_tokens": 1592406.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9013814449310305,
|
||
|
|
"epoch": 0.0715814043960319,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.6107,
|
||
|
|
"mean_token_accuracy": 0.11090241372585297,
|
||
|
|
"num_tokens": 1601665.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.95518798828125,
|
||
|
|
"epoch": 0.07197043376774946,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.6219,
|
||
|
|
"mean_token_accuracy": 0.11311167180538177,
|
||
|
|
"num_tokens": 1609788.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.954713582992554,
|
||
|
|
"epoch": 0.07235946313946703,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.618,
|
||
|
|
"mean_token_accuracy": 0.11602962091565132,
|
||
|
|
"num_tokens": 1618030.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.909007263183594,
|
||
|
|
"epoch": 0.07274849251118459,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.619,
|
||
|
|
"mean_token_accuracy": 0.10842904224991798,
|
||
|
|
"num_tokens": 1626901.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.836823034286499,
|
||
|
|
"epoch": 0.07313752188290217,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.5232,
|
||
|
|
"mean_token_accuracy": 0.1104541540145874,
|
||
|
|
"num_tokens": 1635372.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.920376491546631,
|
||
|
|
"epoch": 0.07352655125461972,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.5485,
|
||
|
|
"mean_token_accuracy": 0.11306027993559838,
|
||
|
|
"num_tokens": 1643791.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.767651128768921,
|
||
|
|
"epoch": 0.07391558062633728,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.518,
|
||
|
|
"mean_token_accuracy": 0.1175017923116684,
|
||
|
|
"num_tokens": 1652161.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.930508375167847,
|
||
|
|
"epoch": 0.07430460999805485,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.5631,
|
||
|
|
"mean_token_accuracy": 0.1112576186656952,
|
||
|
|
"num_tokens": 1661077.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.823507070541382,
|
||
|
|
"epoch": 0.07469363936977241,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.5267,
|
||
|
|
"mean_token_accuracy": 0.1152154453098774,
|
||
|
|
"num_tokens": 1669010.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9437110900878904,
|
||
|
|
"epoch": 0.07508266874148999,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.6996,
|
||
|
|
"mean_token_accuracy": 0.10548838526010514,
|
||
|
|
"num_tokens": 1678002.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.970439100265503,
|
||
|
|
"epoch": 0.07547169811320754,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.6515,
|
||
|
|
"mean_token_accuracy": 0.11191459000110626,
|
||
|
|
"num_tokens": 1687403.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.899893045425415,
|
||
|
|
"epoch": 0.07586072748492512,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.568,
|
||
|
|
"mean_token_accuracy": 0.11637896820902824,
|
||
|
|
"num_tokens": 1695512.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905468416213989,
|
||
|
|
"epoch": 0.07624975685664268,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.562,
|
||
|
|
"mean_token_accuracy": 0.11065016388893127,
|
||
|
|
"num_tokens": 1705116.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.740264987945556,
|
||
|
|
"epoch": 0.07663878622836025,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.4647,
|
||
|
|
"mean_token_accuracy": 0.11217278465628625,
|
||
|
|
"num_tokens": 1713715.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905466890335083,
|
||
|
|
"epoch": 0.0770278156000778,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.534,
|
||
|
|
"mean_token_accuracy": 0.11301849856972694,
|
||
|
|
"num_tokens": 1721881.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.823386716842651,
|
||
|
|
"epoch": 0.07741684497179536,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.5621,
|
||
|
|
"mean_token_accuracy": 0.11369865015149117,
|
||
|
|
"num_tokens": 1730716.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.003415536880493,
|
||
|
|
"epoch": 0.07780587434351294,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.7061,
|
||
|
|
"mean_token_accuracy": 0.11018745675683021,
|
||
|
|
"num_tokens": 1740257.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.86281156539917,
|
||
|
|
"epoch": 0.0781949037152305,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999999989075146,
|
||
|
|
"loss": 6.6085,
|
||
|
|
"mean_token_accuracy": 0.1118568867444992,
|
||
|
|
"num_tokens": 1749071.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.864678907394409,
|
||
|
|
"epoch": 0.07858393308694807,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999999944692927,
|
||
|
|
"loss": 6.6204,
|
||
|
|
"mean_token_accuracy": 0.10326161161065102,
|
||
|
|
"num_tokens": 1757952.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.863972473144531,
|
||
|
|
"epoch": 0.07897296245866563,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499999986617054,
|
||
|
|
"loss": 6.5531,
|
||
|
|
"mean_token_accuracy": 0.11324110552668572,
|
||
|
|
"num_tokens": 1766027.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.801832294464111,
|
||
|
|
"epoch": 0.0793619918303832,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999999753507986,
|
||
|
|
"loss": 6.5527,
|
||
|
|
"mean_token_accuracy": 0.10727588534355163,
|
||
|
|
"num_tokens": 1775039.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.848104572296142,
|
||
|
|
"epoch": 0.07975102120210076,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999999606705267,
|
||
|
|
"loss": 6.5556,
|
||
|
|
"mean_token_accuracy": 0.11754972413182259,
|
||
|
|
"num_tokens": 1783971.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8215718269348145,
|
||
|
|
"epoch": 0.08014005057381832,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999999425762385,
|
||
|
|
"loss": 6.4753,
|
||
|
|
"mean_token_accuracy": 0.11163984313607216,
|
||
|
|
"num_tokens": 1792743.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.859644365310669,
|
||
|
|
"epoch": 0.08052907994553589,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999999210679344,
|
||
|
|
"loss": 6.6316,
|
||
|
|
"mean_token_accuracy": 0.10586050003767014,
|
||
|
|
"num_tokens": 1801435.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.908881664276123,
|
||
|
|
"epoch": 0.08091810931725345,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999998961456145,
|
||
|
|
"loss": 6.5221,
|
||
|
|
"mean_token_accuracy": 0.10814850106835365,
|
||
|
|
"num_tokens": 1810147.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.809201431274414,
|
||
|
|
"epoch": 0.08130713868897102,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999998678092794,
|
||
|
|
"loss": 6.4526,
|
||
|
|
"mean_token_accuracy": 0.11560517325997352,
|
||
|
|
"num_tokens": 1818672.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.868528652191162,
|
||
|
|
"epoch": 0.08169616806068858,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999998360589293,
|
||
|
|
"loss": 6.5984,
|
||
|
|
"mean_token_accuracy": 0.11358216851949691,
|
||
|
|
"num_tokens": 1827590.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.771164989471435,
|
||
|
|
"epoch": 0.08208519743240615,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499999800894565,
|
||
|
|
"loss": 6.513,
|
||
|
|
"mean_token_accuracy": 0.11691295430064201,
|
||
|
|
"num_tokens": 1836467.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7579442977905275,
|
||
|
|
"epoch": 0.08247422680412371,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999997623161866,
|
||
|
|
"loss": 6.4583,
|
||
|
|
"mean_token_accuracy": 0.11373137831687927,
|
||
|
|
"num_tokens": 1845537.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.780694103240966,
|
||
|
|
"epoch": 0.08286325617584128,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999997203237951,
|
||
|
|
"loss": 6.4658,
|
||
|
|
"mean_token_accuracy": 0.12047376260161399,
|
||
|
|
"num_tokens": 1854433.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7921051502227785,
|
||
|
|
"epoch": 0.08325228554755884,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499999674917391,
|
||
|
|
"loss": 6.5716,
|
||
|
|
"mean_token_accuracy": 0.10947082787752152,
|
||
|
|
"num_tokens": 1863708.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.810097408294678,
|
||
|
|
"epoch": 0.0836413149192764,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999996260969748,
|
||
|
|
"loss": 6.4373,
|
||
|
|
"mean_token_accuracy": 0.11977095603942871,
|
||
|
|
"num_tokens": 1871854.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.711810445785522,
|
||
|
|
"epoch": 0.08403034429099397,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999995738625475,
|
||
|
|
"loss": 6.4063,
|
||
|
|
"mean_token_accuracy": 0.1185697853565216,
|
||
|
|
"num_tokens": 1880471.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.751388072967529,
|
||
|
|
"epoch": 0.08441937366271153,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999995182141099,
|
||
|
|
"loss": 6.4624,
|
||
|
|
"mean_token_accuracy": 0.11945423632860183,
|
||
|
|
"num_tokens": 1889882.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6411792755126955,
|
||
|
|
"epoch": 0.0848084030344291,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999994591516626,
|
||
|
|
"loss": 6.3584,
|
||
|
|
"mean_token_accuracy": 0.12587759271264076,
|
||
|
|
"num_tokens": 1898701.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.699534511566162,
|
||
|
|
"epoch": 0.08519743240614666,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999993966752066,
|
||
|
|
"loss": 6.4607,
|
||
|
|
"mean_token_accuracy": 0.11258344799280166,
|
||
|
|
"num_tokens": 1908165.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.743130016326904,
|
||
|
|
"epoch": 0.08558646177786423,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499999330784743,
|
||
|
|
"loss": 6.5679,
|
||
|
|
"mean_token_accuracy": 0.11548311486840249,
|
||
|
|
"num_tokens": 1916295.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.833187913894653,
|
||
|
|
"epoch": 0.08597549114958179,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999992614802725,
|
||
|
|
"loss": 6.4638,
|
||
|
|
"mean_token_accuracy": 0.11991653963923454,
|
||
|
|
"num_tokens": 1924643.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.747153854370117,
|
||
|
|
"epoch": 0.08636452052129936,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999991887617966,
|
||
|
|
"loss": 6.4623,
|
||
|
|
"mean_token_accuracy": 0.11614882722496986,
|
||
|
|
"num_tokens": 1933822.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6497047424316404,
|
||
|
|
"epoch": 0.08675354989301692,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999991126293158,
|
||
|
|
"loss": 6.4652,
|
||
|
|
"mean_token_accuracy": 0.11403647363185883,
|
||
|
|
"num_tokens": 1943278.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.89057731628418,
|
||
|
|
"epoch": 0.08714257926473448,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999990330828318,
|
||
|
|
"loss": 6.4991,
|
||
|
|
"mean_token_accuracy": 0.11635721921920776,
|
||
|
|
"num_tokens": 1951883.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.618956565856934,
|
||
|
|
"epoch": 0.08753160863645205,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999989501223456,
|
||
|
|
"loss": 6.3814,
|
||
|
|
"mean_token_accuracy": 0.12408010512590409,
|
||
|
|
"num_tokens": 1959567.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.809039831161499,
|
||
|
|
"epoch": 0.08792063800816961,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999988637478584,
|
||
|
|
"loss": 6.4599,
|
||
|
|
"mean_token_accuracy": 0.11816074550151826,
|
||
|
|
"num_tokens": 1968190.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56049690246582,
|
||
|
|
"epoch": 0.08830966737988719,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999987739593716,
|
||
|
|
"loss": 6.377,
|
||
|
|
"mean_token_accuracy": 0.12225727364420891,
|
||
|
|
"num_tokens": 1977519.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.749509620666504,
|
||
|
|
"epoch": 0.08869869675160474,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004999986807568865,
|
||
|
|
"loss": 6.3718,
|
||
|
|
"mean_token_accuracy": 0.11851018518209458,
|
||
|
|
"num_tokens": 1985796.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7915668964385985,
|
||
|
|
"epoch": 0.08908772612332232,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999985841404045,
|
||
|
|
"loss": 6.5103,
|
||
|
|
"mean_token_accuracy": 0.1153883047401905,
|
||
|
|
"num_tokens": 1993874.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.830569458007813,
|
||
|
|
"epoch": 0.08947675549503988,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999984841099271,
|
||
|
|
"loss": 6.4631,
|
||
|
|
"mean_token_accuracy": 0.12087473869323731,
|
||
|
|
"num_tokens": 2001663.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.626487779617309,
|
||
|
|
"epoch": 0.08986578486675743,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499998380665456,
|
||
|
|
"loss": 6.4341,
|
||
|
|
"mean_token_accuracy": 0.12093059793114662,
|
||
|
|
"num_tokens": 2010179.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.774807786941528,
|
||
|
|
"epoch": 0.090254814238475,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999982738069924,
|
||
|
|
"loss": 6.3481,
|
||
|
|
"mean_token_accuracy": 0.11917036697268486,
|
||
|
|
"num_tokens": 2020013.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.651696872711182,
|
||
|
|
"epoch": 0.09064384361019256,
|
||
|
|
"grad_norm": 1.765625,
|
||
|
|
"learning_rate": 0.0004999981635345382,
|
||
|
|
"loss": 6.4849,
|
||
|
|
"mean_token_accuracy": 0.12042224928736686,
|
||
|
|
"num_tokens": 2028396.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.807629251480103,
|
||
|
|
"epoch": 0.09103287298191014,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999980498480949,
|
||
|
|
"loss": 6.5699,
|
||
|
|
"mean_token_accuracy": 0.11065206825733184,
|
||
|
|
"num_tokens": 2036947.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.702048110961914,
|
||
|
|
"epoch": 0.0914219023536277,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999979327476644,
|
||
|
|
"loss": 6.4087,
|
||
|
|
"mean_token_accuracy": 0.11726011484861373,
|
||
|
|
"num_tokens": 2045162.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.737331104278565,
|
||
|
|
"epoch": 0.09181093172534527,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999978122332485,
|
||
|
|
"loss": 6.4986,
|
||
|
|
"mean_token_accuracy": 0.11559060364961624,
|
||
|
|
"num_tokens": 2054198.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.650309991836548,
|
||
|
|
"epoch": 0.09219996109706283,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999976883048487,
|
||
|
|
"loss": 6.419,
|
||
|
|
"mean_token_accuracy": 0.11779844760894775,
|
||
|
|
"num_tokens": 2062558.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.701250696182251,
|
||
|
|
"epoch": 0.0925889904687804,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004999975609624673,
|
||
|
|
"loss": 6.2995,
|
||
|
|
"mean_token_accuracy": 0.11358527466654778,
|
||
|
|
"num_tokens": 2070816.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.61013011932373,
|
||
|
|
"epoch": 0.09297801984049796,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999974302061059,
|
||
|
|
"loss": 6.3538,
|
||
|
|
"mean_token_accuracy": 0.11822599768638611,
|
||
|
|
"num_tokens": 2079058.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.643589496612549,
|
||
|
|
"epoch": 0.09336704921221552,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999972960357666,
|
||
|
|
"loss": 6.3214,
|
||
|
|
"mean_token_accuracy": 0.12255356609821319,
|
||
|
|
"num_tokens": 2086679.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.664435195922851,
|
||
|
|
"epoch": 0.09375607858393309,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004999971584514516,
|
||
|
|
"loss": 6.4264,
|
||
|
|
"mean_token_accuracy": 0.11835757493972779,
|
||
|
|
"num_tokens": 2095788.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6650059700012205,
|
||
|
|
"epoch": 0.09414510795565065,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999970174531627,
|
||
|
|
"loss": 6.4504,
|
||
|
|
"mean_token_accuracy": 0.11537863463163375,
|
||
|
|
"num_tokens": 2105435.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.69662823677063,
|
||
|
|
"epoch": 0.09453413732736822,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999968730409022,
|
||
|
|
"loss": 6.3946,
|
||
|
|
"mean_token_accuracy": 0.11899836733937263,
|
||
|
|
"num_tokens": 2114318.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.603922605514526,
|
||
|
|
"epoch": 0.09492316669908578,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999967252146723,
|
||
|
|
"loss": 6.319,
|
||
|
|
"mean_token_accuracy": 0.1297658160328865,
|
||
|
|
"num_tokens": 2122707.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5683904647827145,
|
||
|
|
"epoch": 0.09531219607080335,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999965739744752,
|
||
|
|
"loss": 6.4173,
|
||
|
|
"mean_token_accuracy": 0.1176735907793045,
|
||
|
|
"num_tokens": 2131176.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.759912300109863,
|
||
|
|
"epoch": 0.09570122544252091,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999964193203132,
|
||
|
|
"loss": 6.4613,
|
||
|
|
"mean_token_accuracy": 0.12155932411551476,
|
||
|
|
"num_tokens": 2139872.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.643018627166748,
|
||
|
|
"epoch": 0.09609025481423847,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999962612521888,
|
||
|
|
"loss": 6.3193,
|
||
|
|
"mean_token_accuracy": 0.12510446161031724,
|
||
|
|
"num_tokens": 2148668.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.589841032028199,
|
||
|
|
"epoch": 0.09647928418595604,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999960997701041,
|
||
|
|
"loss": 6.3267,
|
||
|
|
"mean_token_accuracy": 0.12770092412829398,
|
||
|
|
"num_tokens": 2156628.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.672489738464355,
|
||
|
|
"epoch": 0.0968683135576736,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999959348740618,
|
||
|
|
"loss": 6.4077,
|
||
|
|
"mean_token_accuracy": 0.11675584986805916,
|
||
|
|
"num_tokens": 2165620.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6866566181182865,
|
||
|
|
"epoch": 0.09725734292939117,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999957665640641,
|
||
|
|
"loss": 6.474,
|
||
|
|
"mean_token_accuracy": 0.12056236788630485,
|
||
|
|
"num_tokens": 2174493.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.706568670272827,
|
||
|
|
"epoch": 0.09764637230110873,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000499995594840114,
|
||
|
|
"loss": 6.3623,
|
||
|
|
"mean_token_accuracy": 0.11302633062005044,
|
||
|
|
"num_tokens": 2183258.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.616120624542236,
|
||
|
|
"epoch": 0.0980354016728263,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999954197022138,
|
||
|
|
"loss": 6.4286,
|
||
|
|
"mean_token_accuracy": 0.11189185678958893,
|
||
|
|
"num_tokens": 2192263.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.736319494247437,
|
||
|
|
"epoch": 0.09842443104454386,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999952411503661,
|
||
|
|
"loss": 6.4736,
|
||
|
|
"mean_token_accuracy": 0.11438293233513833,
|
||
|
|
"num_tokens": 2201797.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.494112110137939,
|
||
|
|
"epoch": 0.09881346041626143,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999950591845738,
|
||
|
|
"loss": 6.2042,
|
||
|
|
"mean_token_accuracy": 0.129413703083992,
|
||
|
|
"num_tokens": 2209454.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.683527231216431,
|
||
|
|
"epoch": 0.09920248978797899,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999948738048397,
|
||
|
|
"loss": 6.392,
|
||
|
|
"mean_token_accuracy": 0.12001634314656258,
|
||
|
|
"num_tokens": 2217761.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541403865814209,
|
||
|
|
"epoch": 0.09959151915969655,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004999946850111663,
|
||
|
|
"loss": 6.3754,
|
||
|
|
"mean_token_accuracy": 0.118533456325531,
|
||
|
|
"num_tokens": 2225793.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.716179895401001,
|
||
|
|
"epoch": 0.09998054853141412,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999944928035569,
|
||
|
|
"loss": 6.263,
|
||
|
|
"mean_token_accuracy": 0.12969468906521797,
|
||
|
|
"num_tokens": 2234620.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541376686096191,
|
||
|
|
"epoch": 0.10036957790313168,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499994297182014,
|
||
|
|
"loss": 6.3484,
|
||
|
|
"mean_token_accuracy": 0.11944441497325897,
|
||
|
|
"num_tokens": 2242829.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.670366430282593,
|
||
|
|
"epoch": 0.10075860727484925,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999940981465408,
|
||
|
|
"loss": 6.3704,
|
||
|
|
"mean_token_accuracy": 0.11480111479759217,
|
||
|
|
"num_tokens": 2251356.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56609148979187,
|
||
|
|
"epoch": 0.10114763664656681,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999938956971404,
|
||
|
|
"loss": 6.4409,
|
||
|
|
"mean_token_accuracy": 0.11915249675512314,
|
||
|
|
"num_tokens": 2259327.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.683287715911865,
|
||
|
|
"epoch": 0.10153666601828439,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999936898338156,
|
||
|
|
"loss": 6.4538,
|
||
|
|
"mean_token_accuracy": 0.11428613439202309,
|
||
|
|
"num_tokens": 2267948.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.560197353363037,
|
||
|
|
"epoch": 0.10192569539000194,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999934805565698,
|
||
|
|
"loss": 6.281,
|
||
|
|
"mean_token_accuracy": 0.1233622319996357,
|
||
|
|
"num_tokens": 2275828.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.534844875335693,
|
||
|
|
"epoch": 0.10231472476171952,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499993267865406,
|
||
|
|
"loss": 6.2154,
|
||
|
|
"mean_token_accuracy": 0.1286098428070545,
|
||
|
|
"num_tokens": 2284246.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.50963945388794,
|
||
|
|
"epoch": 0.10270375413343708,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999930517603275,
|
||
|
|
"loss": 6.2122,
|
||
|
|
"mean_token_accuracy": 0.13067591562867165,
|
||
|
|
"num_tokens": 2291837.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6015325546264645,
|
||
|
|
"epoch": 0.10309278350515463,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999928322413374,
|
||
|
|
"loss": 6.2854,
|
||
|
|
"mean_token_accuracy": 0.12339815348386765,
|
||
|
|
"num_tokens": 2299853.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.674331474304199,
|
||
|
|
"epoch": 0.1034818128768722,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999926093084394,
|
||
|
|
"loss": 6.3807,
|
||
|
|
"mean_token_accuracy": 0.11902100816369057,
|
||
|
|
"num_tokens": 2308416.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.549804925918579,
|
||
|
|
"epoch": 0.10387084224858976,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999923829616365,
|
||
|
|
"loss": 6.4127,
|
||
|
|
"mean_token_accuracy": 0.11715119779109955,
|
||
|
|
"num_tokens": 2318104.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6144133567810055,
|
||
|
|
"epoch": 0.10425987162030734,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999921532009323,
|
||
|
|
"loss": 6.3325,
|
||
|
|
"mean_token_accuracy": 0.11866103261709213,
|
||
|
|
"num_tokens": 2326807.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.590117406845093,
|
||
|
|
"epoch": 0.1046489009920249,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999919200263304,
|
||
|
|
"loss": 6.3363,
|
||
|
|
"mean_token_accuracy": 0.11958926171064377,
|
||
|
|
"num_tokens": 2335921.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594919157028198,
|
||
|
|
"epoch": 0.10503793036374247,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999916834378342,
|
||
|
|
"loss": 6.3476,
|
||
|
|
"mean_token_accuracy": 0.12185617685317993,
|
||
|
|
"num_tokens": 2344914.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.542745637893677,
|
||
|
|
"epoch": 0.10542695973546003,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999914434354472,
|
||
|
|
"loss": 6.2886,
|
||
|
|
"mean_token_accuracy": 0.11944291591644288,
|
||
|
|
"num_tokens": 2353211.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.57375807762146,
|
||
|
|
"epoch": 0.10581598910717759,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999912000191733,
|
||
|
|
"loss": 6.4112,
|
||
|
|
"mean_token_accuracy": 0.11920397132635116,
|
||
|
|
"num_tokens": 2361717.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566148090362549,
|
||
|
|
"epoch": 0.10620501847889516,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499990953189016,
|
||
|
|
"loss": 6.346,
|
||
|
|
"mean_token_accuracy": 0.12413823828101159,
|
||
|
|
"num_tokens": 2370114.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700903367996216,
|
||
|
|
"epoch": 0.10659404785061272,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999907029449791,
|
||
|
|
"loss": 6.3374,
|
||
|
|
"mean_token_accuracy": 0.11766661703586578,
|
||
|
|
"num_tokens": 2378820.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.436738204956055,
|
||
|
|
"epoch": 0.10698307722233029,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999904492870663,
|
||
|
|
"loss": 6.2537,
|
||
|
|
"mean_token_accuracy": 0.12378470376133918,
|
||
|
|
"num_tokens": 2387119.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5843147277832035,
|
||
|
|
"epoch": 0.10737210659404785,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999901922152816,
|
||
|
|
"loss": 6.3039,
|
||
|
|
"mean_token_accuracy": 0.12202484160661697,
|
||
|
|
"num_tokens": 2396246.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.51186990737915,
|
||
|
|
"epoch": 0.10776113596576542,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999899317296288,
|
||
|
|
"loss": 6.3581,
|
||
|
|
"mean_token_accuracy": 0.11975730657577514,
|
||
|
|
"num_tokens": 2405428.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566965532302857,
|
||
|
|
"epoch": 0.10815016533748298,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999896678301121,
|
||
|
|
"loss": 6.3066,
|
||
|
|
"mean_token_accuracy": 0.12349836975336075,
|
||
|
|
"num_tokens": 2414669.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.655934619903564,
|
||
|
|
"epoch": 0.10853919470920055,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999894005167352,
|
||
|
|
"loss": 6.3868,
|
||
|
|
"mean_token_accuracy": 0.11691371873021125,
|
||
|
|
"num_tokens": 2423193.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.565681409835816,
|
||
|
|
"epoch": 0.10892822408091811,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000499989129789502,
|
||
|
|
"loss": 6.3387,
|
||
|
|
"mean_token_accuracy": 0.1171958826482296,
|
||
|
|
"num_tokens": 2431150.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56759557723999,
|
||
|
|
"epoch": 0.10931725345263567,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999888556484172,
|
||
|
|
"loss": 6.3134,
|
||
|
|
"mean_token_accuracy": 0.1197988323867321,
|
||
|
|
"num_tokens": 2440337.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.470945692062378,
|
||
|
|
"epoch": 0.10970628282435324,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999885780934845,
|
||
|
|
"loss": 6.2513,
|
||
|
|
"mean_token_accuracy": 0.12705043703317642,
|
||
|
|
"num_tokens": 2449246.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.516160583496093,
|
||
|
|
"epoch": 0.1100953121960708,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999882971247081,
|
||
|
|
"loss": 6.2565,
|
||
|
|
"mean_token_accuracy": 0.12589537277817725,
|
||
|
|
"num_tokens": 2457982.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5252786636352536,
|
||
|
|
"epoch": 0.11048434156778837,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999880127420926,
|
||
|
|
"loss": 6.2425,
|
||
|
|
"mean_token_accuracy": 0.12535301148891448,
|
||
|
|
"num_tokens": 2466697.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.493203258514404,
|
||
|
|
"epoch": 0.11087337093950593,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999877249456421,
|
||
|
|
"loss": 6.2222,
|
||
|
|
"mean_token_accuracy": 0.12576746717095375,
|
||
|
|
"num_tokens": 2475457.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.437700080871582,
|
||
|
|
"epoch": 0.1112624003112235,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999874337353609,
|
||
|
|
"loss": 6.2138,
|
||
|
|
"mean_token_accuracy": 0.12601543366909027,
|
||
|
|
"num_tokens": 2484753.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.485835027694702,
|
||
|
|
"epoch": 0.11165142968294106,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999871391112535,
|
||
|
|
"loss": 6.3166,
|
||
|
|
"mean_token_accuracy": 0.12342042103409767,
|
||
|
|
"num_tokens": 2492921.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.581958627700805,
|
||
|
|
"epoch": 0.11204045905465862,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999868410733244,
|
||
|
|
"loss": 6.2879,
|
||
|
|
"mean_token_accuracy": 0.1212073914706707,
|
||
|
|
"num_tokens": 2501371.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5133496761322025,
|
||
|
|
"epoch": 0.11242948842637619,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000499986539621578,
|
||
|
|
"loss": 6.1714,
|
||
|
|
"mean_token_accuracy": 0.12704863548278808,
|
||
|
|
"num_tokens": 2509521.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.48231053352356,
|
||
|
|
"epoch": 0.11281851779809375,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999862347560191,
|
||
|
|
"loss": 6.2989,
|
||
|
|
"mean_token_accuracy": 0.12423472106456757,
|
||
|
|
"num_tokens": 2518316.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.569843530654907,
|
||
|
|
"epoch": 0.11320754716981132,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999859264766521,
|
||
|
|
"loss": 6.3733,
|
||
|
|
"mean_token_accuracy": 0.1180838830769062,
|
||
|
|
"num_tokens": 2527549.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.596394872665405,
|
||
|
|
"epoch": 0.11359657654152888,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999856147834817,
|
||
|
|
"loss": 6.3999,
|
||
|
|
"mean_token_accuracy": 0.12059949561953545,
|
||
|
|
"num_tokens": 2536341.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44488263130188,
|
||
|
|
"epoch": 0.11398560591324645,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999852996765129,
|
||
|
|
"loss": 6.2924,
|
||
|
|
"mean_token_accuracy": 0.13068008571863174,
|
||
|
|
"num_tokens": 2544869.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523885440826416,
|
||
|
|
"epoch": 0.11437463528496401,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999849811557502,
|
||
|
|
"loss": 6.1793,
|
||
|
|
"mean_token_accuracy": 0.13547530099749566,
|
||
|
|
"num_tokens": 2553432.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.51270112991333,
|
||
|
|
"epoch": 0.11476366465668159,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999846592211984,
|
||
|
|
"loss": 6.3122,
|
||
|
|
"mean_token_accuracy": 0.11962430030107499,
|
||
|
|
"num_tokens": 2561996.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515383100509643,
|
||
|
|
"epoch": 0.11515269402839914,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999843338728626,
|
||
|
|
"loss": 6.2467,
|
||
|
|
"mean_token_accuracy": 0.12699604406952858,
|
||
|
|
"num_tokens": 2571315.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.514121627807617,
|
||
|
|
"epoch": 0.1155417234001167,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999840051107476,
|
||
|
|
"loss": 6.3579,
|
||
|
|
"mean_token_accuracy": 0.12020841464400292,
|
||
|
|
"num_tokens": 2579589.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5186272144317625,
|
||
|
|
"epoch": 0.11593075277183428,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999836729348584,
|
||
|
|
"loss": 6.1182,
|
||
|
|
"mean_token_accuracy": 0.1279861733317375,
|
||
|
|
"num_tokens": 2588528.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.421968936920166,
|
||
|
|
"epoch": 0.11631978214355183,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999833373452,
|
||
|
|
"loss": 6.2575,
|
||
|
|
"mean_token_accuracy": 0.12487708628177643,
|
||
|
|
"num_tokens": 2596820.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.408306360244751,
|
||
|
|
"epoch": 0.1167088115152694,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999829983417778,
|
||
|
|
"loss": 6.1765,
|
||
|
|
"mean_token_accuracy": 0.12320946007966996,
|
||
|
|
"num_tokens": 2605502.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.448068284988404,
|
||
|
|
"epoch": 0.11709784088698696,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999826559245965,
|
||
|
|
"loss": 6.1834,
|
||
|
|
"mean_token_accuracy": 0.13115072697401048,
|
||
|
|
"num_tokens": 2613974.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4151896953582765,
|
||
|
|
"epoch": 0.11748687025870454,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999823100936615,
|
||
|
|
"loss": 6.2679,
|
||
|
|
"mean_token_accuracy": 0.12410511299967766,
|
||
|
|
"num_tokens": 2622581.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.444796562194824,
|
||
|
|
"epoch": 0.1178758996304221,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999819608489781,
|
||
|
|
"loss": 6.1459,
|
||
|
|
"mean_token_accuracy": 0.12382340282201768,
|
||
|
|
"num_tokens": 2631868.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3898896217346195,
|
||
|
|
"epoch": 0.11826492900213967,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999816081905515,
|
||
|
|
"loss": 6.1683,
|
||
|
|
"mean_token_accuracy": 0.12991080954670906,
|
||
|
|
"num_tokens": 2640501.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.531676197052002,
|
||
|
|
"epoch": 0.11865395837385723,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999812521183872,
|
||
|
|
"loss": 6.1699,
|
||
|
|
"mean_token_accuracy": 0.1317140817642212,
|
||
|
|
"num_tokens": 2648916.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.465039777755737,
|
||
|
|
"epoch": 0.11904298774557479,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999808926324903,
|
||
|
|
"loss": 6.2552,
|
||
|
|
"mean_token_accuracy": 0.13165784254670143,
|
||
|
|
"num_tokens": 2657725.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.431260061264038,
|
||
|
|
"epoch": 0.11943201711729236,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999805297328665,
|
||
|
|
"loss": 6.2322,
|
||
|
|
"mean_token_accuracy": 0.12672695890069008,
|
||
|
|
"num_tokens": 2665983.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.433292293548584,
|
||
|
|
"epoch": 0.11982104648900992,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999801634195214,
|
||
|
|
"loss": 6.2582,
|
||
|
|
"mean_token_accuracy": 0.1332721345126629,
|
||
|
|
"num_tokens": 2674546.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488146877288818,
|
||
|
|
"epoch": 0.12021007586072749,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999797936924603,
|
||
|
|
"loss": 6.176,
|
||
|
|
"mean_token_accuracy": 0.12813623994588852,
|
||
|
|
"num_tokens": 2684088.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44085841178894,
|
||
|
|
"epoch": 0.12059910523244505,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499979420551689,
|
||
|
|
"loss": 6.2212,
|
||
|
|
"mean_token_accuracy": 0.12631620317697526,
|
||
|
|
"num_tokens": 2693289.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.404530429840088,
|
||
|
|
"epoch": 0.12098813460416262,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499979043997213,
|
||
|
|
"loss": 6.1547,
|
||
|
|
"mean_token_accuracy": 0.13262817338109018,
|
||
|
|
"num_tokens": 2701744.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.463164138793945,
|
||
|
|
"epoch": 0.12137716397588018,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999786640290381,
|
||
|
|
"loss": 6.2138,
|
||
|
|
"mean_token_accuracy": 0.12017801105976104,
|
||
|
|
"num_tokens": 2710584.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.473390579223633,
|
||
|
|
"epoch": 0.12176619334759774,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999782806471701,
|
||
|
|
"loss": 6.221,
|
||
|
|
"mean_token_accuracy": 0.12257171049714088,
|
||
|
|
"num_tokens": 2719478.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.51469931602478,
|
||
|
|
"epoch": 0.12215522271931531,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999778938516147,
|
||
|
|
"loss": 6.3018,
|
||
|
|
"mean_token_accuracy": 0.11738094314932823,
|
||
|
|
"num_tokens": 2729105.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.504203176498413,
|
||
|
|
"epoch": 0.12254425209103287,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000499977503642378,
|
||
|
|
"loss": 6.2567,
|
||
|
|
"mean_token_accuracy": 0.12570588439702987,
|
||
|
|
"num_tokens": 2738300.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.46259298324585,
|
||
|
|
"epoch": 0.12293328146275044,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999771100194656,
|
||
|
|
"loss": 6.1997,
|
||
|
|
"mean_token_accuracy": 0.12281355112791062,
|
||
|
|
"num_tokens": 2747236.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.313042402267456,
|
||
|
|
"epoch": 0.123322310834468,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999767129828837,
|
||
|
|
"loss": 6.1552,
|
||
|
|
"mean_token_accuracy": 0.13333506733179093,
|
||
|
|
"num_tokens": 2755919.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3901971817016605,
|
||
|
|
"epoch": 0.12371134020618557,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999763125326383,
|
||
|
|
"loss": 6.1311,
|
||
|
|
"mean_token_accuracy": 0.13379732444882392,
|
||
|
|
"num_tokens": 2764469.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.470418119430542,
|
||
|
|
"epoch": 0.12410036957790313,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999759086687355,
|
||
|
|
"loss": 6.1465,
|
||
|
|
"mean_token_accuracy": 0.13174793347716332,
|
||
|
|
"num_tokens": 2772663.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.470247459411621,
|
||
|
|
"epoch": 0.1244893989496207,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999755013911813,
|
||
|
|
"loss": 6.1849,
|
||
|
|
"mean_token_accuracy": 0.12125680297613144,
|
||
|
|
"num_tokens": 2780719.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.411885499954224,
|
||
|
|
"epoch": 0.12487842832133826,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499975090699982,
|
||
|
|
"loss": 6.2373,
|
||
|
|
"mean_token_accuracy": 0.12744609639048576,
|
||
|
|
"num_tokens": 2789186.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.416819286346436,
|
||
|
|
"epoch": 0.12526745769305583,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999746765951438,
|
||
|
|
"loss": 6.1496,
|
||
|
|
"mean_token_accuracy": 0.12793729454278946,
|
||
|
|
"num_tokens": 2797993.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.388448762893677,
|
||
|
|
"epoch": 0.1256564870647734,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999742590766729,
|
||
|
|
"loss": 6.1015,
|
||
|
|
"mean_token_accuracy": 0.12969864159822464,
|
||
|
|
"num_tokens": 2806375.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.462837028503418,
|
||
|
|
"epoch": 0.12604551643649095,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999738381445757,
|
||
|
|
"loss": 6.2504,
|
||
|
|
"mean_token_accuracy": 0.1330662988126278,
|
||
|
|
"num_tokens": 2814772.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.313505363464356,
|
||
|
|
"epoch": 0.1264345458082085,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999734137988586,
|
||
|
|
"loss": 6.1229,
|
||
|
|
"mean_token_accuracy": 0.1330338940024376,
|
||
|
|
"num_tokens": 2824231.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.429342603683471,
|
||
|
|
"epoch": 0.1268235751799261,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000499972986039528,
|
||
|
|
"loss": 6.1851,
|
||
|
|
"mean_token_accuracy": 0.12637867406010628,
|
||
|
|
"num_tokens": 2833470.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42327880859375,
|
||
|
|
"epoch": 0.12721260455164365,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999725548665904,
|
||
|
|
"loss": 6.1914,
|
||
|
|
"mean_token_accuracy": 0.1272370584309101,
|
||
|
|
"num_tokens": 2843010.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4151369571685795,
|
||
|
|
"epoch": 0.1276016339233612,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999721202800524,
|
||
|
|
"loss": 6.0894,
|
||
|
|
"mean_token_accuracy": 0.13450721949338912,
|
||
|
|
"num_tokens": 2851545.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.322131395339966,
|
||
|
|
"epoch": 0.12799066329507877,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999716822799206,
|
||
|
|
"loss": 6.2373,
|
||
|
|
"mean_token_accuracy": 0.11726373285055161,
|
||
|
|
"num_tokens": 2861230.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.472705364227295,
|
||
|
|
"epoch": 0.12837969266679633,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999712408662016,
|
||
|
|
"loss": 6.1988,
|
||
|
|
"mean_token_accuracy": 0.12872418239712716,
|
||
|
|
"num_tokens": 2869436.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.349573040008545,
|
||
|
|
"epoch": 0.12876872203851392,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999707960389021,
|
||
|
|
"loss": 6.0591,
|
||
|
|
"mean_token_accuracy": 0.13055680692195892,
|
||
|
|
"num_tokens": 2877688.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446641206741333,
|
||
|
|
"epoch": 0.12915775141023147,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999703477980288,
|
||
|
|
"loss": 6.2037,
|
||
|
|
"mean_token_accuracy": 0.12923076152801513,
|
||
|
|
"num_tokens": 2887043.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.349732732772827,
|
||
|
|
"epoch": 0.12954678078194903,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999698961435885,
|
||
|
|
"loss": 6.1317,
|
||
|
|
"mean_token_accuracy": 0.13411349356174468,
|
||
|
|
"num_tokens": 2895732.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.334634923934937,
|
||
|
|
"epoch": 0.1299358101536666,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999694410755882,
|
||
|
|
"loss": 6.0911,
|
||
|
|
"mean_token_accuracy": 0.12794594317674637,
|
||
|
|
"num_tokens": 2904162.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.453775310516358,
|
||
|
|
"epoch": 0.13032483952538418,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999689825940347,
|
||
|
|
"loss": 6.2303,
|
||
|
|
"mean_token_accuracy": 0.12870074063539505,
|
||
|
|
"num_tokens": 2912783.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386454153060913,
|
||
|
|
"epoch": 0.13071386889710174,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999685206989349,
|
||
|
|
"loss": 6.128,
|
||
|
|
"mean_token_accuracy": 0.13094662353396416,
|
||
|
|
"num_tokens": 2921027.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.379840612411499,
|
||
|
|
"epoch": 0.1311028982688193,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999680553902959,
|
||
|
|
"loss": 6.1558,
|
||
|
|
"mean_token_accuracy": 0.13119837194681166,
|
||
|
|
"num_tokens": 2930398.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.364923095703125,
|
||
|
|
"epoch": 0.13149192764053685,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999675866681247,
|
||
|
|
"loss": 6.1767,
|
||
|
|
"mean_token_accuracy": 0.12759430408477784,
|
||
|
|
"num_tokens": 2938703.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.336649465560913,
|
||
|
|
"epoch": 0.1318809570122544,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999671145324286,
|
||
|
|
"loss": 6.101,
|
||
|
|
"mean_token_accuracy": 0.13444865867495537,
|
||
|
|
"num_tokens": 2947007.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386577987670899,
|
||
|
|
"epoch": 0.132269986383972,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999666389832144,
|
||
|
|
"loss": 6.2399,
|
||
|
|
"mean_token_accuracy": 0.13214273303747176,
|
||
|
|
"num_tokens": 2955485.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.432107162475586,
|
||
|
|
"epoch": 0.13265901575568956,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999661600204897,
|
||
|
|
"loss": 6.0943,
|
||
|
|
"mean_token_accuracy": 0.1316603824496269,
|
||
|
|
"num_tokens": 2964416.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.345300769805908,
|
||
|
|
"epoch": 0.13304804512740712,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999656776442615,
|
||
|
|
"loss": 6.0975,
|
||
|
|
"mean_token_accuracy": 0.12664629369974137,
|
||
|
|
"num_tokens": 2972737.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.319915866851806,
|
||
|
|
"epoch": 0.13343707449912467,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999651918545372,
|
||
|
|
"loss": 6.138,
|
||
|
|
"mean_token_accuracy": 0.12891265898942947,
|
||
|
|
"num_tokens": 2981166.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.400096082687378,
|
||
|
|
"epoch": 0.13382610387084226,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999647026513243,
|
||
|
|
"loss": 6.1841,
|
||
|
|
"mean_token_accuracy": 0.1323157973587513,
|
||
|
|
"num_tokens": 2989689.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.409255075454712,
|
||
|
|
"epoch": 0.13421513324255982,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00049996421003463,
|
||
|
|
"loss": 6.0878,
|
||
|
|
"mean_token_accuracy": 0.1328970320522785,
|
||
|
|
"num_tokens": 2998793.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.303147697448731,
|
||
|
|
"epoch": 0.13460416261427738,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999637140044619,
|
||
|
|
"loss": 6.2446,
|
||
|
|
"mean_token_accuracy": 0.12399912551045418,
|
||
|
|
"num_tokens": 3007320.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372701263427734,
|
||
|
|
"epoch": 0.13499319198599494,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999632145608275,
|
||
|
|
"loss": 6.1419,
|
||
|
|
"mean_token_accuracy": 0.13464085459709169,
|
||
|
|
"num_tokens": 3015024.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.392448997497558,
|
||
|
|
"epoch": 0.1353822213577125,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999627117037343,
|
||
|
|
"loss": 6.2367,
|
||
|
|
"mean_token_accuracy": 0.13206600919365882,
|
||
|
|
"num_tokens": 3023058.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42128438949585,
|
||
|
|
"epoch": 0.13577125072943008,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00049996220543319,
|
||
|
|
"loss": 6.1337,
|
||
|
|
"mean_token_accuracy": 0.1343154013156891,
|
||
|
|
"num_tokens": 3031308.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.368301248550415,
|
||
|
|
"epoch": 0.13616028010114764,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999616957492025,
|
||
|
|
"loss": 6.2115,
|
||
|
|
"mean_token_accuracy": 0.12576463893055917,
|
||
|
|
"num_tokens": 3039598.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332375144958496,
|
||
|
|
"epoch": 0.1365493094728652,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999611826517793,
|
||
|
|
"loss": 6.0264,
|
||
|
|
"mean_token_accuracy": 0.13993713706731797,
|
||
|
|
"num_tokens": 3047598.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.369699382781983,
|
||
|
|
"epoch": 0.13693833884458276,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999606661409281,
|
||
|
|
"loss": 6.1765,
|
||
|
|
"mean_token_accuracy": 0.1314793422818184,
|
||
|
|
"num_tokens": 3055702.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.352033996582032,
|
||
|
|
"epoch": 0.13732736821630034,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999601462166569,
|
||
|
|
"loss": 6.0358,
|
||
|
|
"mean_token_accuracy": 0.13761886060237885,
|
||
|
|
"num_tokens": 3063908.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.316202020645141,
|
||
|
|
"epoch": 0.1377163975880179,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999596228789736,
|
||
|
|
"loss": 6.1396,
|
||
|
|
"mean_token_accuracy": 0.12727851122617723,
|
||
|
|
"num_tokens": 3072077.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371345472335816,
|
||
|
|
"epoch": 0.13810542695973546,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999590961278859,
|
||
|
|
"loss": 6.1301,
|
||
|
|
"mean_token_accuracy": 0.13236963376402855,
|
||
|
|
"num_tokens": 3080498.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.343796157836914,
|
||
|
|
"epoch": 0.13849445633145302,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999585659634021,
|
||
|
|
"loss": 6.135,
|
||
|
|
"mean_token_accuracy": 0.13217933028936385,
|
||
|
|
"num_tokens": 3089055.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.314961290359497,
|
||
|
|
"epoch": 0.13888348570317058,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999580323855301,
|
||
|
|
"loss": 6.1373,
|
||
|
|
"mean_token_accuracy": 0.13297785818576813,
|
||
|
|
"num_tokens": 3096944.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.29940447807312,
|
||
|
|
"epoch": 0.13927251507488816,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999574953942781,
|
||
|
|
"loss": 6.0293,
|
||
|
|
"mean_token_accuracy": 0.13218909054994582,
|
||
|
|
"num_tokens": 3105596.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.27741756439209,
|
||
|
|
"epoch": 0.13966154444660572,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999569549896541,
|
||
|
|
"loss": 6.0162,
|
||
|
|
"mean_token_accuracy": 0.14017163962125778,
|
||
|
|
"num_tokens": 3114349.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2425329208374025,
|
||
|
|
"epoch": 0.14005057381832328,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999564111716665,
|
||
|
|
"loss": 6.1302,
|
||
|
|
"mean_token_accuracy": 0.12543968632817268,
|
||
|
|
"num_tokens": 3122490.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.412037658691406,
|
||
|
|
"epoch": 0.14043960319004084,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999558639403232,
|
||
|
|
"loss": 6.1766,
|
||
|
|
"mean_token_accuracy": 0.12949994951486588,
|
||
|
|
"num_tokens": 3130988.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.349801778793335,
|
||
|
|
"epoch": 0.1408286325617584,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999553132956328,
|
||
|
|
"loss": 6.0352,
|
||
|
|
"mean_token_accuracy": 0.1310783050954342,
|
||
|
|
"num_tokens": 3139488.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.275408506393433,
|
||
|
|
"epoch": 0.14121766193347599,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999547592376035,
|
||
|
|
"loss": 6.0853,
|
||
|
|
"mean_token_accuracy": 0.13912829905748367,
|
||
|
|
"num_tokens": 3147955.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.324730014801025,
|
||
|
|
"epoch": 0.14160669130519354,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999542017662438,
|
||
|
|
"loss": 6.1356,
|
||
|
|
"mean_token_accuracy": 0.12387675121426582,
|
||
|
|
"num_tokens": 3157608.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.365148973464966,
|
||
|
|
"epoch": 0.1419957206769111,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004999536408815623,
|
||
|
|
"loss": 6.0893,
|
||
|
|
"mean_token_accuracy": 0.12791794016957284,
|
||
|
|
"num_tokens": 3166124.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.237749290466309,
|
||
|
|
"epoch": 0.14238475004862866,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999530765835672,
|
||
|
|
"loss": 6.0837,
|
||
|
|
"mean_token_accuracy": 0.12821160182356833,
|
||
|
|
"num_tokens": 3175069.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.356600522994995,
|
||
|
|
"epoch": 0.14277377942034625,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999525088722673,
|
||
|
|
"loss": 6.1196,
|
||
|
|
"mean_token_accuracy": 0.13117128163576125,
|
||
|
|
"num_tokens": 3184259.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.341631460189819,
|
||
|
|
"epoch": 0.1431628087920638,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999519377476711,
|
||
|
|
"loss": 6.0274,
|
||
|
|
"mean_token_accuracy": 0.1311353027820587,
|
||
|
|
"num_tokens": 3193015.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.335974597930909,
|
||
|
|
"epoch": 0.14355183816378136,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999513632097872,
|
||
|
|
"loss": 5.9655,
|
||
|
|
"mean_token_accuracy": 0.1419636234641075,
|
||
|
|
"num_tokens": 3201624.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2722913265228275,
|
||
|
|
"epoch": 0.14394086753549892,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999507852586245,
|
||
|
|
"loss": 6.0784,
|
||
|
|
"mean_token_accuracy": 0.13751533553004264,
|
||
|
|
"num_tokens": 3209474.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228673076629638,
|
||
|
|
"epoch": 0.14432989690721648,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999502038941917,
|
||
|
|
"loss": 6.0466,
|
||
|
|
"mean_token_accuracy": 0.13530608788132667,
|
||
|
|
"num_tokens": 3218550.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159630537033081,
|
||
|
|
"epoch": 0.14471892627893407,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999496191164975,
|
||
|
|
"loss": 6.0135,
|
||
|
|
"mean_token_accuracy": 0.13874994069337845,
|
||
|
|
"num_tokens": 3227108.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.317847490310669,
|
||
|
|
"epoch": 0.14510795565065163,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499949030925551,
|
||
|
|
"loss": 6.0647,
|
||
|
|
"mean_token_accuracy": 0.13484866991639138,
|
||
|
|
"num_tokens": 3235785.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4040697574615475,
|
||
|
|
"epoch": 0.14549698502236919,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999484393213609,
|
||
|
|
"loss": 6.0958,
|
||
|
|
"mean_token_accuracy": 0.12889099717140198,
|
||
|
|
"num_tokens": 3244180.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.206935405731201,
|
||
|
|
"epoch": 0.14588601439408674,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999478443039363,
|
||
|
|
"loss": 5.966,
|
||
|
|
"mean_token_accuracy": 0.13705985099077225,
|
||
|
|
"num_tokens": 3253098.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.353375959396362,
|
||
|
|
"epoch": 0.14627504376580433,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999472458732862,
|
||
|
|
"loss": 6.0139,
|
||
|
|
"mean_token_accuracy": 0.1389046587049961,
|
||
|
|
"num_tokens": 3261726.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.185830402374267,
|
||
|
|
"epoch": 0.1466640731375219,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999466440294198,
|
||
|
|
"loss": 5.9819,
|
||
|
|
"mean_token_accuracy": 0.13572768047451972,
|
||
|
|
"num_tokens": 3270362.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255965852737427,
|
||
|
|
"epoch": 0.14705310250923945,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499946038772346,
|
||
|
|
"loss": 5.9745,
|
||
|
|
"mean_token_accuracy": 0.13993003964424133,
|
||
|
|
"num_tokens": 3278332.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.187082147598266,
|
||
|
|
"epoch": 0.147442131880957,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999454301020741,
|
||
|
|
"loss": 5.9432,
|
||
|
|
"mean_token_accuracy": 0.14198991358280183,
|
||
|
|
"num_tokens": 3286800.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.344804382324218,
|
||
|
|
"epoch": 0.14783116125267456,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999448180186133,
|
||
|
|
"loss": 6.181,
|
||
|
|
"mean_token_accuracy": 0.12529000788927078,
|
||
|
|
"num_tokens": 3296186.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.254264879226684,
|
||
|
|
"epoch": 0.14822019062439215,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000499944202521973,
|
||
|
|
"loss": 6.0373,
|
||
|
|
"mean_token_accuracy": 0.1428308829665184,
|
||
|
|
"num_tokens": 3303973.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.188289737701416,
|
||
|
|
"epoch": 0.1486092199961097,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999435836121624,
|
||
|
|
"loss": 5.9926,
|
||
|
|
"mean_token_accuracy": 0.13803835734724998,
|
||
|
|
"num_tokens": 3312550.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.331698322296143,
|
||
|
|
"epoch": 0.14899824936782727,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499942961289191,
|
||
|
|
"loss": 6.0628,
|
||
|
|
"mean_token_accuracy": 0.13561255410313605,
|
||
|
|
"num_tokens": 3321342.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1749297142028805,
|
||
|
|
"epoch": 0.14938727873954483,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999423355530683,
|
||
|
|
"loss": 5.9403,
|
||
|
|
"mean_token_accuracy": 0.14343732073903084,
|
||
|
|
"num_tokens": 3329293.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.156786012649536,
|
||
|
|
"epoch": 0.1497763081112624,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999417064038035,
|
||
|
|
"loss": 5.9966,
|
||
|
|
"mean_token_accuracy": 0.13348888084292412,
|
||
|
|
"num_tokens": 3338278.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.295070505142212,
|
||
|
|
"epoch": 0.15016533748297997,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999410738414065,
|
||
|
|
"loss": 6.1006,
|
||
|
|
"mean_token_accuracy": 0.1349467881023884,
|
||
|
|
"num_tokens": 3346757.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.215303182601929,
|
||
|
|
"epoch": 0.15055436685469753,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999404378658866,
|
||
|
|
"loss": 6.0975,
|
||
|
|
"mean_token_accuracy": 0.1362791948020458,
|
||
|
|
"num_tokens": 3355903.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2781799793243405,
|
||
|
|
"epoch": 0.1509433962264151,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999397984772536,
|
||
|
|
"loss": 6.0666,
|
||
|
|
"mean_token_accuracy": 0.1276647962629795,
|
||
|
|
"num_tokens": 3365440.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2379114627838135,
|
||
|
|
"epoch": 0.15133242559813265,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999391556755172,
|
||
|
|
"loss": 6.0323,
|
||
|
|
"mean_token_accuracy": 0.13651658967137337,
|
||
|
|
"num_tokens": 3373672.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2155702114105225,
|
||
|
|
"epoch": 0.15172145496985023,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999385094606872,
|
||
|
|
"loss": 6.0032,
|
||
|
|
"mean_token_accuracy": 0.1315799042582512,
|
||
|
|
"num_tokens": 3382733.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174511241912842,
|
||
|
|
"epoch": 0.1521104843415678,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999378598327733,
|
||
|
|
"loss": 5.9656,
|
||
|
|
"mean_token_accuracy": 0.13844937980175018,
|
||
|
|
"num_tokens": 3390842.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.256609535217285,
|
||
|
|
"epoch": 0.15249951371328535,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999372067917854,
|
||
|
|
"loss": 6.1149,
|
||
|
|
"mean_token_accuracy": 0.1254595175385475,
|
||
|
|
"num_tokens": 3399761.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.284492778778076,
|
||
|
|
"epoch": 0.1528885430850029,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999365503377335,
|
||
|
|
"loss": 6.0315,
|
||
|
|
"mean_token_accuracy": 0.13321302980184554,
|
||
|
|
"num_tokens": 3408986.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.235216522216797,
|
||
|
|
"epoch": 0.1532775724567205,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999358904706273,
|
||
|
|
"loss": 5.9892,
|
||
|
|
"mean_token_accuracy": 0.1353617176413536,
|
||
|
|
"num_tokens": 3418051.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.321955776214599,
|
||
|
|
"epoch": 0.15366660182843805,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999352271904771,
|
||
|
|
"loss": 6.0986,
|
||
|
|
"mean_token_accuracy": 0.13750415220856665,
|
||
|
|
"num_tokens": 3427185.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.196172285079956,
|
||
|
|
"epoch": 0.1540556312001556,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999345604972928,
|
||
|
|
"loss": 5.9939,
|
||
|
|
"mean_token_accuracy": 0.13660573363304138,
|
||
|
|
"num_tokens": 3435367.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193881511688232,
|
||
|
|
"epoch": 0.15444466057187317,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999338903910846,
|
||
|
|
"loss": 6.0341,
|
||
|
|
"mean_token_accuracy": 0.1360504299402237,
|
||
|
|
"num_tokens": 3443451.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.246865940093994,
|
||
|
|
"epoch": 0.15483368994359073,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999332168718626,
|
||
|
|
"loss": 6.0401,
|
||
|
|
"mean_token_accuracy": 0.1405157931149006,
|
||
|
|
"num_tokens": 3451038.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.464015769958496,
|
||
|
|
"epoch": 0.15522271931530832,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999325399396371,
|
||
|
|
"loss": 6.189,
|
||
|
|
"mean_token_accuracy": 0.12317560613155365,
|
||
|
|
"num_tokens": 3459693.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.344349575042725,
|
||
|
|
"epoch": 0.15561174868702587,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999318595944183,
|
||
|
|
"loss": 6.0573,
|
||
|
|
"mean_token_accuracy": 0.1302526354789734,
|
||
|
|
"num_tokens": 3468347.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2093932151794435,
|
||
|
|
"epoch": 0.15600077805874343,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999311758362166,
|
||
|
|
"loss": 6.041,
|
||
|
|
"mean_token_accuracy": 0.1344868026673794,
|
||
|
|
"num_tokens": 3476030.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173217630386352,
|
||
|
|
"epoch": 0.156389807430461,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999304886650422,
|
||
|
|
"loss": 6.0088,
|
||
|
|
"mean_token_accuracy": 0.1343566119670868,
|
||
|
|
"num_tokens": 3484840.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.339105176925659,
|
||
|
|
"epoch": 0.15677883680217858,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999297980809058,
|
||
|
|
"loss": 6.1002,
|
||
|
|
"mean_token_accuracy": 0.133415899425745,
|
||
|
|
"num_tokens": 3492662.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.286862468719482,
|
||
|
|
"epoch": 0.15716786617389614,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999291040838176,
|
||
|
|
"loss": 6.0174,
|
||
|
|
"mean_token_accuracy": 0.13295094966888427,
|
||
|
|
"num_tokens": 3501582.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.232885360717773,
|
||
|
|
"epoch": 0.1575568955456137,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999284066737884,
|
||
|
|
"loss": 6.0275,
|
||
|
|
"mean_token_accuracy": 0.1392024390399456,
|
||
|
|
"num_tokens": 3510141.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.297137260437012,
|
||
|
|
"epoch": 0.15794592491733125,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999277058508285,
|
||
|
|
"loss": 6.0623,
|
||
|
|
"mean_token_accuracy": 0.13623598217964172,
|
||
|
|
"num_tokens": 3518530.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16064453125,
|
||
|
|
"epoch": 0.1583349542890488,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999270016149486,
|
||
|
|
"loss": 6.0192,
|
||
|
|
"mean_token_accuracy": 0.1363525167107582,
|
||
|
|
"num_tokens": 3526815.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.216293525695801,
|
||
|
|
"epoch": 0.1587239836607664,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999262939661596,
|
||
|
|
"loss": 6.081,
|
||
|
|
"mean_token_accuracy": 0.13018166050314903,
|
||
|
|
"num_tokens": 3535840.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.298702955245972,
|
||
|
|
"epoch": 0.15911301303248396,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999255829044721,
|
||
|
|
"loss": 6.0981,
|
||
|
|
"mean_token_accuracy": 0.13071646615862847,
|
||
|
|
"num_tokens": 3544876.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.225747776031494,
|
||
|
|
"epoch": 0.15950204240420152,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999248684298968,
|
||
|
|
"loss": 5.8578,
|
||
|
|
"mean_token_accuracy": 0.1430135577917099,
|
||
|
|
"num_tokens": 3553018.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087709617614746,
|
||
|
|
"epoch": 0.15989107177591907,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999241505424447,
|
||
|
|
"loss": 5.9005,
|
||
|
|
"mean_token_accuracy": 0.13955418467521669,
|
||
|
|
"num_tokens": 3560909.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.183088874816894,
|
||
|
|
"epoch": 0.16028010114763663,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999234292421265,
|
||
|
|
"loss": 6.0498,
|
||
|
|
"mean_token_accuracy": 0.13545388653874396,
|
||
|
|
"num_tokens": 3569235.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154008436203003,
|
||
|
|
"epoch": 0.16066913051935422,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999227045289535,
|
||
|
|
"loss": 5.9139,
|
||
|
|
"mean_token_accuracy": 0.13975678011775017,
|
||
|
|
"num_tokens": 3577646.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173991012573242,
|
||
|
|
"epoch": 0.16105815989107178,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999219764029363,
|
||
|
|
"loss": 6.0213,
|
||
|
|
"mean_token_accuracy": 0.13489074483513833,
|
||
|
|
"num_tokens": 3586499.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.236517524719238,
|
||
|
|
"epoch": 0.16144718926278934,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999212448640861,
|
||
|
|
"loss": 6.0194,
|
||
|
|
"mean_token_accuracy": 0.13757209926843644,
|
||
|
|
"num_tokens": 3595391.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141875600814819,
|
||
|
|
"epoch": 0.1618362186345069,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999205099124141,
|
||
|
|
"loss": 5.9667,
|
||
|
|
"mean_token_accuracy": 0.1367950737476349,
|
||
|
|
"num_tokens": 3603774.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.297803211212158,
|
||
|
|
"epoch": 0.16222524800622448,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999197715479313,
|
||
|
|
"loss": 6.0216,
|
||
|
|
"mean_token_accuracy": 0.13554098531603814,
|
||
|
|
"num_tokens": 3611980.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2039124965667725,
|
||
|
|
"epoch": 0.16261427737794204,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999190297706489,
|
||
|
|
"loss": 5.942,
|
||
|
|
"mean_token_accuracy": 0.13699196204543113,
|
||
|
|
"num_tokens": 3620902.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3155577182769775,
|
||
|
|
"epoch": 0.1630033067496596,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999182845805783,
|
||
|
|
"loss": 6.2312,
|
||
|
|
"mean_token_accuracy": 0.12782860547304153,
|
||
|
|
"num_tokens": 3628924.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.297778558731079,
|
||
|
|
"epoch": 0.16339233612137716,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999175359777306,
|
||
|
|
"loss": 6.0695,
|
||
|
|
"mean_token_accuracy": 0.13167304024100304,
|
||
|
|
"num_tokens": 3637538.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203191900253296,
|
||
|
|
"epoch": 0.16378136549309472,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999167839621174,
|
||
|
|
"loss": 6.0779,
|
||
|
|
"mean_token_accuracy": 0.13191662728786469,
|
||
|
|
"num_tokens": 3646309.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213529634475708,
|
||
|
|
"epoch": 0.1641703948648123,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999160285337501,
|
||
|
|
"loss": 5.9364,
|
||
|
|
"mean_token_accuracy": 0.1367933377623558,
|
||
|
|
"num_tokens": 3655204.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21005539894104,
|
||
|
|
"epoch": 0.16455942423652986,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999152696926399,
|
||
|
|
"loss": 6.0641,
|
||
|
|
"mean_token_accuracy": 0.1300017297267914,
|
||
|
|
"num_tokens": 3663939.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.262974691390991,
|
||
|
|
"epoch": 0.16494845360824742,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999145074387985,
|
||
|
|
"loss": 6.0083,
|
||
|
|
"mean_token_accuracy": 0.13462101370096208,
|
||
|
|
"num_tokens": 3673167.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195592164993286,
|
||
|
|
"epoch": 0.16533748297996498,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999137417722374,
|
||
|
|
"loss": 5.9742,
|
||
|
|
"mean_token_accuracy": 0.13803649172186852,
|
||
|
|
"num_tokens": 3682234.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130123567581177,
|
||
|
|
"epoch": 0.16572651235168256,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999129726929684,
|
||
|
|
"loss": 5.9518,
|
||
|
|
"mean_token_accuracy": 0.13907736241817475,
|
||
|
|
"num_tokens": 3690835.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220533561706543,
|
||
|
|
"epoch": 0.16611554172340012,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999122002010029,
|
||
|
|
"loss": 6.0101,
|
||
|
|
"mean_token_accuracy": 0.1316205196082592,
|
||
|
|
"num_tokens": 3699348.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122845840454102,
|
||
|
|
"epoch": 0.16650457109511768,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999114242963527,
|
||
|
|
"loss": 5.924,
|
||
|
|
"mean_token_accuracy": 0.1415353387594223,
|
||
|
|
"num_tokens": 3708205.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129640579223633,
|
||
|
|
"epoch": 0.16689360046683524,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999106449790298,
|
||
|
|
"loss": 5.9912,
|
||
|
|
"mean_token_accuracy": 0.14246149584650994,
|
||
|
|
"num_tokens": 3717016.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.351011037826538,
|
||
|
|
"epoch": 0.1672826298385528,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999098622490458,
|
||
|
|
"loss": 6.0016,
|
||
|
|
"mean_token_accuracy": 0.13569031432271003,
|
||
|
|
"num_tokens": 3725509.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1818685054779055,
|
||
|
|
"epoch": 0.16767165921027039,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999090761064125,
|
||
|
|
"loss": 6.0751,
|
||
|
|
"mean_token_accuracy": 0.13177148699760438,
|
||
|
|
"num_tokens": 3734674.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140064430236817,
|
||
|
|
"epoch": 0.16806068858198794,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499908286551142,
|
||
|
|
"loss": 5.9012,
|
||
|
|
"mean_token_accuracy": 0.1402728170156479,
|
||
|
|
"num_tokens": 3742930.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.204311227798462,
|
||
|
|
"epoch": 0.1684497179537055,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999074935832463,
|
||
|
|
"loss": 5.9945,
|
||
|
|
"mean_token_accuracy": 0.13643383085727692,
|
||
|
|
"num_tokens": 3751314.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.266703701019287,
|
||
|
|
"epoch": 0.16883874732542306,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999066972027373,
|
||
|
|
"loss": 6.1046,
|
||
|
|
"mean_token_accuracy": 0.1291274093091488,
|
||
|
|
"num_tokens": 3760229.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.350693798065185,
|
||
|
|
"epoch": 0.16922777669714065,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999058974096271,
|
||
|
|
"loss": 6.1037,
|
||
|
|
"mean_token_accuracy": 0.13275526687502862,
|
||
|
|
"num_tokens": 3769037.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075402069091797,
|
||
|
|
"epoch": 0.1696168060688582,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499905094203928,
|
||
|
|
"loss": 5.9684,
|
||
|
|
"mean_token_accuracy": 0.14126176312565802,
|
||
|
|
"num_tokens": 3777686.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.287758302688599,
|
||
|
|
"epoch": 0.17000583544057576,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499904287585652,
|
||
|
|
"loss": 6.0575,
|
||
|
|
"mean_token_accuracy": 0.13231970369815826,
|
||
|
|
"num_tokens": 3786412.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2325122356414795,
|
||
|
|
"epoch": 0.17039486481229332,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999034775548113,
|
||
|
|
"loss": 6.091,
|
||
|
|
"mean_token_accuracy": 0.13756789192557334,
|
||
|
|
"num_tokens": 3794981.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184635210037231,
|
||
|
|
"epoch": 0.17078389418401088,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999026641114185,
|
||
|
|
"loss": 5.9679,
|
||
|
|
"mean_token_accuracy": 0.13785844221711158,
|
||
|
|
"num_tokens": 3803069.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228214073181152,
|
||
|
|
"epoch": 0.17117292355572847,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999018472554857,
|
||
|
|
"loss": 6.0562,
|
||
|
|
"mean_token_accuracy": 0.13657879456877708,
|
||
|
|
"num_tokens": 3811986.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255152368545533,
|
||
|
|
"epoch": 0.17156195292744603,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999010269870253,
|
||
|
|
"loss": 5.9669,
|
||
|
|
"mean_token_accuracy": 0.13384350910782813,
|
||
|
|
"num_tokens": 3820626.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.168890142440796,
|
||
|
|
"epoch": 0.17195098229916359,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999002033060498,
|
||
|
|
"loss": 5.9734,
|
||
|
|
"mean_token_accuracy": 0.14005149230360986,
|
||
|
|
"num_tokens": 3828608.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115287494659424,
|
||
|
|
"epoch": 0.17234001167088114,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998993762125716,
|
||
|
|
"loss": 5.9222,
|
||
|
|
"mean_token_accuracy": 0.1419154718518257,
|
||
|
|
"num_tokens": 3837059.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.196029186248779,
|
||
|
|
"epoch": 0.17272904104259873,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998985457066034,
|
||
|
|
"loss": 5.9477,
|
||
|
|
"mean_token_accuracy": 0.13308243378996848,
|
||
|
|
"num_tokens": 3845137.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.161190748214722,
|
||
|
|
"epoch": 0.1731180704143163,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998977117881576,
|
||
|
|
"loss": 5.9399,
|
||
|
|
"mean_token_accuracy": 0.14329548850655555,
|
||
|
|
"num_tokens": 3854012.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.076524972915649,
|
||
|
|
"epoch": 0.17350709978603385,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998968744572472,
|
||
|
|
"loss": 5.8859,
|
||
|
|
"mean_token_accuracy": 0.14090772867202758,
|
||
|
|
"num_tokens": 3862308.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084261083602906,
|
||
|
|
"epoch": 0.1738961291577514,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998960337138845,
|
||
|
|
"loss": 5.8224,
|
||
|
|
"mean_token_accuracy": 0.13599667102098464,
|
||
|
|
"num_tokens": 3870975.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.172693729400635,
|
||
|
|
"epoch": 0.17428515852946896,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998951895580826,
|
||
|
|
"loss": 5.9953,
|
||
|
|
"mean_token_accuracy": 0.1362786665558815,
|
||
|
|
"num_tokens": 3879621.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.119487714767456,
|
||
|
|
"epoch": 0.17467418790118655,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998943419898542,
|
||
|
|
"loss": 5.9608,
|
||
|
|
"mean_token_accuracy": 0.13740068078041076,
|
||
|
|
"num_tokens": 3889214.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195636940002442,
|
||
|
|
"epoch": 0.1750632172729041,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998934910092119,
|
||
|
|
"loss": 5.9972,
|
||
|
|
"mean_token_accuracy": 0.13837300091981888,
|
||
|
|
"num_tokens": 3898250.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.189534759521484,
|
||
|
|
"epoch": 0.17545224664462167,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998926366161689,
|
||
|
|
"loss": 6.0342,
|
||
|
|
"mean_token_accuracy": 0.13376041278243064,
|
||
|
|
"num_tokens": 3906971.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193826007843017,
|
||
|
|
"epoch": 0.17584127601633923,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004998917788107383,
|
||
|
|
"loss": 6.0622,
|
||
|
|
"mean_token_accuracy": 0.13532394245266915,
|
||
|
|
"num_tokens": 3916663.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.125564813613892,
|
||
|
|
"epoch": 0.17623030538805678,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998909175929326,
|
||
|
|
"loss": 5.9445,
|
||
|
|
"mean_token_accuracy": 0.13861310556530954,
|
||
|
|
"num_tokens": 3926848.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.110090446472168,
|
||
|
|
"epoch": 0.17661933475977437,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998900529627653,
|
||
|
|
"loss": 5.9132,
|
||
|
|
"mean_token_accuracy": 0.138637275993824,
|
||
|
|
"num_tokens": 3935729.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222514343261719,
|
||
|
|
"epoch": 0.17700836413149193,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998891849202495,
|
||
|
|
"loss": 5.9225,
|
||
|
|
"mean_token_accuracy": 0.13785927072167398,
|
||
|
|
"num_tokens": 3943408.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115485048294067,
|
||
|
|
"epoch": 0.1773973935032095,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499888313465398,
|
||
|
|
"loss": 5.8904,
|
||
|
|
"mean_token_accuracy": 0.13828733041882516,
|
||
|
|
"num_tokens": 3952473.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.189030885696411,
|
||
|
|
"epoch": 0.17778642287492705,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998874385982247,
|
||
|
|
"loss": 6.0584,
|
||
|
|
"mean_token_accuracy": 0.1308848187327385,
|
||
|
|
"num_tokens": 3960878.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.263873767852783,
|
||
|
|
"epoch": 0.17817545224664463,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998865603187421,
|
||
|
|
"loss": 6.0012,
|
||
|
|
"mean_token_accuracy": 0.13525196462869643,
|
||
|
|
"num_tokens": 3969282.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.142105340957642,
|
||
|
|
"epoch": 0.1785644816183622,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499885678626964,
|
||
|
|
"loss": 5.9793,
|
||
|
|
"mean_token_accuracy": 0.1365065097808838,
|
||
|
|
"num_tokens": 3978516.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130709075927735,
|
||
|
|
"epoch": 0.17895351099007975,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998847935229038,
|
||
|
|
"loss": 5.8469,
|
||
|
|
"mean_token_accuracy": 0.14624039083719254,
|
||
|
|
"num_tokens": 3986580.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984261894226075,
|
||
|
|
"epoch": 0.1793425403617973,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998839050065746,
|
||
|
|
"loss": 5.8505,
|
||
|
|
"mean_token_accuracy": 0.1426392376422882,
|
||
|
|
"num_tokens": 3995144.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.117937326431274,
|
||
|
|
"epoch": 0.17973156973351487,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998830130779902,
|
||
|
|
"loss": 5.8539,
|
||
|
|
"mean_token_accuracy": 0.13852243572473527,
|
||
|
|
"num_tokens": 4003887.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.178174209594727,
|
||
|
|
"epoch": 0.18012059910523245,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499882117737164,
|
||
|
|
"loss": 5.9577,
|
||
|
|
"mean_token_accuracy": 0.13900213465094566,
|
||
|
|
"num_tokens": 4012607.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.117289209365845,
|
||
|
|
"epoch": 0.18050962847695,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998812189841096,
|
||
|
|
"loss": 6.0434,
|
||
|
|
"mean_token_accuracy": 0.13420895710587502,
|
||
|
|
"num_tokens": 4021950.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.188327360153198,
|
||
|
|
"epoch": 0.18089865784866757,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998803168188407,
|
||
|
|
"loss": 6.0003,
|
||
|
|
"mean_token_accuracy": 0.1396230697631836,
|
||
|
|
"num_tokens": 4031076.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.050243377685547,
|
||
|
|
"epoch": 0.18128768722038513,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998794112413708,
|
||
|
|
"loss": 5.8423,
|
||
|
|
"mean_token_accuracy": 0.14782028794288635,
|
||
|
|
"num_tokens": 4040414.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248169994354248,
|
||
|
|
"epoch": 0.18167671659210272,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998785022517137,
|
||
|
|
"loss": 5.9386,
|
||
|
|
"mean_token_accuracy": 0.14150765910744667,
|
||
|
|
"num_tokens": 4048931.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986580514907837,
|
||
|
|
"epoch": 0.18206574596382027,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998775898498835,
|
||
|
|
"loss": 5.8367,
|
||
|
|
"mean_token_accuracy": 0.14155064076185225,
|
||
|
|
"num_tokens": 4057688.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074233341217041,
|
||
|
|
"epoch": 0.18245477533553783,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998766740358936,
|
||
|
|
"loss": 5.9449,
|
||
|
|
"mean_token_accuracy": 0.1420542173087597,
|
||
|
|
"num_tokens": 4066365.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.13965334892273,
|
||
|
|
"epoch": 0.1828438047072554,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998757548097582,
|
||
|
|
"loss": 5.8541,
|
||
|
|
"mean_token_accuracy": 0.14332376196980476,
|
||
|
|
"num_tokens": 4075136.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134494304656982,
|
||
|
|
"epoch": 0.18323283407897295,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998748321714911,
|
||
|
|
"loss": 5.9524,
|
||
|
|
"mean_token_accuracy": 0.14317325055599212,
|
||
|
|
"num_tokens": 4083337.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.069387912750244,
|
||
|
|
"epoch": 0.18362186345069054,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998739061211065,
|
||
|
|
"loss": 5.899,
|
||
|
|
"mean_token_accuracy": 0.1406087227165699,
|
||
|
|
"num_tokens": 4091201.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1495448589324955,
|
||
|
|
"epoch": 0.1840108928224081,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998729766586181,
|
||
|
|
"loss": 5.9458,
|
||
|
|
"mean_token_accuracy": 0.1404791608452797,
|
||
|
|
"num_tokens": 4099480.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.029800033569336,
|
||
|
|
"epoch": 0.18439992219412565,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998720437840403,
|
||
|
|
"loss": 5.8555,
|
||
|
|
"mean_token_accuracy": 0.14272842854261397,
|
||
|
|
"num_tokens": 4108151.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.009803676605225,
|
||
|
|
"epoch": 0.1847889515658432,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004998711074973871,
|
||
|
|
"loss": 5.8595,
|
||
|
|
"mean_token_accuracy": 0.14537928998470306,
|
||
|
|
"num_tokens": 4117380.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103708982467651,
|
||
|
|
"epoch": 0.1851779809375608,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998701677986728,
|
||
|
|
"loss": 5.9192,
|
||
|
|
"mean_token_accuracy": 0.14413200244307517,
|
||
|
|
"num_tokens": 4126757.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091351890563965,
|
||
|
|
"epoch": 0.18556701030927836,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998692246879116,
|
||
|
|
"loss": 5.832,
|
||
|
|
"mean_token_accuracy": 0.14118036180734633,
|
||
|
|
"num_tokens": 4135326.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083584976196289,
|
||
|
|
"epoch": 0.18595603968099592,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998682781651178,
|
||
|
|
"loss": 5.8502,
|
||
|
|
"mean_token_accuracy": 0.15047699064016343,
|
||
|
|
"num_tokens": 4143624.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039449691772461,
|
||
|
|
"epoch": 0.18634506905271347,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998673282303059,
|
||
|
|
"loss": 5.8032,
|
||
|
|
"mean_token_accuracy": 0.14633125066757202,
|
||
|
|
"num_tokens": 4152193.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093126678466797,
|
||
|
|
"epoch": 0.18673409842443103,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998663748834901,
|
||
|
|
"loss": 5.9333,
|
||
|
|
"mean_token_accuracy": 0.14173089787364007,
|
||
|
|
"num_tokens": 4160614.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195434331893921,
|
||
|
|
"epoch": 0.18712312779614862,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998654181246851,
|
||
|
|
"loss": 5.9525,
|
||
|
|
"mean_token_accuracy": 0.1426502361893654,
|
||
|
|
"num_tokens": 4168715.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14034595489502,
|
||
|
|
"epoch": 0.18751215716786618,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998644579539052,
|
||
|
|
"loss": 5.9903,
|
||
|
|
"mean_token_accuracy": 0.14057205021381378,
|
||
|
|
"num_tokens": 4176676.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11949610710144,
|
||
|
|
"epoch": 0.18790118653958374,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499863494371165,
|
||
|
|
"loss": 5.9666,
|
||
|
|
"mean_token_accuracy": 0.13880052268505097,
|
||
|
|
"num_tokens": 4185613.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.10061502456665,
|
||
|
|
"epoch": 0.1882902159113013,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998625273764793,
|
||
|
|
"loss": 5.9744,
|
||
|
|
"mean_token_accuracy": 0.14042351245880128,
|
||
|
|
"num_tokens": 4193985.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.119175815582276,
|
||
|
|
"epoch": 0.18867924528301888,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998615569698626,
|
||
|
|
"loss": 5.8692,
|
||
|
|
"mean_token_accuracy": 0.14560523852705956,
|
||
|
|
"num_tokens": 4202713.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.20410122871399,
|
||
|
|
"epoch": 0.18906827465473644,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998605831513296,
|
||
|
|
"loss": 5.9982,
|
||
|
|
"mean_token_accuracy": 0.13526586964726448,
|
||
|
|
"num_tokens": 4210858.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.077843475341797,
|
||
|
|
"epoch": 0.189457304026454,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998596059208953,
|
||
|
|
"loss": 5.9232,
|
||
|
|
"mean_token_accuracy": 0.1438886322081089,
|
||
|
|
"num_tokens": 4219570.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070500183105469,
|
||
|
|
"epoch": 0.18984633339817156,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998586252785743,
|
||
|
|
"loss": 5.8362,
|
||
|
|
"mean_token_accuracy": 0.14419551193714142,
|
||
|
|
"num_tokens": 4228026.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.118373966217041,
|
||
|
|
"epoch": 0.19023536276988912,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998576412243816,
|
||
|
|
"loss": 5.8484,
|
||
|
|
"mean_token_accuracy": 0.14332474917173385,
|
||
|
|
"num_tokens": 4235993.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020765161514282,
|
||
|
|
"epoch": 0.1906243921416067,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998566537583321,
|
||
|
|
"loss": 5.8452,
|
||
|
|
"mean_token_accuracy": 0.1450585328042507,
|
||
|
|
"num_tokens": 4244225.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020392990112304,
|
||
|
|
"epoch": 0.19101342151332426,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998556628804408,
|
||
|
|
"loss": 5.8412,
|
||
|
|
"mean_token_accuracy": 0.14568918645381929,
|
||
|
|
"num_tokens": 4252989.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1407276630401615,
|
||
|
|
"epoch": 0.19140245088504182,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998546685907225,
|
||
|
|
"loss": 5.8736,
|
||
|
|
"mean_token_accuracy": 0.1443709298968315,
|
||
|
|
"num_tokens": 4261297.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14323468208313,
|
||
|
|
"epoch": 0.19179148025675938,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998536708891927,
|
||
|
|
"loss": 6.0037,
|
||
|
|
"mean_token_accuracy": 0.13726148158311843,
|
||
|
|
"num_tokens": 4270299.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137307929992676,
|
||
|
|
"epoch": 0.19218050962847694,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004998526697758663,
|
||
|
|
"loss": 6.0186,
|
||
|
|
"mean_token_accuracy": 0.13181870952248573,
|
||
|
|
"num_tokens": 4279662.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.12540340423584,
|
||
|
|
"epoch": 0.19256953900019452,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998516652507585,
|
||
|
|
"loss": 5.8237,
|
||
|
|
"mean_token_accuracy": 0.14710504859685897,
|
||
|
|
"num_tokens": 4287876.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.082257652282715,
|
||
|
|
"epoch": 0.19295856837191208,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998506573138846,
|
||
|
|
"loss": 5.9652,
|
||
|
|
"mean_token_accuracy": 0.1425960034132004,
|
||
|
|
"num_tokens": 4296415.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0256585597991945,
|
||
|
|
"epoch": 0.19334759774362964,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998496459652598,
|
||
|
|
"loss": 5.7941,
|
||
|
|
"mean_token_accuracy": 0.14723251685500144,
|
||
|
|
"num_tokens": 4304434.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094099235534668,
|
||
|
|
"epoch": 0.1937366271153472,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998486312048995,
|
||
|
|
"loss": 5.9742,
|
||
|
|
"mean_token_accuracy": 0.1384941779077053,
|
||
|
|
"num_tokens": 4313266.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093673992156982,
|
||
|
|
"epoch": 0.19412565648706478,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998476130328193,
|
||
|
|
"loss": 5.8438,
|
||
|
|
"mean_token_accuracy": 0.14551946073770522,
|
||
|
|
"num_tokens": 4322121.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.059762907028198,
|
||
|
|
"epoch": 0.19451468585878234,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998465914490343,
|
||
|
|
"loss": 5.8574,
|
||
|
|
"mean_token_accuracy": 0.1456399142742157,
|
||
|
|
"num_tokens": 4330596.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101912212371826,
|
||
|
|
"epoch": 0.1949037152304999,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00049984556645356,
|
||
|
|
"loss": 5.9538,
|
||
|
|
"mean_token_accuracy": 0.14571308046579362,
|
||
|
|
"num_tokens": 4337779.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113310956954956,
|
||
|
|
"epoch": 0.19529274460221746,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998445380464124,
|
||
|
|
"loss": 5.7871,
|
||
|
|
"mean_token_accuracy": 0.14770737588405608,
|
||
|
|
"num_tokens": 4346623.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010924863815307,
|
||
|
|
"epoch": 0.19568177397393502,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998435062276066,
|
||
|
|
"loss": 5.8965,
|
||
|
|
"mean_token_accuracy": 0.14267725944519044,
|
||
|
|
"num_tokens": 4355435.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1819150924682615,
|
||
|
|
"epoch": 0.1960708033456526,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998424709971586,
|
||
|
|
"loss": 5.9427,
|
||
|
|
"mean_token_accuracy": 0.14011435583233833,
|
||
|
|
"num_tokens": 4363636.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994958448410034,
|
||
|
|
"epoch": 0.19645983271737016,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998414323550839,
|
||
|
|
"loss": 5.7574,
|
||
|
|
"mean_token_accuracy": 0.1514812633395195,
|
||
|
|
"num_tokens": 4372337.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.082412195205689,
|
||
|
|
"epoch": 0.19684886208908772,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998403903013984,
|
||
|
|
"loss": 5.8105,
|
||
|
|
"mean_token_accuracy": 0.14721191674470901,
|
||
|
|
"num_tokens": 4380528.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.050493812561035,
|
||
|
|
"epoch": 0.19723789146080528,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998393448361179,
|
||
|
|
"loss": 5.8969,
|
||
|
|
"mean_token_accuracy": 0.13829589858651162,
|
||
|
|
"num_tokens": 4389464.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.092096662521362,
|
||
|
|
"epoch": 0.19762692083252287,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499838295959258,
|
||
|
|
"loss": 5.9541,
|
||
|
|
"mean_token_accuracy": 0.13610536456108094,
|
||
|
|
"num_tokens": 4397879.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115645837783814,
|
||
|
|
"epoch": 0.19801595020424043,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499837243670835,
|
||
|
|
"loss": 5.965,
|
||
|
|
"mean_token_accuracy": 0.14079206734895705,
|
||
|
|
"num_tokens": 4406145.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.108259153366089,
|
||
|
|
"epoch": 0.19840497957595798,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998361879708646,
|
||
|
|
"loss": 5.8727,
|
||
|
|
"mean_token_accuracy": 0.1402936451137066,
|
||
|
|
"num_tokens": 4415480.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.099182176589966,
|
||
|
|
"epoch": 0.19879400894767554,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499835128859363,
|
||
|
|
"loss": 5.8755,
|
||
|
|
"mean_token_accuracy": 0.1442495122551918,
|
||
|
|
"num_tokens": 4423355.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.018963813781738,
|
||
|
|
"epoch": 0.1991830383193931,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998340663363461,
|
||
|
|
"loss": 5.7746,
|
||
|
|
"mean_token_accuracy": 0.14996073246002198,
|
||
|
|
"num_tokens": 4432059.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011700248718261,
|
||
|
|
"epoch": 0.1995720676911107,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998330004018301,
|
||
|
|
"loss": 5.8663,
|
||
|
|
"mean_token_accuracy": 0.13528765514492988,
|
||
|
|
"num_tokens": 4441146.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02707347869873,
|
||
|
|
"epoch": 0.19996109706282825,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998319310558312,
|
||
|
|
"loss": 5.7046,
|
||
|
|
"mean_token_accuracy": 0.1531302809715271,
|
||
|
|
"num_tokens": 4448553.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.865385389328003,
|
||
|
|
"epoch": 0.2003501264345458,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998308582983657,
|
||
|
|
"loss": 5.785,
|
||
|
|
"mean_token_accuracy": 0.1515739530324936,
|
||
|
|
"num_tokens": 4456930.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159365510940551,
|
||
|
|
"epoch": 0.20073915580626336,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998297821294497,
|
||
|
|
"loss": 5.9856,
|
||
|
|
"mean_token_accuracy": 0.1445264369249344,
|
||
|
|
"num_tokens": 4464932.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066826963424683,
|
||
|
|
"epoch": 0.20112818517798095,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998287025490995,
|
||
|
|
"loss": 5.7073,
|
||
|
|
"mean_token_accuracy": 0.15195650979876518,
|
||
|
|
"num_tokens": 4473695.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.915977334976196,
|
||
|
|
"epoch": 0.2015172145496985,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998276195573317,
|
||
|
|
"loss": 5.9426,
|
||
|
|
"mean_token_accuracy": 0.1366700403392315,
|
||
|
|
"num_tokens": 4483375.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159323358535767,
|
||
|
|
"epoch": 0.20190624392141607,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998265331541627,
|
||
|
|
"loss": 5.9638,
|
||
|
|
"mean_token_accuracy": 0.13707406520843507,
|
||
|
|
"num_tokens": 4491695.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056016826629639,
|
||
|
|
"epoch": 0.20229527329313363,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998254433396088,
|
||
|
|
"loss": 5.9221,
|
||
|
|
"mean_token_accuracy": 0.14026020020246505,
|
||
|
|
"num_tokens": 4500361.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072783470153809,
|
||
|
|
"epoch": 0.20268430266485118,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998243501136867,
|
||
|
|
"loss": 5.8419,
|
||
|
|
"mean_token_accuracy": 0.1397676981985569,
|
||
|
|
"num_tokens": 4509368.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088675785064697,
|
||
|
|
"epoch": 0.20307333203656877,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998232534764129,
|
||
|
|
"loss": 5.8232,
|
||
|
|
"mean_token_accuracy": 0.14180155843496323,
|
||
|
|
"num_tokens": 4518146.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058323574066162,
|
||
|
|
"epoch": 0.20346236140828633,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998221534278041,
|
||
|
|
"loss": 5.8875,
|
||
|
|
"mean_token_accuracy": 0.13800363019108772,
|
||
|
|
"num_tokens": 4526128.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.097913789749145,
|
||
|
|
"epoch": 0.2038513907800039,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998210499678769,
|
||
|
|
"loss": 5.9263,
|
||
|
|
"mean_token_accuracy": 0.14337622076272966,
|
||
|
|
"num_tokens": 4534724.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008050632476807,
|
||
|
|
"epoch": 0.20424042015172145,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998199430966481,
|
||
|
|
"loss": 5.7847,
|
||
|
|
"mean_token_accuracy": 0.14045033752918243,
|
||
|
|
"num_tokens": 4543725.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033035039901733,
|
||
|
|
"epoch": 0.20462944952343903,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998188328141346,
|
||
|
|
"loss": 5.8689,
|
||
|
|
"mean_token_accuracy": 0.14495224952697755,
|
||
|
|
"num_tokens": 4551758.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990800094604492,
|
||
|
|
"epoch": 0.2050184788951566,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998177191203531,
|
||
|
|
"loss": 5.7433,
|
||
|
|
"mean_token_accuracy": 0.15320585817098617,
|
||
|
|
"num_tokens": 4559990.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993824911117554,
|
||
|
|
"epoch": 0.20540750826687415,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998166020153204,
|
||
|
|
"loss": 5.793,
|
||
|
|
"mean_token_accuracy": 0.1404377117753029,
|
||
|
|
"num_tokens": 4568651.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941356039047241,
|
||
|
|
"epoch": 0.2057965376385917,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998154814990538,
|
||
|
|
"loss": 5.722,
|
||
|
|
"mean_token_accuracy": 0.15070193260908127,
|
||
|
|
"num_tokens": 4577981.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004185390472412,
|
||
|
|
"epoch": 0.20618556701030927,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00049981435757157,
|
||
|
|
"loss": 5.882,
|
||
|
|
"mean_token_accuracy": 0.1453938066959381,
|
||
|
|
"num_tokens": 4586480.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.035228633880616,
|
||
|
|
"epoch": 0.20657459638202685,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998132302328862,
|
||
|
|
"loss": 5.7768,
|
||
|
|
"mean_token_accuracy": 0.1519497200846672,
|
||
|
|
"num_tokens": 4595554.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000116539001465,
|
||
|
|
"epoch": 0.2069636257537444,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998120994830195,
|
||
|
|
"loss": 5.7928,
|
||
|
|
"mean_token_accuracy": 0.14965005293488504,
|
||
|
|
"num_tokens": 4604091.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103025817871094,
|
||
|
|
"epoch": 0.20735265512546197,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499810965321987,
|
||
|
|
"loss": 5.9041,
|
||
|
|
"mean_token_accuracy": 0.14321340918540953,
|
||
|
|
"num_tokens": 4612603.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094974136352539,
|
||
|
|
"epoch": 0.20774168449717953,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998098277498059,
|
||
|
|
"loss": 5.8089,
|
||
|
|
"mean_token_accuracy": 0.14330320209264755,
|
||
|
|
"num_tokens": 4621041.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965013837814331,
|
||
|
|
"epoch": 0.2081307138688971,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998086867664934,
|
||
|
|
"loss": 5.8381,
|
||
|
|
"mean_token_accuracy": 0.1479259341955185,
|
||
|
|
"num_tokens": 4629849.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067577695846557,
|
||
|
|
"epoch": 0.20851974324061467,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000499807542372067,
|
||
|
|
"loss": 5.9079,
|
||
|
|
"mean_token_accuracy": 0.14189650267362594,
|
||
|
|
"num_tokens": 4639426.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020753288269043,
|
||
|
|
"epoch": 0.20890877261233223,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998063945665439,
|
||
|
|
"loss": 5.8312,
|
||
|
|
"mean_token_accuracy": 0.14925678074359894,
|
||
|
|
"num_tokens": 4647257.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024092960357666,
|
||
|
|
"epoch": 0.2092978019840498,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998052433499416,
|
||
|
|
"loss": 5.8148,
|
||
|
|
"mean_token_accuracy": 0.14485211595892905,
|
||
|
|
"num_tokens": 4655773.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031063079833984,
|
||
|
|
"epoch": 0.20968683135576735,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998040887222776,
|
||
|
|
"loss": 5.844,
|
||
|
|
"mean_token_accuracy": 0.14211719036102294,
|
||
|
|
"num_tokens": 4664292.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070610380172729,
|
||
|
|
"epoch": 0.21007586072748494,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998029306835693,
|
||
|
|
"loss": 5.8802,
|
||
|
|
"mean_token_accuracy": 0.14487007558345794,
|
||
|
|
"num_tokens": 4672774.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192492723464966,
|
||
|
|
"epoch": 0.2104648900992025,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998017692338344,
|
||
|
|
"loss": 6.0024,
|
||
|
|
"mean_token_accuracy": 0.13652608394622803,
|
||
|
|
"num_tokens": 4681855.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003230619430542,
|
||
|
|
"epoch": 0.21085391947092005,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998006043730905,
|
||
|
|
"loss": 5.7837,
|
||
|
|
"mean_token_accuracy": 0.15081765204668046,
|
||
|
|
"num_tokens": 4689771.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.06316032409668,
|
||
|
|
"epoch": 0.2112429488426376,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997994361013551,
|
||
|
|
"loss": 5.9318,
|
||
|
|
"mean_token_accuracy": 0.13612701371312141,
|
||
|
|
"num_tokens": 4698808.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027731704711914,
|
||
|
|
"epoch": 0.21163197821435517,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997982644186461,
|
||
|
|
"loss": 5.8201,
|
||
|
|
"mean_token_accuracy": 0.1442001700401306,
|
||
|
|
"num_tokens": 4707627.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994128227233887,
|
||
|
|
"epoch": 0.21202100758607276,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997970893249813,
|
||
|
|
"loss": 5.8134,
|
||
|
|
"mean_token_accuracy": 0.1453290104866028,
|
||
|
|
"num_tokens": 4716091.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026619577407837,
|
||
|
|
"epoch": 0.21241003695779032,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997959108203785,
|
||
|
|
"loss": 5.8173,
|
||
|
|
"mean_token_accuracy": 0.14737472012639047,
|
||
|
|
"num_tokens": 4724042.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.927079200744629,
|
||
|
|
"epoch": 0.21279906632950787,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997947289048554,
|
||
|
|
"loss": 5.7431,
|
||
|
|
"mean_token_accuracy": 0.15547642409801482,
|
||
|
|
"num_tokens": 4731745.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977909660339355,
|
||
|
|
"epoch": 0.21318809570122543,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997935435784302,
|
||
|
|
"loss": 5.9151,
|
||
|
|
"mean_token_accuracy": 0.14134541749954224,
|
||
|
|
"num_tokens": 4740386.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.097658681869507,
|
||
|
|
"epoch": 0.21357712507294302,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997923548411208,
|
||
|
|
"loss": 5.9154,
|
||
|
|
"mean_token_accuracy": 0.14041005820035934,
|
||
|
|
"num_tokens": 4749809.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157984495162964,
|
||
|
|
"epoch": 0.21396615444466058,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499791162692945,
|
||
|
|
"loss": 6.0245,
|
||
|
|
"mean_token_accuracy": 0.13882595300674438,
|
||
|
|
"num_tokens": 4759507.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020778369903565,
|
||
|
|
"epoch": 0.21435518381637814,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997899671339214,
|
||
|
|
"loss": 5.7893,
|
||
|
|
"mean_token_accuracy": 0.1458857201039791,
|
||
|
|
"num_tokens": 4768793.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058682203292847,
|
||
|
|
"epoch": 0.2147442131880957,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997887681640675,
|
||
|
|
"loss": 5.9431,
|
||
|
|
"mean_token_accuracy": 0.14112222120165824,
|
||
|
|
"num_tokens": 4777344.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091257619857788,
|
||
|
|
"epoch": 0.21513324255981325,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997875657834021,
|
||
|
|
"loss": 5.859,
|
||
|
|
"mean_token_accuracy": 0.1439730390906334,
|
||
|
|
"num_tokens": 4785934.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021985816955566,
|
||
|
|
"epoch": 0.21552227193153084,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997863599919432,
|
||
|
|
"loss": 5.8154,
|
||
|
|
"mean_token_accuracy": 0.1487823836505413,
|
||
|
|
"num_tokens": 4794889.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963295888900757,
|
||
|
|
"epoch": 0.2159113013032484,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997851507897089,
|
||
|
|
"loss": 5.9177,
|
||
|
|
"mean_token_accuracy": 0.1420752465724945,
|
||
|
|
"num_tokens": 4803597.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021999406814575,
|
||
|
|
"epoch": 0.21630033067496596,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997839381767178,
|
||
|
|
"loss": 5.7093,
|
||
|
|
"mean_token_accuracy": 0.14998439997434615,
|
||
|
|
"num_tokens": 4812706.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942576360702515,
|
||
|
|
"epoch": 0.21668936004668352,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997827221529882,
|
||
|
|
"loss": 5.7645,
|
||
|
|
"mean_token_accuracy": 0.14373311623930932,
|
||
|
|
"num_tokens": 4821790.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044412851333618,
|
||
|
|
"epoch": 0.2170783894184011,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004997815027185386,
|
||
|
|
"loss": 5.8268,
|
||
|
|
"mean_token_accuracy": 0.14614877104759216,
|
||
|
|
"num_tokens": 4830123.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031355142593384,
|
||
|
|
"epoch": 0.21746741879011866,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997802798733874,
|
||
|
|
"loss": 5.7584,
|
||
|
|
"mean_token_accuracy": 0.14889259934425353,
|
||
|
|
"num_tokens": 4838066.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985014152526856,
|
||
|
|
"epoch": 0.21785644816183622,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997790536175534,
|
||
|
|
"loss": 5.8295,
|
||
|
|
"mean_token_accuracy": 0.1473879933357239,
|
||
|
|
"num_tokens": 4846877.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0131855487823485,
|
||
|
|
"epoch": 0.21824547753355378,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004997778239510548,
|
||
|
|
"loss": 5.8809,
|
||
|
|
"mean_token_accuracy": 0.13904760181903839,
|
||
|
|
"num_tokens": 4856960.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0483003616333,
|
||
|
|
"epoch": 0.21863450690527134,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997765908739106,
|
||
|
|
"loss": 5.8844,
|
||
|
|
"mean_token_accuracy": 0.1458500951528549,
|
||
|
|
"num_tokens": 4865440.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985370063781739,
|
||
|
|
"epoch": 0.21902353627698892,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997753543861395,
|
||
|
|
"loss": 5.7839,
|
||
|
|
"mean_token_accuracy": 0.1455774076282978,
|
||
|
|
"num_tokens": 4874187.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1545000076293945,
|
||
|
|
"epoch": 0.21941256564870648,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00049977411448776,
|
||
|
|
"loss": 5.9234,
|
||
|
|
"mean_token_accuracy": 0.13685425370931625,
|
||
|
|
"num_tokens": 4883151.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033831405639648,
|
||
|
|
"epoch": 0.21980159502042404,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997728711787912,
|
||
|
|
"loss": 5.8376,
|
||
|
|
"mean_token_accuracy": 0.14152983725070953,
|
||
|
|
"num_tokens": 4890968.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.948618221282959,
|
||
|
|
"epoch": 0.2201906243921416,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004997716244592518,
|
||
|
|
"loss": 5.7224,
|
||
|
|
"mean_token_accuracy": 0.15324778854846954,
|
||
|
|
"num_tokens": 4899389.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.957552099227906,
|
||
|
|
"epoch": 0.22057965376385918,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997703743291607,
|
||
|
|
"loss": 5.7836,
|
||
|
|
"mean_token_accuracy": 0.15218881666660308,
|
||
|
|
"num_tokens": 4907622.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971472644805909,
|
||
|
|
"epoch": 0.22096868313557674,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000499769120788537,
|
||
|
|
"loss": 5.7855,
|
||
|
|
"mean_token_accuracy": 0.14718300998210906,
|
||
|
|
"num_tokens": 4916151.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953951168060303,
|
||
|
|
"epoch": 0.2213577125072943,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997678638373995,
|
||
|
|
"loss": 5.6926,
|
||
|
|
"mean_token_accuracy": 0.1555492803454399,
|
||
|
|
"num_tokens": 4923938.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977941274642944,
|
||
|
|
"epoch": 0.22174674187901186,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997666034757676,
|
||
|
|
"loss": 5.8041,
|
||
|
|
"mean_token_accuracy": 0.15950555503368377,
|
||
|
|
"num_tokens": 4932027.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992272996902466,
|
||
|
|
"epoch": 0.22213577125072942,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997653397036603,
|
||
|
|
"loss": 5.8234,
|
||
|
|
"mean_token_accuracy": 0.15327517986297606,
|
||
|
|
"num_tokens": 4940229.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.946475648880005,
|
||
|
|
"epoch": 0.222524800622447,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997640725210965,
|
||
|
|
"loss": 5.8766,
|
||
|
|
"mean_token_accuracy": 0.1445116177201271,
|
||
|
|
"num_tokens": 4948662.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985954427719117,
|
||
|
|
"epoch": 0.22291382999416456,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997628019280958,
|
||
|
|
"loss": 5.8304,
|
||
|
|
"mean_token_accuracy": 0.14730205610394478,
|
||
|
|
"num_tokens": 4956847.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0246001243591305,
|
||
|
|
"epoch": 0.22330285936588212,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997615279246773,
|
||
|
|
"loss": 5.7519,
|
||
|
|
"mean_token_accuracy": 0.14672646746039392,
|
||
|
|
"num_tokens": 4965139.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093596029281616,
|
||
|
|
"epoch": 0.22369188873759968,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997602505108603,
|
||
|
|
"loss": 5.9346,
|
||
|
|
"mean_token_accuracy": 0.1362128235399723,
|
||
|
|
"num_tokens": 4973671.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992952871322632,
|
||
|
|
"epoch": 0.22408091810931724,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997589696866644,
|
||
|
|
"loss": 5.7985,
|
||
|
|
"mean_token_accuracy": 0.14313325881958008,
|
||
|
|
"num_tokens": 4981970.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994722890853882,
|
||
|
|
"epoch": 0.22446994748103483,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997576854521088,
|
||
|
|
"loss": 5.8276,
|
||
|
|
"mean_token_accuracy": 0.14740151315927505,
|
||
|
|
"num_tokens": 4990591.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008001279830933,
|
||
|
|
"epoch": 0.22485897685275238,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499756397807213,
|
||
|
|
"loss": 5.8338,
|
||
|
|
"mean_token_accuracy": 0.1426657348871231,
|
||
|
|
"num_tokens": 4999623.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0818774700164795,
|
||
|
|
"epoch": 0.22524800622446994,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997551067519966,
|
||
|
|
"loss": 5.8912,
|
||
|
|
"mean_token_accuracy": 0.13916059359908103,
|
||
|
|
"num_tokens": 5008387.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989216756820679,
|
||
|
|
"epoch": 0.2256370355961875,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997538122864792,
|
||
|
|
"loss": 5.8194,
|
||
|
|
"mean_token_accuracy": 0.14748692139983177,
|
||
|
|
"num_tokens": 5016788.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08019700050354,
|
||
|
|
"epoch": 0.2260260649679051,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997525144106804,
|
||
|
|
"loss": 5.8442,
|
||
|
|
"mean_token_accuracy": 0.14615625888109207,
|
||
|
|
"num_tokens": 5025508.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974547910690307,
|
||
|
|
"epoch": 0.22641509433962265,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00049975121312462,
|
||
|
|
"loss": 5.8181,
|
||
|
|
"mean_token_accuracy": 0.14417650923132896,
|
||
|
|
"num_tokens": 5035081.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942454242706299,
|
||
|
|
"epoch": 0.2268041237113402,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997499084283177,
|
||
|
|
"loss": 5.7548,
|
||
|
|
"mean_token_accuracy": 0.15317937284708022,
|
||
|
|
"num_tokens": 5043655.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.948886728286743,
|
||
|
|
"epoch": 0.22719315308305776,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997486003217932,
|
||
|
|
"loss": 5.7784,
|
||
|
|
"mean_token_accuracy": 0.14860536009073258,
|
||
|
|
"num_tokens": 5052080.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9562623500823975,
|
||
|
|
"epoch": 0.22758218245477532,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997472888050664,
|
||
|
|
"loss": 5.7576,
|
||
|
|
"mean_token_accuracy": 0.15349135398864747,
|
||
|
|
"num_tokens": 5061325.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030727291107178,
|
||
|
|
"epoch": 0.2279712118264929,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997459738781573,
|
||
|
|
"loss": 5.8539,
|
||
|
|
"mean_token_accuracy": 0.14812101200222969,
|
||
|
|
"num_tokens": 5069461.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0146770000457765,
|
||
|
|
"epoch": 0.22836024119821047,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997446555410857,
|
||
|
|
"loss": 5.8223,
|
||
|
|
"mean_token_accuracy": 0.14278532564640045,
|
||
|
|
"num_tokens": 5077747.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042302083969116,
|
||
|
|
"epoch": 0.22874927056992803,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997433337938716,
|
||
|
|
"loss": 5.8714,
|
||
|
|
"mean_token_accuracy": 0.15094365030527115,
|
||
|
|
"num_tokens": 5086300.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.889710426330566,
|
||
|
|
"epoch": 0.22913829994164558,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997420086365351,
|
||
|
|
"loss": 5.639,
|
||
|
|
"mean_token_accuracy": 0.1529846578836441,
|
||
|
|
"num_tokens": 5094762.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962165880203247,
|
||
|
|
"epoch": 0.22952732931336317,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004997406800690966,
|
||
|
|
"loss": 5.8148,
|
||
|
|
"mean_token_accuracy": 0.14716944992542266,
|
||
|
|
"num_tokens": 5103364.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089474296569824,
|
||
|
|
"epoch": 0.22991635868508073,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997393480915758,
|
||
|
|
"loss": 5.9175,
|
||
|
|
"mean_token_accuracy": 0.14378761649131774,
|
||
|
|
"num_tokens": 5111730.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014431476593018,
|
||
|
|
"epoch": 0.2303053880567983,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004997380127039931,
|
||
|
|
"loss": 5.721,
|
||
|
|
"mean_token_accuracy": 0.14942315146327018,
|
||
|
|
"num_tokens": 5119878.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.950433588027954,
|
||
|
|
"epoch": 0.23069441742851585,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997366739063688,
|
||
|
|
"loss": 5.8318,
|
||
|
|
"mean_token_accuracy": 0.14808186888694763,
|
||
|
|
"num_tokens": 5129146.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973391675949097,
|
||
|
|
"epoch": 0.2310834468002334,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997353316987231,
|
||
|
|
"loss": 5.8516,
|
||
|
|
"mean_token_accuracy": 0.14153072685003282,
|
||
|
|
"num_tokens": 5137989.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0436218738555905,
|
||
|
|
"epoch": 0.231472476171951,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997339860810765,
|
||
|
|
"loss": 5.8711,
|
||
|
|
"mean_token_accuracy": 0.14632160738110542,
|
||
|
|
"num_tokens": 5146722.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.069381904602051,
|
||
|
|
"epoch": 0.23186150554366855,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997326370534495,
|
||
|
|
"loss": 5.8568,
|
||
|
|
"mean_token_accuracy": 0.14624862521886825,
|
||
|
|
"num_tokens": 5154902.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.035060167312622,
|
||
|
|
"epoch": 0.2322505349153861,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004997312846158622,
|
||
|
|
"loss": 5.8534,
|
||
|
|
"mean_token_accuracy": 0.1460738830268383,
|
||
|
|
"num_tokens": 5163594.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965574455261231,
|
||
|
|
"epoch": 0.23263956428710367,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004997299287683355,
|
||
|
|
"loss": 5.7492,
|
||
|
|
"mean_token_accuracy": 0.15077491253614425,
|
||
|
|
"num_tokens": 5172139.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024194145202637,
|
||
|
|
"epoch": 0.23302859365882125,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997285695108898,
|
||
|
|
"loss": 5.8685,
|
||
|
|
"mean_token_accuracy": 0.1467841848731041,
|
||
|
|
"num_tokens": 5180077.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.930562591552734,
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997272068435458,
|
||
|
|
"loss": 5.7271,
|
||
|
|
"mean_token_accuracy": 0.1471436142921448,
|
||
|
|
"num_tokens": 5188500.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"eval_entropy": 5.6941922486115235,
|
||
|
|
"eval_loss": 5.846546649932861,
|
||
|
|
"eval_mean_token_accuracy": 0.15339850671912067,
|
||
|
|
"eval_num_tokens": 5188500.0,
|
||
|
|
"eval_runtime": 21.835,
|
||
|
|
"eval_samples_per_second": 1903.278,
|
||
|
|
"eval_steps_per_second": 237.921,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 128520,
|
||
|
|
"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": 1038909989191680.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|