autoprogrammer's picture
Add checkpoint-342 (epoch ckpt)
761b0be verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 342,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.043859649122807015,
"grad_norm": 56.5707893371582,
"learning_rate": 3.6363636363636366e-06,
"loss": 3.5797,
"step": 5
},
{
"epoch": 0.08771929824561403,
"grad_norm": 29.886016845703125,
"learning_rate": 8.181818181818183e-06,
"loss": 1.7984,
"step": 10
},
{
"epoch": 0.13157894736842105,
"grad_norm": 29.6209774017334,
"learning_rate": 9.997973265157192e-06,
"loss": 0.5489,
"step": 15
},
{
"epoch": 0.17543859649122806,
"grad_norm": 5.7636399269104,
"learning_rate": 9.985593613021873e-06,
"loss": 0.3193,
"step": 20
},
{
"epoch": 0.21929824561403508,
"grad_norm": 6.628712177276611,
"learning_rate": 9.961988113473708e-06,
"loss": 0.2388,
"step": 25
},
{
"epoch": 0.2631578947368421,
"grad_norm": 3.4682586193084717,
"learning_rate": 9.927209918004095e-06,
"loss": 0.1914,
"step": 30
},
{
"epoch": 0.30701754385964913,
"grad_norm": 2.8765273094177246,
"learning_rate": 9.881337335184879e-06,
"loss": 0.1452,
"step": 35
},
{
"epoch": 0.3508771929824561,
"grad_norm": 3.5053396224975586,
"learning_rate": 9.824473654344297e-06,
"loss": 0.1294,
"step": 40
},
{
"epoch": 0.39473684210526316,
"grad_norm": 4.058867931365967,
"learning_rate": 9.756746912994832e-06,
"loss": 0.1301,
"step": 45
},
{
"epoch": 0.43859649122807015,
"grad_norm": 2.281430244445801,
"learning_rate": 9.678309608536626e-06,
"loss": 0.1142,
"step": 50
},
{
"epoch": 0.4824561403508772,
"grad_norm": 5.376229286193848,
"learning_rate": 9.58933835488563e-06,
"loss": 0.1276,
"step": 55
},
{
"epoch": 0.5263157894736842,
"grad_norm": 3.5856456756591797,
"learning_rate": 9.490033484799608e-06,
"loss": 0.1227,
"step": 60
},
{
"epoch": 0.5701754385964912,
"grad_norm": 3.554062843322754,
"learning_rate": 9.380618598797473e-06,
"loss": 0.1237,
"step": 65
},
{
"epoch": 0.6140350877192983,
"grad_norm": 3.1894707679748535,
"learning_rate": 9.26134006168757e-06,
"loss": 0.1014,
"step": 70
},
{
"epoch": 0.6578947368421053,
"grad_norm": 2.8556902408599854,
"learning_rate": 9.132466447838598e-06,
"loss": 0.0928,
"step": 75
},
{
"epoch": 0.7017543859649122,
"grad_norm": 2.012010097503662,
"learning_rate": 8.994287936442226e-06,
"loss": 0.0915,
"step": 80
},
{
"epoch": 0.7456140350877193,
"grad_norm": 2.8497273921966553,
"learning_rate": 8.84711565812904e-06,
"loss": 0.1006,
"step": 85
},
{
"epoch": 0.7894736842105263,
"grad_norm": 2.1030471324920654,
"learning_rate": 8.691280994409044e-06,
"loss": 0.1018,
"step": 90
},
{
"epoch": 0.8333333333333334,
"grad_norm": 2.3723015785217285,
"learning_rate": 8.527134831514116e-06,
"loss": 0.0849,
"step": 95
},
{
"epoch": 0.8771929824561403,
"grad_norm": 2.6458847522735596,
"learning_rate": 8.355046770322528e-06,
"loss": 0.0925,
"step": 100
},
{
"epoch": 0.9210526315789473,
"grad_norm": 3.4910573959350586,
"learning_rate": 8.175404294144482e-06,
"loss": 0.0842,
"step": 105
},
{
"epoch": 0.9649122807017544,
"grad_norm": 2.0795462131500244,
"learning_rate": 7.98861189624256e-06,
"loss": 0.1061,
"step": 110
},
{
"epoch": 1.0087719298245614,
"grad_norm": 1.9848618507385254,
"learning_rate": 7.79509016905158e-06,
"loss": 0.0732,
"step": 115
},
{
"epoch": 1.0526315789473684,
"grad_norm": 1.0972084999084473,
"learning_rate": 7.595274857148651e-06,
"loss": 0.0557,
"step": 120
},
{
"epoch": 1.0964912280701755,
"grad_norm": 1.0524636507034302,
"learning_rate": 7.389615876105773e-06,
"loss": 0.0495,
"step": 125
},
{
"epoch": 1.1403508771929824,
"grad_norm": 1.3278300762176514,
"learning_rate": 7.178576299434239e-06,
"loss": 0.0575,
"step": 130
},
{
"epoch": 1.1842105263157894,
"grad_norm": 1.2919989824295044,
"learning_rate": 6.962631315901861e-06,
"loss": 0.0417,
"step": 135
},
{
"epoch": 1.2280701754385965,
"grad_norm": 1.8236581087112427,
"learning_rate": 6.742267159570796e-06,
"loss": 0.0503,
"step": 140
},
{
"epoch": 1.2719298245614035,
"grad_norm": 1.1337546110153198,
"learning_rate": 6.51798001496514e-06,
"loss": 0.0362,
"step": 145
},
{
"epoch": 1.3157894736842106,
"grad_norm": 0.995852530002594,
"learning_rate": 6.290274899833517e-06,
"loss": 0.0503,
"step": 150
},
{
"epoch": 1.3596491228070176,
"grad_norm": 1.819360613822937,
"learning_rate": 6.059664528022267e-06,
"loss": 0.0493,
"step": 155
},
{
"epoch": 1.4035087719298245,
"grad_norm": 0.9036810398101807,
"learning_rate": 5.82666815501964e-06,
"loss": 0.0412,
"step": 160
},
{
"epoch": 1.4473684210526316,
"grad_norm": 1.3854684829711914,
"learning_rate": 5.5918104087704925e-06,
"loss": 0.0328,
"step": 165
},
{
"epoch": 1.4912280701754386,
"grad_norm": 1.4495540857315063,
"learning_rate": 5.355620108394018e-06,
"loss": 0.0416,
"step": 170
},
{
"epoch": 1.5350877192982457,
"grad_norm": 0.9957414865493774,
"learning_rate": 5.118629073464424e-06,
"loss": 0.0446,
"step": 175
},
{
"epoch": 1.5789473684210527,
"grad_norm": 1.6074761152267456,
"learning_rate": 4.8813709265355766e-06,
"loss": 0.0543,
"step": 180
},
{
"epoch": 1.6228070175438596,
"grad_norm": 1.2443127632141113,
"learning_rate": 4.644379891605983e-06,
"loss": 0.0346,
"step": 185
},
{
"epoch": 1.6666666666666665,
"grad_norm": 1.4209715127944946,
"learning_rate": 4.40818959122951e-06,
"loss": 0.0476,
"step": 190
},
{
"epoch": 1.7105263157894737,
"grad_norm": 1.8186906576156616,
"learning_rate": 4.173331844980362e-06,
"loss": 0.0498,
"step": 195
},
{
"epoch": 1.7543859649122808,
"grad_norm": 1.7225463390350342,
"learning_rate": 3.940335471977733e-06,
"loss": 0.0401,
"step": 200
},
{
"epoch": 1.7982456140350878,
"grad_norm": 0.9068968892097473,
"learning_rate": 3.7097251001664824e-06,
"loss": 0.0315,
"step": 205
},
{
"epoch": 1.8421052631578947,
"grad_norm": 1.039904236793518,
"learning_rate": 3.482019985034861e-06,
"loss": 0.0364,
"step": 210
},
{
"epoch": 1.8859649122807016,
"grad_norm": 1.110565185546875,
"learning_rate": 3.257732840429206e-06,
"loss": 0.0356,
"step": 215
},
{
"epoch": 1.9298245614035088,
"grad_norm": 1.3308241367340088,
"learning_rate": 3.0373686840981396e-06,
"loss": 0.037,
"step": 220
},
{
"epoch": 1.973684210526316,
"grad_norm": 1.6800122261047363,
"learning_rate": 2.821423700565763e-06,
"loss": 0.0424,
"step": 225
},
{
"epoch": 2.017543859649123,
"grad_norm": 0.8371121883392334,
"learning_rate": 2.610384123894229e-06,
"loss": 0.0306,
"step": 230
},
{
"epoch": 2.06140350877193,
"grad_norm": 1.0123708248138428,
"learning_rate": 2.4047251428513485e-06,
"loss": 0.0164,
"step": 235
},
{
"epoch": 2.1052631578947367,
"grad_norm": 0.5331275463104248,
"learning_rate": 2.2049098309484195e-06,
"loss": 0.0157,
"step": 240
},
{
"epoch": 2.1491228070175437,
"grad_norm": 1.2166616916656494,
"learning_rate": 2.0113881037574423e-06,
"loss": 0.0166,
"step": 245
},
{
"epoch": 2.192982456140351,
"grad_norm": 0.5046775937080383,
"learning_rate": 1.8245957058555203e-06,
"loss": 0.0092,
"step": 250
},
{
"epoch": 2.236842105263158,
"grad_norm": 0.9175070524215698,
"learning_rate": 1.6449532296774739e-06,
"loss": 0.0139,
"step": 255
},
{
"epoch": 2.280701754385965,
"grad_norm": 0.49616050720214844,
"learning_rate": 1.4728651684858835e-06,
"loss": 0.0128,
"step": 260
},
{
"epoch": 2.324561403508772,
"grad_norm": 0.9484066367149353,
"learning_rate": 1.3087190055909572e-06,
"loss": 0.0093,
"step": 265
},
{
"epoch": 2.3684210526315788,
"grad_norm": 0.5505629181861877,
"learning_rate": 1.1528843418709623e-06,
"loss": 0.0107,
"step": 270
},
{
"epoch": 2.412280701754386,
"grad_norm": 0.7632048726081848,
"learning_rate": 1.005712063557776e-06,
"loss": 0.0112,
"step": 275
},
{
"epoch": 2.456140350877193,
"grad_norm": 1.2667402029037476,
"learning_rate": 8.675335521614036e-07,
"loss": 0.0196,
"step": 280
},
{
"epoch": 2.5,
"grad_norm": 0.6271050572395325,
"learning_rate": 7.386599383124321e-07,
"loss": 0.0089,
"step": 285
},
{
"epoch": 2.543859649122807,
"grad_norm": 0.5146286487579346,
"learning_rate": 6.193814012025278e-07,
"loss": 0.0172,
"step": 290
},
{
"epoch": 2.587719298245614,
"grad_norm": 0.699334979057312,
"learning_rate": 5.099665152003929e-07,
"loss": 0.0127,
"step": 295
},
{
"epoch": 2.6315789473684212,
"grad_norm": 0.8023162484169006,
"learning_rate": 4.106616451143719e-07,
"loss": 0.0112,
"step": 300
},
{
"epoch": 2.675438596491228,
"grad_norm": 2.9173905849456787,
"learning_rate": 3.2169039146337457e-07,
"loss": 0.0133,
"step": 305
},
{
"epoch": 2.719298245614035,
"grad_norm": 0.9328063726425171,
"learning_rate": 2.4325308700516805e-07,
"loss": 0.0135,
"step": 310
},
{
"epoch": 2.763157894736842,
"grad_norm": 0.5964072942733765,
"learning_rate": 1.7552634565570325e-07,
"loss": 0.012,
"step": 315
},
{
"epoch": 2.807017543859649,
"grad_norm": 1.0408029556274414,
"learning_rate": 1.1866266481512234e-07,
"loss": 0.0136,
"step": 320
},
{
"epoch": 2.8508771929824563,
"grad_norm": 1.102298378944397,
"learning_rate": 7.279008199590543e-08,
"loss": 0.0131,
"step": 325
},
{
"epoch": 2.8947368421052633,
"grad_norm": 0.39352259039878845,
"learning_rate": 3.8011886526292394e-08,
"loss": 0.0172,
"step": 330
},
{
"epoch": 2.93859649122807,
"grad_norm": 0.9281210899353027,
"learning_rate": 1.4406386978128017e-08,
"loss": 0.0141,
"step": 335
},
{
"epoch": 2.982456140350877,
"grad_norm": 0.5657672882080078,
"learning_rate": 2.0267348428087974e-09,
"loss": 0.0087,
"step": 340
}
],
"logging_steps": 5,
"max_steps": 342,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.409409897081078e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}