| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03067896381799705, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000613579276359941, | |
| "grad_norm": 0.7742927074432373, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000613579276359941, | |
| "eval_loss": 1.1403805017471313, | |
| "eval_runtime": 4.4011, | |
| "eval_samples_per_second": 11.361, | |
| "eval_steps_per_second": 2.954, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001227158552719882, | |
| "grad_norm": 0.8999025821685791, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8522, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018407378290798229, | |
| "grad_norm": 0.8794368505477905, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.8313, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002454317105439764, | |
| "grad_norm": 0.8324950337409973, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6943, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030678963817997048, | |
| "grad_norm": 0.7109367251396179, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036814756581596457, | |
| "grad_norm": 0.6520911455154419, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.4892, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004295054934519586, | |
| "grad_norm": 0.82011479139328, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.4507, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004908634210879528, | |
| "grad_norm": 0.8380539417266846, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4156, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005522213487239468, | |
| "grad_norm": 0.6644391417503357, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.3562, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0061357927635994096, | |
| "grad_norm": 0.53641676902771, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.3009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00674937203995935, | |
| "grad_norm": 0.5484210848808289, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.2981, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0073629513163192915, | |
| "grad_norm": 0.5699116587638855, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2974, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007976530592679233, | |
| "grad_norm": 0.6507757902145386, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2081, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008590109869039173, | |
| "grad_norm": 0.4994022250175476, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1585, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009203689145399114, | |
| "grad_norm": 0.4449547231197357, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1426, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009817268421759055, | |
| "grad_norm": 0.3562922179698944, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1198, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010430847698118997, | |
| "grad_norm": 0.2882676422595978, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.1233, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011044426974478936, | |
| "grad_norm": 0.30532220005989075, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.1247, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011658006250838878, | |
| "grad_norm": 0.3165493607521057, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1136, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012271585527198819, | |
| "grad_norm": 0.3052116334438324, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1113, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01288516480355876, | |
| "grad_norm": 0.3051818013191223, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1184, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0134987440799187, | |
| "grad_norm": 0.2674170732498169, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1071, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014112323356278642, | |
| "grad_norm": 0.33439406752586365, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1337, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014725902632638583, | |
| "grad_norm": 0.3004717230796814, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1355, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015339481908998524, | |
| "grad_norm": 0.41335827112197876, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1544, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015339481908998524, | |
| "eval_loss": 0.10041550546884537, | |
| "eval_runtime": 4.444, | |
| "eval_samples_per_second": 11.251, | |
| "eval_steps_per_second": 2.925, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015953061185358466, | |
| "grad_norm": 0.26287588477134705, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0904, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.016566640461718407, | |
| "grad_norm": 0.2254049926996231, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0666, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017180219738078345, | |
| "grad_norm": 0.18865813314914703, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0741, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.017793799014438286, | |
| "grad_norm": 0.20661719143390656, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0737, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.018407378290798228, | |
| "grad_norm": 0.20987176895141602, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0836, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01902095756715817, | |
| "grad_norm": 0.1971331536769867, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.066, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01963453684351811, | |
| "grad_norm": 0.19305665791034698, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0698, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.020248116119878052, | |
| "grad_norm": 0.2463589310646057, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0877, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.020861695396237993, | |
| "grad_norm": 0.22322812676429749, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0831, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.021475274672597935, | |
| "grad_norm": 0.2534312605857849, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0936, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022088853948957873, | |
| "grad_norm": 0.26816612482070923, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0723, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.022702433225317814, | |
| "grad_norm": 0.31204140186309814, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.094, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.023316012501677755, | |
| "grad_norm": 0.207439124584198, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0737, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.023929591778037697, | |
| "grad_norm": 0.14335572719573975, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0493, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.024543171054397638, | |
| "grad_norm": 0.17882516980171204, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0657, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02515675033075758, | |
| "grad_norm": 0.17820951342582703, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.062, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02577032960711752, | |
| "grad_norm": 0.1789134442806244, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0618, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02638390888347746, | |
| "grad_norm": 0.16019491851329803, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0569, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0269974881598374, | |
| "grad_norm": 0.17127665877342224, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0615, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02761106743619734, | |
| "grad_norm": 0.17631715536117554, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0661, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028224646712557283, | |
| "grad_norm": 0.21898619830608368, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0683, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.028838225988917224, | |
| "grad_norm": 0.2262589931488037, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0705, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.029451805265277166, | |
| "grad_norm": 0.22292573750019073, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0725, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.030065384541637107, | |
| "grad_norm": 0.29249176383018494, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0901, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03067896381799705, | |
| "grad_norm": 0.3059021830558777, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0922, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03067896381799705, | |
| "eval_loss": 0.06421475112438202, | |
| "eval_runtime": 4.4458, | |
| "eval_samples_per_second": 11.247, | |
| "eval_steps_per_second": 2.924, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.654149397184512e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |