| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0018726416419321916, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.7452832838643834e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5633, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.7452832838643834e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 230.0979, | |
| "eval_samples_per_second": 48.862, | |
| "eval_steps_per_second": 24.433, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.490566567728767e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001123584985159315, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014981133135457534, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00018726416419321916, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000224716997031863, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002621698298705068, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00029962266270915067, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00033707549554779447, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003745283283864383, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004119811612250822, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000449433994063726, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00048688682690236983, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00048688682690236983, | |
| "eval_loss": NaN, | |
| "eval_runtime": 232.4031, | |
| "eval_samples_per_second": 48.377, | |
| "eval_steps_per_second": 24.191, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005243396597410136, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005617924925796575, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005992453254183013, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006366981582569452, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006741509910955889, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007116038239342328, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0007490566567728766, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007865094896115205, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008239623224501644, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0008614151552888081, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000898867988127452, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009363208209660958, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009737736538047397, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0009737736538047397, | |
| "eval_loss": NaN, | |
| "eval_runtime": 232.5958, | |
| "eval_samples_per_second": 48.337, | |
| "eval_steps_per_second": 24.171, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0010112264866433834, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0010486793194820273, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0010861321523206711, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.001123584985159315, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0011610378179979588, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0011984906508366027, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0012359434836752465, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0012733963165138904, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0013108491493525342, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0013483019821911779, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0013857548150298217, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0014232076478684656, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0014606604807071094, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0014606604807071094, | |
| "eval_loss": NaN, | |
| "eval_runtime": 232.3683, | |
| "eval_samples_per_second": 48.384, | |
| "eval_steps_per_second": 24.194, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0014981133135457533, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0015355661463843972, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.001573018979223041, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0016104718120616849, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0016479246449003287, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0016853774777389726, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0017228303105776162, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00176028314341626, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001797735976254904, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0018351888090935478, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0018726416419321916, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 716757218623488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |