| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08431258892343363, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016862517784686727, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 1615680.5, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016862517784686727, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7188, | |
| "eval_samples_per_second": 13.445, | |
| "eval_steps_per_second": 3.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033725035569373454, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005058755335406018, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006745007113874691, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008431258892343363, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010117510670812036, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011803762449280709, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013490014227749382, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015176266006218053, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016862517784686726, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018548769563155397, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02023502134162407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021921273120092743, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023607524898561418, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02529377667703009, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026980028455498763, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028666280233967435, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030352532012436106, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03203878379090478, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03372503556937345, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03541128734784212, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.037097539126310794, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03878379090477947, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04047004268324814, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042156294461716814, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042156294461716814, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7563, | |
| "eval_samples_per_second": 13.311, | |
| "eval_steps_per_second": 3.461, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043842546240185486, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04552879801865416, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.047215049797122835, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.048901301575591506, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05058755335406018, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05227380513252885, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05396005691099753, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0556463086894662, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05733256046793487, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05901881224640354, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06070506402487221, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06239131580334089, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06407756758180956, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06576381936027823, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0674500711387469, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06913632291721558, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07082257469568425, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07250882647415292, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07419507825262159, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07588133003109027, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07756758180955894, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07925383358802761, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08094008536649629, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08262633714496495, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08431258892343363, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08431258892343363, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7257, | |
| "eval_samples_per_second": 13.42, | |
| "eval_steps_per_second": 3.489, | |
| "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": 6.107028064200294e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |