| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.3789473684210525, | |
| "eval_steps": 25, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.645, | |
| "eval_samples_per_second": 13.718, | |
| "eval_steps_per_second": 3.567, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.1263157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.2947368421052632, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.4631578947368422, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0842105263157893, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.2526315789473683, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.5894736842105264, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.7578947368421054, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.042105263157895, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.2105263157894735, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.3789473684210525, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.148510102234071e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |