| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017471063550993666, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003494212710198733, | |
| "grad_norm": 0.9871466159820557, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003494212710198733, | |
| "eval_loss": 6.968719482421875, | |
| "eval_runtime": 6.7906, | |
| "eval_samples_per_second": 70.98, | |
| "eval_steps_per_second": 35.49, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006988425420397466, | |
| "grad_norm": 0.9154462814331055, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9651, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006988425420397466, | |
| "eval_loss": 6.968451976776123, | |
| "eval_runtime": 0.5552, | |
| "eval_samples_per_second": 868.155, | |
| "eval_steps_per_second": 434.077, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0104826381305962, | |
| "grad_norm": 1.0225493907928467, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9895, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013976850840794933, | |
| "grad_norm": 0.9295715093612671, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9829, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013976850840794933, | |
| "eval_loss": 6.967185020446777, | |
| "eval_runtime": 0.5617, | |
| "eval_samples_per_second": 858.171, | |
| "eval_steps_per_second": 429.085, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017471063550993666, | |
| "grad_norm": 0.9725064635276794, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9789, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 26366607360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |