| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02476780185758514, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004953560371517028, | |
| "grad_norm": 11.30569839477539, | |
| "learning_rate": 1e-05, | |
| "loss": 9.3005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004953560371517028, | |
| "eval_loss": 9.037757873535156, | |
| "eval_runtime": 47.5878, | |
| "eval_samples_per_second": 7.145, | |
| "eval_steps_per_second": 3.572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009907120743034056, | |
| "grad_norm": 9.093804359436035, | |
| "learning_rate": 2e-05, | |
| "loss": 8.6296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009907120743034056, | |
| "eval_loss": 8.909144401550293, | |
| "eval_runtime": 6.262, | |
| "eval_samples_per_second": 54.296, | |
| "eval_steps_per_second": 27.148, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014860681114551083, | |
| "grad_norm": 9.863807678222656, | |
| "learning_rate": 3e-05, | |
| "loss": 8.7409, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019814241486068113, | |
| "grad_norm": 9.737456321716309, | |
| "learning_rate": 4e-05, | |
| "loss": 8.355, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019814241486068113, | |
| "eval_loss": 8.654722213745117, | |
| "eval_runtime": 6.3784, | |
| "eval_samples_per_second": 53.305, | |
| "eval_steps_per_second": 26.653, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "grad_norm": 8.69847297668457, | |
| "learning_rate": 5e-05, | |
| "loss": 8.3105, | |
| "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": 356152655216640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |