| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014134275618374558, | |
| "eval_steps": 5, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028268551236749115, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 7.6743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028268551236749115, | |
| "eval_loss": 7.129258632659912, | |
| "eval_runtime": 13.6697, | |
| "eval_samples_per_second": 43.6, | |
| "eval_steps_per_second": 5.487, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005653710247349823, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 7.3349, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008480565371024734, | |
| "grad_norm": 5.114774703979492, | |
| "learning_rate": 2e-05, | |
| "loss": 7.4669, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011307420494699646, | |
| "grad_norm": 4.991275310516357, | |
| "learning_rate": 4e-05, | |
| "loss": 7.1521, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014134275618374558, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 7.7429, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014134275618374558, | |
| "eval_loss": 7.097643852233887, | |
| "eval_runtime": 20.7137, | |
| "eval_samples_per_second": 28.773, | |
| "eval_steps_per_second": 3.621, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6719419828928512.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |