| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010755579456843238, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021511158913686476, | |
| "grad_norm": 0.26105204224586487, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021511158913686476, | |
| "eval_loss": 6.925580024719238, | |
| "eval_runtime": 22.4294, | |
| "eval_samples_per_second": 34.91, | |
| "eval_steps_per_second": 17.477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004302231782737295, | |
| "grad_norm": 0.23727715015411377, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9281, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004302231782737295, | |
| "eval_loss": 6.925536155700684, | |
| "eval_runtime": 1.1629, | |
| "eval_samples_per_second": 673.301, | |
| "eval_steps_per_second": 337.08, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006453347674105943, | |
| "grad_norm": 0.2646751403808594, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00860446356547459, | |
| "grad_norm": 0.2786233425140381, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9247, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00860446356547459, | |
| "eval_loss": 6.9252238273620605, | |
| "eval_runtime": 1.1886, | |
| "eval_samples_per_second": 658.754, | |
| "eval_steps_per_second": 329.798, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010755579456843238, | |
| "grad_norm": 0.24613913893699646, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9331, | |
| "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": 29332850688.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |