| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.92, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.7793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.26405462622642517, | |
| "eval_runtime": 11.5683, | |
| "eval_samples_per_second": 8.644, | |
| "eval_steps_per_second": 1.124, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2954, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.2351, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.2440207302570343, | |
| "eval_runtime": 7.6137, | |
| "eval_samples_per_second": 13.134, | |
| "eval_steps_per_second": 1.707, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "step": 18, | |
| "total_flos": 20252706734080.0, | |
| "train_loss": 0.41913825935787624, | |
| "train_runtime": 456.4567, | |
| "train_samples_per_second": 1.314, | |
| "train_steps_per_second": 0.039 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 20252706734080.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |