| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.88, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 7.777152342888169, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1099, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 16.73439679513658, | |
| "learning_rate": 1.8314696123025456e-05, | |
| "loss": 1.4124, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.0609177350997925, | |
| "eval_runtime": 29.2943, | |
| "eval_samples_per_second": 11.743, | |
| "eval_steps_per_second": 0.751, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 5.812382258796925, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0531, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.7984542846679688, | |
| "eval_runtime": 29.1159, | |
| "eval_samples_per_second": 11.815, | |
| "eval_steps_per_second": 0.756, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 4.083532053678706, | |
| "learning_rate": 1.6853038769745466e-06, | |
| "loss": 0.8342, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.7293975949287415, | |
| "eval_runtime": 29.1022, | |
| "eval_samples_per_second": 11.82, | |
| "eval_steps_per_second": 0.756, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "step": 18, | |
| "total_flos": 3716488888320.0, | |
| "train_loss": 1.0256306529045105, | |
| "train_runtime": 397.67, | |
| "train_samples_per_second": 3.018, | |
| "train_steps_per_second": 0.045 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3716488888320.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |