| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9998156002212797, | |
| "global_step": 4067, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002875, | |
| "loss": 2.3916, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.449199914932251, | |
| "eval_runtime": 81.8972, | |
| "eval_samples_per_second": 456.072, | |
| "eval_steps_per_second": 57.01, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00027499077490774905, | |
| "loss": 2.193, | |
| "step": 2711 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.462963819503784, | |
| "eval_runtime": 81.6595, | |
| "eval_samples_per_second": 457.399, | |
| "eval_steps_per_second": 57.176, | |
| "step": 2711 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0002624815498154981, | |
| "loss": 2.0534, | |
| "step": 4067 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.501068592071533, | |
| "eval_runtime": 80.5824, | |
| "eval_samples_per_second": 463.513, | |
| "eval_steps_per_second": 57.941, | |
| "step": 4067 | |
| } | |
| ], | |
| "max_steps": 32520, | |
| "num_train_epochs": 24, | |
| "total_flos": 1.6618537585823386e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |