| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 2075, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.7951807228915666e-05, | |
| "loss": 1.7836, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.5903614457831325e-05, | |
| "loss": 1.7368, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3855421686746989e-05, | |
| "loss": 1.72, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.8072289156626506e-06, | |
| "loss": 1.6937, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_bleu": 21.3823, | |
| "eval_gen_len": 28.2551, | |
| "eval_loss": 1.8005332946777344, | |
| "eval_runtime": 121.1926, | |
| "eval_samples_per_second": 10.867, | |
| "eval_steps_per_second": 0.091, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 2075, | |
| "num_train_epochs": 1, | |
| "total_flos": 7080945498390528.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |