| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.922630560928432, | |
| "eval_steps": 500, | |
| "global_step": 960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.21875e-05, | |
| "loss": 4.1586, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 2.0648, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.6562500000000002e-05, | |
| "loss": 1.7655, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.6324, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 1.5631, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.5197, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 1.3541666666666666e-05, | |
| "loss": 1.4763, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.4491, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 3.125e-06, | |
| "loss": 1.4228, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "step": 960, | |
| "total_flos": 4.8490452612096e+16, | |
| "train_loss": 0.7002776622772217, | |
| "train_runtime": 2199.0947, | |
| "train_samples_per_second": 84.601, | |
| "train_steps_per_second": 0.437 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 960, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "total_flos": 4.8490452612096e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |