| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.989090909090909, | |
| "global_step": 340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8431, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_runtime": 196.4833, | |
| "eval_samples_per_second": 29.728, | |
| "eval_steps_per_second": 0.468, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1753, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_runtime": 196.6946, | |
| "eval_samples_per_second": 29.696, | |
| "eval_steps_per_second": 0.468, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7899, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_runtime": 197.3831, | |
| "eval_samples_per_second": 29.592, | |
| "eval_steps_per_second": 0.466, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5618, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_runtime": 200.0691, | |
| "eval_samples_per_second": 29.195, | |
| "eval_steps_per_second": 0.46, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.4302, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_runtime": 198.1115, | |
| "eval_samples_per_second": 29.483, | |
| "eval_steps_per_second": 0.464, | |
| "step": 340 | |
| } | |
| ], | |
| "max_steps": 340, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.9333975281854054e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |