| { |
| "best_metric": 0.3856528401374817, |
| "best_model_checkpoint": "ckpt_output/checkpoint-30", |
| "epoch": 4.8, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00018568571761675893, |
| "loss": 1.6945, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 0.8912153244018555, |
| "eval_runtime": 10.4021, |
| "eval_samples_per_second": 4.711, |
| "eval_steps_per_second": 4.711, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 0.00013701381553399145, |
| "loss": 0.5639, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_loss": 0.39273881912231445, |
| "eval_runtime": 10.4024, |
| "eval_samples_per_second": 4.71, |
| "eval_steps_per_second": 4.71, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 7.324716614707793e-05, |
| "loss": 0.3821, |
| "step": 18 |
| }, |
| { |
| "epoch": 2.88, |
| "eval_loss": 0.3932119607925415, |
| "eval_runtime": 10.394, |
| "eval_samples_per_second": 4.714, |
| "eval_steps_per_second": 4.714, |
| "step": 18 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 1.4314282383241096e-05, |
| "loss": 0.3224, |
| "step": 25 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.3916894495487213, |
| "eval_runtime": 10.4021, |
| "eval_samples_per_second": 4.711, |
| "eval_steps_per_second": 4.711, |
| "step": 25 |
| }, |
| { |
| "epoch": 4.8, |
| "learning_rate": 0.0, |
| "loss": 0.3501, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.8, |
| "eval_loss": 0.3856528401374817, |
| "eval_runtime": 10.3967, |
| "eval_samples_per_second": 4.713, |
| "eval_steps_per_second": 4.713, |
| "step": 30 |
| } |
| ], |
| "max_steps": 30, |
| "num_train_epochs": 5, |
| "total_flos": 4.0472554450944e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
