| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5, |
| "global_step": 27, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 4.8782, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 2e-05, |
| "loss": 4.939, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.19, |
| "eval_accuracy": 0.34086021505376346, |
| "eval_loss": 4.759700775146484, |
| "eval_runtime": 1.5757, |
| "eval_samples_per_second": 6.346, |
| "eval_steps_per_second": 1.904, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 9.411764705882354e-06, |
| "loss": 4.7845, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.37, |
| "eval_accuracy": 0.3449657869012708, |
| "eval_loss": 4.6188225746154785, |
| "eval_runtime": 1.5762, |
| "eval_samples_per_second": 6.344, |
| "eval_steps_per_second": 1.903, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5, |
| "step": 27, |
| "total_flos": 3751274298212352.0, |
| "train_loss": 4.820629755655925, |
| "train_runtime": 65.8946, |
| "train_samples_per_second": 1.624, |
| "train_steps_per_second": 0.41 |
| } |
| ], |
| "max_steps": 27, |
| "num_train_epochs": 1, |
| "total_flos": 3751274298212352.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
