| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 3668, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14, |
| "learning_rate": 9.134948096885815e-06, |
| "loss": 4.3058, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 7.693194925028837e-06, |
| "loss": 3.8423, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.27, |
| "eval_loss": 3.5093352794647217, |
| "eval_runtime": 26.1408, |
| "eval_samples_per_second": 220.728, |
| "eval_steps_per_second": 13.81, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 6.251441753171857e-06, |
| "loss": 3.7858, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 4.809688581314879e-06, |
| "loss": 3.7475, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.55, |
| "eval_loss": 3.46193265914917, |
| "eval_runtime": 26.4806, |
| "eval_samples_per_second": 217.896, |
| "eval_steps_per_second": 13.633, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 3.367935409457901e-06, |
| "loss": 3.7268, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 1.926182237600923e-06, |
| "loss": 3.7098, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.82, |
| "eval_loss": 3.436793327331543, |
| "eval_runtime": 26.5912, |
| "eval_samples_per_second": 216.989, |
| "eval_steps_per_second": 13.576, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 4.844290657439446e-07, |
| "loss": 3.6983, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 3668, |
| "total_flos": 733768405493760.0, |
| "train_loss": 3.8245478040389433, |
| "train_runtime": 4489.0093, |
| "train_samples_per_second": 13.072, |
| "train_steps_per_second": 0.817 |
| } |
| ], |
| "max_steps": 3668, |
| "num_train_epochs": 1, |
| "total_flos": 733768405493760.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
