| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.924001924001924, |
| "eval_steps": 500, |
| "global_step": 4000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00087999037999038, |
| "loss": 1.1949, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.0007597402597402598, |
| "loss": 0.9577, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.0006397306397306397, |
| "loss": 0.9099, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.0005194805194805195, |
| "loss": 0.8691, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.7804527282714844, |
| "eval_runtime": 17.7961, |
| "eval_samples_per_second": 622.946, |
| "eval_steps_per_second": 38.941, |
| "step": 2079 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.0003992303992303992, |
| "loss": 0.8256, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.000278980278980279, |
| "loss": 0.8047, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.00015873015873015873, |
| "loss": 0.7912, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 3.848003848003848e-05, |
| "loss": 0.7796, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4158, |
| "num_train_epochs": 2, |
| "save_steps": 1000, |
| "total_flos": 5349369107152896.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
