| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9998741029837593, |
| "eval_steps": 500, |
| "global_step": 3971, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13, |
| "learning_rate": 4.370435658524301e-05, |
| "loss": 2.0905, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 3.740871317048602e-05, |
| "loss": 1.9275, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 3.111306975572904e-05, |
| "loss": 1.893, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 2.481742634097205e-05, |
| "loss": 1.8706, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 1.8521782926215058e-05, |
| "loss": 1.8604, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 1.2226139511458072e-05, |
| "loss": 1.8527, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 5.930496096701083e-06, |
| "loss": 1.8332, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 3971, |
| "total_flos": 3541933009403904.0, |
| "train_loss": 1.8941770739472503, |
| "train_runtime": 1134.2734, |
| "train_samples_per_second": 112.041, |
| "train_steps_per_second": 3.501 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3971, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "total_flos": 3541933009403904.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
