| { | |
| "best_metric": 1.6951390504837036, | |
| "best_model_checkpoint": "./outputs/checkpoint-800", | |
| "epoch": 0.5828779599271403, | |
| "eval_steps": 100, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1907, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.0242879390716553, | |
| "eval_runtime": 144.9414, | |
| "eval_samples_per_second": 43.286, | |
| "eval_steps_per_second": 5.416, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9738, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.9313020706176758, | |
| "eval_runtime": 143.9274, | |
| "eval_samples_per_second": 43.591, | |
| "eval_steps_per_second": 5.454, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9003, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.8709847927093506, | |
| "eval_runtime": 144.0274, | |
| "eval_samples_per_second": 43.561, | |
| "eval_steps_per_second": 5.45, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 1.849, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.8261810541152954, | |
| "eval_runtime": 144.0251, | |
| "eval_samples_per_second": 43.562, | |
| "eval_steps_per_second": 5.45, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7978, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.783812403678894, | |
| "eval_runtime": 143.9209, | |
| "eval_samples_per_second": 43.593, | |
| "eval_steps_per_second": 5.454, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7696, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.7559951543807983, | |
| "eval_runtime": 143.9146, | |
| "eval_samples_per_second": 43.595, | |
| "eval_steps_per_second": 5.455, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7308, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.7238949537277222, | |
| "eval_runtime": 143.9925, | |
| "eval_samples_per_second": 43.572, | |
| "eval_steps_per_second": 5.452, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7094, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.6951390504837036, | |
| "eval_runtime": 143.9787, | |
| "eval_samples_per_second": 43.576, | |
| "eval_steps_per_second": 5.452, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4116, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 4.770481186612838e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |