| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16815554387808723, | |
| "eval_steps": 500, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.4763257575757574e-05, | |
| "loss": 4.136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.450021043771044e-05, | |
| "loss": 3.8037, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.42371632996633e-05, | |
| "loss": 3.7217, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.3974116161616165e-05, | |
| "loss": 3.7068, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.3711069023569023e-05, | |
| "loss": 3.6665, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.3448021885521888e-05, | |
| "loss": 3.6629, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.318497474747475e-05, | |
| "loss": 3.6539, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.292192760942761e-05, | |
| "loss": 3.6554, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.2658880471380472e-05, | |
| "loss": 3.6323, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.2395833333333337e-05, | |
| "loss": 3.6276, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.2132786195286195e-05, | |
| "loss": 3.5915, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.186973905723906e-05, | |
| "loss": 3.6035, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.160669191919192e-05, | |
| "loss": 3.5998, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.1343644781144782e-05, | |
| "loss": 3.5809, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.1080597643097644e-05, | |
| "loss": 3.5888, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.0817550505050505e-05, | |
| "loss": 3.6076, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4757, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.9644023431710966e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |