| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2559836170485089, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.031997952131063614, | |
| "grad_norm": 0.06517554074525833, | |
| "learning_rate": 2.9680020478689362e-05, | |
| "loss": 0.2761, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06399590426212723, | |
| "grad_norm": 0.05590095743536949, | |
| "learning_rate": 2.936004095737873e-05, | |
| "loss": 0.0085, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09599385639319083, | |
| "grad_norm": 0.06787142902612686, | |
| "learning_rate": 2.9040061436068092e-05, | |
| "loss": 0.007, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.12799180852425446, | |
| "grad_norm": 0.019182974472641945, | |
| "learning_rate": 2.8720081914757454e-05, | |
| "loss": 0.0063, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15998976065531806, | |
| "grad_norm": 0.02994903363287449, | |
| "learning_rate": 2.840010239344682e-05, | |
| "loss": 0.0056, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.19198771278638166, | |
| "grad_norm": 0.016078654676675797, | |
| "learning_rate": 2.8080122872136184e-05, | |
| "loss": 0.0056, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2239856649174453, | |
| "grad_norm": 0.0162887554615736, | |
| "learning_rate": 2.776014335082555e-05, | |
| "loss": 0.0051, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.2559836170485089, | |
| "grad_norm": 0.024330032989382744, | |
| "learning_rate": 2.744016382951491e-05, | |
| "loss": 0.0053, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 23439, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |