| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.47340779643464753, |
| "eval_steps": 100, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00023670389821732376, |
| "grad_norm": 2.5553174018859863, |
| "learning_rate": 0.001, |
| "loss": 10.9944, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.023670389821732377, |
| "grad_norm": 0.545368492603302, |
| "learning_rate": 0.001, |
| "loss": 7.7121, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04734077964346475, |
| "grad_norm": 0.528997540473938, |
| "learning_rate": 0.001, |
| "loss": 6.3787, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.07101116946519713, |
| "grad_norm": 1.7439062595367432, |
| "learning_rate": 0.001, |
| "loss": 5.9739, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.0946815592869295, |
| "grad_norm": 1.6054385900497437, |
| "learning_rate": 0.001, |
| "loss": 5.7237, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.11835194910866188, |
| "grad_norm": 1.6123534440994263, |
| "learning_rate": 0.001, |
| "loss": 5.5599, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.14202233893039426, |
| "grad_norm": 1.2416802644729614, |
| "learning_rate": 0.001, |
| "loss": 5.4246, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.16569272875212665, |
| "grad_norm": 0.967766523361206, |
| "learning_rate": 0.001, |
| "loss": 5.3145, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.189363118573859, |
| "grad_norm": 1.3783754110336304, |
| "learning_rate": 0.001, |
| "loss": 5.2298, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.2130335083955914, |
| "grad_norm": 1.336877703666687, |
| "learning_rate": 0.001, |
| "loss": 5.1636, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.23670389821732377, |
| "grad_norm": 1.2909138202667236, |
| "learning_rate": 0.001, |
| "loss": 5.1127, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.26037428803905616, |
| "grad_norm": 0.715796172618866, |
| "learning_rate": 0.001, |
| "loss": 5.0768, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.2840446778607885, |
| "grad_norm": 1.2406651973724365, |
| "learning_rate": 0.001, |
| "loss": 5.0397, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.3077150676825209, |
| "grad_norm": 1.1353099346160889, |
| "learning_rate": 0.001, |
| "loss": 5.0067, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.3313854575042533, |
| "grad_norm": 0.5953907370567322, |
| "learning_rate": 0.001, |
| "loss": 4.9782, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.35505584732598566, |
| "grad_norm": 1.2066272497177124, |
| "learning_rate": 0.001, |
| "loss": 4.955, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.378726237147718, |
| "grad_norm": 1.0147947072982788, |
| "learning_rate": 0.001, |
| "loss": 4.937, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.4023966269694504, |
| "grad_norm": 1.634466290473938, |
| "learning_rate": 0.001, |
| "loss": 4.9147, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.4260670167911828, |
| "grad_norm": 1.3447681665420532, |
| "learning_rate": 0.001, |
| "loss": 4.9013, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.44973740661291517, |
| "grad_norm": 1.3308050632476807, |
| "learning_rate": 0.001, |
| "loss": 4.8883, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.47340779643464753, |
| "grad_norm": 1.0306942462921143, |
| "learning_rate": 0.001, |
| "loss": 4.8728, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 40000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 2000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.2659866836992e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
