| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004645329121568263, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.290658243136526e-05, | |
| "eval_loss": 3.4346907138824463, | |
| "eval_runtime": 103.4058, | |
| "eval_samples_per_second": 43.827, | |
| "eval_steps_per_second": 21.914, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004645329121568263, | |
| "grad_norm": 53.352237701416016, | |
| "learning_rate": 5e-05, | |
| "loss": 14.1732, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009290658243136526, | |
| "grad_norm": 46.14546203613281, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5962, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009290658243136526, | |
| "eval_loss": 3.422771453857422, | |
| "eval_runtime": 91.0381, | |
| "eval_samples_per_second": 49.781, | |
| "eval_steps_per_second": 24.891, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001393598736470479, | |
| "grad_norm": 59.03391647338867, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 13.7805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018581316486273051, | |
| "grad_norm": 55.08629608154297, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 13.6346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018581316486273051, | |
| "eval_loss": 3.3875956535339355, | |
| "eval_runtime": 82.7452, | |
| "eval_samples_per_second": 54.771, | |
| "eval_steps_per_second": 27.385, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0023226645607841317, | |
| "grad_norm": 42.40216827392578, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 13.662, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002787197472940958, | |
| "grad_norm": 62.32259750366211, | |
| "learning_rate": 5e-05, | |
| "loss": 13.374, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002787197472940958, | |
| "eval_loss": 3.3690028190612793, | |
| "eval_runtime": 82.7158, | |
| "eval_samples_per_second": 54.79, | |
| "eval_steps_per_second": 27.395, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0032517303850977844, | |
| "grad_norm": 45.002403259277344, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 13.2412, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0037162632972546103, | |
| "grad_norm": 46.37054443359375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 14.1311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037162632972546103, | |
| "eval_loss": 3.3640120029449463, | |
| "eval_runtime": 82.6509, | |
| "eval_samples_per_second": 54.833, | |
| "eval_steps_per_second": 27.417, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004180796209411437, | |
| "grad_norm": 47.186546325683594, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 13.5162, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004645329121568263, | |
| "grad_norm": 41.13740539550781, | |
| "learning_rate": 0.0, | |
| "loss": 12.9763, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004645329121568263, | |
| "eval_loss": 3.361578941345215, | |
| "eval_runtime": 82.2327, | |
| "eval_samples_per_second": 55.112, | |
| "eval_steps_per_second": 27.556, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 456188542058496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |