| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 9, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022222222222222223, | |
| "eval_loss": 1.8410741090774536, | |
| "eval_runtime": 16.746, | |
| "eval_samples_per_second": 18.094, | |
| "eval_steps_per_second": 2.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.0834723711013794, | |
| "eval_runtime": 15.6719, | |
| "eval_samples_per_second": 19.334, | |
| "eval_steps_per_second": 2.425, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 1.0347282886505127, | |
| "learning_rate": 9.16998908944939e-05, | |
| "loss": 1.536, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.5606896281242371, | |
| "eval_runtime": 15.6642, | |
| "eval_samples_per_second": 19.343, | |
| "eval_steps_per_second": 2.426, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.5371178388595581, | |
| "learning_rate": 6.264666911958404e-05, | |
| "loss": 0.689, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.47360849380493164, | |
| "eval_runtime": 15.691, | |
| "eval_samples_per_second": 19.31, | |
| "eval_steps_per_second": 2.422, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.3193366229534149, | |
| "learning_rate": 2.7137883834768073e-05, | |
| "loss": 0.4522, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.4535110592842102, | |
| "eval_runtime": 15.7131, | |
| "eval_samples_per_second": 19.283, | |
| "eval_steps_per_second": 2.418, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.3237155079841614, | |
| "learning_rate": 3.299194563372604e-06, | |
| "loss": 0.443, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4497634768486023, | |
| "eval_runtime": 15.6856, | |
| "eval_samples_per_second": 19.317, | |
| "eval_steps_per_second": 2.423, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 45, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 12, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.254044464667689e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |