| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0179640718562875, | |
| "eval_steps": 11, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023952095808383235, | |
| "eval_loss": 0.5102269649505615, | |
| "eval_runtime": 0.9638, | |
| "eval_samples_per_second": 18.675, | |
| "eval_steps_per_second": 9.338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "grad_norm": 4.35016393661499, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 5.59436559677124, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7789, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2634730538922156, | |
| "eval_loss": 0.0816006287932396, | |
| "eval_runtime": 0.9633, | |
| "eval_samples_per_second": 18.686, | |
| "eval_steps_per_second": 9.343, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3592814371257485, | |
| "grad_norm": 1.298175573348999, | |
| "learning_rate": 9.409606321741775e-05, | |
| "loss": 0.1859, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "grad_norm": 0.027312569320201874, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5269461077844312, | |
| "eval_loss": 0.00016009138198569417, | |
| "eval_runtime": 0.9649, | |
| "eval_samples_per_second": 18.654, | |
| "eval_steps_per_second": 9.327, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5988023952095808, | |
| "grad_norm": 0.010692027397453785, | |
| "learning_rate": 5.490085701647805e-05, | |
| "loss": 0.001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.718562874251497, | |
| "grad_norm": 0.04211507365107536, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0005, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7904191616766467, | |
| "eval_loss": 8.166131738107651e-05, | |
| "eval_runtime": 0.9645, | |
| "eval_samples_per_second": 18.663, | |
| "eval_steps_per_second": 9.332, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8383233532934131, | |
| "grad_norm": 0.00778238708153367, | |
| "learning_rate": 1.134947733186315e-05, | |
| "loss": 0.0006, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9580838323353293, | |
| "grad_norm": 0.010310592129826546, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0002, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7710808372936704.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |