| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1908, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5796774193548387, | |
| "eval_loss": 0.20986367762088776, | |
| "eval_runtime": 5.1673, | |
| "eval_samples_per_second": 599.927, | |
| "eval_steps_per_second": 12.579, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 0.5460540056228638, | |
| "learning_rate": 1.4758909853249476e-05, | |
| "loss": 0.332, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8129032258064516, | |
| "eval_loss": 0.1050410121679306, | |
| "eval_runtime": 5.3586, | |
| "eval_samples_per_second": 578.505, | |
| "eval_steps_per_second": 12.13, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8709677419354839, | |
| "eval_loss": 0.07279336452484131, | |
| "eval_runtime": 5.2066, | |
| "eval_samples_per_second": 595.399, | |
| "eval_steps_per_second": 12.484, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 0.4723931849002838, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 0.1214, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.892258064516129, | |
| "eval_loss": 0.058892734348773956, | |
| "eval_runtime": 5.2068, | |
| "eval_samples_per_second": 595.377, | |
| "eval_steps_per_second": 12.484, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.716981132075472, | |
| "grad_norm": 0.3437352180480957, | |
| "learning_rate": 4.276729559748428e-06, | |
| "loss": 0.0826, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8951612903225806, | |
| "eval_loss": 0.05154057592153549, | |
| "eval_runtime": 5.4583, | |
| "eval_samples_per_second": 567.941, | |
| "eval_steps_per_second": 11.908, | |
| "step": 1590 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1908, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 391368939443328.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.9907493566825466, | |
| "num_train_epochs": 6, | |
| "temperature": 9 | |
| } | |
| } | |