| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010664960273022983, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1329920546045965e-05, | |
| "eval_loss": 0.7577171921730042, | |
| "eval_runtime": 1233.952, | |
| "eval_samples_per_second": 15.997, | |
| "eval_steps_per_second": 7.999, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021329920546045967, | |
| "grad_norm": 1.3220651149749756, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 2.8728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00042659841092091935, | |
| "grad_norm": 1.1727917194366455, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.8062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006398976163813789, | |
| "grad_norm": 1.2135999202728271, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 1.6181, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008531968218418387, | |
| "grad_norm": 1.0141725540161133, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 1.3658, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "grad_norm": 1.1369566917419434, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.3735, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "eval_loss": 0.33222588896751404, | |
| "eval_runtime": 1234.8799, | |
| "eval_samples_per_second": 15.985, | |
| "eval_steps_per_second": 7.993, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.836410097106944e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |