| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 88, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 3.400967597961426, | |
| "learning_rate": 0.0002, | |
| "loss": 4.591463470458985, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 1.1452261209487915, | |
| "learning_rate": 0.00019219658547282067, | |
| "loss": 2.028125, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 0.8850991129875183, | |
| "learning_rate": 0.00017000420745694254, | |
| "loss": 1.224452018737793, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 0.8366519212722778, | |
| "learning_rate": 0.00013688639245240078, | |
| "loss": 1.0118728637695313, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 1.1907519102096558, | |
| "learning_rate": 9.801178123349298e-05, | |
| "loss": 0.8368052482604981, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 1.1898653507232666, | |
| "learning_rate": 5.9447467918700614e-05, | |
| "loss": 0.6491528511047363, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.363636363636363, | |
| "grad_norm": 1.27790367603302, | |
| "learning_rate": 2.7212118963050592e-05, | |
| "loss": 0.5388798236846923, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 1.2382910251617432, | |
| "learning_rate": 6.336650173127223e-06, | |
| "loss": 0.43643603324890134, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 88, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 60, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1852343085367296.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |