| { | |
| "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": 0.975609756097561, | |
| "grad_norm": 3.4229159355163574, | |
| "learning_rate": 0.0002, | |
| "loss": 4.659366226196289, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.8780487804878048, | |
| "grad_norm": 1.1556655168533325, | |
| "learning_rate": 0.00019219658547282067, | |
| "loss": 2.0287652969360352, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.7804878048780486, | |
| "grad_norm": 0.8790391683578491, | |
| "learning_rate": 0.00017000420745694254, | |
| "loss": 1.2084564208984374, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.682926829268293, | |
| "grad_norm": 0.981283962726593, | |
| "learning_rate": 0.00013688639245240078, | |
| "loss": 1.0302597045898438, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.585365853658536, | |
| "grad_norm": 1.0220673084259033, | |
| "learning_rate": 9.801178123349298e-05, | |
| "loss": 0.8048470497131348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.487804878048781, | |
| "grad_norm": 0.9974339008331299, | |
| "learning_rate": 5.9447467918700614e-05, | |
| "loss": 0.6644424438476563, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.390243902439025, | |
| "grad_norm": 1.2583245038986206, | |
| "learning_rate": 2.7212118963050592e-05, | |
| "loss": 0.5137343406677246, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.2926829268292686, | |
| "grad_norm": 1.1937904357910156, | |
| "learning_rate": 6.336650173127223e-06, | |
| "loss": 0.4234976291656494, | |
| "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": 1648669707730944.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |