| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004363477691720301, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004363477691720301, | |
| "grad_norm": 6.069176197052002, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008726955383440602, | |
| "grad_norm": 5.544577598571777, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7163, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013090433075160903, | |
| "grad_norm": 4.14764404296875, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 3.3414, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017453910766881205, | |
| "grad_norm": 6.233680725097656, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.8764, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021817388458601505, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.2109, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0026180866150321805, | |
| "grad_norm": 4.936144828796387, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 3.3856, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003054434384204211, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.5814, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003490782153376241, | |
| "grad_norm": 4.964231491088867, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3529, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003927129922548271, | |
| "grad_norm": 5.627495765686035, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 3.4286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004363477691720301, | |
| "grad_norm": 4.651506423950195, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 3.0882, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004363477691720301, | |
| "eval_loss": 2.8977768421173096, | |
| "eval_runtime": 33.2733, | |
| "eval_samples_per_second": 14.516, | |
| "eval_steps_per_second": 14.516, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |