| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007024021252166866, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018010310902991962, | |
| "eval_loss": NaN, | |
| "eval_runtime": 718.7196, | |
| "eval_samples_per_second": 52.045, | |
| "eval_steps_per_second": 6.506, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018010310902991963, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018010310902991963, | |
| "eval_loss": NaN, | |
| "eval_runtime": 717.1542, | |
| "eval_samples_per_second": 52.159, | |
| "eval_steps_per_second": 6.52, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0036020621805983926, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036020621805983926, | |
| "eval_loss": NaN, | |
| "eval_runtime": 715.5675, | |
| "eval_samples_per_second": 52.275, | |
| "eval_steps_per_second": 6.535, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0054030932708975885, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0054030932708975885, | |
| "eval_loss": NaN, | |
| "eval_runtime": 715.4625, | |
| "eval_samples_per_second": 52.282, | |
| "eval_steps_per_second": 6.536, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.023621133126861e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |