| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.648318780452506e-05, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.2161062601508354e-05, | |
| "grad_norm": 0.04531170427799225, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.2161062601508354e-05, | |
| "eval_loss": 10.37723159790039, | |
| "eval_runtime": 40.482, | |
| "eval_samples_per_second": 323.403, | |
| "eval_steps_per_second": 161.701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.432212520301671e-05, | |
| "grad_norm": 0.04875646531581879, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.648318780452506e-05, | |
| "grad_norm": 0.05363098531961441, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3819, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.648318780452506e-05, | |
| "eval_loss": 10.377202987670898, | |
| "eval_runtime": 40.0347, | |
| "eval_samples_per_second": 327.016, | |
| "eval_steps_per_second": 163.508, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 45258178560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |