| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.962962962962963, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 5.733253479003906, | |
| "learning_rate": 8.43120818934367e-05, | |
| "loss": 1.8123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 3.543480634689331, | |
| "learning_rate": 3.019601169804216e-05, | |
| "loss": 0.9568, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 2.944624900817871, | |
| "learning_rate": 0.0, | |
| "loss": 0.4777, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "step": 30, | |
| "total_flos": 579260105883648.0, | |
| "train_loss": 1.0822439193725586, | |
| "train_runtime": 95.7478, | |
| "train_samples_per_second": 2.538, | |
| "train_steps_per_second": 0.313 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 579260105883648.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |