| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2760143527463428, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05520287054926856, | |
| "grad_norm": 1.2856197357177734, | |
| "learning_rate": 1.1037527593818985e-05, | |
| "loss": 0.7609, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11040574109853712, | |
| "grad_norm": 1.0077331066131592, | |
| "learning_rate": 2.207505518763797e-05, | |
| "loss": 0.5552, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1656086116478057, | |
| "grad_norm": 1.2774763107299805, | |
| "learning_rate": 3.311258278145696e-05, | |
| "loss": 0.5229, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22081148219707425, | |
| "grad_norm": 1.3611174821853638, | |
| "learning_rate": 4.415011037527594e-05, | |
| "loss": 0.5191, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2760143527463428, | |
| "grad_norm": 1.112617015838623, | |
| "learning_rate": 5.518763796909493e-05, | |
| "loss": 0.5068, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 9055, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.624764282039173e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |