| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 814, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12298232129131437, |
| "grad_norm": 6.340283393859863, |
| "learning_rate": 4.9933489107396326e-05, |
| "loss": 2.0775, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24596464258262873, |
| "grad_norm": 5.597610950469971, |
| "learning_rate": 4.6913866856909926e-05, |
| "loss": 2.2188, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.3689469638739431, |
| "grad_norm": 5.629631519317627, |
| "learning_rate": 3.991940046522724e-05, |
| "loss": 2.2347, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.49192928516525747, |
| "grad_norm": 5.603486061096191, |
| "learning_rate": 3.0218780389368545e-05, |
| "loss": 2.2132, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.6149116064565718, |
| "grad_norm": 5.57080602645874, |
| "learning_rate": 1.9571552451450542e-05, |
| "loss": 2.1841, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7378939277478862, |
| "grad_norm": 5.660244464874268, |
| "learning_rate": 9.908962828396607e-06, |
| "loss": 2.15, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.8608762490392006, |
| "grad_norm": 5.181326389312744, |
| "learning_rate": 2.98365919315127e-06, |
| "loss": 2.1234, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.9838585703305149, |
| "grad_norm": 5.189568519592285, |
| "learning_rate": 5.178692436005883e-08, |
| "loss": 2.0872, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 814, |
| "total_flos": 5454715103844864.0, |
| "train_loss": 2.1604688349168484, |
| "train_runtime": 2203.1408, |
| "train_samples_per_second": 11.81, |
| "train_steps_per_second": 0.369 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 814, |
| "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": 5454715103844864.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
