| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09836065573770492, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01092896174863388, | |
| "eval_loss": 2.294912338256836, | |
| "eval_runtime": 9.8437, | |
| "eval_samples_per_second": 15.644, | |
| "eval_steps_per_second": 2.032, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03278688524590164, | |
| "grad_norm": 1.559897541999817, | |
| "learning_rate": 1.5e-05, | |
| "loss": 8.8979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 1.6194515228271484, | |
| "learning_rate": 3e-05, | |
| "loss": 9.1763, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09836065573770492, | |
| "grad_norm": 1.691707968711853, | |
| "learning_rate": 4.5e-05, | |
| "loss": 9.2363, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09836065573770492, | |
| "eval_loss": 2.229104518890381, | |
| "eval_runtime": 9.9458, | |
| "eval_samples_per_second": 15.484, | |
| "eval_steps_per_second": 2.011, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2088976735207424e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |