| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.4615384615384617, |
| "eval_steps": 500, |
| "global_step": 6, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.41025641025641024, |
| "grad_norm": 7.4654604530352335, |
| "learning_rate": 8e-05, |
| "loss": 1.2076, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.8205128205128205, |
| "grad_norm": 7.4395259391373045, |
| "learning_rate": 7.236067977499791e-05, |
| "loss": 1.2055, |
| "step": 2 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 34.989069195788765, |
| "learning_rate": 5.23606797749979e-05, |
| "loss": 2.0812, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.641025641025641, |
| "grad_norm": 10.277460775430583, |
| "learning_rate": 2.7639320225002108e-05, |
| "loss": 1.5248, |
| "step": 4 |
| }, |
| { |
| "epoch": 2.051282051282051, |
| "grad_norm": 36.16234180637347, |
| "learning_rate": 7.639320225002106e-06, |
| "loss": 1.4295, |
| "step": 5 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 104.90419830450709, |
| "learning_rate": 0.0, |
| "loss": 1.5441, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "step": 6, |
| "total_flos": 1.5439682546014618e+17, |
| "train_loss": 1.4987796743710835, |
| "train_runtime": 1553.2698, |
| "train_samples_per_second": 2.407, |
| "train_steps_per_second": 0.004 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 6, |
| "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": 1.5439682546014618e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
