| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9310344827586206, |
| "eval_steps": 500, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9655172413793104, |
| "eval_loss": 1.096757173538208, |
| "eval_runtime": 6.7816, |
| "eval_samples_per_second": 28.459, |
| "eval_steps_per_second": 0.59, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.396551724137931, |
| "grad_norm": 2.9408685872324747, |
| "learning_rate": 5e-06, |
| "loss": 1.2507, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.9482758620689655, |
| "eval_loss": 1.0302181243896484, |
| "eval_runtime": 6.5287, |
| "eval_samples_per_second": 29.562, |
| "eval_steps_per_second": 0.613, |
| "step": 14 |
| }, |
| { |
| "epoch": 2.793103448275862, |
| "grad_norm": 3.329244747809881, |
| "learning_rate": 5e-06, |
| "loss": 1.0989, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.9310344827586206, |
| "eval_loss": 0.9940618276596069, |
| "eval_runtime": 5.3751, |
| "eval_samples_per_second": 35.907, |
| "eval_steps_per_second": 0.744, |
| "step": 21 |
| }, |
| { |
| "epoch": 2.9310344827586206, |
| "step": 21, |
| "total_flos": 34966402498560.0, |
| "train_loss": 1.1650703861599876, |
| "train_runtime": 999.8758, |
| "train_samples_per_second": 10.972, |
| "train_steps_per_second": 0.021 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 21, |
| "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": 34966402498560.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
