| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 2071, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0004828585224529213, |
| "grad_norm": 6.790188789367676, |
| "learning_rate": 0.0, |
| "loss": 4.1585, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.48285852245292127, |
| "grad_norm": 6.372687339782715, |
| "learning_rate": 6.028968014484008e-06, |
| "loss": 3.2055, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.48285852245292127, |
| "eval_cosine_accuracy": 0.9400568008422852, |
| "eval_loss": 0.5675864219665527, |
| "eval_runtime": 35.3676, |
| "eval_samples_per_second": 268.862, |
| "eval_steps_per_second": 1.074, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9657170449058425, |
| "grad_norm": 8.225760459899902, |
| "learning_rate": 1.2063971031985518e-05, |
| "loss": 2.0069, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.9657170449058425, |
| "eval_cosine_accuracy": 0.9479440450668335, |
| "eval_loss": 0.5088897347450256, |
| "eval_runtime": 35.33, |
| "eval_samples_per_second": 269.148, |
| "eval_steps_per_second": 1.076, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 16568, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "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": 0.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
