| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 2000, |
| "global_step": 4749, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00021059281878487945, |
| "grad_norm": 5.663685321807861, |
| "learning_rate": 0.0, |
| "loss": 3.071, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.42118563756975885, |
| "grad_norm": 2.951986312866211, |
| "learning_rate": 4.210193765796125e-06, |
| "loss": 2.5694, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.42118563756975885, |
| "eval_cosine_accuracy": 0.9467061161994934, |
| "eval_loss": 0.70719313621521, |
| "eval_runtime": 24.761, |
| "eval_samples_per_second": 381.931, |
| "eval_steps_per_second": 1.494, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8423712751395177, |
| "grad_norm": 3.3405182361602783, |
| "learning_rate": 8.42038753159225e-06, |
| "loss": 1.8962, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.8423712751395177, |
| "eval_cosine_accuracy": 0.947446346282959, |
| "eval_loss": 0.6832706928253174, |
| "eval_runtime": 23.9291, |
| "eval_samples_per_second": 395.21, |
| "eval_steps_per_second": 1.546, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 23745, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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 |
| } |
|
|
