| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 2000, |
| "global_step": 8988, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00011125945705384957, |
| "grad_norm": 6.3739542961120605, |
| "learning_rate": 0.0, |
| "loss": 2.9555, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.22251891410769917, |
| "grad_norm": 4.010181903839111, |
| "learning_rate": 6.672972070768888e-06, |
| "loss": 2.5193, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.22251891410769917, |
| "eval_cosine_accuracy": 0.9481027126312256, |
| "eval_loss": 1.1309852600097656, |
| "eval_runtime": 23.41, |
| "eval_samples_per_second": 404.144, |
| "eval_steps_per_second": 1.581, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.44503782821539833, |
| "grad_norm": 4.1902337074279785, |
| "learning_rate": 1.3349282296650718e-05, |
| "loss": 1.9678, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.44503782821539833, |
| "eval_cosine_accuracy": 0.949688196182251, |
| "eval_loss": 1.11049485206604, |
| "eval_runtime": 24.2815, |
| "eval_samples_per_second": 389.638, |
| "eval_steps_per_second": 1.524, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.6675567423230975, |
| "grad_norm": 4.1325764656066895, |
| "learning_rate": 2.002559252253255e-05, |
| "loss": 1.6578, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.6675567423230975, |
| "eval_cosine_accuracy": 0.9524363279342651, |
| "eval_loss": 1.1041761636734009, |
| "eval_runtime": 23.4441, |
| "eval_samples_per_second": 403.556, |
| "eval_steps_per_second": 1.578, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.8900756564307967, |
| "grad_norm": 3.8412773609161377, |
| "learning_rate": 2.6691888283075553e-05, |
| "loss": 1.4707, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.8900756564307967, |
| "eval_cosine_accuracy": 0.9552901387214661, |
| "eval_loss": 1.0991708040237427, |
| "eval_runtime": 27.9755, |
| "eval_samples_per_second": 338.189, |
| "eval_steps_per_second": 1.323, |
| "step": 8000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 26964, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
