| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 2000, |
| "global_step": 5352, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0001868460388639761, |
| "grad_norm": 7.283207893371582, |
| "learning_rate": 0.0, |
| "loss": 2.5638, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.37369207772795215, |
| "grad_norm": 3.523808479309082, |
| "learning_rate": 1.1207250981125022e-05, |
| "loss": 1.8628, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.37369207772795215, |
| "eval_cosine_accuracy": 0.9401501417160034, |
| "eval_loss": 0.63667231798172, |
| "eval_runtime": 26.3233, |
| "eval_samples_per_second": 359.263, |
| "eval_steps_per_second": 1.406, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.7473841554559043, |
| "grad_norm": 2.6587321758270264, |
| "learning_rate": 2.242010839095496e-05, |
| "loss": 1.1435, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.7473841554559043, |
| "eval_cosine_accuracy": 0.9509358406066895, |
| "eval_loss": 0.5591555237770081, |
| "eval_runtime": 24.4044, |
| "eval_samples_per_second": 387.511, |
| "eval_steps_per_second": 1.516, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 16056, |
| "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 |
| } |
|
|
