| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2165, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046189376443418013, | |
| "grad_norm": 12.800962448120117, | |
| "learning_rate": 0.0, | |
| "loss": 4.0583, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.23094688221709006, | |
| "eval_cosine_accuracy": 0.9421356916427612, | |
| "eval_loss": 1.4610942602157593, | |
| "eval_runtime": 21.999, | |
| "eval_samples_per_second": 432.064, | |
| "eval_steps_per_second": 1.727, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "eval_cosine_accuracy": 0.9457128047943115, | |
| "eval_loss": 1.3612146377563477, | |
| "eval_runtime": 21.8898, | |
| "eval_samples_per_second": 434.22, | |
| "eval_steps_per_second": 1.736, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6928406466512702, | |
| "eval_cosine_accuracy": 0.9528669118881226, | |
| "eval_loss": 1.288307547569275, | |
| "eval_runtime": 21.8186, | |
| "eval_samples_per_second": 435.638, | |
| "eval_steps_per_second": 1.742, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9237875288683602, | |
| "eval_cosine_accuracy": 0.9522356390953064, | |
| "eval_loss": 1.2684112787246704, | |
| "eval_runtime": 21.8066, | |
| "eval_samples_per_second": 435.877, | |
| "eval_steps_per_second": 1.743, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 18.849971771240234, | |
| "learning_rate": 1.6664098613251156e-05, | |
| "loss": 2.6124, | |
| "step": 2165 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6495, | |
| "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 | |
| } | |