| { |
| "best_global_step": 500, |
| "best_metric": 0.6913547039757092, |
| "best_model_checkpoint": "models/regressor_entropy/checkpoint-500", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10005002501250625, |
| "grad_norm": 14.2173433303833, |
| "learning_rate": 1.9413333333333336e-05, |
| "loss": 0.8382, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2001000500250125, |
| "grad_norm": 3.459506034851074, |
| "learning_rate": 1.8746666666666668e-05, |
| "loss": 0.0652, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3001500750375188, |
| "grad_norm": 2.5837254524230957, |
| "learning_rate": 1.8080000000000003e-05, |
| "loss": 0.0618, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.400200100050025, |
| "grad_norm": 1.4972238540649414, |
| "learning_rate": 1.7413333333333335e-05, |
| "loss": 0.0539, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5002501250625313, |
| "grad_norm": 1.6930369138717651, |
| "learning_rate": 1.674666666666667e-05, |
| "loss": 0.0289, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.6003001500750376, |
| "grad_norm": 3.687997579574585, |
| "learning_rate": 1.6080000000000002e-05, |
| "loss": 0.0414, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7003501750875438, |
| "grad_norm": 2.0027990341186523, |
| "learning_rate": 1.5413333333333337e-05, |
| "loss": 0.0256, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.80040020010005, |
| "grad_norm": 3.859266996383667, |
| "learning_rate": 1.4746666666666667e-05, |
| "loss": 0.0299, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9004502251125562, |
| "grad_norm": 1.8132652044296265, |
| "learning_rate": 1.408e-05, |
| "loss": 0.024, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 8.49107837677002, |
| "learning_rate": 1.3413333333333334e-05, |
| "loss": 0.029, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.008338933810591698, |
| "eval_mae": 0.0746353268623352, |
| "eval_mse": 0.008338933810591698, |
| "eval_r": 0.8314774224088765, |
| "eval_r2": 0.6913547039757092, |
| "eval_runtime": 16.2927, |
| "eval_samples_per_second": 30.689, |
| "eval_steps_per_second": 15.344, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1500, |
| "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": 2.1797446777995264e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
