| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 15, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07111111111111111, |
| "grad_norm": 44.67733383178711, |
| "learning_rate": 4.880952380952381e-05, |
| "loss": 1.7088, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.14222222222222222, |
| "grad_norm": 20.603527069091797, |
| "learning_rate": 4.761904761904762e-05, |
| "loss": 1.3736, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.21333333333333335, |
| "grad_norm": 13.383973121643066, |
| "learning_rate": 4.642857142857143e-05, |
| "loss": 1.0633, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.28444444444444444, |
| "grad_norm": 18.217517852783203, |
| "learning_rate": 4.523809523809524e-05, |
| "loss": 0.9657, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 24.33879280090332, |
| "learning_rate": 4.404761904761905e-05, |
| "loss": 1.2461, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.4266666666666667, |
| "grad_norm": 19.84720230102539, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 1.5754, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.49777777777777776, |
| "grad_norm": 24.253826141357422, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 1.5207, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.5688888888888889, |
| "grad_norm": 20.438188552856445, |
| "learning_rate": 4.047619047619048e-05, |
| "loss": 1.6296, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 16.69805335998535, |
| "learning_rate": 3.928571428571429e-05, |
| "loss": 1.4452, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 17.387191772460938, |
| "learning_rate": 3.809523809523809e-05, |
| "loss": 1.4346, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.7822222222222223, |
| "grad_norm": 11.59079647064209, |
| "learning_rate": 3.690476190476191e-05, |
| "loss": 0.9738, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.8533333333333334, |
| "grad_norm": 16.189956665039062, |
| "learning_rate": 3.571428571428572e-05, |
| "loss": 1.1562, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.9244444444444444, |
| "grad_norm": 15.003352165222168, |
| "learning_rate": 3.4523809523809526e-05, |
| "loss": 1.2251, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.9955555555555555, |
| "grad_norm": 25.233856201171875, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.2984, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.610274314880371, |
| "learning_rate": 3.2142857142857144e-05, |
| "loss": 0.0679, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.07889434695243835, |
| "eval_runtime": 4.8099, |
| "eval_samples_per_second": 20.791, |
| "eval_steps_per_second": 5.198, |
| "step": 15 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 42, |
| "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": 1.6833713556946944e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
