| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.365853658536585, |
| "eval_steps": 200, |
| "global_step": 3400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0002, |
| "loss": 0.1872, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.61, |
| "eval_runtime": 75.0556, |
| "eval_samples_per_second": 3.677, |
| "eval_steps_per_second": 0.24, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0954, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.22, |
| "eval_runtime": 74.9815, |
| "eval_samples_per_second": 3.681, |
| "eval_steps_per_second": 0.24, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 0.0002, |
| "loss": 0.0797, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.83, |
| "eval_runtime": 75.1061, |
| "eval_samples_per_second": 3.675, |
| "eval_steps_per_second": 0.24, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 0.0002, |
| "loss": 0.06, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.44, |
| "eval_runtime": 74.9943, |
| "eval_samples_per_second": 3.68, |
| "eval_steps_per_second": 0.24, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 0.0002, |
| "loss": 0.0551, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.05, |
| "eval_runtime": 74.9839, |
| "eval_samples_per_second": 3.681, |
| "eval_steps_per_second": 0.24, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.66, |
| "learning_rate": 0.0002, |
| "loss": 0.0422, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.66, |
| "eval_runtime": 75.0437, |
| "eval_samples_per_second": 3.678, |
| "eval_steps_per_second": 0.24, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.27, |
| "learning_rate": 0.0002, |
| "loss": 0.041, |
| "step": 1400 |
| }, |
| { |
| "epoch": 4.27, |
| "eval_runtime": 74.9611, |
| "eval_samples_per_second": 3.682, |
| "eval_steps_per_second": 0.24, |
| "step": 1400 |
| }, |
| { |
| "epoch": 4.88, |
| "learning_rate": 0.0002, |
| "loss": 0.038, |
| "step": 1600 |
| }, |
| { |
| "epoch": 4.88, |
| "eval_runtime": 75.1592, |
| "eval_samples_per_second": 3.672, |
| "eval_steps_per_second": 0.239, |
| "step": 1600 |
| }, |
| { |
| "epoch": 5.49, |
| "learning_rate": 0.0002, |
| "loss": 0.0348, |
| "step": 1800 |
| }, |
| { |
| "epoch": 5.49, |
| "eval_runtime": 75.1286, |
| "eval_samples_per_second": 3.674, |
| "eval_steps_per_second": 0.24, |
| "step": 1800 |
| }, |
| { |
| "epoch": 6.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0366, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.1, |
| "eval_runtime": 34.8655, |
| "eval_samples_per_second": 7.916, |
| "eval_steps_per_second": 0.516, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0355, |
| "step": 2200 |
| }, |
| { |
| "epoch": 6.71, |
| "eval_runtime": 34.8275, |
| "eval_samples_per_second": 7.925, |
| "eval_steps_per_second": 0.517, |
| "step": 2200 |
| }, |
| { |
| "epoch": 7.32, |
| "learning_rate": 0.0002, |
| "loss": 0.034, |
| "step": 2400 |
| }, |
| { |
| "epoch": 7.32, |
| "eval_runtime": 34.837, |
| "eval_samples_per_second": 7.923, |
| "eval_steps_per_second": 0.517, |
| "step": 2400 |
| }, |
| { |
| "epoch": 7.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0317, |
| "step": 2600 |
| }, |
| { |
| "epoch": 7.93, |
| "eval_runtime": 34.829, |
| "eval_samples_per_second": 7.924, |
| "eval_steps_per_second": 0.517, |
| "step": 2600 |
| }, |
| { |
| "epoch": 8.54, |
| "learning_rate": 0.0002, |
| "loss": 0.029, |
| "step": 2800 |
| }, |
| { |
| "epoch": 8.54, |
| "eval_runtime": 34.8248, |
| "eval_samples_per_second": 7.925, |
| "eval_steps_per_second": 0.517, |
| "step": 2800 |
| }, |
| { |
| "epoch": 9.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0289, |
| "step": 3000 |
| }, |
| { |
| "epoch": 9.15, |
| "eval_runtime": 34.8563, |
| "eval_samples_per_second": 7.918, |
| "eval_steps_per_second": 0.516, |
| "step": 3000 |
| }, |
| { |
| "epoch": 9.76, |
| "learning_rate": 0.0002, |
| "loss": 0.0271, |
| "step": 3200 |
| }, |
| { |
| "epoch": 9.76, |
| "eval_runtime": 34.8437, |
| "eval_samples_per_second": 7.921, |
| "eval_steps_per_second": 0.517, |
| "step": 3200 |
| }, |
| { |
| "epoch": 10.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0268, |
| "step": 3400 |
| }, |
| { |
| "epoch": 10.37, |
| "eval_runtime": 34.8527, |
| "eval_samples_per_second": 7.919, |
| "eval_steps_per_second": 0.516, |
| "step": 3400 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 3936, |
| "num_train_epochs": 12, |
| "save_steps": 200, |
| "total_flos": 1.095252831633408e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
