| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004, | |
| "grad_norm": 161.0, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 16.3125, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 370.0, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 15.9951, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012, | |
| "grad_norm": 334.0, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 16.2349, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 247.0, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 16.2399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 440.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 15.5578, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 308.0, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 16.0425, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.028, | |
| "grad_norm": 197.0, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 15.3377, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 478.0, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 15.9414, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.036, | |
| "grad_norm": 204.0, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 14.6811, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 123.5, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 15.3669, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.044, | |
| "grad_norm": 135.0, | |
| "learning_rate": 8.8e-06, | |
| "loss": 15.0323, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 81.0, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 15.1514, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.052, | |
| "grad_norm": 109.0, | |
| "learning_rate": 1.04e-05, | |
| "loss": 14.244, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 39.75, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 14.3183, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 99.5, | |
| "learning_rate": 1.2e-05, | |
| "loss": 14.354, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 115.0, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 14.8329, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.068, | |
| "grad_norm": 124.5, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 14.649, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 60.0, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 14.1903, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.076, | |
| "grad_norm": 74.5, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 14.0663, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 98.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 13.9515, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.084, | |
| "grad_norm": 146.0, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 14.2023, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 195.0, | |
| "learning_rate": 1.76e-05, | |
| "loss": 16.903, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.092, | |
| "grad_norm": 123.0, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 14.2629, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 197.0, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 14.205, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 91.0, | |
| "learning_rate": 2e-05, | |
| "loss": 14.2966, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 85.0, | |
| "learning_rate": 1.9999025240093045e-05, | |
| "loss": 14.077, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.108, | |
| "grad_norm": 63.5, | |
| "learning_rate": 1.9996101150403543e-05, | |
| "loss": 13.4959, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 79.0, | |
| "learning_rate": 1.9991228300988586e-05, | |
| "loss": 13.2863, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.116, | |
| "grad_norm": 77.0, | |
| "learning_rate": 1.9984407641819812e-05, | |
| "loss": 14.0289, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 32.5, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 13.218, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.124, | |
| "grad_norm": 59.0, | |
| "learning_rate": 1.9964928592495046e-05, | |
| "loss": 13.0716, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 77.0, | |
| "learning_rate": 1.9952273999818312e-05, | |
| "loss": 13.5455, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.132, | |
| "grad_norm": 48.5, | |
| "learning_rate": 1.9937679191605964e-05, | |
| "loss": 12.7523, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.136, | |
| "grad_norm": 202.0, | |
| "learning_rate": 1.9921147013144782e-05, | |
| "loss": 13.2838, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 42.0, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 13.847, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 50.5, | |
| "learning_rate": 1.988228381446553e-05, | |
| "loss": 13.4523, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.148, | |
| "grad_norm": 55.75, | |
| "learning_rate": 1.985996037070505e-05, | |
| "loss": 12.9266, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.152, | |
| "grad_norm": 78.0, | |
| "learning_rate": 1.983571470813386e-05, | |
| "loss": 13.1995, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.156, | |
| "grad_norm": 83.0, | |
| "learning_rate": 1.9809551553491918e-05, | |
| "loss": 13.4139, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 70.0, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 12.9478, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.164, | |
| "grad_norm": 81.5, | |
| "learning_rate": 1.9751493543055634e-05, | |
| "loss": 13.0514, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "grad_norm": 82.5, | |
| "learning_rate": 1.9719610005785466e-05, | |
| "loss": 12.3466, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.172, | |
| "grad_norm": 63.0, | |
| "learning_rate": 1.9685831611286312e-05, | |
| "loss": 12.3433, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 78.0, | |
| "learning_rate": 1.9650164944723116e-05, | |
| "loss": 12.3277, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 65.5, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 12.2445, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.184, | |
| "grad_norm": 75.0, | |
| "learning_rate": 1.9573194975320672e-05, | |
| "loss": 12.6102, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.188, | |
| "grad_norm": 57.5, | |
| "learning_rate": 1.9531906677929472e-05, | |
| "loss": 11.9526, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 37.5, | |
| "learning_rate": 1.9488760116444966e-05, | |
| "loss": 12.2256, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.196, | |
| "grad_norm": 76.0, | |
| "learning_rate": 1.944376370237481e-05, | |
| "loss": 12.1101, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 62.75, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 12.0318, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "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": 9.5664155394048e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |