| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 37.00083333333333, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 4.9999999999999996e-06, |
| "loss": 11.019, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00025, |
| "loss": 8.1576, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 0.0005, |
| "loss": 6.8013, |
| "step": 100 |
| }, |
| { |
| "epoch": 5.01, |
| "learning_rate": 0.0005833333333333333, |
| "loss": 6.7167, |
| "step": 150 |
| }, |
| { |
| "epoch": 7.01, |
| "learning_rate": 0.0005555555555555556, |
| "loss": 6.6474, |
| "step": 200 |
| }, |
| { |
| "epoch": 9.01, |
| "learning_rate": 0.0005277777777777777, |
| "loss": 6.6081, |
| "step": 250 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 0.0005, |
| "loss": 6.5764, |
| "step": 300 |
| }, |
| { |
| "epoch": 12.02, |
| "learning_rate": 0.00047222222222222224, |
| "loss": 6.4283, |
| "step": 350 |
| }, |
| { |
| "epoch": 14.02, |
| "learning_rate": 0.00044444444444444436, |
| "loss": 6.4218, |
| "step": 400 |
| }, |
| { |
| "epoch": 16.02, |
| "learning_rate": 0.00041666666666666664, |
| "loss": 6.2987, |
| "step": 450 |
| }, |
| { |
| "epoch": 18.01, |
| "learning_rate": 0.00038888888888888887, |
| "loss": 6.1713, |
| "step": 500 |
| }, |
| { |
| "epoch": 20.01, |
| "learning_rate": 0.0003611111111111111, |
| "loss": 6.0415, |
| "step": 550 |
| }, |
| { |
| "epoch": 22.0, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 5.9176, |
| "step": 600 |
| }, |
| { |
| "epoch": 24.0, |
| "learning_rate": 0.00030555555555555555, |
| "loss": 5.7948, |
| "step": 650 |
| }, |
| { |
| "epoch": 25.02, |
| "learning_rate": 0.0002777777777777778, |
| "loss": 5.6087, |
| "step": 700 |
| }, |
| { |
| "epoch": 27.02, |
| "learning_rate": 0.00025, |
| "loss": 5.5749, |
| "step": 750 |
| }, |
| { |
| "epoch": 29.01, |
| "learning_rate": 0.00022222222222222218, |
| "loss": 5.4786, |
| "step": 800 |
| }, |
| { |
| "epoch": 31.01, |
| "learning_rate": 0.00019444444444444443, |
| "loss": 5.3877, |
| "step": 850 |
| }, |
| { |
| "epoch": 33.01, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 5.3031, |
| "step": 900 |
| }, |
| { |
| "epoch": 35.0, |
| "learning_rate": 0.0001388888888888889, |
| "loss": 5.2301, |
| "step": 950 |
| }, |
| { |
| "epoch": 37.0, |
| "learning_rate": 0.00011111111111111109, |
| "loss": 5.1653, |
| "step": 1000 |
| }, |
| { |
| "epoch": 37.0, |
| "eval_loss": 5.702059268951416, |
| "eval_runtime": 1.9567, |
| "eval_samples_per_second": 51.105, |
| "eval_steps_per_second": 3.577, |
| "step": 1000 |
| }, |
| { |
| "epoch": 37.0, |
| "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 5.702059268951416, |
| "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 299.4834834485122, |
| "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 1.9567, |
| "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 51.105, |
| "step": 1000 |
| } |
| ], |
| "max_steps": 1200, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 2.7375043608576e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
