| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 42.00666666666667, |
| "global_step": 1100, |
| "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": 11.1259, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00025, |
| "loss": 8.8129, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 0.0005, |
| "loss": 7.1869, |
| "step": 100 |
| }, |
| { |
| "epoch": 5.02, |
| "learning_rate": 0.0005833333333333333, |
| "loss": 6.5568, |
| "step": 150 |
| }, |
| { |
| "epoch": 7.01, |
| "learning_rate": 0.0005555555555555556, |
| "loss": 6.0674, |
| "step": 200 |
| }, |
| { |
| "epoch": 9.01, |
| "learning_rate": 0.0005277777777777777, |
| "loss": 5.7599, |
| "step": 250 |
| }, |
| { |
| "epoch": 11.01, |
| "learning_rate": 0.0005, |
| "loss": 5.5578, |
| "step": 300 |
| }, |
| { |
| "epoch": 13.01, |
| "learning_rate": 0.00047222222222222224, |
| "loss": 5.3958, |
| "step": 350 |
| }, |
| { |
| "epoch": 15.01, |
| "learning_rate": 0.00044444444444444436, |
| "loss": 5.2326, |
| "step": 400 |
| }, |
| { |
| "epoch": 17.01, |
| "learning_rate": 0.00041666666666666664, |
| "loss": 5.0814, |
| "step": 450 |
| }, |
| { |
| "epoch": 19.0, |
| "learning_rate": 0.00038888888888888887, |
| "loss": 4.9099, |
| "step": 500 |
| }, |
| { |
| "epoch": 21.0, |
| "learning_rate": 0.0003611111111111111, |
| "loss": 4.7405, |
| "step": 550 |
| }, |
| { |
| "epoch": 23.0, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 4.5977, |
| "step": 600 |
| }, |
| { |
| "epoch": 24.02, |
| "learning_rate": 0.00030555555555555555, |
| "loss": 4.4226, |
| "step": 650 |
| }, |
| { |
| "epoch": 26.02, |
| "learning_rate": 0.0002777777777777778, |
| "loss": 4.3734, |
| "step": 700 |
| }, |
| { |
| "epoch": 28.02, |
| "learning_rate": 0.00025, |
| "loss": 4.2801, |
| "step": 750 |
| }, |
| { |
| "epoch": 30.02, |
| "learning_rate": 0.00022222222222222218, |
| "loss": 4.195, |
| "step": 800 |
| }, |
| { |
| "epoch": 32.02, |
| "learning_rate": 0.00019444444444444443, |
| "loss": 4.117, |
| "step": 850 |
| }, |
| { |
| "epoch": 34.01, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 4.0469, |
| "step": 900 |
| }, |
| { |
| "epoch": 36.01, |
| "learning_rate": 0.0001388888888888889, |
| "loss": 3.9843, |
| "step": 950 |
| }, |
| { |
| "epoch": 38.01, |
| "learning_rate": 0.00011111111111111109, |
| "loss": 3.9288, |
| "step": 1000 |
| }, |
| { |
| "epoch": 38.01, |
| "eval_loss": 5.421392917633057, |
| "eval_runtime": 5.2963, |
| "eval_samples_per_second": 16.238, |
| "eval_steps_per_second": 1.133, |
| "step": 1000 |
| }, |
| { |
| "epoch": 38.01, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 5.421392917633057, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 226.1939727440261, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 5.2963, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 16.238, |
| "step": 1000 |
| }, |
| { |
| "epoch": 40.01, |
| "learning_rate": 8.333333333333333e-05, |
| "loss": 3.8811, |
| "step": 1050 |
| }, |
| { |
| "epoch": 42.01, |
| "learning_rate": 5.5555555555555545e-05, |
| "loss": 3.8399, |
| "step": 1100 |
| } |
| ], |
| "max_steps": 1200, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 3.01211183480832e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
