| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 47.020833333333336, |
| "global_step": 1200, |
| "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": 10.9507, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00025, |
| "loss": 8.5124, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 0.0005, |
| "loss": 7.4735, |
| "step": 100 |
| }, |
| { |
| "epoch": 5.02, |
| "learning_rate": 0.0005833333333333333, |
| "loss": 7.3737, |
| "step": 150 |
| }, |
| { |
| "epoch": 7.02, |
| "learning_rate": 0.0005555555555555556, |
| "loss": 7.1503, |
| "step": 200 |
| }, |
| { |
| "epoch": 9.02, |
| "learning_rate": 0.0005277777777777777, |
| "loss": 6.9697, |
| "step": 250 |
| }, |
| { |
| "epoch": 11.02, |
| "learning_rate": 0.0005, |
| "loss": 6.6856, |
| "step": 300 |
| }, |
| { |
| "epoch": 13.02, |
| "learning_rate": 0.00047222222222222224, |
| "loss": 6.3809, |
| "step": 350 |
| }, |
| { |
| "epoch": 15.02, |
| "learning_rate": 0.00044444444444444436, |
| "loss": 6.0381, |
| "step": 400 |
| }, |
| { |
| "epoch": 17.02, |
| "learning_rate": 0.00041666666666666664, |
| "loss": 5.6691, |
| "step": 450 |
| }, |
| { |
| "epoch": 19.02, |
| "learning_rate": 0.00038888888888888887, |
| "loss": 5.3832, |
| "step": 500 |
| }, |
| { |
| "epoch": 21.02, |
| "learning_rate": 0.0003611111111111111, |
| "loss": 5.1423, |
| "step": 550 |
| }, |
| { |
| "epoch": 23.02, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 4.9255, |
| "step": 600 |
| }, |
| { |
| "epoch": 25.02, |
| "learning_rate": 0.00030555555555555555, |
| "loss": 4.7399, |
| "step": 650 |
| }, |
| { |
| "epoch": 27.02, |
| "learning_rate": 0.0002777777777777778, |
| "loss": 4.582, |
| "step": 700 |
| }, |
| { |
| "epoch": 29.02, |
| "learning_rate": 0.00025, |
| "loss": 4.4476, |
| "step": 750 |
| }, |
| { |
| "epoch": 31.02, |
| "learning_rate": 0.00022222222222222218, |
| "loss": 4.334, |
| "step": 800 |
| }, |
| { |
| "epoch": 33.02, |
| "learning_rate": 0.00019444444444444443, |
| "loss": 4.2328, |
| "step": 850 |
| }, |
| { |
| "epoch": 35.02, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 4.1455, |
| "step": 900 |
| }, |
| { |
| "epoch": 37.02, |
| "learning_rate": 0.0001388888888888889, |
| "loss": 4.0675, |
| "step": 950 |
| }, |
| { |
| "epoch": 39.02, |
| "learning_rate": 0.00011111111111111109, |
| "loss": 3.9999, |
| "step": 1000 |
| }, |
| { |
| "epoch": 39.02, |
| "eval_loss": 5.124108791351318, |
| "eval_runtime": 1.1643, |
| "eval_samples_per_second": 81.596, |
| "eval_steps_per_second": 5.153, |
| "step": 1000 |
| }, |
| { |
| "epoch": 39.02, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 5.124108791351318, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 168.02433016888105, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.1643, |
| "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 81.596, |
| "step": 1000 |
| }, |
| { |
| "epoch": 41.02, |
| "learning_rate": 8.333333333333333e-05, |
| "loss": 3.9418, |
| "step": 1050 |
| }, |
| { |
| "epoch": 43.02, |
| "learning_rate": 5.5555555555555545e-05, |
| "loss": 3.8928, |
| "step": 1100 |
| }, |
| { |
| "epoch": 45.02, |
| "learning_rate": 2.7777777777777772e-05, |
| "loss": 3.8551, |
| "step": 1150 |
| }, |
| { |
| "epoch": 47.02, |
| "learning_rate": 0.0, |
| "loss": 3.8293, |
| "step": 1200 |
| } |
| ], |
| "max_steps": 1200, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 3.2574232461312e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
