| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 30.016666666666666, |
| "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": 10.107, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00025, |
| "loss": 6.9276, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 0.0005, |
| "loss": 4.9315, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.0005833333333333333, |
| "loss": 4.3684, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.02, |
| "learning_rate": 0.0005555555555555556, |
| "loss": 4.0546, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.03, |
| "learning_rate": 0.0005277777777777777, |
| "loss": 3.9329, |
| "step": 250 |
| }, |
| { |
| "epoch": 8.01, |
| "learning_rate": 0.0005, |
| "loss": 3.83, |
| "step": 300 |
| }, |
| { |
| "epoch": 9.02, |
| "learning_rate": 0.00047222222222222224, |
| "loss": 3.6134, |
| "step": 350 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 0.00044444444444444436, |
| "loss": 3.4876, |
| "step": 400 |
| }, |
| { |
| "epoch": 12.02, |
| "learning_rate": 0.00041666666666666664, |
| "loss": 3.3228, |
| "step": 450 |
| }, |
| { |
| "epoch": 13.03, |
| "learning_rate": 0.00038888888888888887, |
| "loss": 3.2223, |
| "step": 500 |
| }, |
| { |
| "epoch": 15.01, |
| "learning_rate": 0.0003611111111111111, |
| "loss": 3.1724, |
| "step": 550 |
| }, |
| { |
| "epoch": 16.02, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 3.0668, |
| "step": 600 |
| }, |
| { |
| "epoch": 18.0, |
| "learning_rate": 0.00030555555555555555, |
| "loss": 3.0338, |
| "step": 650 |
| }, |
| { |
| "epoch": 19.01, |
| "learning_rate": 0.0002777777777777778, |
| "loss": 2.9462, |
| "step": 700 |
| }, |
| { |
| "epoch": 20.02, |
| "learning_rate": 0.00025, |
| "loss": 2.8965, |
| "step": 750 |
| }, |
| { |
| "epoch": 22.01, |
| "learning_rate": 0.00022222222222222218, |
| "loss": 2.8837, |
| "step": 800 |
| }, |
| { |
| "epoch": 23.02, |
| "learning_rate": 0.00019444444444444443, |
| "loss": 2.8106, |
| "step": 850 |
| }, |
| { |
| "epoch": 24.03, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 2.7726, |
| "step": 900 |
| }, |
| { |
| "epoch": 26.01, |
| "learning_rate": 0.0001388888888888889, |
| "loss": 2.7668, |
| "step": 950 |
| }, |
| { |
| "epoch": 27.02, |
| "learning_rate": 0.00011111111111111109, |
| "loss": 2.7047, |
| "step": 1000 |
| }, |
| { |
| "epoch": 27.02, |
| "eval_loss": 3.4166903495788574, |
| "eval_runtime": 2.4384, |
| "eval_samples_per_second": 54.135, |
| "eval_steps_per_second": 3.691, |
| "step": 1000 |
| }, |
| { |
| "epoch": 27.02, |
| "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 3.4166903495788574, |
| "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 30.468408184611675, |
| "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.4384, |
| "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 54.135, |
| "step": 1000 |
| }, |
| { |
| "epoch": 29.0, |
| "learning_rate": 8.333333333333333e-05, |
| "loss": 2.7036, |
| "step": 1050 |
| }, |
| { |
| "epoch": 30.02, |
| "learning_rate": 5.5555555555555545e-05, |
| "loss": 2.6476, |
| "step": 1100 |
| } |
| ], |
| "max_steps": 1200, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 2.9864634089472e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
