| { |
| "best_metric": 0.795165784121227, |
| "best_model_checkpoint": "./checkpoints/clip-10240-supervised-multilingual-allnli/checkpoint-360", |
| "epoch": 1.024390243902439, |
| "global_step": 420, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 1.5e-05, |
| "loss": 0.8484, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 3e-05, |
| "loss": 0.7777, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 2.8421052631578946e-05, |
| "loss": 0.7529, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 2.6842105263157896e-05, |
| "loss": 0.7607, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 2.526315789473684e-05, |
| "loss": 0.7252, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 2.368421052631579e-05, |
| "loss": 0.7217, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 2.2105263157894736e-05, |
| "loss": 0.7206, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 2.0526315789473685e-05, |
| "loss": 0.7009, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 1.894736842105263e-05, |
| "loss": 0.6858, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 1.736842105263158e-05, |
| "loss": 0.6757, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 1.5789473684210526e-05, |
| "loss": 0.6694, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 1.4210526315789473e-05, |
| "loss": 0.67, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 1.263157894736842e-05, |
| "loss": 0.6589, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 1.1052631578947368e-05, |
| "loss": 0.6497, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 9.473684210526315e-06, |
| "loss": 0.6149, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 7.894736842105263e-06, |
| "loss": 0.6474, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 6.31578947368421e-06, |
| "loss": 0.6406, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 4.736842105263158e-06, |
| "loss": 0.6158, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 3.157894736842105e-06, |
| "loss": 0.6183, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 1.5789473684210526e-06, |
| "loss": 0.6133, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.0, |
| "loss": 0.5305, |
| "step": 420 |
| } |
| ], |
| "max_steps": 420, |
| "num_train_epochs": 2, |
| "total_flos": 0.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
