| { |
| "best_metric": 2.981389284133911, |
| "best_model_checkpoint": "output/the-weeknd/checkpoint-106", |
| "epoch": 1.0, |
| "global_step": 106, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00013644815685030044, |
| "loss": 3.409, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00013420910752136943, |
| "loss": 3.2483, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00013053193113565, |
| "loss": 3.0377, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00012549723002188386, |
| "loss": 3.0596, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00011921536294226248, |
| "loss": 3.0678, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00011182402606970539, |
| "loss": 3.2314, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00010348523473933653, |
| "loss": 2.9575, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 9.438177213303674e-05, |
| "loss": 3.1683, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 8.471318274057549e-05, |
| "loss": 2.8512, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 7.469139841915333e-05, |
| "loss": 3.019, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 6.45360929264912e-05, |
| "loss": 2.9363, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 5.4469866754360664e-05, |
| "loss": 2.8768, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 4.4713367809200255e-05, |
| "loss": 3.0883, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3.548045489267091e-05, |
| "loss": 2.7904, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 2.6973509996844513e-05, |
| "loss": 2.8138, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 1.9379002166758867e-05, |
| "loss": 2.7592, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 1.2863400168810263e-05, |
| "loss": 2.9738, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 7.569523557760342e-06, |
| "loss": 2.7268, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 3.6134121256024702e-06, |
| "loss": 2.7342, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 1.0817823527948575e-06, |
| "loss": 2.7255, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 3.012661549670772e-08, |
| "loss": 2.8881, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.981389284133911, |
| "eval_runtime": 7.0259, |
| "eval_samples_per_second": 21.35, |
| "eval_steps_per_second": 2.704, |
| "step": 106 |
| } |
| ], |
| "max_steps": 106, |
| "num_train_epochs": 1, |
| "total_flos": 110526529536000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
