| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 29.025, |
| "global_step": 900, |
| "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": 10.9361, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00025, |
| "loss": 8.2553, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 0.0005, |
| "loss": 6.7321, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.03, |
| "learning_rate": 0.0005833333333333333, |
| "loss": 6.4515, |
| "step": 150 |
| }, |
| { |
| "epoch": 6.02, |
| "learning_rate": 0.0005555555555555556, |
| "loss": 6.2916, |
| "step": 200 |
| }, |
| { |
| "epoch": 8.01, |
| "learning_rate": 0.0005277777777777777, |
| "loss": 6.103, |
| "step": 250 |
| }, |
| { |
| "epoch": 9.03, |
| "learning_rate": 0.0005, |
| "loss": 5.7716, |
| "step": 300 |
| }, |
| { |
| "epoch": 11.02, |
| "learning_rate": 0.00047222222222222224, |
| "loss": 5.4902, |
| "step": 350 |
| }, |
| { |
| "epoch": 13.01, |
| "learning_rate": 0.00044444444444444436, |
| "loss": 5.1844, |
| "step": 400 |
| }, |
| { |
| "epoch": 14.03, |
| "learning_rate": 0.00041666666666666664, |
| "loss": 4.8669, |
| "step": 450 |
| }, |
| { |
| "epoch": 16.02, |
| "learning_rate": 0.00038888888888888887, |
| "loss": 4.6547, |
| "step": 500 |
| }, |
| { |
| "epoch": 18.01, |
| "learning_rate": 0.0003611111111111111, |
| "loss": 4.4311, |
| "step": 550 |
| }, |
| { |
| "epoch": 19.02, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 4.1923, |
| "step": 600 |
| }, |
| { |
| "epoch": 21.02, |
| "learning_rate": 0.00030555555555555555, |
| "loss": 4.0473, |
| "step": 650 |
| }, |
| { |
| "epoch": 23.01, |
| "learning_rate": 0.0002777777777777778, |
| "loss": 3.9047, |
| "step": 700 |
| }, |
| { |
| "epoch": 24.02, |
| "learning_rate": 0.00025, |
| "loss": 3.7631, |
| "step": 750 |
| }, |
| { |
| "epoch": 26.02, |
| "learning_rate": 0.00022222222222222218, |
| "loss": 3.7075, |
| "step": 800 |
| }, |
| { |
| "epoch": 28.01, |
| "learning_rate": 0.00019444444444444443, |
| "loss": 3.6326, |
| "step": 850 |
| }, |
| { |
| "epoch": 29.02, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 3.5357, |
| "step": 900 |
| } |
| ], |
| "max_steps": 1200, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 2.4406504833024e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
