| { |
| "best_metric": 2.4571237564086914, |
| "best_model_checkpoint": "output/van-morrison/checkpoint-115", |
| "epoch": 1.0, |
| "global_step": 115, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00013656105589809228, |
| "loss": 3.0979, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00013465612591205902, |
| "loss": 2.9758, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00013152069528327408, |
| "loss": 2.6762, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00012721317115188912, |
| "loss": 2.6908, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.0001218137945423232, |
| "loss": 2.7183, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00011542314562479968, |
| "loss": 2.7673, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0001081602700970799, |
| "loss": 2.8558, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00010016046158835704, |
| "loss": 2.8996, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 9.157274139492964e-05, |
| "loss": 2.656, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 8.255708249541069e-05, |
| "loss": 2.578, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 7.328142955681643e-05, |
| "loss": 2.6088, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 6.391857044318358e-05, |
| "loss": 2.5993, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 5.4642917504589336e-05, |
| "loss": 2.5848, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 4.562725860507035e-05, |
| "loss": 2.635, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 3.703953841164296e-05, |
| "loss": 2.5448, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 2.903972990292012e-05, |
| "loss": 2.625, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 2.177685437520034e-05, |
| "loss": 2.6109, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 1.5386205457676793e-05, |
| "loss": 2.5033, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 9.986828848110884e-06, |
| "loss": 2.4888, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 5.679304716725937e-06, |
| "loss": 2.5557, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 2.5438740879409795e-06, |
| "loss": 2.6542, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 6.389441019077102e-07, |
| "loss": 2.5193, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0, |
| "loss": 2.5805, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.4571237564086914, |
| "eval_runtime": 6.8446, |
| "eval_samples_per_second": 22.353, |
| "eval_steps_per_second": 2.922, |
| "step": 115 |
| } |
| ], |
| "max_steps": 115, |
| "num_train_epochs": 1, |
| "total_flos": 120063688704000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
