| { |
| "best_metric": 0.9400093918760273, |
| "best_model_checkpoint": "model_saves/roberta-large_spell_10k_1_p3/checkpoint-536", |
| "epoch": 8.0, |
| "global_step": 2144, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9394000380147363, |
| "eval_loss": 0.42779237031936646, |
| "eval_runtime": 3.428, |
| "eval_samples_per_second": 1278.298, |
| "eval_steps_per_second": 10.21, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9400093918760273, |
| "eval_loss": 0.44778749346733093, |
| "eval_runtime": 3.421, |
| "eval_samples_per_second": 1280.926, |
| "eval_steps_per_second": 10.231, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9385279352407786, |
| "eval_loss": 0.47391462326049805, |
| "eval_runtime": 3.4347, |
| "eval_samples_per_second": 1275.806, |
| "eval_steps_per_second": 10.19, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.2854, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9385894296671474, |
| "eval_loss": 0.5202155113220215, |
| "eval_runtime": 3.4286, |
| "eval_samples_per_second": 1278.079, |
| "eval_steps_per_second": 10.208, |
| "step": 1072 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9398584510113038, |
| "eval_loss": 0.586251974105835, |
| "eval_runtime": 3.4236, |
| "eval_samples_per_second": 1279.933, |
| "eval_steps_per_second": 10.223, |
| "step": 1340 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9392379163452186, |
| "eval_loss": 0.6210373640060425, |
| "eval_runtime": 3.4049, |
| "eval_samples_per_second": 1286.985, |
| "eval_steps_per_second": 10.279, |
| "step": 1608 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9384999832287928, |
| "eval_loss": 0.6681624054908752, |
| "eval_runtime": 3.4013, |
| "eval_samples_per_second": 1288.333, |
| "eval_steps_per_second": 10.29, |
| "step": 1876 |
| }, |
| { |
| "epoch": 7.46, |
| "learning_rate": 1e-05, |
| "loss": 0.1207, |
| "step": 2000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9382092823041402, |
| "eval_loss": 0.7321578860282898, |
| "eval_runtime": 3.4179, |
| "eval_samples_per_second": 1282.092, |
| "eval_steps_per_second": 10.24, |
| "step": 2144 |
| }, |
| { |
| "epoch": 8.0, |
| "step": 2144, |
| "total_flos": 2.819055740256256e+16, |
| "train_loss": 0.04357551994608409, |
| "train_runtime": 253.8864, |
| "train_samples_per_second": 2026.733, |
| "train_steps_per_second": 15.834 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 2.819055740256256e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
