| { |
| "best_metric": 0.8600789143532662, |
| "best_model_checkpoint": "training_with_callbacks/checkpoint-7880", |
| "epoch": 10.0, |
| "global_step": 15760, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.9368020304568528e-05, |
| "loss": 0.5589, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 1.8733502538071068e-05, |
| "loss": 0.4001, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 1.81002538071066e-05, |
| "loss": 0.3671, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8556491163135005, |
| "eval_loss": 0.33663880825042725, |
| "eval_macro_f1": 0.8274802013644363, |
| "eval_micro_f1": 0.8556491163135005, |
| "eval_runtime": 45.4196, |
| "eval_samples_per_second": 237.937, |
| "eval_steps_per_second": 14.883, |
| "step": 1576 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 1.7465736040609138e-05, |
| "loss": 0.3096, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 1.6831218274111674e-05, |
| "loss": 0.2976, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 1.6196700507614215e-05, |
| "loss": 0.3043, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8647173128527806, |
| "eval_loss": 0.3377376198768616, |
| "eval_macro_f1": 0.8410857961930669, |
| "eval_micro_f1": 0.8647173128527806, |
| "eval_runtime": 45.0937, |
| "eval_samples_per_second": 239.656, |
| "eval_steps_per_second": 14.991, |
| "step": 3152 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 1.5562182741116755e-05, |
| "loss": 0.2492, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 1.4927664974619292e-05, |
| "loss": 0.2329, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 1.4293147208121828e-05, |
| "loss": 0.2413, |
| "step": 4500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8739705746275562, |
| "eval_loss": 0.32710105180740356, |
| "eval_macro_f1": 0.8518710972157342, |
| "eval_micro_f1": 0.8739705746275562, |
| "eval_runtime": 45.1151, |
| "eval_samples_per_second": 239.543, |
| "eval_steps_per_second": 14.984, |
| "step": 4728 |
| }, |
| { |
| "epoch": 3.17, |
| "learning_rate": 1.3658629441624367e-05, |
| "loss": 0.2021, |
| "step": 5000 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 1.30253807106599e-05, |
| "loss": 0.1933, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 1.2392131979695431e-05, |
| "loss": 0.1887, |
| "step": 6000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.872119922272601, |
| "eval_loss": 0.367958664894104, |
| "eval_macro_f1": 0.8499428993945666, |
| "eval_micro_f1": 0.8721199222726009, |
| "eval_runtime": 45.2612, |
| "eval_samples_per_second": 238.77, |
| "eval_steps_per_second": 14.936, |
| "step": 6304 |
| }, |
| { |
| "epoch": 4.12, |
| "learning_rate": 1.175761421319797e-05, |
| "loss": 0.1702, |
| "step": 6500 |
| }, |
| { |
| "epoch": 4.44, |
| "learning_rate": 1.1123096446700508e-05, |
| "loss": 0.1574, |
| "step": 7000 |
| }, |
| { |
| "epoch": 4.76, |
| "learning_rate": 1.0488578680203047e-05, |
| "loss": 0.1494, |
| "step": 7500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8798926621634126, |
| "eval_loss": 0.3825337588787079, |
| "eval_macro_f1": 0.8600789143532662, |
| "eval_micro_f1": 0.8798926621634126, |
| "eval_runtime": 44.9299, |
| "eval_samples_per_second": 240.53, |
| "eval_steps_per_second": 15.046, |
| "step": 7880 |
| }, |
| { |
| "epoch": 5.08, |
| "learning_rate": 9.855329949238578e-06, |
| "loss": 0.1449, |
| "step": 8000 |
| }, |
| { |
| "epoch": 5.39, |
| "learning_rate": 9.220812182741118e-06, |
| "loss": 0.1263, |
| "step": 8500 |
| }, |
| { |
| "epoch": 5.71, |
| "learning_rate": 8.586294416243655e-06, |
| "loss": 0.1255, |
| "step": 9000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8775793467197187, |
| "eval_loss": 0.471343457698822, |
| "eval_macro_f1": 0.8558476837008455, |
| "eval_micro_f1": 0.8775793467197187, |
| "eval_runtime": 45.3421, |
| "eval_samples_per_second": 238.343, |
| "eval_steps_per_second": 14.909, |
| "step": 9456 |
| }, |
| { |
| "epoch": 6.03, |
| "learning_rate": 7.951776649746194e-06, |
| "loss": 0.1259, |
| "step": 9500 |
| }, |
| { |
| "epoch": 6.35, |
| "learning_rate": 7.319796954314721e-06, |
| "loss": 0.0964, |
| "step": 10000 |
| }, |
| { |
| "epoch": 6.66, |
| "learning_rate": 6.68527918781726e-06, |
| "loss": 0.1086, |
| "step": 10500 |
| }, |
| { |
| "epoch": 6.98, |
| "learning_rate": 6.050761421319798e-06, |
| "loss": 0.1077, |
| "step": 11000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8795225316924216, |
| "eval_loss": 0.5118919610977173, |
| "eval_macro_f1": 0.8578917168529726, |
| "eval_micro_f1": 0.8795225316924216, |
| "eval_runtime": 45.4537, |
| "eval_samples_per_second": 237.759, |
| "eval_steps_per_second": 14.872, |
| "step": 11032 |
| }, |
| { |
| "epoch": 7.3, |
| "learning_rate": 5.416243654822335e-06, |
| "loss": 0.0846, |
| "step": 11500 |
| }, |
| { |
| "epoch": 7.61, |
| "learning_rate": 4.781725888324874e-06, |
| "loss": 0.0851, |
| "step": 12000 |
| }, |
| { |
| "epoch": 7.93, |
| "learning_rate": 4.1472081218274114e-06, |
| "loss": 0.0875, |
| "step": 12500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8807254557231424, |
| "eval_loss": 0.5281736254692078, |
| "eval_macro_f1": 0.8573342434559597, |
| "eval_micro_f1": 0.8807254557231424, |
| "eval_runtime": 45.6116, |
| "eval_samples_per_second": 236.935, |
| "eval_steps_per_second": 14.821, |
| "step": 12608 |
| }, |
| { |
| "epoch": 8.25, |
| "learning_rate": 3.5126903553299495e-06, |
| "loss": 0.0705, |
| "step": 13000 |
| }, |
| { |
| "epoch": 8.57, |
| "learning_rate": 2.8781725888324876e-06, |
| "loss": 0.0711, |
| "step": 13500 |
| }, |
| { |
| "epoch": 8.88, |
| "learning_rate": 2.2449238578680207e-06, |
| "loss": 0.0702, |
| "step": 14000 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8808179883408902, |
| "eval_loss": 0.591612696647644, |
| "eval_macro_f1": 0.8563906267141775, |
| "eval_micro_f1": 0.8808179883408902, |
| "eval_runtime": 45.3025, |
| "eval_samples_per_second": 238.552, |
| "eval_steps_per_second": 14.922, |
| "step": 14184 |
| }, |
| { |
| "epoch": 9.2, |
| "learning_rate": 1.6116751269035535e-06, |
| "loss": 0.063, |
| "step": 14500 |
| }, |
| { |
| "epoch": 9.52, |
| "learning_rate": 9.771573604060914e-07, |
| "loss": 0.0609, |
| "step": 15000 |
| }, |
| { |
| "epoch": 9.84, |
| "learning_rate": 3.4263959390862946e-07, |
| "loss": 0.0539, |
| "step": 15500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.8817433145183677, |
| "eval_loss": 0.6316967010498047, |
| "eval_macro_f1": 0.8560485298070233, |
| "eval_micro_f1": 0.8817433145183678, |
| "eval_runtime": 45.5653, |
| "eval_samples_per_second": 237.176, |
| "eval_steps_per_second": 14.836, |
| "step": 15760 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 15760, |
| "total_flos": 1.3269191906021376e+17, |
| "train_loss": 0.1755784906106552, |
| "train_runtime": 5214.2121, |
| "train_samples_per_second": 96.718, |
| "train_steps_per_second": 3.023 |
| } |
| ], |
| "max_steps": 15760, |
| "num_train_epochs": 10, |
| "total_flos": 1.3269191906021376e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
