| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 19.9984, |
| "global_step": 6240, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8859999775886536, |
| "eval_loss": 0.41977837681770325, |
| "eval_runtime": 6.3492, |
| "eval_samples_per_second": 157.5, |
| "eval_steps_per_second": 19.688, |
| "step": 312 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 3.4640443499072686e-05, |
| "loss": 0.3303, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9139999747276306, |
| "eval_loss": 0.2853889763355255, |
| "eval_runtime": 6.6289, |
| "eval_samples_per_second": 150.854, |
| "eval_steps_per_second": 18.857, |
| "step": 624 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8999999761581421, |
| "eval_loss": 0.5696914792060852, |
| "eval_runtime": 6.6792, |
| "eval_samples_per_second": 149.719, |
| "eval_steps_per_second": 18.715, |
| "step": 936 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 3.1622983263961825e-05, |
| "loss": 0.1347, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9229999780654907, |
| "eval_loss": 0.4335395395755768, |
| "eval_runtime": 6.4722, |
| "eval_samples_per_second": 154.508, |
| "eval_steps_per_second": 19.313, |
| "step": 1248 |
| }, |
| { |
| "epoch": 4.81, |
| "learning_rate": 2.860552302885096e-05, |
| "loss": 0.0664, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9190000295639038, |
| "eval_loss": 0.4839023947715759, |
| "eval_runtime": 6.7996, |
| "eval_samples_per_second": 147.068, |
| "eval_steps_per_second": 18.383, |
| "step": 1560 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9190000295639038, |
| "eval_loss": 0.5429013967514038, |
| "eval_runtime": 6.5724, |
| "eval_samples_per_second": 152.151, |
| "eval_steps_per_second": 19.019, |
| "step": 1872 |
| }, |
| { |
| "epoch": 6.41, |
| "learning_rate": 2.5588062793740103e-05, |
| "loss": 0.0351, |
| "step": 2000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9150000214576721, |
| "eval_loss": 0.6175604462623596, |
| "eval_runtime": 6.7693, |
| "eval_samples_per_second": 147.725, |
| "eval_steps_per_second": 18.466, |
| "step": 2184 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9269999861717224, |
| "eval_loss": 0.591762900352478, |
| "eval_runtime": 6.5318, |
| "eval_samples_per_second": 153.098, |
| "eval_steps_per_second": 19.137, |
| "step": 2496 |
| }, |
| { |
| "epoch": 8.01, |
| "learning_rate": 2.257060255862924e-05, |
| "loss": 0.0165, |
| "step": 2500 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9210000038146973, |
| "eval_loss": 0.6061341762542725, |
| "eval_runtime": 6.749, |
| "eval_samples_per_second": 148.17, |
| "eval_steps_per_second": 18.521, |
| "step": 2808 |
| }, |
| { |
| "epoch": 9.61, |
| "learning_rate": 1.9553142323518382e-05, |
| "loss": 0.015, |
| "step": 3000 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9200000166893005, |
| "eval_loss": 0.6652878522872925, |
| "eval_runtime": 6.6337, |
| "eval_samples_per_second": 150.747, |
| "eval_steps_per_second": 18.843, |
| "step": 3120 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.925000011920929, |
| "eval_loss": 0.6655992269515991, |
| "eval_runtime": 6.4644, |
| "eval_samples_per_second": 154.693, |
| "eval_steps_per_second": 19.337, |
| "step": 3432 |
| }, |
| { |
| "epoch": 11.22, |
| "learning_rate": 1.6535682088407518e-05, |
| "loss": 0.0069, |
| "step": 3500 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.9269999861717224, |
| "eval_loss": 0.6695793271064758, |
| "eval_runtime": 6.6791, |
| "eval_samples_per_second": 149.72, |
| "eval_steps_per_second": 18.715, |
| "step": 3744 |
| }, |
| { |
| "epoch": 12.82, |
| "learning_rate": 1.3518221853296657e-05, |
| "loss": 0.0041, |
| "step": 4000 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.9229999780654907, |
| "eval_loss": 0.7150284051895142, |
| "eval_runtime": 6.7408, |
| "eval_samples_per_second": 148.349, |
| "eval_steps_per_second": 18.544, |
| "step": 4056 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.9269999861717224, |
| "eval_loss": 0.6533876657485962, |
| "eval_runtime": 6.7726, |
| "eval_samples_per_second": 147.654, |
| "eval_steps_per_second": 18.457, |
| "step": 4368 |
| }, |
| { |
| "epoch": 14.42, |
| "learning_rate": 1.0500761618185796e-05, |
| "loss": 0.0068, |
| "step": 4500 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.925000011920929, |
| "eval_loss": 0.7126875519752502, |
| "eval_runtime": 6.7003, |
| "eval_samples_per_second": 149.246, |
| "eval_steps_per_second": 18.656, |
| "step": 4680 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.9330000281333923, |
| "eval_loss": 0.6162614822387695, |
| "eval_runtime": 6.7879, |
| "eval_samples_per_second": 147.32, |
| "eval_steps_per_second": 18.415, |
| "step": 4992 |
| }, |
| { |
| "epoch": 16.03, |
| "learning_rate": 7.483301383074935e-06, |
| "loss": 0.0031, |
| "step": 5000 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.9309999942779541, |
| "eval_loss": 0.645462155342102, |
| "eval_runtime": 6.6169, |
| "eval_samples_per_second": 151.128, |
| "eval_steps_per_second": 18.891, |
| "step": 5304 |
| }, |
| { |
| "epoch": 17.63, |
| "learning_rate": 4.465841147964074e-06, |
| "loss": 0.0015, |
| "step": 5500 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.9350000023841858, |
| "eval_loss": 0.6278481483459473, |
| "eval_runtime": 6.7752, |
| "eval_samples_per_second": 147.597, |
| "eval_steps_per_second": 18.45, |
| "step": 5616 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 0.9340000152587891, |
| "eval_loss": 0.6360601782798767, |
| "eval_runtime": 6.5534, |
| "eval_samples_per_second": 152.593, |
| "eval_steps_per_second": 19.074, |
| "step": 5928 |
| }, |
| { |
| "epoch": 19.23, |
| "learning_rate": 1.4483809128532133e-06, |
| "loss": 0.0015, |
| "step": 6000 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.9359999895095825, |
| "eval_loss": 0.6466162204742432, |
| "eval_runtime": 6.7187, |
| "eval_samples_per_second": 148.838, |
| "eval_steps_per_second": 18.605, |
| "step": 6240 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 6240, |
| "total_flos": 6577427171727360.0, |
| "train_loss": 0.04982372024477137, |
| "train_runtime": 4408.0257, |
| "train_samples_per_second": 22.686, |
| "train_steps_per_second": 1.416 |
| } |
| ], |
| "max_steps": 6240, |
| "num_train_epochs": 20, |
| "total_flos": 6577427171727360.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
