| { |
| "best_metric": 0.10133440792560577, |
| "best_model_checkpoint": "intent_classification_model/checkpoint-344", |
| "epoch": 16.0, |
| "eval_steps": 500, |
| "global_step": 1376, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.956140350877193, |
| "eval_loss": 0.24781915545463562, |
| "eval_runtime": 0.1669, |
| "eval_samples_per_second": 2049.176, |
| "eval_steps_per_second": 131.818, |
| "step": 86 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9766081871345029, |
| "eval_loss": 0.10303749144077301, |
| "eval_runtime": 0.2792, |
| "eval_samples_per_second": 1224.804, |
| "eval_steps_per_second": 78.789, |
| "step": 172 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.12486349791288376, |
| "eval_runtime": 0.1527, |
| "eval_samples_per_second": 2239.207, |
| "eval_steps_per_second": 144.043, |
| "step": 258 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9766081871345029, |
| "eval_loss": 0.10133440792560577, |
| "eval_runtime": 0.1513, |
| "eval_samples_per_second": 2260.581, |
| "eval_steps_per_second": 145.418, |
| "step": 344 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9766081871345029, |
| "eval_loss": 0.11906354874372482, |
| "eval_runtime": 0.1397, |
| "eval_samples_per_second": 2448.535, |
| "eval_steps_per_second": 157.508, |
| "step": 430 |
| }, |
| { |
| "epoch": 5.81, |
| "learning_rate": 1.2732558139534886e-05, |
| "loss": 0.1903, |
| "step": 500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9678362573099415, |
| "eval_loss": 0.14922283589839935, |
| "eval_runtime": 0.1511, |
| "eval_samples_per_second": 2264.082, |
| "eval_steps_per_second": 145.643, |
| "step": 516 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.10685376077890396, |
| "eval_runtime": 0.1562, |
| "eval_samples_per_second": 2189.014, |
| "eval_steps_per_second": 140.814, |
| "step": 602 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.12596090137958527, |
| "eval_runtime": 0.1543, |
| "eval_samples_per_second": 2216.873, |
| "eval_steps_per_second": 142.606, |
| "step": 688 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9707602339181286, |
| "eval_loss": 0.129041388630867, |
| "eval_runtime": 0.1334, |
| "eval_samples_per_second": 2563.696, |
| "eval_steps_per_second": 164.916, |
| "step": 774 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.12375017255544662, |
| "eval_runtime": 0.1513, |
| "eval_samples_per_second": 2261.041, |
| "eval_steps_per_second": 145.447, |
| "step": 860 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.12813875079154968, |
| "eval_runtime": 0.1546, |
| "eval_samples_per_second": 2212.042, |
| "eval_steps_per_second": 142.295, |
| "step": 946 |
| }, |
| { |
| "epoch": 11.63, |
| "learning_rate": 5.465116279069767e-06, |
| "loss": 0.0258, |
| "step": 1000 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.13388033211231232, |
| "eval_runtime": 0.1607, |
| "eval_samples_per_second": 2128.444, |
| "eval_steps_per_second": 136.917, |
| "step": 1032 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.1308409869670868, |
| "eval_runtime": 0.1401, |
| "eval_samples_per_second": 2441.546, |
| "eval_steps_per_second": 157.058, |
| "step": 1118 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.13211463391780853, |
| "eval_runtime": 0.1539, |
| "eval_samples_per_second": 2222.296, |
| "eval_steps_per_second": 142.955, |
| "step": 1204 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.13366281986236572, |
| "eval_runtime": 0.1507, |
| "eval_samples_per_second": 2269.433, |
| "eval_steps_per_second": 145.987, |
| "step": 1290 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.13524049520492554, |
| "eval_runtime": 0.1603, |
| "eval_samples_per_second": 2133.42, |
| "eval_steps_per_second": 137.238, |
| "step": 1376 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1376, |
| "num_train_epochs": 16, |
| "save_steps": 500, |
| "total_flos": 70181981180580.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
