| { | |
| "best_metric": 0.06275933235883713, | |
| "best_model_checkpoint": "intent_classification_model/checkpoint-152", | |
| "epoch": 16.0, | |
| "eval_steps": 500, | |
| "global_step": 1216, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9867549668874173, | |
| "eval_loss": 0.20886486768722534, | |
| "eval_runtime": 0.1475, | |
| "eval_samples_per_second": 2048.099, | |
| "eval_steps_per_second": 128.854, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9834437086092715, | |
| "eval_loss": 0.06275933235883713, | |
| "eval_runtime": 0.1586, | |
| "eval_samples_per_second": 1904.103, | |
| "eval_steps_per_second": 119.795, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9867549668874173, | |
| "eval_loss": 0.06509935110807419, | |
| "eval_runtime": 0.1445, | |
| "eval_samples_per_second": 2090.586, | |
| "eval_steps_per_second": 131.527, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9768211920529801, | |
| "eval_loss": 0.08112386614084244, | |
| "eval_runtime": 0.1335, | |
| "eval_samples_per_second": 2262.833, | |
| "eval_steps_per_second": 142.364, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9701986754966887, | |
| "eval_loss": 0.11257749050855637, | |
| "eval_runtime": 0.134, | |
| "eval_samples_per_second": 2253.71, | |
| "eval_steps_per_second": 141.79, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.11174333095550537, | |
| "eval_runtime": 0.1339, | |
| "eval_samples_per_second": 2255.512, | |
| "eval_steps_per_second": 141.903, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 1.1776315789473684e-05, | |
| "loss": 0.1883, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9768211920529801, | |
| "eval_loss": 0.10020075738430023, | |
| "eval_runtime": 0.145, | |
| "eval_samples_per_second": 2083.04, | |
| "eval_steps_per_second": 131.052, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.116866335272789, | |
| "eval_runtime": 0.1348, | |
| "eval_samples_per_second": 2240.912, | |
| "eval_steps_per_second": 140.985, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9701986754966887, | |
| "eval_loss": 0.14152054488658905, | |
| "eval_runtime": 0.1308, | |
| "eval_samples_per_second": 2309.736, | |
| "eval_steps_per_second": 145.314, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.1344088315963745, | |
| "eval_runtime": 0.1195, | |
| "eval_samples_per_second": 2526.256, | |
| "eval_steps_per_second": 158.937, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.13409321010112762, | |
| "eval_runtime": 0.1399, | |
| "eval_samples_per_second": 2159.267, | |
| "eval_steps_per_second": 135.848, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.12705937027931213, | |
| "eval_runtime": 0.1366, | |
| "eval_samples_per_second": 2210.321, | |
| "eval_steps_per_second": 139.06, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.13874845206737518, | |
| "eval_runtime": 0.1374, | |
| "eval_samples_per_second": 2197.254, | |
| "eval_steps_per_second": 138.238, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 3.5526315789473687e-06, | |
| "loss": 0.018, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.13716736435890198, | |
| "eval_runtime": 0.1193, | |
| "eval_samples_per_second": 2530.546, | |
| "eval_steps_per_second": 159.207, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.13588877022266388, | |
| "eval_runtime": 0.1396, | |
| "eval_samples_per_second": 2163.789, | |
| "eval_steps_per_second": 136.132, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9735099337748344, | |
| "eval_loss": 0.13579562306404114, | |
| "eval_runtime": 0.1288, | |
| "eval_samples_per_second": 2345.226, | |
| "eval_steps_per_second": 147.547, | |
| "step": 1216 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1216, | |
| "num_train_epochs": 16, | |
| "save_steps": 500, | |
| "total_flos": 62384098266840.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |