metadata
base_model: vikp/line_detector_3
tags:
- generated_from_trainer
model-index:
- name: line_detector_3
results: []
line_detector_3
This model is a fine-tuned version of vikp/line_detector_3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1230
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 20
- eval_batch_size: 12
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1302 | 0.1527 | 1000 | 0.1327 |
| 0.1147 | 0.3054 | 2000 | 0.1314 |
| 0.1395 | 0.4581 | 3000 | 0.1318 |
| 0.1302 | 0.6108 | 4000 | 0.1312 |
| 0.1349 | 0.7635 | 5000 | 0.1315 |
| 0.1431 | 0.9162 | 6000 | 0.1305 |
| 0.1318 | 1.0689 | 7000 | 0.1305 |
| 0.118 | 1.2216 | 8000 | 0.1295 |
| 0.1116 | 1.3743 | 9000 | 0.1286 |
| 0.1513 | 1.5270 | 10000 | 0.1273 |
| 0.1158 | 1.6796 | 11000 | 0.1290 |
| 0.1408 | 1.8323 | 12000 | 0.1289 |
| 0.1227 | 1.9850 | 13000 | 0.1281 |
| 0.1347 | 2.1377 | 14000 | 0.1291 |
| 0.1066 | 2.2904 | 15000 | 0.1285 |
| 0.116 | 2.4431 | 16000 | 0.1275 |
| 0.1164 | 2.5958 | 17000 | 0.1253 |
| 0.1269 | 2.7485 | 18000 | 0.1259 |
| 0.1293 | 2.9012 | 19000 | 0.1256 |
| 0.1241 | 3.0539 | 20000 | 0.1245 |
| 0.1329 | 3.2066 | 21000 | 0.1263 |
| 0.1166 | 3.3593 | 22000 | 0.1266 |
| 0.1292 | 3.5120 | 23000 | 0.1230 |
| 0.1189 | 3.6647 | 24000 | 0.1274 |
| 0.1073 | 3.8174 | 25000 | 0.1251 |
| 0.1308 | 3.9701 | 26000 | 0.1230 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1