Update README.md
Browse files
README.md
CHANGED
|
@@ -1,87 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: vikp/line_detector_3
|
| 3 |
-
tags:
|
| 4 |
-
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
- name: line_detector_3
|
| 7 |
results: []
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
-
|
| 13 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vikp/line_detector/runs/5crpjf7u)
|
| 14 |
-
# line_detector_3
|
| 15 |
-
|
| 16 |
-
This model is a fine-tuned version of [vikp/line_detector_3](https://huggingface.co/vikp/line_detector_3) on an unknown dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.1230
|
| 19 |
-
|
| 20 |
-
## Model description
|
| 21 |
-
|
| 22 |
-
More information needed
|
| 23 |
-
|
| 24 |
-
## Intended uses & limitations
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Training and evaluation data
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training procedure
|
| 33 |
-
|
| 34 |
-
### Training hyperparameters
|
| 35 |
-
|
| 36 |
-
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate: 6e-05
|
| 38 |
-
- train_batch_size: 20
|
| 39 |
-
- eval_batch_size: 12
|
| 40 |
-
- seed: 42
|
| 41 |
-
- distributed_type: multi-GPU
|
| 42 |
-
- gradient_accumulation_steps: 4
|
| 43 |
-
- total_train_batch_size: 80
|
| 44 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
-
- lr_scheduler_type: cosine
|
| 46 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
-
- num_epochs: 4
|
| 48 |
-
- mixed_precision_training: Native AMP
|
| 49 |
-
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
-
|:-------------:|:------:|:-----:|:---------------:|
|
| 54 |
-
| 0.1302 | 0.1527 | 1000 | 0.1327 |
|
| 55 |
-
| 0.1147 | 0.3054 | 2000 | 0.1314 |
|
| 56 |
-
| 0.1395 | 0.4581 | 3000 | 0.1318 |
|
| 57 |
-
| 0.1302 | 0.6108 | 4000 | 0.1312 |
|
| 58 |
-
| 0.1349 | 0.7635 | 5000 | 0.1315 |
|
| 59 |
-
| 0.1431 | 0.9162 | 6000 | 0.1305 |
|
| 60 |
-
| 0.1318 | 1.0689 | 7000 | 0.1305 |
|
| 61 |
-
| 0.118 | 1.2216 | 8000 | 0.1295 |
|
| 62 |
-
| 0.1116 | 1.3743 | 9000 | 0.1286 |
|
| 63 |
-
| 0.1513 | 1.5270 | 10000 | 0.1273 |
|
| 64 |
-
| 0.1158 | 1.6796 | 11000 | 0.1290 |
|
| 65 |
-
| 0.1408 | 1.8323 | 12000 | 0.1289 |
|
| 66 |
-
| 0.1227 | 1.9850 | 13000 | 0.1281 |
|
| 67 |
-
| 0.1347 | 2.1377 | 14000 | 0.1291 |
|
| 68 |
-
| 0.1066 | 2.2904 | 15000 | 0.1285 |
|
| 69 |
-
| 0.116 | 2.4431 | 16000 | 0.1275 |
|
| 70 |
-
| 0.1164 | 2.5958 | 17000 | 0.1253 |
|
| 71 |
-
| 0.1269 | 2.7485 | 18000 | 0.1259 |
|
| 72 |
-
| 0.1293 | 2.9012 | 19000 | 0.1256 |
|
| 73 |
-
| 0.1241 | 3.0539 | 20000 | 0.1245 |
|
| 74 |
-
| 0.1329 | 3.2066 | 21000 | 0.1263 |
|
| 75 |
-
| 0.1166 | 3.3593 | 22000 | 0.1266 |
|
| 76 |
-
| 0.1292 | 3.5120 | 23000 | 0.1230 |
|
| 77 |
-
| 0.1189 | 3.6647 | 24000 | 0.1274 |
|
| 78 |
-
| 0.1073 | 3.8174 | 25000 | 0.1251 |
|
| 79 |
-
| 0.1308 | 3.9701 | 26000 | 0.1230 |
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
### Framework versions
|
| 83 |
-
|
| 84 |
-
- Transformers 4.42.3
|
| 85 |
-
- Pytorch 2.3.1+cu121
|
| 86 |
-
- Datasets 2.20.0
|
| 87 |
-
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
base_model: vikp/line_detector_3
|
|
|
|
|
|
|
| 3 |
model-index:
|
| 4 |
- name: line_detector_3
|
| 5 |
results: []
|
| 6 |
+
license: cc-by-nc-sa-4.0
|
| 7 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|