update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
- f1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: distilbert-base-uncased_finetuned_SPEECH_TEXT_DISPLAY
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# distilbert-base-uncased_finetuned_SPEECH_TEXT_DISPLAY
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.2319
|
| 21 |
+
- Accuracy: 0.7368
|
| 22 |
+
- F1: 0.7282
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 2e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 40
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 53 |
+
| 1.0388 | 1.0 | 19 | 0.9710 | 0.4211 | 0.2495 |
|
| 54 |
+
| 0.9432 | 2.0 | 38 | 0.9188 | 0.5789 | 0.4964 |
|
| 55 |
+
| 0.7889 | 3.0 | 57 | 0.8813 | 0.5789 | 0.5263 |
|
| 56 |
+
| 0.5823 | 4.0 | 76 | 0.7974 | 0.6842 | 0.6452 |
|
| 57 |
+
| 0.4275 | 5.0 | 95 | 0.7669 | 0.6316 | 0.5965 |
|
| 58 |
+
| 0.2995 | 6.0 | 114 | 0.6675 | 0.8421 | 0.8344 |
|
| 59 |
+
| 0.1676 | 7.0 | 133 | 0.7643 | 0.7368 | 0.7333 |
|
| 60 |
+
| 0.0976 | 8.0 | 152 | 0.7864 | 0.7895 | 0.7839 |
|
| 61 |
+
| 0.0477 | 9.0 | 171 | 0.7838 | 0.7895 | 0.7772 |
|
| 62 |
+
| 0.0247 | 10.0 | 190 | 1.1000 | 0.6842 | 0.6817 |
|
| 63 |
+
| 0.0127 | 11.0 | 209 | 0.9551 | 0.7895 | 0.7772 |
|
| 64 |
+
| 0.0084 | 12.0 | 228 | 1.1178 | 0.6842 | 0.6792 |
|
| 65 |
+
| 0.0071 | 13.0 | 247 | 1.1489 | 0.6842 | 0.6792 |
|
| 66 |
+
| 0.0055 | 14.0 | 266 | 1.1278 | 0.7368 | 0.7282 |
|
| 67 |
+
| 0.0051 | 15.0 | 285 | 1.0925 | 0.7368 | 0.7282 |
|
| 68 |
+
| 0.0049 | 16.0 | 304 | 1.1031 | 0.7368 | 0.7282 |
|
| 69 |
+
| 0.0042 | 17.0 | 323 | 1.1299 | 0.7368 | 0.7282 |
|
| 70 |
+
| 0.0037 | 18.0 | 342 | 1.1644 | 0.7368 | 0.7282 |
|
| 71 |
+
| 0.0035 | 19.0 | 361 | 1.1659 | 0.7368 | 0.7282 |
|
| 72 |
+
| 0.0031 | 20.0 | 380 | 1.1704 | 0.7368 | 0.7282 |
|
| 73 |
+
| 0.0028 | 21.0 | 399 | 1.1664 | 0.7368 | 0.7282 |
|
| 74 |
+
| 0.0029 | 22.0 | 418 | 1.1693 | 0.7368 | 0.7282 |
|
| 75 |
+
| 0.0028 | 23.0 | 437 | 1.1858 | 0.7368 | 0.7282 |
|
| 76 |
+
| 0.0024 | 24.0 | 456 | 1.2007 | 0.7368 | 0.7282 |
|
| 77 |
+
| 0.0024 | 25.0 | 475 | 1.1982 | 0.7368 | 0.7282 |
|
| 78 |
+
| 0.0022 | 26.0 | 494 | 1.1896 | 0.7368 | 0.7282 |
|
| 79 |
+
| 0.002 | 27.0 | 513 | 1.1955 | 0.7368 | 0.7282 |
|
| 80 |
+
| 0.0019 | 28.0 | 532 | 1.2016 | 0.7368 | 0.7282 |
|
| 81 |
+
| 0.0019 | 29.0 | 551 | 1.2066 | 0.7368 | 0.7282 |
|
| 82 |
+
| 0.0021 | 30.0 | 570 | 1.2120 | 0.7368 | 0.7282 |
|
| 83 |
+
| 0.0019 | 31.0 | 589 | 1.2145 | 0.7368 | 0.7282 |
|
| 84 |
+
| 0.0019 | 32.0 | 608 | 1.2179 | 0.7368 | 0.7282 |
|
| 85 |
+
| 0.0018 | 33.0 | 627 | 1.2221 | 0.7368 | 0.7282 |
|
| 86 |
+
| 0.0019 | 34.0 | 646 | 1.2237 | 0.7368 | 0.7282 |
|
| 87 |
+
| 0.0016 | 35.0 | 665 | 1.2275 | 0.7368 | 0.7282 |
|
| 88 |
+
| 0.0016 | 36.0 | 684 | 1.2294 | 0.7368 | 0.7282 |
|
| 89 |
+
| 0.0015 | 37.0 | 703 | 1.2305 | 0.7368 | 0.7282 |
|
| 90 |
+
| 0.0017 | 38.0 | 722 | 1.2315 | 0.7368 | 0.7282 |
|
| 91 |
+
| 0.0016 | 39.0 | 741 | 1.2318 | 0.7368 | 0.7282 |
|
| 92 |
+
| 0.0018 | 40.0 | 760 | 1.2319 | 0.7368 | 0.7282 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.22.2
|
| 98 |
+
- Pytorch 1.10.2
|
| 99 |
+
- Datasets 2.5.2
|
| 100 |
+
- Tokenizers 0.12.1
|