End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: bert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: bert_sst5_padding70model
|
| 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 |
+
# bert_sst5_padding70model
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 4.3219
|
| 21 |
+
- Accuracy: 0.5195
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 20
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 52 |
+
| 1.455 | 1.0 | 534 | 1.3095 | 0.4014 |
|
| 53 |
+
| 1.0688 | 2.0 | 1068 | 1.0861 | 0.5231 |
|
| 54 |
+
| 0.8152 | 3.0 | 1602 | 1.1682 | 0.5317 |
|
| 55 |
+
| 0.6373 | 4.0 | 2136 | 1.3330 | 0.5330 |
|
| 56 |
+
| 0.4456 | 5.0 | 2670 | 1.6174 | 0.5167 |
|
| 57 |
+
| 0.3164 | 6.0 | 3204 | 1.8698 | 0.5190 |
|
| 58 |
+
| 0.2454 | 7.0 | 3738 | 2.1769 | 0.5167 |
|
| 59 |
+
| 0.1684 | 8.0 | 4272 | 2.6182 | 0.5281 |
|
| 60 |
+
| 0.1367 | 9.0 | 4806 | 2.9459 | 0.5068 |
|
| 61 |
+
| 0.1176 | 10.0 | 5340 | 3.2425 | 0.5104 |
|
| 62 |
+
| 0.1056 | 11.0 | 5874 | 3.3523 | 0.5262 |
|
| 63 |
+
| 0.0844 | 12.0 | 6408 | 3.5235 | 0.5258 |
|
| 64 |
+
| 0.0538 | 13.0 | 6942 | 3.7476 | 0.5181 |
|
| 65 |
+
| 0.0614 | 14.0 | 7476 | 3.8546 | 0.5131 |
|
| 66 |
+
| 0.0369 | 15.0 | 8010 | 3.9777 | 0.5217 |
|
| 67 |
+
| 0.0229 | 16.0 | 8544 | 4.1242 | 0.5176 |
|
| 68 |
+
| 0.0183 | 17.0 | 9078 | 4.1762 | 0.5181 |
|
| 69 |
+
| 0.014 | 18.0 | 9612 | 4.2317 | 0.5222 |
|
| 70 |
+
| 0.012 | 19.0 | 10146 | 4.2420 | 0.5235 |
|
| 71 |
+
| 0.0143 | 20.0 | 10680 | 4.3219 | 0.5195 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.33.2
|
| 77 |
+
- Pytorch 2.0.1+cu117
|
| 78 |
+
- Datasets 2.14.5
|
| 79 |
+
- Tokenizers 0.13.3
|