---
license: mit
base_model: allistair99/bert-base-uncased-BiLSTM-Optiparam-ADVQA36K-V6-frozen
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-BiLSTM-Optiparam-ADVQA36K-V17-frozen
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# bert-base-uncased-BiLSTM-Optiparam-ADVQA36K-V17-frozen

This model is a fine-tuned version of [allistair99/bert-base-uncased-BiLSTM-Optiparam-ADVQA36K-V6-frozen](https://huggingface.co/allistair99/bert-base-uncased-BiLSTM-Optiparam-ADVQA36K-V6-frozen) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9070

## 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: 3e-05
- train_batch_size: 6
- eval_batch_size: 60
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.6528        | 0.0599 | 100  | 3.7418          |
| 0.6524        | 0.1198 | 200  | 3.7774          |
| 0.6187        | 0.1796 | 300  | 3.8111          |
| 0.6459        | 0.2395 | 400  | 3.8232          |
| 0.6209        | 0.2994 | 500  | 3.8193          |
| 0.5822        | 0.3593 | 600  | 3.8461          |
| 0.6185        | 0.4192 | 700  | 3.8422          |
| 0.5614        | 0.4790 | 800  | 3.8721          |
| 0.5595        | 0.5389 | 900  | 3.8921          |
| 0.6357        | 0.5988 | 1000 | 3.9008          |
| 0.6525        | 0.6587 | 1100 | 3.8820          |
| 0.6087        | 0.7186 | 1200 | 3.8966          |
| 0.6543        | 0.7784 | 1300 | 3.8788          |
| 0.6059        | 0.8383 | 1400 | 3.8911          |
| 0.6144        | 0.8982 | 1500 | 3.8987          |
| 0.6643        | 0.9581 | 1600 | 3.8843          |
| 0.6235        | 1.0180 | 1700 | 3.8767          |
| 0.6359        | 1.0778 | 1800 | 3.8895          |
| 0.5603        | 1.1377 | 1900 | 3.9057          |
| 0.6097        | 1.1976 | 2000 | 3.9029          |
| 0.5495        | 1.2575 | 2100 | 3.9160          |
| 0.5933        | 1.3174 | 2200 | 3.9189          |
| 0.5581        | 1.3772 | 2300 | 3.9328          |
| 0.6335        | 1.4371 | 2400 | 3.9183          |
| 0.5758        | 1.4970 | 2500 | 3.9175          |
| 0.6225        | 1.5569 | 2600 | 3.9148          |
| 0.614         | 1.6168 | 2700 | 3.9207          |
| 0.6308        | 1.6766 | 2800 | 3.9118          |
| 0.6868        | 1.7365 | 2900 | 3.9006          |
| 0.6504        | 1.7964 | 3000 | 3.8873          |
| 0.6167        | 1.8563 | 3100 | 3.8818          |
| 0.6991        | 1.9162 | 3200 | 3.8855          |
| 0.6896        | 1.9760 | 3300 | 3.8765          |
| 0.5594        | 2.0359 | 3400 | 3.8792          |
| 0.4856        | 2.0958 | 3500 | 3.8959          |
| 0.4625        | 2.1557 | 3600 | 3.9098          |
| 0.5035        | 2.2156 | 3700 | 3.9176          |
| 0.5774        | 2.2754 | 3800 | 3.9170          |
| 0.5703        | 2.3353 | 3900 | 3.9172          |
| 0.5814        | 2.3952 | 4000 | 3.9216          |
| 0.606         | 2.4551 | 4100 | 3.9188          |
| 0.5638        | 2.5150 | 4200 | 3.9221          |
| 0.6057        | 2.5749 | 4300 | 3.9243          |
| 0.6336        | 2.6347 | 4400 | 3.9215          |
| 0.5966        | 2.6946 | 4500 | 3.9190          |
| 0.6996        | 2.7545 | 4600 | 3.9162          |
| 0.7667        | 2.8144 | 4700 | 3.9126          |
| 0.7258        | 2.8743 | 4800 | 3.9099          |
| 0.8214        | 2.9341 | 4900 | 3.9081          |
| 0.9071        | 2.9940 | 5000 | 3.9070          |


### Framework versions

- Transformers 4.41.0
- Pytorch 2.6.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1