---
base_model: haryoaw/scenario-MDBT-TCR-MSV-CL
datasets:
- massive
library_name: transformers
license: mit
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: scenario-NON-KD-PO-COPY-D2_data-AmazonScience_massive_all_1_144
  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. -->

# scenario-NON-KD-PO-COPY-D2_data-AmazonScience_massive_all_1_144

This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR-MSV-CL](https://huggingface.co/haryoaw/scenario-MDBT-TCR-MSV-CL) on the massive dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5665
- Accuracy: 0.8558
- F1: 0.8311

## 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 44
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch  | Step   | Validation Loss | Accuracy | F1     |
|:-------------:|:------:|:------:|:---------------:|:--------:|:------:|
| 0.5779        | 0.2672 | 5000   | 0.7006          | 0.8215   | 0.7800 |
| 0.4401        | 0.5344 | 10000  | 0.6600          | 0.8367   | 0.8068 |
| 0.3571        | 0.8017 | 15000  | 0.6767          | 0.8420   | 0.8071 |
| 0.2321        | 1.0689 | 20000  | 0.7530          | 0.8447   | 0.8130 |
| 0.216         | 1.3361 | 25000  | 0.7689          | 0.8438   | 0.8194 |
| 0.2181        | 1.6033 | 30000  | 0.7638          | 0.8471   | 0.8226 |
| 0.2032        | 1.8706 | 35000  | 0.7350          | 0.8514   | 0.8280 |
| 0.1469        | 2.1378 | 40000  | 0.8351          | 0.8493   | 0.8240 |
| 0.1467        | 2.4050 | 45000  | 0.8268          | 0.8528   | 0.8282 |
| 0.1486        | 2.6722 | 50000  | 0.8476          | 0.8514   | 0.8299 |
| 0.1479        | 2.9394 | 55000  | 0.8659          | 0.8525   | 0.8308 |
| 0.1067        | 3.2067 | 60000  | 1.0128          | 0.8449   | 0.8221 |
| 0.103         | 3.4739 | 65000  | 0.9880          | 0.8515   | 0.8268 |
| 0.1118        | 3.7411 | 70000  | 0.9170          | 0.8539   | 0.8299 |
| 0.0911        | 4.0083 | 75000  | 1.0024          | 0.8516   | 0.8287 |
| 0.077         | 4.2756 | 80000  | 1.0851          | 0.8512   | 0.8301 |
| 0.0813        | 4.5428 | 85000  | 1.0700          | 0.8526   | 0.8337 |
| 0.0803        | 4.8100 | 90000  | 1.0729          | 0.8540   | 0.8309 |
| 0.0553        | 5.0772 | 95000  | 1.1523          | 0.8521   | 0.8297 |
| 0.0601        | 5.3444 | 100000 | 1.1660          | 0.8537   | 0.8309 |
| 0.0546        | 5.6117 | 105000 | 1.2625          | 0.8524   | 0.8287 |
| 0.0541        | 5.8789 | 110000 | 1.2396          | 0.8510   | 0.8307 |
| 0.0447        | 6.1461 | 115000 | 1.3191          | 0.8519   | 0.8285 |
| 0.0501        | 6.4133 | 120000 | 1.2660          | 0.8523   | 0.8267 |
| 0.0471        | 6.6806 | 125000 | 1.3370          | 0.8522   | 0.8273 |
| 0.0455        | 6.9478 | 130000 | 1.3123          | 0.8524   | 0.8255 |
| 0.0319        | 7.2150 | 135000 | 1.3950          | 0.8549   | 0.8314 |
| 0.0359        | 7.4822 | 140000 | 1.4211          | 0.8531   | 0.8293 |
| 0.0377        | 7.7495 | 145000 | 1.4256          | 0.8532   | 0.8271 |
| 0.0255        | 8.0167 | 150000 | 1.4738          | 0.8537   | 0.8300 |
| 0.0229        | 8.2839 | 155000 | 1.4912          | 0.8562   | 0.8319 |
| 0.0216        | 8.5511 | 160000 | 1.4886          | 0.8573   | 0.8335 |
| 0.0236        | 8.8183 | 165000 | 1.4929          | 0.8554   | 0.8304 |
| 0.0161        | 9.0856 | 170000 | 1.5159          | 0.8569   | 0.8331 |
| 0.0146        | 9.3528 | 175000 | 1.5538          | 0.8568   | 0.8324 |
| 0.0175        | 9.6200 | 180000 | 1.5709          | 0.8554   | 0.8301 |
| 0.0204        | 9.8872 | 185000 | 1.5665          | 0.8558   | 0.8311 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.19.1