abhinavp's picture
Model save
219709a verified
---
tags:
- generated_from_trainer
model-index:
- name: superlative-quantifier-lstm-2
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. -->
# superlative-quantifier-lstm-2
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9856
## 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: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7739 | 0.03 | 76320 | 4.7591 |
| 4.4948 | 1.03 | 152640 | 4.4813 |
| 4.3521 | 0.03 | 228960 | 4.3474 |
| 4.2673 | 1.03 | 305280 | 4.2657 |
| 4.2044 | 0.03 | 381600 | 4.2106 |
| 4.1584 | 1.03 | 457920 | 4.1697 |
| 4.1237 | 0.03 | 534240 | 4.1397 |
| 4.0937 | 1.03 | 610560 | 4.1153 |
| 4.0646 | 0.03 | 686880 | 4.0961 |
| 4.0397 | 1.03 | 763200 | 4.0802 |
| 4.0188 | 0.03 | 839520 | 4.0677 |
| 3.9979 | 1.03 | 915840 | 4.0576 |
| 3.9875 | 0.03 | 992160 | 4.0478 |
| 3.9694 | 1.03 | 1068480 | 4.0406 |
| 3.9548 | 0.03 | 1144800 | 4.0342 |
| 3.9407 | 0.03 | 1221120 | 4.0289 |
| 3.9259 | 1.03 | 1297440 | 4.0236 |
| 3.9208 | 2.03 | 1373760 | 4.0188 |
| 3.9086 | 0.03 | 1450080 | 4.0158 |
| 3.9049 | 1.03 | 1526400 | 4.0122 |
| 3.9024 | 2.03 | 1602720 | 4.0090 |
| 3.8964 | 0.03 | 1679040 | 4.0069 |
| 3.8947 | 0.03 | 1755360 | 4.0043 |
| 3.8923 | 0.03 | 1831680 | 4.0024 |
| 3.8834 | 0.03 | 1908000 | 4.0003 |
| 3.8735 | 1.03 | 1984320 | 3.9990 |
| 3.8695 | 0.03 | 2060640 | 3.9974 |
| 3.8628 | 1.03 | 2136960 | 3.9960 |
| 3.8635 | 2.03 | 2213280 | 3.9948 |
| 3.8567 | 0.03 | 2289600 | 3.9936 |
| 3.8478 | 1.03 | 2365920 | 3.9924 |
| 3.8426 | 2.03 | 2442240 | 3.9914 |
| 3.8355 | 0.03 | 2518560 | 3.9904 |
| 3.8351 | 0.03 | 2594880 | 3.9893 |
| 3.8282 | 1.03 | 2671200 | 3.9884 |
| 3.8322 | 2.03 | 2747520 | 3.9875 |
| 3.8311 | 0.03 | 2823840 | 3.9872 |
| 3.8322 | 0.03 | 2900160 | 3.9865 |
| 3.8356 | 1.03 | 2976480 | 3.9860 |
| 3.8367 | 2.02 | 3052726 | 3.9856 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3