|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: superlative-quantifier-lstm-4 |
|
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-4 |
|
|
|
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: 3.9898 |
|
|
|
## 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: 4 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7903 | 0.03 | 76320 | 4.7765 | |
|
| 4.5105 | 1.03 | 152640 | 4.4958 | |
|
| 4.3672 | 0.03 | 228960 | 4.3606 | |
|
| 4.282 | 1.03 | 305280 | 4.2770 | |
|
| 4.2196 | 0.03 | 381600 | 4.2205 | |
|
| 4.1715 | 1.03 | 457920 | 4.1797 | |
|
| 4.1356 | 2.03 | 534240 | 4.1483 | |
|
| 4.1053 | 0.03 | 610560 | 4.1234 | |
|
| 4.0757 | 1.03 | 686880 | 4.1042 | |
|
| 4.0511 | 2.03 | 763200 | 4.0878 | |
|
| 4.0272 | 0.03 | 839520 | 4.0751 | |
|
| 4.009 | 1.03 | 915840 | 4.0643 | |
|
| 3.9972 | 0.03 | 992160 | 4.0550 | |
|
| 3.9818 | 1.03 | 1068480 | 4.0474 | |
|
| 3.9665 | 0.03 | 1144800 | 4.0404 | |
|
| 3.9515 | 1.03 | 1221120 | 4.0340 | |
|
| 3.9376 | 0.03 | 1297440 | 4.0286 | |
|
| 3.9283 | 1.03 | 1373760 | 4.0239 | |
|
| 3.9186 | 0.03 | 1450080 | 4.0205 | |
|
| 3.9169 | 1.03 | 1526400 | 4.0173 | |
|
| 3.9113 | 0.03 | 1602720 | 4.0143 | |
|
| 3.9058 | 1.03 | 1679040 | 4.0113 | |
|
| 3.9044 | 2.03 | 1755360 | 4.0088 | |
|
| 3.8991 | 0.03 | 1831680 | 4.0061 | |
|
| 3.891 | 1.03 | 1908000 | 4.0039 | |
|
| 3.8847 | 0.03 | 1984320 | 4.0019 | |
|
| 3.8766 | 0.03 | 2060640 | 4.0003 | |
|
| 3.8712 | 1.03 | 2136960 | 3.9989 | |
|
| 3.8716 | 0.03 | 2213280 | 3.9979 | |
|
| 3.8644 | 0.03 | 2289600 | 3.9967 | |
|
| 3.8586 | 1.03 | 2365920 | 3.9958 | |
|
| 3.8509 | 2.03 | 2442240 | 3.9947 | |
|
| 3.8473 | 0.03 | 2518560 | 3.9940 | |
|
| 3.8436 | 1.03 | 2594880 | 3.9932 | |
|
| 3.8378 | 2.03 | 2671200 | 3.9925 | |
|
| 3.8413 | 0.03 | 2747520 | 3.9915 | |
|
| 3.8424 | 0.03 | 2823840 | 3.9909 | |
|
| 3.8415 | 1.03 | 2900160 | 3.9904 | |
|
| 3.843 | 0.03 | 2976480 | 3.9900 | |
|
| 3.8446 | 1.02 | 3052726 | 3.9898 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
