|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: pp-mod-subj2-transformer-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. --> |
|
|
|
|
|
# pp-mod-subj2-transformer-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: 3.9223 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2283 | 0.03 | 76320 | 4.2421 | |
|
|
| 4.0271 | 1.03 | 152640 | 4.0738 | |
|
|
| 3.9174 | 0.03 | 228960 | 3.9986 | |
|
|
| 3.8489 | 1.03 | 305280 | 3.9597 | |
|
|
| 3.7995 | 0.03 | 381600 | 3.9343 | |
|
|
| 3.7523 | 1.03 | 457920 | 3.9182 | |
|
|
| 3.7141 | 0.03 | 534240 | 3.9086 | |
|
|
| 3.6827 | 1.03 | 610560 | 3.9013 | |
|
|
| 3.6528 | 0.03 | 686880 | 3.8980 | |
|
|
| 3.631 | 1.03 | 763200 | 3.8950 | |
|
|
| 3.6044 | 0.03 | 839520 | 3.8937 | |
|
|
| 3.585 | 1.03 | 915840 | 3.8944 | |
|
|
| 3.5657 | 0.03 | 992160 | 3.8947 | |
|
|
| 3.5512 | 1.03 | 1068480 | 3.8962 | |
|
|
| 3.5323 | 0.03 | 1144800 | 3.8979 | |
|
|
| 3.5208 | 1.03 | 1221120 | 3.8985 | |
|
|
| 3.5069 | 0.03 | 1297440 | 3.9003 | |
|
|
| 3.4961 | 1.03 | 1373760 | 3.9020 | |
|
|
| 3.4837 | 0.03 | 1450080 | 3.9046 | |
|
|
| 3.4734 | 1.03 | 1526400 | 3.9057 | |
|
|
| 3.467 | 0.03 | 1602720 | 3.9072 | |
|
|
| 3.4521 | 0.03 | 1679040 | 3.9103 | |
|
|
| 3.4393 | 0.03 | 1755360 | 3.9114 | |
|
|
| 3.4263 | 1.03 | 1831680 | 3.9125 | |
|
|
| 3.4128 | 0.03 | 1908000 | 3.9144 | |
|
|
| 3.4044 | 1.03 | 1984320 | 3.9173 | |
|
|
| 3.3896 | 0.03 | 2060640 | 3.9184 | |
|
|
| 3.3783 | 1.03 | 2136960 | 3.9205 | |
|
|
| 3.3693 | 0.03 | 2213280 | 3.9207 | |
|
|
| 3.3573 | 1.03 | 2289600 | 3.9216 | |
|
|
| 3.3449 | 0.03 | 2365920 | 3.9224 | |
|
|
| 3.3398 | 1.03 | 2442240 | 3.9248 | |
|
|
| 3.3304 | 0.03 | 2518560 | 3.9255 | |
|
|
| 3.3236 | 0.03 | 2594880 | 3.9254 | |
|
|
| 3.3142 | 1.03 | 2671200 | 3.9252 | |
|
|
| 3.3084 | 0.03 | 2747520 | 3.9259 | |
|
|
| 3.3044 | 0.03 | 2823840 | 3.9250 | |
|
|
| 3.2939 | 1.03 | 2900160 | 3.9242 | |
|
|
| 3.2868 | 0.03 | 2976480 | 3.9232 | |
|
|
| 3.2769 | 0.02 | 3052726 | 3.9223 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
