|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: rel-cl2-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. --> |
|
|
|
|
|
# rel-cl2-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: 3.8732 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2351 | 0.03 | 76320 | 4.2024 | |
|
|
| 4.0288 | 1.03 | 152640 | 4.0335 | |
|
|
| 3.9259 | 0.03 | 228960 | 3.9588 | |
|
|
| 3.8543 | 1.03 | 305280 | 3.9178 | |
|
|
| 3.804 | 0.03 | 381600 | 3.8922 | |
|
|
| 3.7641 | 1.03 | 457920 | 3.8757 | |
|
|
| 3.7273 | 0.03 | 534240 | 3.8649 | |
|
|
| 3.6967 | 1.03 | 610560 | 3.8587 | |
|
|
| 3.6658 | 0.03 | 686880 | 3.8543 | |
|
|
| 3.6407 | 1.03 | 763200 | 3.8511 | |
|
|
| 3.614 | 0.03 | 839520 | 3.8498 | |
|
|
| 3.5939 | 1.03 | 915840 | 3.8499 | |
|
|
| 3.5759 | 0.03 | 992160 | 3.8488 | |
|
|
| 3.5578 | 1.03 | 1068480 | 3.8506 | |
|
|
| 3.5451 | 0.03 | 1144800 | 3.8510 | |
|
|
| 3.534 | 1.03 | 1221120 | 3.8518 | |
|
|
| 3.5188 | 0.03 | 1297440 | 3.8544 | |
|
|
| 3.5058 | 1.03 | 1373760 | 3.8540 | |
|
|
| 3.4925 | 0.03 | 1450080 | 3.8565 | |
|
|
| 3.4832 | 1.03 | 1526400 | 3.8572 | |
|
|
| 3.4735 | 0.03 | 1602720 | 3.8599 | |
|
|
| 3.4643 | 1.03 | 1679040 | 3.8618 | |
|
|
| 3.4536 | 0.03 | 1755360 | 3.8628 | |
|
|
| 3.4408 | 1.03 | 1831680 | 3.8638 | |
|
|
| 3.4261 | 0.03 | 1908000 | 3.8659 | |
|
|
| 3.4152 | 1.03 | 1984320 | 3.8671 | |
|
|
| 3.4012 | 0.03 | 2060640 | 3.8685 | |
|
|
| 3.3916 | 0.03 | 2136960 | 3.8690 | |
|
|
| 3.3778 | 1.03 | 2213280 | 3.8713 | |
|
|
| 3.3672 | 0.03 | 2289600 | 3.8723 | |
|
|
| 3.3592 | 1.03 | 2365920 | 3.8732 | |
|
|
| 3.3547 | 0.03 | 2442240 | 3.8739 | |
|
|
| 3.3438 | 1.03 | 2518560 | 3.8749 | |
|
|
| 3.335 | 0.03 | 2594880 | 3.8767 | |
|
|
| 3.3251 | 1.03 | 2671200 | 3.8758 | |
|
|
| 3.3196 | 0.03 | 2747520 | 3.8764 | |
|
|
| 3.3133 | 1.03 | 2823840 | 3.8760 | |
|
|
| 3.3082 | 0.03 | 2900160 | 3.8752 | |
|
|
| 3.299 | 0.03 | 2976480 | 3.8748 | |
|
|
| 3.2919 | 1.02 | 3052726 | 3.8732 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
