|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: seq2seq_huggingface_mix_results |
|
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. --> |
|
|
|
# seq2seq_huggingface_mix_results |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 7.0175 |
|
|
|
## 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: 12 |
|
- eval_batch_size: 12 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 48 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 10.5072 | 0.0480 | 10 | 10.4491 | |
|
| 10.3574 | 0.0959 | 20 | 10.1991 | |
|
| 10.0831 | 0.1439 | 30 | 9.8790 | |
|
| 9.7946 | 0.1918 | 40 | 9.5780 | |
|
| 9.5118 | 0.2398 | 50 | 9.3344 | |
|
| 9.3333 | 0.2878 | 60 | 9.1722 | |
|
| 9.1888 | 0.3357 | 70 | 9.0610 | |
|
| 9.0913 | 0.3837 | 80 | 8.9742 | |
|
| 9.0007 | 0.4317 | 90 | 8.9005 | |
|
| 8.9134 | 0.4796 | 100 | 8.8328 | |
|
| 8.8583 | 0.5276 | 110 | 8.7615 | |
|
| 8.7722 | 0.5755 | 120 | 8.6873 | |
|
| 8.7092 | 0.6235 | 130 | 8.6137 | |
|
| 8.6223 | 0.6715 | 140 | 8.5340 | |
|
| 8.5312 | 0.7194 | 150 | 8.4538 | |
|
| 8.4582 | 0.7674 | 160 | 8.3681 | |
|
| 8.3748 | 0.8153 | 170 | 8.2801 | |
|
| 8.2637 | 0.8633 | 180 | 8.1936 | |
|
| 8.1704 | 0.9113 | 190 | 8.1001 | |
|
| 8.0697 | 0.9592 | 200 | 8.0079 | |
|
| 7.9792 | 1.0072 | 210 | 7.9126 | |
|
| 7.9 | 1.0552 | 220 | 7.8175 | |
|
| 7.8134 | 1.1031 | 230 | 7.7236 | |
|
| 7.7153 | 1.1511 | 240 | 7.6328 | |
|
| 7.6087 | 1.1990 | 250 | 7.5477 | |
|
| 7.5328 | 1.2470 | 260 | 7.4634 | |
|
| 7.4347 | 1.2950 | 270 | 7.3862 | |
|
| 7.3531 | 1.3429 | 280 | 7.3179 | |
|
| 7.3059 | 1.3909 | 290 | 7.2513 | |
|
| 7.2403 | 1.4388 | 300 | 7.1955 | |
|
| 7.2128 | 1.4868 | 310 | 7.1506 | |
|
| 7.1508 | 1.5348 | 320 | 7.1105 | |
|
| 7.1104 | 1.5827 | 330 | 7.0835 | |
|
| 7.067 | 1.6307 | 340 | 7.0655 | |
|
| 7.0594 | 1.6787 | 350 | 7.0558 | |
|
| 7.0591 | 1.7266 | 360 | 7.0411 | |
|
| 7.0129 | 1.7746 | 370 | 7.0381 | |
|
| 7.0107 | 1.8225 | 380 | 7.0344 | |
|
| 7.0549 | 1.8705 | 390 | 7.0268 | |
|
| 7.0358 | 1.9185 | 400 | 7.0249 | |
|
| 7.0395 | 1.9664 | 410 | 7.0242 | |
|
| 7.0105 | 2.0144 | 420 | 7.0215 | |
|
| 7.0113 | 2.0624 | 430 | 7.0259 | |
|
| 6.9985 | 2.1103 | 440 | 7.0213 | |
|
| 7.0218 | 2.1583 | 450 | 7.0218 | |
|
| 6.9735 | 2.2062 | 460 | 7.0275 | |
|
| 7.0132 | 2.2542 | 470 | 7.0254 | |
|
| 7.0241 | 2.3022 | 480 | 7.0219 | |
|
| 7.0127 | 2.3501 | 490 | 7.0238 | |
|
| 6.9644 | 2.3981 | 500 | 7.0249 | |
|
| 7.0103 | 2.4460 | 510 | 7.0259 | |
|
| 7.006 | 2.4940 | 520 | 7.0266 | |
|
| 6.9882 | 2.5420 | 530 | 7.0235 | |
|
| 7.0016 | 2.5899 | 540 | 7.0235 | |
|
| 7.002 | 2.6379 | 550 | 7.0217 | |
|
| 6.9782 | 2.6859 | 560 | 7.0196 | |
|
| 6.9833 | 2.7338 | 570 | 7.0198 | |
|
| 6.9967 | 2.7818 | 580 | 7.0202 | |
|
| 6.9644 | 2.8297 | 590 | 7.0196 | |
|
| 6.9825 | 2.8777 | 600 | 7.0199 | |
|
| 7.0097 | 2.9257 | 610 | 7.0178 | |
|
| 6.9909 | 2.9736 | 620 | 7.0175 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
