Downloads · 30 days
11
38% of all-time downloads
train_4
Thalesian/train_4
train_4 is a machine learning model from Thalesian. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
29
Public
Parameters
60.5M
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors242 MB · 99%
At a glance
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- May 3, 2025
- Updated
- Jun 14, 2025
- SHA
- 7f60b0d1
Model card
From the Hugging Face model README
<!-- 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. -->
train_4
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2634
- Bleu: 41.2138
- Chrf: 62.1018
- Meteor: 0.6063
- Gen Len: 12.0513
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Meteor | Gen Len |
|---|---|---|---|---|---|---|---|
| 0.0315 | 1.0 | 7999 | 0.2397 | 41.3664 | 62.1386 | 0.6072 | 12.0471 |
| 0.031 | 2.0 | 15998 | 0.2417 | 41.2882 | 61.9925 | 0.6082 | 12.0537 |
| 0.0308 | 3.0 | 23997 | 0.2431 | 41.3403 | 62.1009 | 0.607 | 12.0402 |
| 0.0307 | 4.0 | 31996 | 0.2440 | 41.3147 | 62.0719 | 0.6058 | 12.0619 |
| 0.03 | 5.0 | 39995 | 0.2460 | 41.5271 | 62.2126 | 0.6075 | 12.0566 |
| 0.0294 | 6.0 | 47994 | 0.2482 | 41.4353 | 62.1959 | 0.6087 | 12.0842 |
| 0.0294 | 7.0 | 55993 | 0.2486 | 41.2568 | 62.2425 | 0.608 | 12.0799 |
| 0.029 | 8.0 | 63992 | 0.2501 | 41.1446 | 62.0782 | 0.6069 | 12.0694 |
| 0.0285 | 9.0 | 71991 | 0.2489 | 41.1554 | 61.9691 | 0.606 | 12.0449 |
| 0.0283 | 10.0 | 79990 | 0.2518 | 40.9903 | 62.0095 | 0.607 | 12.0369 |
| 0.0278 | 11.0 | 87989 | 0.2523 | 41.0357 | 62.2308 | 0.6075 | 12.0701 |
| 0.028 | 12.0 | 95988 | 0.2534 | 40.7796 | 61.9287 | 0.6058 | 12.0524 |
| 0.0275 | 13.0 | 103987 | 0.2546 | 41.2298 | 62.1716 | 0.6072 | 12.0691 |
| 0.027 | 14.0 | 111986 | 0.2565 | 41.0546 | 62.0676 | 0.6068 | 12.0681 |
| 0.0269 | 15.0 | 119985 | 0.2577 | 41.2507 | 62.1826 | 0.6075 | 12.0539 |
| 0.0265 | 16.0 | 127984 | 0.2578 | 41.0927 | 62.1228 | 0.607 | 12.0877 |
| 0.0265 | 17.0 | 135983 | 0.2609 | 41.0459 | 62.1203 | 0.607 | 12.067 |
| 0.0258 | 18.0 | 143982 | 0.2632 | 41.0598 | 62.0328 | 0.6064 | 12.077 |
| 0.0259 | 19.0 | 151981 | 0.2606 | 41.1115 | 62.1225 | 0.6077 | 12.0667 |
| 0.0256 | 20.0 | 159980 | 0.2634 | 41.2138 | 62.1018 | 0.6063 | 12.0513 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.8.0.dev20250429
- Datasets 2.14.0
- Tokenizers 0.21.1
- Library
- transformers
- Type
- t5
- Created
- May 3, 2025
- Updated
- Jun 14, 2025