Downloads · 30 days
12
11% of all-time downloads
qwen-1_5b-sft-eng-hin-deu-sampled
Mayank6255/qwen-1_5b-sft-eng-hin-deu-sampled
qwen-1_5b-sft-eng-hin-deu-sampled is a text generation model from Mayank6255. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
110
Public
Repo size
22.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json407 MB · 85%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- qwen2
- Access
- Public
- Created
- Jan 6, 2026
- Updated
- Jan 6, 2026
- SHA
- 0dffbd90
Try a prompt
Base models
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. -->
qwen-1_5b-sft-eng-hin-deu-sampled
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the aya_eng_hin_deu_sampled_train dataset. It achieves the following results on the evaluation set:
- Loss: 1.2735
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 4
- total_eval_batch_size: 2
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4713 | 0.1502 | 500 | 1.3942 |
| 1.2315 | 0.3003 | 1000 | 1.3718 |
| 1.1988 | 0.4505 | 1500 | 1.3374 |
| 1.3186 | 0.6006 | 2000 | 1.3062 |
| 1.2864 | 0.7508 | 2500 | 1.2844 |
| 1.0945 | 0.9009 | 3000 | 1.2749 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- other
- Created
- Jan 6, 2026
- Updated
- Jan 6, 2026