Downloads · 30 days
6
21% of all-time downloads
MistralAI_iwslt15_10000_2
Tohrumi/MistralAI_iwslt15_10000_2
MistralAI_iwslt15_10000_2 is a translation model from Tohrumi. Use it when you need text moved from one language to another. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
28
Public
Repo size
1.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors168 MB · 99%
At a glance
- Task
- Translation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Apr 27, 2024
- Updated
- Apr 27, 2024
- SHA
- c510177d
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. -->
MistralAI_iwslt15_10000_2
This model is a fine-tuned version of unsloth/mistral-7b-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0438
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 4269
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1684 | 0.32 | 100 | 1.0926 |
| 1.0883 | 0.64 | 200 | 1.0701 |
| 1.0672 | 0.96 | 300 | 1.0498 |
| 0.9315 | 1.28 | 400 | 1.0547 |
| 0.8973 | 1.6 | 500 | 1.0495 |
| 0.8831 | 1.92 | 600 | 1.0438 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.2
- Task
- Translation
- Library
- peft
- License
- apache-2.0
- Created
- Apr 27, 2024
- Updated
- Apr 27, 2024