Downloads · 30 days
3
14% of all-time downloads
mistral-7b-expo-7b-L2EXPO-25-4
hZzy/mistral-7b-expo-7b-L2EXPO-25-4
mistral-7b-expo-7b-L2EXPO-25-4 is a machine learning model from hZzy. 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 peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
21
Public
Repo size
27.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.3 MB · 91%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Apr 13, 2025
- Updated
- Apr 13, 2025
- SHA
- d22b7bc4
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. -->
mistral-7b-expo-7b-L2EXPO-25-4
This model is a fine-tuned version of hZzy/mistral-7b-sft-25-1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4999
- Objective: 0.4940
- Reward Accuracy: 0.5839
- Logp Accuracy: 0.5408
- Log Diff Policy: 2.1519
- Chosen Logps: -96.3920
- Rejected Logps: -98.5440
- Chosen Rewards: -0.0186
- Rejected Rewards: -0.0371
- Logits: -2.4049
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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 12
- total_train_batch_size: 144
- total_eval_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Objective | Reward Accuracy | Logp Accuracy | Log Diff Policy | Chosen Logps | Rejected Logps | Chosen Rewards | Rejected Rewards | Logits |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6287 | 0.2022 | 100 | 0.5117 | 0.5059 | 0.5134 | 0.5050 | 0.3360 | -93.0305 | -93.3666 | 0.0151 | 0.0146 | -2.4626 |
| 0.605 | 0.4044 | 200 | 0.5099 | 0.5041 | 0.5330 | 0.5106 | 0.5330 | -91.7677 | -92.3007 | 0.0277 | 0.0253 | -2.4516 |
| 0.5935 | 0.6067 | 300 | 0.5062 | 0.4997 | 0.5615 | 0.5207 | 1.0350 | -88.0347 | -89.0698 | 0.0650 | 0.0576 | -2.4513 |
| 0.5815 | 0.8089 | 400 | 0.4999 | 0.4940 | 0.5839 | 0.5408 | 2.1519 | -96.3920 | -98.5440 | -0.0186 | -0.0371 | -2.4049 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.19.1
- Library
- peft
- License
- apache-2.0
- Created
- Apr 13, 2025
- Updated
- Apr 13, 2025