Mistral-7B-0.3_auto
Collection
36 items
•
Updated
Mistral-7B_task-1_120-samples_config-1_full_auto
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-1_auto and the GaetanMichelet/chat-120_ft_task-1_auto datasets. It achieves the following results on the evaluation set:
- Loss: 0.8231
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6872 | 1.0 | 11 | 1.5146 |
| 1.0353 | 2.0 | 22 | 1.0329 |
| 0.8377 | 3.0 | 33 | 0.8575 |
| 0.7346 | 4.0 | 44 | 0.8231 |
| 0.5798 | 5.0 | 55 | 0.8247 |
| 0.4162 | 6.0 | 66 | 0.8889 |
| 0.2904 | 7.0 | 77 | 1.0324 |
| 0.2039 | 8.0 | 88 | 1.1253 |
| 0.155 | 9.0 | 99 | 1.1651 |
| 0.1233 | 10.0 | 110 | 1.1567 |
| 0.1064 | 11.0 | 121 | 1.2436 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for GaetanMichelet/Mistral-7B_task-1_120-samples_config-1_full_auto
Base model
mistralai/Mistral-7B-v0.3
Finetuned
mistralai/Mistral-7B-Instruct-v0.3