Mistral_ei_oc_structured_train
This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the emollms_ei_oc_structured dataset. It achieves the following results on the evaluation set:
- Loss: 0.0778
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.4849 | 0.3604 | 10 | 0.1087 |
0.0931 | 0.7207 | 20 | 0.0948 |
0.0758 | 1.0811 | 30 | 0.0815 |
0.067 | 1.4414 | 40 | 0.0778 |
0.0619 | 1.8018 | 50 | 0.0781 |
0.059 | 2.1622 | 60 | 0.0818 |
0.0497 | 2.5225 | 70 | 0.0838 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for Holmeister/Mistral_ei_oc_structured_train
Base model
mistralai/Mistral-7B-v0.3
Adapter
this model