llama-2-chat-hagrid-att-seg-proba-rag-agent-13b
This model is a fine-tuned version of meta-llama/Llama-2-13b-chat-hf on the AttriRAG/ragnroll_train_data_hagrid_seg_proba dataset. It achieves the following results on the evaluation set:
- Loss: 1.1339
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3629 | 0.98 | 22 | 1.2015 |
| 1.2369 | 2.0 | 45 | 1.1331 |
| 1.1925 | 2.98 | 67 | 1.1213 |
| 1.1988 | 4.0 | 90 | 1.1191 |
| 1.0622 | 4.98 | 112 | 1.1235 |
| 1.025 | 6.0 | 135 | 1.1315 |
| 0.9374 | 6.98 | 157 | 1.1338 |
| 1.067 | 7.82 | 176 | 1.1339 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.15.2
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for AttriRAG/ragnroll_llama2_13b
Base model
meta-llama/Llama-2-13b-chat-hf