🌐 NoMIRACL Dataset [EMNLP'24]
Collection
A collection of multilingual relevance assessment datasets. We also have SFT fine-tuned models (Mistral-7B & Llama-3 8B)
•
7 items
•
Updated
Meta-Llama-3-8B-Instruct-nomiracl-sft
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the nthakur/nomiracl-instruct dataset. It achieves the following results on the evaluation set:
- Loss: 1.6358
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6576 | 0.2981 | 200 | 1.6656 |
| 1.6447 | 0.5961 | 400 | 1.6409 |
| 1.6245 | 0.8942 | 600 | 1.6358 |
Framework versions
- PEFT 0.7.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for nthakur/Meta-Llama-3-8B-Instruct-nomiracl-sft
Base model
meta-llama/Meta-Llama-3-8B-Instruct