LLM for ARC
Collection
4 items
•
Updated
heavy-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/transduction_heavy_100k_jsonl and the barc0/transduction_heavy_suggestfunction_100k_jsonl datasets. It achieves the following results on the evaluation set:
- Loss: 0.0319
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: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0446 | 1.0 | 1478 | 0.0433 |
| 0.0229 | 2.0 | 2956 | 0.0323 |
| 0.014 | 3.0 | 4434 | 0.0319 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1
- Downloads last month
- 29
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.