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
- 567
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.