SFT Final Models
Collection
Models that were trained on clembench v0.9 - v1.6
•
4 items
•
Updated
llama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps
This model is a fine-tuned version of meta-llama/Llama-3.1-70B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2135
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 7331
- optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- lr_scheduler_warmup_steps: 5
- training_steps: 600
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2173 | 0.0565 | 100 | 0.2761 |
| 0.1566 | 0.1130 | 200 | 0.2389 |
| 0.1592 | 0.1695 | 300 | 0.2348 |
| 0.1357 | 0.2260 | 400 | 0.2198 |
| 0.1349 | 0.2825 | 500 | 0.2149 |
| 0.1269 | 0.3390 | 600 | 0.2135 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.21.0
- Downloads last month
- 34
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 clembench-playpen/llama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps
Base model
meta-llama/Llama-3.1-70B
Finetuned
meta-llama/Llama-3.1-70B-Instruct