cheesewafer/Llama3-8B-Instruct-sft-sciworld
0450
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Llama3-8B-Instruct SFT for ScienceWorld
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct for the ScienceWorld environment.
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: 2e-05
- trainbatchsize: 4
- evalbatchsize: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- totaltrainbatch_size: 32
- totalevalbatch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- lrschedulerwarmup_ratio: 0.1
- num_epochs: 3
Training results
Framework versions
- Transformers 4.45.0
- Pytorch 2.1.2
- Datasets 3.0.0
- Tokenizers 0.20.0