barc0/induction-20k-25seeds-barc-llama3.1-8b-instruct-lora64-induction-gpt4omini35k_lr2e-4_epoch3
014
<!-- 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. -->
induction-20k-25seeds-barc-llama3.1-8b-instruct-lora64-induction-gpt4omini35klr2e-4epoch3
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/induction20kgpt4o-minigeneratedproblemsseed25.jsonlmessagesformat0.3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3318
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
- trainbatchsize: 8
- evalbatchsize: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 128
- 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
- PEFT 0.13.0
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1