ucla-cmllab/tinyllama-sft-vicuna-processed-indicator-0.6
023
<!-- 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. -->
tinyllama-sft-vicuna-processed-indicator-0.6-full
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the yihanwang617/vicunacleanprocessedindicator0.6 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8936
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: 16
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- 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: 1
Training results
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1