IDEA-AI4S/mol-vicuna-7b-v1.5-all-lora-ep5

<!-- 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. -->

sft

This model is a fine-tuned version of lmsys/vicuna-7b-v1.5 on the uspto1ktpl, the smol270ki2s, the smol270ks2i, the smol270ki2f, the smol270kf2i, the rcr57krp, the rcr10kcp, the rcr70ksp, the molinst125krs, the molinst125kfs, the bhsm10kyr and the hte4k_ras datasets.

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: 4
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 2
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 128
• —totalevalbatch_size: 8
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 200
• —num_epochs: 5.0

Training results

Framework versions

• —PEFT 0.10.0
• —Transformers 4.39.3
• —Pytorch 2.1.2
• —Datasets 2.16.1
• —Tokenizers 0.15.0