metadata

language:
  - zh
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - nycu-112-2-deeplearning-hw2
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
  - DandinPower/ZH-Reading-Comprehension-Mistral-Instruct
model-index:
  - name: mistral_7b_lora_completion_only
    results: []

mistral_7b_lora_completion_only

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the DandinPower/ZH-Reading-Comprehension-Mistral-Instruct dataset. It achieves the following results on the evaluation set:

Loss: 0.1344

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 16
total_eval_batch_size: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 700
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.1996	0.3690	250	0.1814
0.1856	0.7380	500	0.1344
0.1515	1.1070	750	0.1724
0.1547	1.4760	1000	0.1977
0.0953	1.8450	1250	0.1641
0.0788	2.2140	1500	0.1450
0.0715	2.5830	1750	0.1359
0.0646	2.9520	2000	0.1427

Framework versions

PEFT 0.10.0
Transformers 4.40.0
Pytorch 2.2.2+cu121
Datasets 2.19.0
Tokenizers 0.19.1