euneeei/hw-midm-7B-nsmc

Model Card for Model ID

euneeei/hw-midm-7B-nsmc

Training Data

• 한국어로 된 네이버 영화 리뷰 데이터셋입니다.

• train dataset : 3000개

• test dataset : 1000개

Factors

learning_rate : 1e-4-> 2e-4 max_steps=500 설정 warmup_steps=100 설정

[More Information Needed]

Metrics

	precision	recall	f1-score	support
negative	0.87	0.95	091	492
positive	0.94	0.87	0.90	508
accuracy			0.91	1000
macro avg	0.91	0.91	0.91	1000
weighted avg	0.91	0.91	0.91	1000

• confusion metrics

[[ 466, 26 ]

[68, 440]]

[More Information Needed]

Results

• 정확도 0.51 -> 0.91로 높아졌습니다

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: False
• load_in_4bit: True
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: nf4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: bfloat16

Framework versions

• PEFT 0.7.0