org_modelorg_model

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0305
• F1 Micro: 0.7988
• F1 Macro: 0.7745
• F1 Weighted: 0.8091

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	F1 Weighted
1.7847	0.0064	25	1.4983	0.7827	0.7547	0.7929
1.3333	0.0127	50	1.2986	0.7926	0.7660	0.8031
1.2721	0.0191	75	1.2255	0.7755	0.7520	0.7862
1.127	0.0255	100	1.1722	0.7945	0.7694	0.8053
1.1108	0.0318	125	1.1561	0.7922	0.7556	0.7971
1.0969	0.0382	150	1.1181	0.7875	0.7581	0.7955
1.0714	0.0446	175	1.1001	0.7884	0.7658	0.7993
1.0219	0.0510	200	1.0758	0.8000	0.7727	0.8091
1.0979	0.0573	225	1.0671	0.7973	0.7656	0.8040
1.0846	0.0637	250	1.0632	0.7866	0.7582	0.7944
0.9977	0.0701	275	1.0590	0.7934	0.7600	0.7991
1.1262	0.0764	300	1.0404	0.7984	0.7699	0.8066
1.0066	0.0828	325	1.0396	0.7981	0.7681	0.8053
1.0534	0.0892	350	1.0360	0.8005	0.7768	0.8113
1.0302	0.0955	375	1.0320	0.7993	0.7754	0.8099
1.0965	0.1019	400	1.0305	0.7988	0.7745	0.8091

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.3.0+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1