chefdiff

This model is a fine-tuned version of avsolatorio/GIST-large-Embedding-v0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2966
• F1: 0.6367
• Roc Auc: 0.7929
• Accuracy: 0.0909

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 35

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.4056	1.0	50	0.3591	0.1786	0.5651	0.0182
0.3103	2.0	100	0.3197	0.3214	0.6256	0.0909
0.2522	3.0	150	0.2939	0.3551	0.6471	0.0727
0.2039	4.0	200	0.2741	0.4813	0.7092	0.1273
0.1632	5.0	250	0.2714	0.5493	0.7380	0.0909
0.1308	6.0	300	0.2532	0.4740	0.6994	0.1636
0.1056	7.0	350	0.2644	0.5641	0.7575	0.0909
0.0837	8.0	400	0.2541	0.5684	0.7579	0.1091
0.0679	9.0	450	0.2542	0.6112	0.7782	0.1273
0.0562	10.0	500	0.2587	0.6342	0.7932	0.1455
0.0476	11.0	550	0.2547	0.6399	0.7913	0.1455
0.0421	12.0	600	0.2683	0.6429	0.7998	0.1273
0.0369	13.0	650	0.2738	0.6146	0.7839	0.0909
0.0335	14.0	700	0.2678	0.6387	0.7920	0.0909
0.0298	15.0	750	0.2700	0.6123	0.7812	0.0909
0.0275	16.0	800	0.2737	0.6152	0.7804	0.0909
0.0255	17.0	850	0.2741	0.6339	0.7852	0.1091
0.024	18.0	900	0.2778	0.6564	0.8052	0.1091
0.0223	19.0	950	0.2815	0.6521	0.8019	0.1091
0.0213	20.0	1000	0.2778	0.6296	0.7902	0.0727
0.0201	21.0	1050	0.2861	0.6340	0.7900	0.0909
0.0192	22.0	1100	0.2819	0.6413	0.7949	0.0909
0.0185	23.0	1150	0.2913	0.6280	0.7888	0.0727
0.0178	24.0	1200	0.2874	0.6347	0.7938	0.0727
0.0172	25.0	1250	0.2890	0.6271	0.7879	0.0909
0.0166	26.0	1300	0.2900	0.6306	0.7901	0.0727
0.0161	27.0	1350	0.2944	0.6284	0.7896	0.0727
0.0158	28.0	1400	0.2931	0.6407	0.7954	0.0909
0.0154	29.0	1450	0.2942	0.6345	0.7937	0.0727
0.015	30.0	1500	0.2960	0.6413	0.7942	0.0909
0.0147	31.0	1550	0.2927	0.6477	0.7966	0.0909
0.0147	32.0	1600	0.2952	0.6396	0.7943	0.0909
0.0145	33.0	1650	0.2965	0.6314	0.7924	0.0727
0.0144	34.0	1700	0.2971	0.6367	0.7929	0.0909
0.0143	35.0	1750	0.2966	0.6367	0.7929	0.0909

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2