fewshot-CDW-CE-2500-samples

This model is a fine-tuned version of Davidozito/zeroshot-classification on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0805
• Accuracy: 0.616
• F1 Macro: 0.6067
• F1 Weighted: 0.6080
• Precision Macro: 0.6045
• Recall Macro: 0.6145

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted	Precision Macro	Recall Macro
1.1439	0.2482	70	1.0859	0.588	0.5617	0.5627	0.5738	0.5871
1.1046	0.4965	140	1.0853	0.584	0.5567	0.5581	0.5711	0.5826
1.1447	0.7447	210	1.0838	0.616	0.6043	0.6051	0.6034	0.6153
1.1458	0.9929	280	1.0819	0.616	0.5988	0.6004	0.5990	0.6142
1.1758	1.2411	350	1.0817	0.612	0.6035	0.6046	0.6015	0.6109
1.1216	1.4894	420	1.0805	0.616	0.6067	0.6080	0.6045	0.6145
1.1226	1.7376	490	1.0814	0.608	0.5919	0.5933	0.5926	0.6062
1.1099	1.9858	560	1.0815	0.604	0.5859	0.5875	0.5898	0.6020
1.1501	2.2340	630	1.0800	0.6	0.5802	0.5820	0.5833	0.5977
1.0893	2.4823	700	1.0807	0.6	0.5766	0.5784	0.5861	0.5980
1.1044	2.7305	770	1.0795	0.604	0.5802	0.5823	0.5896	0.6015
1.1724	2.9787	840	1.0801	0.6	0.5769	0.5788	0.5841	0.5980
1.1321	3.2270	910	1.0785	0.608	0.5872	0.5892	0.5883	0.6057
1.1286	3.4752	980	1.0785	0.616	0.5988	0.6003	0.5998	0.6142
1.1226	3.7234	1050	1.0798	0.604	0.5877	0.5889	0.5901	0.6027
1.1209	3.9716	1120	1.0801	0.604	0.5883	0.5895	0.5913	0.6027
1.1135	4.2199	1190	1.0806	0.604	0.5884	0.5894	0.5903	0.6030
1.1102	4.4681	1260	1.0797	0.604	0.5878	0.5890	0.5882	0.6027
1.1222	4.7163	1330	1.0801	0.6	0.5852	0.5863	0.5854	0.5988
1.0991	4.9645	1400	1.0801	0.6	0.5852	0.5863	0.5854	0.5988

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.1
• Datasets 3.6.0
• Tokenizers 0.21.1