fewshot-CDW-CE-1000-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: 1.1290
• Accuracy: 0.62
• F1 Macro: 0.6187
• F1 Weighted: 0.6223
• Precision Macro: 0.6294
• Recall Macro: 0.6167

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
1.1359	0.2478	28	1.1319	0.58	0.5708	0.5765	0.5775	0.5737
1.1457	0.4956	56	1.1288	0.6	0.5926	0.5980	0.5987	0.5937
1.171	0.7434	84	1.1291	0.59	0.5843	0.5888	0.5966	0.5847
1.1105	0.9912	112	1.1287	0.6	0.5982	0.6021	0.6071	0.5962
1.0822	1.2389	140	1.1295	0.6	0.5909	0.5958	0.5988	0.5947
1.0855	1.4867	168	1.1294	0.6	0.5971	0.6010	0.6029	0.5962
1.1396	1.7345	196	1.1294	0.59	0.5871	0.5912	0.5921	0.5862
1.1243	1.9823	224	1.1296	0.61	0.6088	0.6126	0.6182	0.6067
1.092	2.2301	252	1.1291	0.6	0.5983	0.6018	0.6043	0.5967
1.1624	2.4779	280	1.1287	0.6	0.6002	0.6034	0.6088	0.5972
1.0876	2.7257	308	1.1283	0.61	0.6062	0.6103	0.6184	0.6057
1.1741	2.9735	336	1.1287	0.61	0.6085	0.6118	0.6158	0.6067
1.187	3.2212	364	1.1290	0.62	0.6187	0.6223	0.6294	0.6167
1.1748	3.4690	392	1.1289	0.62	0.6187	0.6223	0.6294	0.6167
1.1556	3.7168	420	1.1287	0.61	0.6065	0.6106	0.6146	0.6062
1.1189	3.9646	448	1.1285	0.61	0.6065	0.6106	0.6146	0.6062
1.1245	4.2124	476	1.1284	0.61	0.6073	0.6114	0.6164	0.6062
1.0478	4.4602	504	1.1283	0.61	0.6073	0.6114	0.6164	0.6062
1.1255	4.7080	532	1.1283	0.6	0.5971	0.6010	0.6029	0.5962
1.1973	4.9558	560	1.1283	0.6	0.5971	0.6010	0.6029	0.5962

Framework versions

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