stance_baseline_v3_no_hs

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5660
• Accuracy Stance: 0.6486
• F1 Macro Stance: 0.5062
• F1 Weighted Stance: 0.6487
• F1 Macro Total: 0.5062
• F1 Weighted Total: 0.6487

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: 6e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 1337
• 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
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Stance	F1 Macro Stance	F1 Weighted Stance	F1 Macro Total	F1 Weighted Total
No log	1.0	40	1.0524	0.4189	0.1968	0.2474	0.1968	0.2474
No log	2.0	80	1.0348	0.4189	0.1968	0.2474	0.1968	0.2474
No log	3.0	120	1.0255	0.4189	0.1968	0.2474	0.1968	0.2474
No log	4.0	160	1.0130	0.4189	0.1968	0.2474	0.1968	0.2474
No log	5.0	200	0.9886	0.5338	0.3664	0.5145	0.3664	0.5145
No log	6.0	240	0.9873	0.6014	0.3911	0.5627	0.3911	0.5627
No log	7.0	280	0.9706	0.6081	0.4024	0.5774	0.4024	0.5774
No log	8.0	320	0.9717	0.6419	0.4297	0.6149	0.4297	0.6149
No log	9.0	360	1.0853	0.6014	0.3888	0.5616	0.3888	0.5616
No log	10.0	400	1.0963	0.6351	0.4706	0.6179	0.4706	0.6179
No log	11.0	440	1.1777	0.6554	0.4908	0.6413	0.4908	0.6413
No log	12.0	480	1.2402	0.6622	0.4559	0.6499	0.4559	0.6499
0.7077	13.0	520	1.4222	0.6554	0.4501	0.6426	0.4501	0.6426
0.7077	14.0	560	1.4854	0.6554	0.4501	0.6426	0.4501	0.6426
0.7077	15.0	600	1.5660	0.6486	0.5062	0.6487	0.5062	0.6487
0.7077	16.0	640	1.6567	0.6689	0.5004	0.6580	0.5004	0.6580
0.7077	17.0	680	1.7668	0.6216	0.4593	0.6256	0.4593	0.6256
0.7077	18.0	720	1.7738	0.6284	0.5002	0.6410	0.5002	0.6410
0.7077	19.0	760	1.8503	0.6014	0.4831	0.6275	0.4831	0.6275
0.7077	20.0	800	1.8763	0.6284	0.4890	0.6468	0.4890	0.6468

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.0.1
• Tokenizers 0.21.1