rlcc-appearance-sentences-concat

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

• Loss: 2.5543
• Accuracy: 0.4707
• F1 Macro: 0.4487
• Precision Macro: 0.4725
• Recall Macro: 0.4410
• Total Tf: [193, 217, 1013, 217]

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• 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_steps: 85
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Total Tf
1.292	1.0	86	1.3110	0.2512	0.1977	0.4337	0.2660	[103, 307, 923, 307]
1.1703	2.0	172	1.2537	0.3366	0.3036	0.3749	0.3527	[138, 272, 958, 272]
0.8801	3.0	258	1.1573	0.4439	0.4465	0.4466	0.4541	[182, 228, 1002, 228]
0.5821	4.0	344	1.3719	0.4341	0.4443	0.4338	0.4644	[178, 232, 998, 232]
0.4175	5.0	430	1.5656	0.4415	0.4463	0.4558	0.4559	[181, 229, 1001, 229]
0.3133	6.0	516	1.6554	0.4585	0.4430	0.4598	0.4359	[188, 222, 1008, 222]
0.2509	7.0	602	1.9255	0.4537	0.4495	0.4583	0.4567	[186, 224, 1006, 224]
0.213	8.0	688	1.9323	0.4756	0.4771	0.4836	0.4729	[195, 215, 1015, 215]
0.1492	9.0	774	2.0154	0.4634	0.4275	0.4657	0.4218	[190, 220, 1010, 220]
0.1111	10.0	860	2.1794	0.4561	0.4377	0.4638	0.4255	[187, 223, 1007, 223]
0.0944	11.0	946	2.4171	0.4634	0.4460	0.4651	0.4373	[190, 220, 1010, 220]
0.0675	12.0	1032	2.4941	0.4707	0.4673	0.4727	0.4658	[193, 217, 1013, 217]
0.0442	13.0	1118	2.5543	0.4707	0.4487	0.4725	0.4410	[193, 217, 1013, 217]

Framework versions

• Transformers 4.51.1
• Pytorch 2.8.0.dev20250409+cu128
• Datasets 3.5.0
• Tokenizers 0.21.1