resnet-Mistral-NWPU-without-captioning

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

• Loss: 0.6734
• Accuracy: 85.81
• Bleu-1: 0.8454
• Bleu-2: 0.7530
• Bleu-3: 0.6787
• Bleu-4: 0.6185
• Meteor: 0.7628
• Rouge-l: 0.7459
• Cider: 1.7133

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 50
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
• num_epochs: 128
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor	Rouge-l	Cider
0.9140	1.0	2215	0.8423	84.93	0.6232	0.4660	0.3643	0.2934	0.5122	0.4914	0.6281
0.7188	2.0	4430	0.6733	85.14	0.8170	0.7101	0.6264	0.5598	0.7170	0.7011	1.6003
0.6307	3.0	6645	0.6352	84.85	0.8156	0.7147	0.6351	0.5718	0.7339	0.7189	1.6351
0.5816	4.0	8860	0.6199	85.47	0.8478	0.7590	0.6859	0.6258	0.7567	0.7437	1.7018
0.5472	5.0	11075	0.6150	85.72	0.8534	0.7622	0.6889	0.6294	0.7619	0.7520	1.7586
0.5181	6.0	13290	0.6200	85.88	0.8502	0.7589	0.6839	0.6222	0.7658	0.7529	1.7791
0.5136	7.0	15505	0.6292	85.86	0.8484	0.7569	0.6829	0.6229	0.7693	0.7508	1.7448
0.4969	8.0	17720	0.6366	86.0	0.8494	0.7585	0.6856	0.6270	0.7635	0.7525	1.7570
0.4822	9.0	19935	0.6396	86.05	0.8511	0.7584	0.6819	0.6196	0.7729	0.7540	1.7505
0.4699	10.0	22150	0.6504	85.99	0.8489	0.7573	0.6851	0.6267	0.7590	0.7488	1.7718
0.4587	11.0	24365	0.6524	86.12	0.8489	0.7585	0.6868	0.6284	0.7674	0.7524	1.7675
0.4477	12.0	26580	0.6663	86.03	0.8521	0.7600	0.6864	0.6271	0.7624	0.7506	1.7499
0.4650	13.0	28795	0.6658	86.3	0.8477	0.7576	0.6853	0.6263	0.7605	0.7482	1.7700
0.4477	14.0	31010	0.6734	85.81	0.8454	0.7530	0.6787	0.6185	0.7628	0.7459	1.7133

Framework versions

• Transformers 5.12.1
• Pytorch 2.12.1+cu130
• Datasets 5.0.0
• Tokenizers 0.22.2