resnet-Mistral-RSICD-without-captioning

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

• Loss: 1.6785
• Accuracy: 81.18
• Bleu-1: 0.5736
• Bleu-2: 0.4319
• Bleu-3: 0.3396
• Bleu-4: 0.2759
• Meteor: 0.5344
• Rouge-l: 0.4954
• Cider: 1.4771

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
No log	1.0	768	1.4061	82.65	0.5036	0.3424	0.2502	0.1903	0.4546	0.4403	0.7049
2.3492	2.0	1536	1.3189	79.85	0.5796	0.4327	0.3329	0.2610	0.5539	0.5180	1.2374
0.8899	3.0	2304	1.3039	81.73	0.6458	0.5136	0.4197	0.3491	0.6192	0.5765	1.9040
0.6509	4.0	3072	1.4074	80.46	0.5811	0.4413	0.3488	0.2815	0.5618	0.5164	1.4791
0.6509	5.0	3840	1.4987	80.8	0.6079	0.4679	0.3707	0.2993	0.5801	0.5366	1.5093
0.4869	6.0	4608	1.5561	81.42	0.6178	0.4827	0.3876	0.3188	0.5972	0.5529	1.7118
0.4182	7.0	5376	1.6325	80.44	0.5808	0.4495	0.3574	0.2922	0.5724	0.5214	1.5221
0.3774	8.0	6144	1.6785	81.18	0.5736	0.4319	0.3396	0.2759	0.5344	0.4954	1.4771

Framework versions

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