vit-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: 1.6545
• Accuracy: 81.45
• Bleu-1: 0.6169
• Bleu-2: 0.4800
• Bleu-3: 0.3863
• Bleu-4: 0.3200
• Meteor: 0.5836
• Rouge-l: 0.5397
• Cider: 1.7724

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	1.2887	79.76	0.4667	0.3026	0.2114	0.1536	0.4084	0.3974	0.4796
1.5992	2.0	1536	1.2363	79.46	0.6192	0.4797	0.3803	0.3051	0.6187	0.5594	1.4971
0.8374	3.0	2304	1.2232	81.12	0.6701	0.5450	0.4535	0.3812	0.6651	0.6151	2.0863
0.6004	4.0	3072	1.3637	81.23	0.6497	0.5194	0.4264	0.3566	0.6317	0.5895	1.9473
0.6004	5.0	3840	1.4562	80.42	0.6183	0.4829	0.3908	0.3225	0.5940	0.5471	1.6977
0.4218	6.0	4608	1.5248	81.13	0.6281	0.5004	0.4114	0.3448	0.6080	0.5694	1.8229
0.3469	7.0	5376	1.6350	81.47	0.6318	0.5015	0.4077	0.3377	0.6178	0.5670	1.7947
0.3105	8.0	6144	1.6545	81.45	0.6169	0.4800	0.3863	0.3200	0.5836	0.5397	1.7724

Framework versions

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