You can deploy this model and start earning money today!

swadhindas324/
vit-resnet-mistral-RSICD-with-8-captioning

Name: vit-resnet-mistral-RSICD-with-8-captioning
Availability: InStock

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-resnet-mistral-RSICD-with-8-captioning

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

Loss: 1.1770
Accuracy: 83.88
Bleu-1: 0.7275
Bleu-2: 0.6029
Bleu-3: 0.5063
Bleu-4: 0.4303
Meteor: 0.6788
Rouge-l: 0.6472
Cider: 2.3701

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	0.6924	80.37	0.4668	0.3027	0.2115	0.1537	0.4085	0.3975	0.4800
0.9637	2.0	1536	0.6616	80.24	0.5549	0.4056	0.3111	0.2439	0.5279	0.4954	0.9839
0.4716	3.0	2304	0.6212	83.38	0.7454	0.6255	0.5321	0.4552	0.6557	0.6455	2.2909
0.3470	4.0	3072	0.6679	83.82	0.7342	0.6144	0.5240	0.4521	0.6340	0.6272	2.3159
0.3470	5.0	3840	0.7207	83.32	0.7317	0.6160	0.5262	0.4556	0.6499	0.6341	2.3694
0.2447	6.0	4608	0.7526	84.05	0.7399	0.6158	0.5198	0.4432	0.6427	0.6314	2.3119
0.1948	7.0	5376	0.8032	83.69	0.7347	0.6164	0.5225	0.4459	0.6812	0.6483	2.3921
0.1711	8.0	6144	0.8195	84.16	0.7342	0.6198	0.5295	0.4563	0.6747	0.6470	2.4336
0.1711	9.0	6912	0.8561	83.95	0.7370	0.6125	0.5167	0.4404	0.6774	0.6463	2.3687
0.1524	10.0	7680	0.8763	84.12	0.7356	0.6143	0.5224	0.4499	0.6919	0.6528	2.4211
0.1470	11.0	8448	0.9044	84.01	0.7389	0.6199	0.5284	0.4561	0.6791	0.6464	2.4703
0.1441	12.0	9216	0.9296	83.5	0.7231	0.6004	0.5047	0.4285	0.6838	0.6444	2.3777
0.1441	13.0	9984	0.9519	84.21	0.7406	0.6192	0.5240	0.4489	0.6815	0.6542	2.4091
0.1356	14.0	10752	0.9723	84.15	0.7382	0.6203	0.5274	0.4528	0.6866	0.6520	2.4164
0.1272	15.0	11520	1.0075	83.9	0.7358	0.6138	0.5188	0.4426	0.6842	0.6514	2.4024
0.1215	16.0	12288	1.0199	84.15	0.7375	0.6179	0.5243	0.4500	0.6861	0.6521	2.4349
0.1215	17.0	13056	1.0389	84.05	0.7385	0.6197	0.5270	0.4525	0.6882	0.6576	2.4893
0.1144	18.0	13824	1.0510	83.9	0.7394	0.6186	0.5237	0.4487	0.6876	0.6598	2.4246
0.1112	19.0	14592	1.0873	83.48	0.7153	0.5912	0.4932	0.4164	0.6785	0.6314	2.2957
0.1097	20.0	15360	1.0828	84.56	0.7465	0.6260	0.5314	0.4564	0.6920	0.6640	2.5345
0.1097	21.0	16128	1.1118	84.15	0.7452	0.6256	0.5324	0.4580	0.6903	0.6610	2.4724
0.1035	22.0	16896	1.1358	84.08	0.7436	0.6226	0.5273	0.4515	0.6979	0.6587	2.4689
0.1025	23.0	17664	1.1475	83.86	0.7353	0.6158	0.5209	0.4438	0.6971	0.6577	2.4045
0.1019	24.0	18432	1.1575	84.03	0.7375	0.6160	0.5193	0.4424	0.6893	0.6549	2.4593
0.1019	25.0	19200	1.1770	83.88	0.7275	0.6029	0.5063	0.4303	0.6788	0.6472	2.3701

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

swadhindas324/vit-resnet-mistral-RSICD-with-8-captioning

vit-resnet-mistral-RSICD-with-8-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

swadhindas324/
vit-resnet-mistral-RSICD-with-8-captioning