You can deploy this model and start earning money today!

swadhindas324/
vit-convnext-mistral-SYDNEY-with-4-loss-supressed-captioning

Name: vit-convnext-mistral-SYDNEY-with-4-loss-supressed-captioning
Availability: InStock

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-convnext-mistral-SYDNEY-with-4-loss-supressed-captioning

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

Loss: 0.9319
Accuracy: 68.75
Bleu-1: 0.7864
Bleu-2: 0.7163
Bleu-3: 0.6503
Bleu-4: 0.5921
Meteor: 0.7453
Rouge-l: 0.7255
Cider: 2.3804

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	44	1.2296	65.37	0.5252	0.4032	0.3224	0.2518	0.4467	0.4543	0.8346
No log	2.0	88	0.6964	66.27	0.6151	0.5148	0.4371	0.3711	0.5162	0.5474	1.3648
No log	3.0	132	0.6614	65.84	0.7380	0.6434	0.5525	0.4716	0.6469	0.6335	1.8987
No log	4.0	176	0.6674	67.38	0.8133	0.7218	0.6332	0.5529	0.7103	0.7174	2.4369
No log	5.0	220	0.6476	65.32	0.7935	0.7171	0.6419	0.5646	0.7219	0.6696	2.2464
No log	6.0	264	0.6605	67.91	0.7953	0.7136	0.6347	0.5618	0.7358	0.7246	2.5266
No log	7.0	308	0.6905	68.06	0.7992	0.7335	0.6702	0.6110	0.7601	0.7332	2.7482
No log	8.0	352	0.6837	67.86	0.8151	0.7411	0.6736	0.6106	0.7730	0.7449	2.6854
No log	9.0	396	0.7190	68.6	0.8024	0.7298	0.6615	0.5968	0.7468	0.7134	2.4580
No log	10.0	440	0.7749	66.22	0.7899	0.7082	0.6382	0.5739	0.7416	0.7095	2.5376
No log	11.0	484	0.7556	68.85	0.8243	0.7394	0.6686	0.6038	0.7501	0.7109	2.6842
No log	12.0	528	0.7951	68.55	0.7995	0.7260	0.6582	0.5989	0.7626	0.7334	2.6056
No log	13.0	572	0.7994	65.95	0.7953	0.7055	0.6217	0.5384	0.7276	0.6858	2.2482
No log	14.0	616	0.8367	67.22	0.8177	0.7381	0.6655	0.5988	0.7603	0.7472	2.6258
No log	15.0	660	0.8587	68.13	0.7692	0.6919	0.6197	0.5424	0.7281	0.6740	2.1296
No log	16.0	704	0.8305	68.99	0.7926	0.7178	0.6539	0.5966	0.7772	0.7443	2.6449
No log	17.0	748	0.8717	66.9	0.7751	0.6928	0.6256	0.5662	0.7379	0.6923	2.2768
No log	18.0	792	0.8707	67.15	0.8016	0.7338	0.6675	0.6079	0.7596	0.7405	2.5837
No log	19.0	836	0.8950	67.42	0.7895	0.7120	0.6443	0.5829	0.7555	0.7181	2.4227
No log	20.0	880	0.8799	68.41	0.7887	0.7099	0.6318	0.5571	0.7467	0.7253	2.3426
No log	21.0	924	0.8889	68.32	0.7890	0.7195	0.6611	0.6089	0.7616	0.7309	2.5406
No log	22.0	968	0.8895	69.28	0.8032	0.7294	0.6696	0.6136	0.7794	0.7446	2.6656
No log	23.0	1012	0.9772	68.31	0.7893	0.7148	0.6484	0.5894	0.7337	0.7151	2.5355
0.4188	24.0	1056	0.9319	68.75	0.7864	0.7163	0.6503	0.5921	0.7453	0.7255	2.3804

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

swadhindas324/vit-convnext-mistral-SYDNEY-with-4-loss-supressed-captioning

vit-convnext-mistral-SYDNEY-with-4-loss-supressed-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

swadhindas324/
vit-convnext-mistral-SYDNEY-with-4-loss-supressed-captioning