You can deploy this model and start earning money today!

swadhindas324/
vit-convnext-mistral-UCM-with-6-captioning

Name: vit-convnext-mistral-UCM-with-6-captioning
Availability: InStock

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-convnext-mistral-UCM-with-6-captioning

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

Loss: 0.4355
Accuracy: 75.3
Bleu-1: 0.8426
Bleu-2: 0.7886
Bleu-3: 0.7417
Bleu-4: 0.6972
Meteor: 0.8181
Rouge-l: 0.8093
Cider: 3.5403

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	148	0.6420	72.41	0.4179	0.2841	0.2081	0.1558	0.3184	0.3494	0.3553
No log	2.0	296	0.4693	71.9	0.2588	0.1748	0.1062	0.0626	0.1847	0.2135	0.1572
No log	3.0	444	0.4215	69.91	0.5943	0.5029	0.4415	0.3993	0.5319	0.5485	1.8629
No log	4.0	592	0.3571	73.62	0.8269	0.7613	0.7087	0.6615	0.7853	0.7793	3.2202
No log	5.0	740	0.3435	73.97	0.8315	0.7691	0.7176	0.6715	0.8096	0.7942	3.3729
No log	6.0	888	0.3515	74.19	0.8319	0.7780	0.7277	0.6829	0.8125	0.7987	3.3463
0.4522	7.0	1036	0.3400	74.6	0.8800	0.8303	0.7822	0.7357	0.8449	0.8327	3.5412
0.4522	8.0	1184	0.3499	74.6	0.8549	0.7999	0.7517	0.7065	0.8249	0.8123	3.4880
0.4522	9.0	1332	0.3574	74.58	0.8530	0.8001	0.7537	0.7113	0.8233	0.8162	3.4880
0.4522	10.0	1480	0.3573	74.88	0.8489	0.7914	0.7425	0.6985	0.8003	0.8015	3.4224
0.4522	11.0	1628	0.3525	73.72	0.8389	0.7814	0.7328	0.6895	0.8275	0.8132	3.3948
0.4522	12.0	1776	0.3814	73.67	0.8485	0.7883	0.7386	0.6918	0.8161	0.8110	3.3615
0.4522	13.0	1924	0.3829	74.15	0.8502	0.7992	0.7561	0.7164	0.8296	0.8212	3.5661
0.1648	14.0	2072	0.3941	75.25	0.8444	0.7863	0.7404	0.7001	0.8092	0.7940	3.3888
0.1648	15.0	2220	0.3887	75.27	0.8552	0.7977	0.7506	0.7043	0.8342	0.8186	3.5894
0.1648	16.0	2368	0.3836	75.04	0.8675	0.8138	0.7683	0.7266	0.8270	0.8183	3.5621
0.1648	17.0	2516	0.3945	74.83	0.8653	0.8166	0.7744	0.7349	0.8525	0.8402	3.6410
0.1648	18.0	2664	0.3971	74.27	0.8600	0.8043	0.7606	0.7210	0.8356	0.8272	3.5370
0.1648	19.0	2812	0.4079	74.71	0.8610	0.8063	0.7603	0.7167	0.8373	0.8202	3.5690
0.1648	20.0	2960	0.3928	74.75	0.8469	0.7898	0.7424	0.6976	0.8336	0.8206	3.4968
0.1398	21.0	3108	0.4159	74.39	0.8565	0.8034	0.7563	0.7142	0.8378	0.8250	3.5657
0.1398	22.0	3256	0.4261	74.86	0.8532	0.7987	0.7502	0.7057	0.8369	0.8198	3.5519
0.1398	23.0	3404	0.4157	74.03	0.8435	0.7820	0.7311	0.6829	0.8180	0.8007	3.3732
0.1398	24.0	3552	0.4171	74.97	0.8573	0.8048	0.7582	0.7156	0.8272	0.8115	3.4984
0.1398	25.0	3700	0.4135	74.4	0.8425	0.7885	0.7420	0.6980	0.8216	0.8092	3.4106
0.1398	26.0	3848	0.4427	74.99	0.8565	0.8014	0.7556	0.7141	0.8394	0.8221	3.5866
0.1398	27.0	3996	0.4355	75.3	0.8426	0.7886	0.7417	0.6972	0.8181	0.8093	3.5403

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

swadhindas324/vit-convnext-mistral-UCM-with-6-captioning

vit-convnext-mistral-UCM-with-6-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

swadhindas324/
vit-convnext-mistral-UCM-with-6-captioning