You can deploy this model and start earning money today!

swadhindas324/
vit-convnext-mistral-UCM-with-3-captioning

Name: vit-convnext-mistral-UCM-with-3-captioning
Availability: InStock

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-convnext-mistral-UCM-with-3-captioning

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

Loss: 0.4372
Accuracy: 75.53
Bleu-1: 0.8627
Bleu-2: 0.8112
Bleu-3: 0.7658
Bleu-4: 0.7239
Meteor: 0.8304
Rouge-l: 0.8256
Cider: 3.5118

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	0.6406	72.32	0.4172	0.2854	0.2097	0.1564	0.3236	0.3502	0.3524
No log	2.0	296	0.4585	71.92	0.2412	0.1707	0.1121	0.0728	0.1824	0.2082	0.1994
No log	3.0	444	0.4085	71.13	0.6062	0.5150	0.4529	0.4100	0.5433	0.5566	1.8893
No log	4.0	592	0.3466	73.4	0.8308	0.7693	0.7191	0.6746	0.7866	0.7815	3.2786
No log	5.0	740	0.3394	73.74	0.8311	0.7677	0.7177	0.6737	0.8124	0.8034	3.3353
No log	6.0	888	0.3529	73.53	0.8355	0.7808	0.7306	0.6837	0.8244	0.8055	3.3163
0.4450	7.0	1036	0.3428	74.63	0.8649	0.8148	0.7732	0.7345	0.8369	0.8214	3.5129
0.4450	8.0	1184	0.3394	74.78	0.8464	0.7942	0.7467	0.7009	0.8260	0.8181	3.4389
0.4450	9.0	1332	0.3570	74.41	0.8515	0.7967	0.7481	0.7040	0.8242	0.8123	3.3959
0.4450	10.0	1480	0.3486	74.68	0.8502	0.7948	0.7483	0.7061	0.8090	0.8013	3.3846
0.4450	11.0	1628	0.3497	73.55	0.8312	0.7651	0.7109	0.6627	0.8213	0.8011	3.3275
0.4450	12.0	1776	0.3582	73.92	0.8432	0.7868	0.7370	0.6884	0.8139	0.8081	3.3499
0.4450	13.0	1924	0.3680	74.32	0.8405	0.7881	0.7433	0.7025	0.8160	0.8079	3.4987
0.1631	14.0	2072	0.3669	75.23	0.8647	0.8172	0.7748	0.7343	0.8507	0.8296	3.6661
0.1631	15.0	2220	0.3788	75.37	0.8496	0.7924	0.7437	0.6976	0.8272	0.8171	3.5535
0.1631	16.0	2368	0.3822	73.69	0.8345	0.7750	0.7251	0.6791	0.8172	0.7995	3.4251
0.1631	17.0	2516	0.3877	74.77	0.8712	0.8224	0.7794	0.7385	0.8573	0.8416	3.5698
0.1631	18.0	2664	0.3945	74.46	0.8534	0.7996	0.7549	0.7152	0.8265	0.8196	3.4915
0.1631	19.0	2812	0.4029	75.37	0.8638	0.8138	0.7696	0.7300	0.8454	0.8306	3.5878
0.1631	20.0	2960	0.4169	74.91	0.8488	0.7913	0.7418	0.6984	0.8324	0.8160	3.5802
0.1384	21.0	3108	0.4167	74.39	0.8530	0.7963	0.7491	0.7067	0.8249	0.8176	3.5116
0.1384	22.0	3256	0.4096	74.81	0.8485	0.7956	0.7522	0.7122	0.8314	0.8181	3.5981
0.1384	23.0	3404	0.4053	74.14	0.8425	0.7826	0.7315	0.6835	0.8237	0.8101	3.3488
0.1384	24.0	3552	0.4309	74.73	0.8468	0.7926	0.7448	0.7023	0.8245	0.8125	3.3588
0.1384	25.0	3700	0.4346	74.98	0.8654	0.8130	0.7663	0.7215	0.8399	0.8268	3.4991
0.1384	26.0	3848	0.4275	74.48	0.8517	0.8015	0.7577	0.7205	0.8274	0.8143	3.5162
0.1384	27.0	3996	0.4372	75.53	0.8627	0.8112	0.7658	0.7239	0.8304	0.8256	3.5118

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-3-captioning

vit-convnext-mistral-UCM-with-3-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

swadhindas324/
vit-convnext-mistral-UCM-with-3-captioning