You can deploy this model and start earning money today!

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

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

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

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

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

Loss: 0.5258
Accuracy: 68.97
Bleu-1: 0.8045
Bleu-2: 0.7347
Bleu-3: 0.6710
Bleu-4: 0.6156
Meteor: 0.7787
Rouge-l: 0.7512
Cider: 2.6786

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	0.9258	65.63	0.5632	0.4520	0.3703	0.3000	0.4710	0.4938	1.0434
No log	2.0	88	0.5175	62.82	0.5480	0.4380	0.3590	0.2933	0.4270	0.4606	0.7265
No log	3.0	132	0.4455	66.69	0.6525	0.5538	0.4735	0.4059	0.5622	0.5845	1.5436
No log	4.0	176	0.4232	66.1	0.7932	0.6983	0.6074	0.5184	0.6959	0.6702	2.3273
No log	5.0	220	0.4054	66.49	0.8023	0.7209	0.6396	0.5536	0.7165	0.6728	2.2197
No log	6.0	264	0.4040	68.02	0.8081	0.7245	0.6401	0.5645	0.7440	0.7322	2.4222
No log	7.0	308	0.4052	67.86	0.7972	0.7293	0.6645	0.6044	0.7799	0.7354	2.6543
No log	8.0	352	0.3922	67.49	0.8307	0.7725	0.7176	0.6638	0.7922	0.7526	2.8876
No log	9.0	396	0.4109	68.64	0.8275	0.7618	0.6974	0.6355	0.7782	0.7618	2.7673
No log	10.0	440	0.4073	67.61	0.8384	0.7722	0.7082	0.6488	0.7928	0.7448	2.9108
No log	11.0	484	0.4264	67.8	0.8172	0.7530	0.6932	0.6382	0.8008	0.7578	2.8284
No log	12.0	528	0.4335	69.64	0.7611	0.6710	0.5946	0.5264	0.7344	0.6996	2.3793
No log	13.0	572	0.4258	67.46	0.8306	0.7650	0.6971	0.6282	0.7568	0.7227	2.7481
No log	14.0	616	0.4549	68.2	0.8135	0.7479	0.6866	0.6291	0.7637	0.7448	2.8142
No log	15.0	660	0.4608	68.84	0.8032	0.7265	0.6557	0.5875	0.7418	0.7181	2.4772
No log	16.0	704	0.4587	68.81	0.8221	0.7424	0.6769	0.6180	0.7721	0.7348	2.5252
No log	17.0	748	0.4633	68.43	0.8329	0.7683	0.7091	0.6560	0.7956	0.7679	2.7229
No log	18.0	792	0.4635	68.58	0.8202	0.7498	0.6836	0.6207	0.7771	0.7445	2.5162
No log	19.0	836	0.4435	68.78	0.8184	0.7488	0.6891	0.6366	0.7753	0.7456	2.6220
No log	20.0	880	0.4845	68.97	0.8121	0.7386	0.6715	0.6102	0.7742	0.7377	2.5947
No log	21.0	924	0.4734	69.44	0.8224	0.7590	0.7043	0.6551	0.8003	0.7767	2.7119
No log	22.0	968	0.4701	69.14	0.7923	0.7250	0.6630	0.6053	0.7682	0.7426	2.5513
No log	23.0	1012	0.5167	68.08	0.8154	0.7415	0.6714	0.6062	0.7571	0.7318	2.6143
0.2734	24.0	1056	0.4805	69.57	0.8260	0.7617	0.6999	0.6421	0.7917	0.7768	2.7170
0.2734	25.0	1100	0.5060	68.4	0.8188	0.7503	0.6885	0.6314	0.7739	0.7416	2.7101
0.2734	26.0	1144	0.5231	68.74	0.8418	0.7752	0.7074	0.6451	0.7823	0.7576	2.8024
0.2734	27.0	1188	0.5178	69.25	0.8019	0.7231	0.6597	0.6034	0.7496	0.7199	2.7348
0.2734	28.0	1232	0.5214	69.93	0.8289	0.7592	0.6901	0.6267	0.7979	0.7663	2.7060
0.2734	29.0	1276	0.5116	68.54	0.8331	0.7620	0.6999	0.6497	0.7778	0.7473	2.7272
0.2734	30.0	1320	0.5260	69.09	0.8123	0.7406	0.6830	0.6337	0.7887	0.7461	2.7900
0.2734	31.0	1364	0.5367	69.42	0.8276	0.7577	0.6896	0.6292	0.7894	0.7665	2.6546
0.2734	32.0	1408	0.5236	68.99	0.8325	0.7686	0.7071	0.6523	0.8003	0.7656	2.8716
0.2734	33.0	1452	0.5594	69.17	0.8367	0.7712	0.7072	0.6466	0.7785	0.7626	2.7878
0.2734	34.0	1496	0.5258	68.97	0.8045	0.7347	0.6710	0.6156	0.7787	0.7512	2.6786

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-tag-supressed-captioning

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