You can deploy this model and start earning money today!

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

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

Views

No views yet

vit-convnext-mistral-UCM-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:

More information needed

More information needed

More information needed

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 Loss	Epoch	Step	Validation Loss	Accuracy	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor	Rouge-l	Cider
No log	1.0	148	0.8624	72.39	0.4259	0.2978	0.2198	0.1659	0.3264	0.3613	0.3720
No log	2.0	296	0.7334	71.97	0.4417	0.3312	0.2599	0.2131	0.3421	0.3870	0.9765
No log	3.0	444	0.5855	73.55	0.8060	0.7430	0.6925	0.6493	0.7729	0.7698	3.1551
No log	4.0	592	0.5832	73.47	0.8373	0.7681	0.7111	0.6614	0.7956	0.7876	3.2255
No log	5.0	740	0.5988	73.28	0.8326	0.7788	0.7321	0.6918	0.8058	0.7958	3.3558
No log	6.0	888	0.6343	74.23	0.8316	0.7767	0.7274	0.6820	0.8196	0.8092	3.3270
0.6497	7.0	1036	0.6275	74.44	0.8634	0.8102	0.7623	0.7188	0.8330	0.8234	3.5178
0.6497	8.0	1184	0.6640	74.25	0.8511	0.7940	0.7456	0.7007	0.8214	0.8119	3.4913
0.6497	9.0	1332	0.6641	75.11	0.8851	0.8401	0.7979	0.7591	0.8400	0.8363	3.6271
0.6497	10.0	1480	0.6672	73.81	0.8330	0.7730	0.7204	0.6738	0.8109	0.7963	3.2772
0.6497	11.0	1628	0.7047	74.07	0.8431	0.7839	0.7351	0.6870	0.8337	0.8181	3.3776
0.6497	12.0	1776	0.6998	74.99	0.8364	0.7833	0.7378	0.6966	0.8097	0.8102	3.4113
0.6497	13.0	1924	0.7499	73.78	0.8394	0.7822	0.7318	0.6858	0.8251	0.8186	3.4153
0.2975	14.0	2072	0.7304	74.57	0.8657	0.8087	0.7583	0.7097	0.8457	0.8270	3.4611
0.2975	15.0	2220	0.7419	74.8	0.8476	0.7868	0.7369	0.6889	0.8132	0.8056	3.4982
0.2975	16.0	2368	0.7585	74.96	0.8626	0.8128	0.7690	0.7290	0.8407	0.8246	3.6254
0.2975	17.0	2516	0.7720	74.87	0.8674	0.8133	0.7671	0.7253	0.8353	0.8248	3.5275
0.2975	18.0	2664	0.7935	74.85	0.8609	0.8074	0.7610	0.7159	0.8517	0.8349	3.5133
0.2975	19.0	2812	0.8038	74.74	0.8507	0.7955	0.7465	0.7002	0.8308	0.8137	3.4101