xclip-base-patch32-finetuned-custom-subset

This model is a fine-tuned version of microsoft/xclip-base-patch32 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5862
• Accuracy: 0.7308

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1420

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8431	0.0507	72	0.5928	0.7308
0.6657	1.0507	144	0.7383	0.7308
0.8019	2.0507	216	0.6047	0.7308
0.6275	3.0507	288	0.5946	0.7308
0.561	4.0507	360	0.6646	0.7308
0.594	5.0507	432	0.6098	0.7308
0.6472	6.0507	504	0.5915	0.7308
0.623	7.0507	576	0.5948	0.7308
0.5711	8.0507	648	0.6056	0.7308
0.5967	9.0507	720	0.5887	0.7308
0.5831	10.0507	792	0.5860	0.7308
0.6101	11.0507	864	0.6044	0.7308
0.6265	12.0507	936	0.5856	0.7308
0.6373	13.0507	1008	0.5882	0.7308
0.665	14.0507	1080	0.5852	0.7308
0.6183	15.0507	1152	0.5837	0.7308
0.7786	16.0507	1224	0.5834	0.7308
0.5489	17.0507	1296	0.5849	0.7308
0.6512	18.0507	1368	0.5843	0.7308
0.5266	19.0366	1420	0.5862	0.7308

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.1.1
• Datasets 2.13.2
• Tokenizers 0.19.1