Halmultilingual-MiniLMv2-L6-mnli-xnli_finetuned_rm_con

This model is a fine-tuned version of MoritzLaurer/multilingual-MiniLMv2-L6-mnli-xnli on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
No log	1.0	88	1.0857	0.3779	0.3578
No log	2.0	176	0.9439	0.5371	0.5400
No log	3.0	264	0.8541	0.6129	0.6160
No log	4.0	352	0.8159	0.6457	0.6478
No log	5.0	440	0.7920	0.6707	0.6730
0.9092	6.0	528	0.7702	0.6814	0.6830
0.9092	7.0	616	0.7609	0.7007	0.7031
0.9092	8.0	704	0.7559	0.6993	0.6999
0.9092	9.0	792	0.7471	0.7093	0.7111
0.9092	10.0	880	0.7395	0.7064	0.7078
0.9092	11.0	968	0.7337	0.7164	0.7178
0.6686	12.0	1056	0.7262	0.7157	0.7172
0.6686	13.0	1144	0.7242	0.7186	0.7199
0.6686	14.0	1232	0.7246	0.7207	0.7219
0.6686	15.0	1320	0.7241	0.7207	0.7222
0.6686	16.0	1408	0.7234	0.7229	0.7237
0.6686	17.0	1496	0.7249	0.7229	0.7242
0.6049	18.0	1584	0.7239	0.725	0.7267
0.6049	19.0	1672	0.7217	0.725	0.7261
0.6049	20.0	1760	0.7223	0.7257	0.7270