lora_fine_tuned_cb_croslo

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

• Loss: 1.3172
• Accuracy: 0.3182
• F1: 0.1536

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.0956	3.5714	50	1.1024	0.3636	0.3027
0.8669	7.1429	100	1.1540	0.3182	0.1536
0.7634	10.7143	150	1.2351	0.3182	0.1536
0.7	14.2857	200	1.2885	0.3182	0.1536
0.6951	17.8571	250	1.3121	0.3182	0.1536
0.7047	21.4286	300	1.3145	0.3182	0.1536
0.6769	25.0	350	1.3154	0.3182	0.1536
0.6886	28.5714	400	1.3172	0.3182	0.1536

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.40.1
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.19.1