README.md

metadata

base_model: DeepPavlov/bert-base-bg-cs-pl-ru-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: damage_trigger_effect_2023-12-18_15_20
    results: []

damage_trigger_effect_2023-12-18_15_20

This model is a fine-tuned version of DeepPavlov/bert-base-bg-cs-pl-ru-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5807
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.8588

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	34	0.5744	0.0	0.0	0.0	0.8099
No log	2.0	68	0.4567	0.0	0.0	0.0	0.8393
No log	3.0	102	0.4566	0.0	0.0	0.0	0.8474
No log	4.0	136	0.4308	0.0	0.0	0.0	0.8585
No log	5.0	170	0.4606	0.0	0.0	0.0	0.8422
No log	6.0	204	0.4777	0.0	0.0	0.0	0.8510
No log	7.0	238	0.4681	0.0	0.0	0.0	0.8569
No log	8.0	272	0.5150	0.0	0.0	0.0	0.8523
No log	9.0	306	0.4945	0.0	0.0	0.0	0.8650
No log	10.0	340	0.5582	0.0	0.0	0.0	0.8533
No log	11.0	374	0.5274	0.0	0.0	0.0	0.8591
No log	12.0	408	0.5547	0.0	0.0	0.0	0.8595
No log	13.0	442	0.5707	0.0	0.0	0.0	0.8598
No log	14.0	476	0.5814	0.0	0.0	0.0	0.8549
0.2474	15.0	510	0.5807	0.0	0.0	0.0	0.8588

Framework versions

• Transformers 4.36.1
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0