README.md

metadata

license: mit
base_model: cointegrated/rubert-tiny2
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: rubert-tiny2-odonata-extended-ner
    results: []

rubert-tiny2-odonata-extended-ner

This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0226
• Precision: 0.5313
• Recall: 0.551
• F1: 0.5410
• Accuracy: 0.9930

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	32	0.1425	0.0	0.0	0.0	0.9910
No log	2.0	64	0.0643	0.0	0.0	0.0	0.9910
No log	3.0	96	0.0604	0.0	0.0	0.0	0.9910
No log	4.0	128	0.0575	0.0	0.0	0.0	0.9910
No log	5.0	160	0.0523	0.0	0.0	0.0	0.9910
No log	6.0	192	0.0427	0.0	0.0	0.0	0.9910
No log	7.0	224	0.0330	0.7753	0.069	0.1267	0.9913
No log	8.0	256	0.0288	0.6309	0.376	0.4712	0.9921
No log	9.0	288	0.0264	0.6145	0.373	0.4642	0.9924
No log	10.0	320	0.0251	0.5489	0.432	0.4835	0.9926
No log	11.0	352	0.0242	0.5354	0.484	0.5084	0.9927
No log	12.0	384	0.0235	0.5393	0.515	0.5269	0.9928
No log	13.0	416	0.0230	0.5310	0.54	0.5354	0.9929
No log	14.0	448	0.0228	0.5287	0.553	0.5406	0.9930
No log	15.0	480	0.0226	0.5313	0.551	0.5410	0.9930

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1+cpu
• Datasets 2.19.2
• Tokenizers 0.19.1