metadata
license: apache-2.0
base_model: om-ashish-soni/pos-morph-analysis-eng
tags:
- generated_from_trainer
datasets:
- universal_dependencies
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: pos-morph-analysis-eng
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: universal_dependencies
type: universal_dependencies
config: en_lines
split: validation
args: en_lines
metrics:
- name: Precision
type: precision
value: 0.9470202237521514
- name: Recall
type: recall
value: 0.951318348822131
- name: F1
type: f1
value: 0.9491644204851751
- name: Accuracy
type: accuracy
value: 0.9499257471691108
pos-morph-analysis-eng
This model is a fine-tuned version of om-ashish-soni/pos-morph-analysis-eng on the universal_dependencies dataset. It achieves the following results on the evaluation set:
- Loss: 0.2405
- Precision: 0.9470
- Recall: 0.9513
- F1: 0.9492
- Accuracy: 0.9499
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 99 | 0.3058 | 0.9324 | 0.9376 | 0.9350 | 0.9369 |
| No log | 1.99 | 198 | 0.2559 | 0.9423 | 0.9461 | 0.9442 | 0.9456 |
| No log | 2.99 | 297 | 0.2424 | 0.9449 | 0.9497 | 0.9473 | 0.9488 |
| No log | 3.99 | 396 | 0.2405 | 0.9470 | 0.9513 | 0.9492 | 0.9499 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3