Downloads · 30 days
11
29% of all-time downloads
relatives_psr_seq-cbert_finetuned
djamina/relatives_psr_seq-cbert_finetuned
relatives_psr_seq-cbert_finetuned is a token classification model from djamina. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
38
Public
Parameters
405M
3.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- camembert
- Access
- Public
- Created
- Jun 4, 2024
- Updated
- Jun 5, 2024
- SHA
- 6a7ded43
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
relatives_psr_seq-cbert_finetuned
This model is a fine-tuned version of camembert/camembert-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7099
- Precision: 0.6914
- Recall: 0.2252
- F1: 0.2193
- Accuracy: 0.7578
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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 49 | 0.8241 | 0.9512 | 0.2 | 0.1722 | 0.7560 |
| No log | 2.0 | 98 | 0.8026 | 0.8243 | 0.2100 | 0.1933 | 0.7555 |
| No log | 3.0 | 147 | 0.7535 | 0.8077 | 0.2045 | 0.1823 | 0.7563 |
| No log | 4.0 | 196 | 0.7228 | 0.8227 | 0.2220 | 0.2109 | 0.7586 |
| No log | 5.0 | 245 | 0.7099 | 0.6914 | 0.2252 | 0.2193 | 0.7578 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- camembert
- Languages
- fr
- Created
- Jun 4, 2024
- Updated
- Jun 5, 2024