update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
- f1
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
model-index:
|
| 10 |
+
- name: distilrubert_tiny-2nd-finetune-epru
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# distilrubert_tiny-2nd-finetune-epru
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mmillet/distilrubert-tiny-cased-conversational-v1_single_finetuned_on_cedr_augmented](https://huggingface.co/mmillet/distilrubert-tiny-cased-conversational-v1_single_finetuned_on_cedr_augmented) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4467
|
| 22 |
+
- Accuracy: 0.8712
|
| 23 |
+
- F1: 0.8718
|
| 24 |
+
- Precision: 0.8867
|
| 25 |
+
- Recall: 0.8712
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 0.0001
|
| 45 |
+
- train_batch_size: 64
|
| 46 |
+
- eval_batch_size: 64
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 20
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 56 |
+
| 0.4947 | 1.0 | 12 | 0.4142 | 0.8773 | 0.8777 | 0.8907 | 0.8773 |
|
| 57 |
+
| 0.2614 | 2.0 | 24 | 0.3178 | 0.9018 | 0.9011 | 0.9069 | 0.9018 |
|
| 58 |
+
| 0.2079 | 3.0 | 36 | 0.3234 | 0.8773 | 0.8784 | 0.8850 | 0.8773 |
|
| 59 |
+
| 0.1545 | 4.0 | 48 | 0.3729 | 0.8834 | 0.8830 | 0.8946 | 0.8834 |
|
| 60 |
+
| 0.1028 | 5.0 | 60 | 0.2964 | 0.9018 | 0.9016 | 0.9073 | 0.9018 |
|
| 61 |
+
| 0.0986 | 6.0 | 72 | 0.2971 | 0.9141 | 0.9139 | 0.9152 | 0.9141 |
|
| 62 |
+
| 0.0561 | 7.0 | 84 | 0.3482 | 0.8957 | 0.8962 | 0.9023 | 0.8957 |
|
| 63 |
+
| 0.0336 | 8.0 | 96 | 0.3731 | 0.8957 | 0.8953 | 0.9014 | 0.8957 |
|
| 64 |
+
| 0.0364 | 9.0 | 108 | 0.4467 | 0.8712 | 0.8718 | 0.8867 | 0.8712 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.20.0
|
| 70 |
+
- Pytorch 1.11.0+cu113
|
| 71 |
+
- Datasets 2.3.2
|
| 72 |
+
- Tokenizers 0.12.1
|