Commit
•
504883a
1
Parent(s):
37b8e8e
End of training
Browse files
README.md
CHANGED
|
@@ -3,11 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: distilbert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
metrics:
|
| 7 |
-
- precision
|
| 8 |
-
- recall
|
| 9 |
-
- f1
|
| 10 |
-
- accuracy
|
| 11 |
model-index:
|
| 12 |
- name: trainer
|
| 13 |
results: []
|
|
@@ -19,12 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# trainer
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 4.5429
|
| 24 |
-
- Precision: 0.6049
|
| 25 |
-
- Recall: 0.5714
|
| 26 |
-
- F1: 0.5559
|
| 27 |
-
- Accuracy: 0.5714
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -43,9 +32,9 @@ More information needed
|
|
| 43 |
### Training hyperparameters
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
-
- learning_rate:
|
| 47 |
-
- train_batch_size:
|
| 48 |
-
- eval_batch_size:
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
|
@@ -53,21 +42,11 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
-
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
-
| 0.0126 | 0.57 | 30 | 3.5750 | 0.6388 | 0.6190 | 0.6167 | 0.6190 |
|
| 59 |
-
| 0.0144 | 1.13 | 60 | 3.7088 | 0.6787 | 0.6548 | 0.6479 | 0.6548 |
|
| 60 |
-
| 0.0364 | 1.7 | 90 | 3.5580 | 0.6614 | 0.6548 | 0.6488 | 0.6548 |
|
| 61 |
-
| 0.0991 | 2.26 | 120 | 3.8208 | 0.6775 | 0.6429 | 0.6407 | 0.6429 |
|
| 62 |
-
| 0.0 | 2.83 | 150 | 4.5110 | 0.6127 | 0.5833 | 0.5646 | 0.5833 |
|
| 63 |
-
| 0.0 | 3.4 | 180 | 4.5298 | 0.6127 | 0.5833 | 0.5646 | 0.5833 |
|
| 64 |
-
| 0.0 | 3.96 | 210 | 4.5318 | 0.6127 | 0.5833 | 0.5646 | 0.5833 |
|
| 65 |
-
| 0.0 | 4.53 | 240 | 4.5429 | 0.6049 | 0.5714 | 0.5559 | 0.5714 |
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
-
- Transformers 4.
|
| 71 |
- Pytorch 2.2.1+cu121
|
| 72 |
- Datasets 2.18.0
|
| 73 |
- Tokenizers 0.15.2
|
|
|
|
| 3 |
base_model: distilbert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: trainer
|
| 8 |
results: []
|
|
|
|
| 14 |
# trainer
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 2e-05
|
| 36 |
+
- train_batch_size: 16
|
| 37 |
+
- eval_batch_size: 16
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
|
|
|
| 42 |
|
| 43 |
### Training results
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
+
- Transformers 4.39.3
|
| 50 |
- Pytorch 2.2.1+cu121
|
| 51 |
- Datasets 2.18.0
|
| 52 |
- Tokenizers 0.15.2
|