End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilbert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imdb
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: N_distilbert_imdb_padding30model
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imdb
|
| 18 |
+
type: imdb
|
| 19 |
+
config: plain_text
|
| 20 |
+
split: test
|
| 21 |
+
args: plain_text
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.93196
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# N_distilbert_imdb_padding30model
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.7513
|
| 36 |
+
- Accuracy: 0.9320
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 2e-05
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 16
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 20
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 67 |
+
| 0.2412 | 1.0 | 1563 | 0.2749 | 0.9004 |
|
| 68 |
+
| 0.1694 | 2.0 | 3126 | 0.2355 | 0.9270 |
|
| 69 |
+
| 0.1055 | 3.0 | 4689 | 0.3029 | 0.9262 |
|
| 70 |
+
| 0.0621 | 4.0 | 6252 | 0.3240 | 0.9282 |
|
| 71 |
+
| 0.0422 | 5.0 | 7815 | 0.4462 | 0.9269 |
|
| 72 |
+
| 0.0366 | 6.0 | 9378 | 0.4963 | 0.9274 |
|
| 73 |
+
| 0.0309 | 7.0 | 10941 | 0.5017 | 0.9286 |
|
| 74 |
+
| 0.0189 | 8.0 | 12504 | 0.6588 | 0.9198 |
|
| 75 |
+
| 0.0217 | 9.0 | 14067 | 0.5946 | 0.9218 |
|
| 76 |
+
| 0.02 | 10.0 | 15630 | 0.6104 | 0.9248 |
|
| 77 |
+
| 0.0112 | 11.0 | 17193 | 0.5921 | 0.9293 |
|
| 78 |
+
| 0.0096 | 12.0 | 18756 | 0.6499 | 0.9290 |
|
| 79 |
+
| 0.0075 | 13.0 | 20319 | 0.6577 | 0.9299 |
|
| 80 |
+
| 0.0036 | 14.0 | 21882 | 0.6225 | 0.9289 |
|
| 81 |
+
| 0.0043 | 15.0 | 23445 | 0.6558 | 0.9290 |
|
| 82 |
+
| 0.0015 | 16.0 | 25008 | 0.6923 | 0.9314 |
|
| 83 |
+
| 0.0036 | 17.0 | 26571 | 0.7606 | 0.9284 |
|
| 84 |
+
| 0.0 | 18.0 | 28134 | 0.7696 | 0.931 |
|
| 85 |
+
| 0.0028 | 19.0 | 29697 | 0.7493 | 0.9319 |
|
| 86 |
+
| 0.0005 | 20.0 | 31260 | 0.7513 | 0.9320 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
### Framework versions
|
| 90 |
+
|
| 91 |
+
- Transformers 4.33.2
|
| 92 |
+
- Pytorch 2.0.1+cu117
|
| 93 |
+
- Datasets 2.14.5
|
| 94 |
+
- Tokenizers 0.13.3
|