Edison
commited on
Commit
•
622c696
1
Parent(s):
abff96a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: hf-distilbert-imdb-mlm-cosine
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# hf-distilbert-imdb-mlm-cosine
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.0939
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
+
- train_batch_size: 64
|
| 38 |
+
- eval_batch_size: 64
|
| 39 |
+
- seed: 420
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: cosine
|
| 42 |
+
- num_epochs: 20.0
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 2.5054 | 1.0 | 383 | 2.3043 |
|
| 49 |
+
| 2.3885 | 2.0 | 766 | 2.2447 |
|
| 50 |
+
| 2.3418 | 3.0 | 1149 | 2.2319 |
|
| 51 |
+
| 2.3045 | 4.0 | 1532 | 2.1883 |
|
| 52 |
+
| 2.2772 | 5.0 | 1915 | 2.1893 |
|
| 53 |
+
| 2.2543 | 6.0 | 2298 | 2.1683 |
|
| 54 |
+
| 2.2308 | 7.0 | 2681 | 2.1454 |
|
| 55 |
+
| 2.2139 | 8.0 | 3064 | 2.1403 |
|
| 56 |
+
| 2.2008 | 9.0 | 3447 | 2.1165 |
|
| 57 |
+
| 2.1937 | 10.0 | 3830 | 2.1281 |
|
| 58 |
+
| 2.1778 | 11.0 | 4213 | 2.1189 |
|
| 59 |
+
| 2.1742 | 12.0 | 4596 | 2.1218 |
|
| 60 |
+
| 2.1611 | 13.0 | 4979 | 2.0996 |
|
| 61 |
+
| 2.1562 | 14.0 | 5362 | 2.0992 |
|
| 62 |
+
| 2.1508 | 15.0 | 5745 | 2.1013 |
|
| 63 |
+
| 2.1469 | 16.0 | 6128 | 2.0945 |
|
| 64 |
+
| 2.1437 | 17.0 | 6511 | 2.0899 |
|
| 65 |
+
| 2.1436 | 18.0 | 6894 | 2.0827 |
|
| 66 |
+
| 2.1443 | 19.0 | 7277 | 2.0935 |
|
| 67 |
+
| 2.1389 | 20.0 | 7660 | 2.0939 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.30.2
|
| 73 |
+
- Pytorch 2.0.1+cu117
|
| 74 |
+
- Datasets 2.13.1
|
| 75 |
+
- Tokenizers 0.13.3
|