End of training
Browse files- README.md +85 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
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: BERTModified-rawbert-finetuned-wikitext-test
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# BERTModified-rawbert-finetuned-wikitext-test
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 21.0426
|
24 |
+
- Precision: 0.0375
|
25 |
+
- Recall: 0.0375
|
26 |
+
- F1: 0.0375
|
27 |
+
- Accuracy: 0.0375
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 4
|
48 |
+
- eval_batch_size: 4
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 20
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 21.2097 | 1.0 | 25 | 21.0754 | 0.0157 | 0.0157 | 0.0157 | 0.0157 |
|
59 |
+
| 18.2793 | 2.0 | 50 | 20.8093 | 0.0133 | 0.0133 | 0.0133 | 0.0133 |
|
60 |
+
| 15.8444 | 3.0 | 75 | 20.6771 | 0.0157 | 0.0157 | 0.0157 | 0.0157 |
|
61 |
+
| 13.5759 | 4.0 | 100 | 20.6509 | 0.0218 | 0.0218 | 0.0218 | 0.0218 |
|
62 |
+
| 11.8523 | 5.0 | 125 | 20.6608 | 0.0230 | 0.0230 | 0.0230 | 0.0230 |
|
63 |
+
| 10.2973 | 6.0 | 150 | 20.6500 | 0.0242 | 0.0242 | 0.0242 | 0.0242 |
|
64 |
+
| 9.0372 | 7.0 | 175 | 20.7158 | 0.0266 | 0.0266 | 0.0266 | 0.0266 |
|
65 |
+
| 7.9788 | 8.0 | 200 | 20.7644 | 0.0290 | 0.0290 | 0.0290 | 0.0290 |
|
66 |
+
| 7.0864 | 9.0 | 225 | 20.7891 | 0.0278 | 0.0278 | 0.0278 | 0.0278 |
|
67 |
+
| 6.3465 | 10.0 | 250 | 20.8286 | 0.0302 | 0.0302 | 0.0302 | 0.0302 |
|
68 |
+
| 5.6973 | 11.0 | 275 | 20.8867 | 0.0351 | 0.0351 | 0.0351 | 0.0351 |
|
69 |
+
| 5.2951 | 12.0 | 300 | 20.9121 | 0.0363 | 0.0363 | 0.0363 | 0.0363 |
|
70 |
+
| 4.8066 | 13.0 | 325 | 20.9479 | 0.0375 | 0.0375 | 0.0375 | 0.0375 |
|
71 |
+
| 4.4862 | 14.0 | 350 | 21.0011 | 0.0351 | 0.0351 | 0.0351 | 0.0351 |
|
72 |
+
| 4.1891 | 15.0 | 375 | 21.0011 | 0.0363 | 0.0363 | 0.0363 | 0.0363 |
|
73 |
+
| 3.9551 | 16.0 | 400 | 21.0193 | 0.0423 | 0.0423 | 0.0423 | 0.0423 |
|
74 |
+
| 3.7954 | 17.0 | 425 | 21.0099 | 0.0351 | 0.0351 | 0.0351 | 0.0351 |
|
75 |
+
| 3.5836 | 18.0 | 450 | 21.0166 | 0.0411 | 0.0411 | 0.0411 | 0.0411 |
|
76 |
+
| 3.5873 | 19.0 | 475 | 21.0315 | 0.0399 | 0.0399 | 0.0399 | 0.0399 |
|
77 |
+
| 3.5297 | 20.0 | 500 | 21.0524 | 0.0387 | 0.0387 | 0.0387 | 0.0387 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.38.2
|
83 |
+
- Pytorch 2.1.0+cu121
|
84 |
+
- Datasets 2.18.0
|
85 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 550791244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4216bf14ceac536ae4596fff3b9de9aa58b528b109ea6c2fe6a751a019d01c1a
|
3 |
size 550791244
|