update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: mini-mlm-imdb
|
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 |
+
# mini-mlm-imdb
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.7643
|
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: 3e-05
|
37 |
+
- train_batch_size: 32
|
38 |
+
- eval_batch_size: 32
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: constant
|
42 |
+
- num_epochs: 200
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
+
| 3.2543 | 0.16 | 500 | 3.0042 |
|
49 |
+
| 3.1664 | 0.32 | 1000 | 2.9716 |
|
50 |
+
| 3.1428 | 0.48 | 1500 | 2.9460 |
|
51 |
+
| 3.1363 | 0.64 | 2000 | 2.9316 |
|
52 |
+
| 3.1088 | 0.8 | 2500 | 2.9068 |
|
53 |
+
| 3.0943 | 0.96 | 3000 | 2.9046 |
|
54 |
+
| 3.0436 | 1.12 | 3500 | 2.8918 |
|
55 |
+
| 3.0326 | 1.28 | 4000 | 2.8762 |
|
56 |
+
| 3.0302 | 1.44 | 4500 | 2.8765 |
|
57 |
+
| 3.0232 | 1.6 | 5000 | 2.8658 |
|
58 |
+
| 3.0123 | 1.76 | 5500 | 2.8538 |
|
59 |
+
| 3.0164 | 1.92 | 6000 | 2.8530 |
|
60 |
+
| 2.992 | 2.08 | 6500 | 2.8487 |
|
61 |
+
| 2.9922 | 2.24 | 7000 | 2.8440 |
|
62 |
+
| 2.9862 | 2.4 | 7500 | 2.8348 |
|
63 |
+
| 2.9621 | 2.56 | 8000 | 2.8324 |
|
64 |
+
| 2.9926 | 2.72 | 8500 | 2.8235 |
|
65 |
+
| 2.9871 | 2.88 | 9000 | 2.8223 |
|
66 |
+
| 2.9593 | 3.04 | 9500 | 2.8131 |
|
67 |
+
| 2.9404 | 3.2 | 10000 | 2.8119 |
|
68 |
+
| 2.9278 | 3.36 | 10500 | 2.8076 |
|
69 |
+
| 2.943 | 3.52 | 11000 | 2.8015 |
|
70 |
+
| 2.9074 | 3.68 | 11500 | 2.8067 |
|
71 |
+
| 2.9247 | 3.84 | 12000 | 2.8027 |
|
72 |
+
| 2.9188 | 4.0 | 12500 | 2.7975 |
|
73 |
+
| 2.9011 | 4.16 | 13000 | 2.7905 |
|
74 |
+
| 2.8973 | 4.32 | 13500 | 2.7893 |
|
75 |
+
| 2.8796 | 4.48 | 14000 | 2.7915 |
|
76 |
+
| 2.9026 | 4.64 | 14500 | 2.7787 |
|
77 |
+
| 2.9022 | 4.8 | 15000 | 2.7819 |
|
78 |
+
| 2.8942 | 4.96 | 15500 | 2.7843 |
|
79 |
+
| 2.8844 | 5.12 | 16000 | 2.7771 |
|
80 |
+
| 2.8777 | 5.28 | 16500 | 2.7701 |
|
81 |
+
| 2.8899 | 5.44 | 17000 | 2.7778 |
|
82 |
+
| 2.8973 | 5.6 | 17500 | 2.7702 |
|
83 |
+
| 2.877 | 5.76 | 18000 | 2.7592 |
|
84 |
+
| 2.8704 | 5.92 | 18500 | 2.7711 |
|
85 |
+
| 2.8649 | 6.08 | 19000 | 2.7610 |
|
86 |
+
| 2.8619 | 6.24 | 19500 | 2.7643 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.25.1
|
92 |
+
- Pytorch 1.12.1
|
93 |
+
- Datasets 2.7.1
|
94 |
+
- Tokenizers 0.13.2
|