update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: bert_12_layer_model_v2_complete_training_new_wt_init_120
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# bert_12_layer_model_v2_complete_training_new_wt_init_120
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_96](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_96) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.3044
|
19 |
+
- Accuracy: 0.5675
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 1e-05
|
39 |
+
- train_batch_size: 48
|
40 |
+
- eval_batch_size: 48
|
41 |
+
- seed: 10
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 10000
|
46 |
+
- num_epochs: 5
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
52 |
+
| 2.5079 | 0.08 | 10000 | 2.4011 | 0.5539 |
|
53 |
+
| 2.4953 | 0.16 | 20000 | 2.3921 | 0.5553 |
|
54 |
+
| 2.484 | 0.25 | 30000 | 2.3823 | 0.5568 |
|
55 |
+
| 2.4828 | 0.33 | 40000 | 2.3711 | 0.5582 |
|
56 |
+
| 2.4639 | 0.41 | 50000 | 2.3587 | 0.5598 |
|
57 |
+
| 2.4572 | 0.49 | 60000 | 2.3521 | 0.5610 |
|
58 |
+
| 2.4385 | 0.57 | 70000 | 2.3430 | 0.5626 |
|
59 |
+
| 2.4307 | 0.66 | 80000 | 2.3337 | 0.5633 |
|
60 |
+
| 2.4162 | 0.74 | 90000 | 2.3208 | 0.5647 |
|
61 |
+
| 2.4088 | 0.82 | 100000 | 2.3133 | 0.5663 |
|
62 |
+
| 2.4139 | 0.9 | 110000 | 2.3044 | 0.5675 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.30.1
|
68 |
+
- Pytorch 1.14.0a0+410ce96
|
69 |
+
- Datasets 2.12.0
|
70 |
+
- Tokenizers 0.13.3
|