Commit
•
a5762a1
1
Parent(s):
946b1e0
Training in progress epoch 0
Browse files- README.md +5 -34
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Train Loss:
|
| 19 |
-
- Validation Loss:
|
| 20 |
-
- Train Accuracy: 0.
|
| 21 |
-
- Epoch:
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -44,36 +44,7 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
| 46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
| 47 |
-
| 5.
|
| 48 |
-
| 4.8091 | 4.5518 | 0.19 | 1 |
|
| 49 |
-
| 4.2565 | 3.9529 | 0.4833 | 2 |
|
| 50 |
-
| 3.5496 | 3.3870 | 0.6733 | 3 |
|
| 51 |
-
| 2.9320 | 2.8781 | 0.76 | 4 |
|
| 52 |
-
| 2.3851 | 2.4109 | 0.8233 | 5 |
|
| 53 |
-
| 1.8879 | 2.0233 | 0.8633 | 6 |
|
| 54 |
-
| 1.4473 | 1.6912 | 0.8667 | 7 |
|
| 55 |
-
| 1.1197 | 1.4349 | 0.8867 | 8 |
|
| 56 |
-
| 0.8654 | 1.2351 | 0.8767 | 9 |
|
| 57 |
-
| 0.6786 | 1.1051 | 0.8933 | 10 |
|
| 58 |
-
| 0.5352 | 0.9739 | 0.8967 | 11 |
|
| 59 |
-
| 0.4209 | 0.8814 | 0.8967 | 12 |
|
| 60 |
-
| 0.3455 | 0.8079 | 0.8933 | 13 |
|
| 61 |
-
| 0.2878 | 0.7635 | 0.8967 | 14 |
|
| 62 |
-
| 0.2364 | 0.7142 | 0.9 | 15 |
|
| 63 |
-
| 0.2115 | 0.6899 | 0.9 | 16 |
|
| 64 |
-
| 0.1827 | 0.6554 | 0.9067 | 17 |
|
| 65 |
-
| 0.1625 | 0.6388 | 0.8967 | 18 |
|
| 66 |
-
| 0.1422 | 0.6158 | 0.9033 | 19 |
|
| 67 |
-
| 0.1321 | 0.6181 | 0.9 | 20 |
|
| 68 |
-
| 0.1187 | 0.5910 | 0.8933 | 21 |
|
| 69 |
-
| 0.1072 | 0.5873 | 0.8967 | 22 |
|
| 70 |
-
| 0.0988 | 0.5725 | 0.8967 | 23 |
|
| 71 |
-
| 0.0902 | 0.5619 | 0.8967 | 24 |
|
| 72 |
-
| 0.0844 | 0.5506 | 0.8967 | 25 |
|
| 73 |
-
| 0.0776 | 0.5489 | 0.89 | 26 |
|
| 74 |
-
| 0.0724 | 0.5411 | 0.8933 | 27 |
|
| 75 |
-
| 0.0687 | 0.5280 | 0.8933 | 28 |
|
| 76 |
-
| 0.0645 | 0.5256 | 0.89 | 29 |
|
| 77 |
|
| 78 |
|
| 79 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 5.1229
|
| 19 |
+
- Validation Loss: 5.0343
|
| 20 |
+
- Train Accuracy: 0.0067
|
| 21 |
+
- Epoch: 0
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 44 |
|
| 45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
| 46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
| 47 |
+
| 5.1229 | 5.0343 | 0.0067 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
|
| 50 |
### Framework versions
|
config.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"classifier_dropout": 0.5,
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
-
"hidden_dropout_prob": 0.
|
| 11 |
"hidden_size": 1024,
|
| 12 |
"id2label": {
|
| 13 |
"0": "LABEL_0",
|
|
|
|
| 7 |
"classifier_dropout": 0.5,
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.4,
|
| 11 |
"hidden_size": 1024,
|
| 12 |
"id2label": {
|
| 13 |
"0": "LABEL_0",
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1341734528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ceb1cb66d5c12908f681272d87fa414f0da25747c3d3938af4c0d693866738fe
|
| 3 |
size 1341734528
|