Commit
·
ecc628c
1
Parent(s):
6fd29ed
Training in progress epoch 0
Browse files- README.md +5 -25
- 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 |
|
|
@@ -44,27 +44,7 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
| 46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
| 47 |
-
|
|
| 48 |
-
| 4.4240 | 4.0959 | 0.4233 | 1 |
|
| 49 |
-
| 3.6373 | 3.4046 | 0.69 | 2 |
|
| 50 |
-
| 2.8675 | 2.7514 | 0.8233 | 3 |
|
| 51 |
-
| 2.1664 | 2.1956 | 0.8667 | 4 |
|
| 52 |
-
| 1.5991 | 1.7330 | 0.86 | 5 |
|
| 53 |
-
| 1.1413 | 1.4153 | 0.8833 | 6 |
|
| 54 |
-
| 0.8233 | 1.1592 | 0.8867 | 7 |
|
| 55 |
-
| 0.6009 | 0.9746 | 0.9033 | 8 |
|
| 56 |
-
| 0.4423 | 0.8468 | 0.9067 | 9 |
|
| 57 |
-
| 0.3338 | 0.7524 | 0.8967 | 10 |
|
| 58 |
-
| 0.2628 | 0.6865 | 0.8967 | 11 |
|
| 59 |
-
| 0.2142 | 0.6403 | 0.8933 | 12 |
|
| 60 |
-
| 0.1774 | 0.6060 | 0.8933 | 13 |
|
| 61 |
-
| 0.1522 | 0.5770 | 0.89 | 14 |
|
| 62 |
-
| 0.1316 | 0.5526 | 0.89 | 15 |
|
| 63 |
-
| 0.1163 | 0.5336 | 0.8867 | 16 |
|
| 64 |
-
| 0.1027 | 0.5190 | 0.89 | 17 |
|
| 65 |
-
| 0.0923 | 0.5043 | 0.8933 | 18 |
|
| 66 |
-
| 0.0851 | 0.4970 | 0.8867 | 19 |
|
| 67 |
-
| 0.0761 | 0.4911 | 0.8833 | 20 |
|
| 68 |
|
| 69 |
|
| 70 |
### 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: 5.0926
|
| 19 |
+
- Validation Loss: 4.9378
|
| 20 |
+
- Train Accuracy: 0.0267
|
| 21 |
+
- Epoch: 0
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 44 |
|
| 45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
| 46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
| 47 |
+
| 5.0926 | 4.9378 | 0.0267 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
|
| 50 |
### Framework versions
|
config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"classifier_dropout": 0.
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.0,
|
|
|
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": 0.5,
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.0,
|
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 sha256:4f715d2e0cda7d3b61d3f2c3887909d5c2b33c550fcdf5ee6398cfb4cc851585
|
| 3 |
size 1341734528
|