Training in progress epoch 0
Browse files- README.md +5 -40
- config.json +1 -1
- generation_config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
library_name: transformers
|
| 3 |
base_model: bert-base-chinese
|
| 4 |
tags:
|
| 5 |
- generated_from_keras_callback
|
|
@@ -15,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Train Loss:
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -42,46 +41,12 @@ The following hyperparameters were used during training:
|
|
| 42 |
|
| 43 |
| Train Loss | Epoch |
|
| 44 |
|:----------:|:-----:|
|
| 45 |
-
|
|
| 46 |
-
| 0.0878 | 1 |
|
| 47 |
-
| 0.0852 | 2 |
|
| 48 |
-
| 0.0824 | 3 |
|
| 49 |
-
| 0.0810 | 4 |
|
| 50 |
-
| 0.0812 | 5 |
|
| 51 |
-
| 0.0790 | 6 |
|
| 52 |
-
| 0.0772 | 7 |
|
| 53 |
-
| 0.0755 | 8 |
|
| 54 |
-
| 0.0749 | 9 |
|
| 55 |
-
| 0.0717 | 10 |
|
| 56 |
-
| 0.0722 | 11 |
|
| 57 |
-
| 0.0718 | 12 |
|
| 58 |
-
| 0.0689 | 13 |
|
| 59 |
-
| 0.0863 | 14 |
|
| 60 |
-
| 0.0838 | 15 |
|
| 61 |
-
| 0.0731 | 16 |
|
| 62 |
-
| 0.0768 | 17 |
|
| 63 |
-
| 0.0675 | 18 |
|
| 64 |
-
| 0.0646 | 19 |
|
| 65 |
-
| 0.0650 | 20 |
|
| 66 |
-
| 0.0627 | 21 |
|
| 67 |
-
| 0.0610 | 22 |
|
| 68 |
-
| 0.0594 | 23 |
|
| 69 |
-
| 0.0585 | 24 |
|
| 70 |
-
| 0.0585 | 25 |
|
| 71 |
-
| 0.0577 | 26 |
|
| 72 |
-
| 0.0569 | 27 |
|
| 73 |
-
| 0.0565 | 28 |
|
| 74 |
-
| 0.0542 | 29 |
|
| 75 |
-
| 0.0531 | 30 |
|
| 76 |
-
| 0.0531 | 31 |
|
| 77 |
-
| 0.0532 | 32 |
|
| 78 |
-
| 0.0535 | 33 |
|
| 79 |
-
| 0.0530 | 34 |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|
| 83 |
|
| 84 |
-
- Transformers 4.44.
|
| 85 |
-
- TensorFlow 2.
|
| 86 |
- Datasets 2.21.0
|
| 87 |
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: bert-base-chinese
|
| 3 |
tags:
|
| 4 |
- generated_from_keras_callback
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 6.5795
|
| 18 |
+
- Epoch: 0
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 41 |
|
| 42 |
| Train Loss | Epoch |
|
| 43 |
|:----------:|:-----:|
|
| 44 |
+
| 6.5795 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
+
- Transformers 4.44.0
|
| 50 |
+
- TensorFlow 2.16.1
|
| 51 |
- Datasets 2.21.0
|
| 52 |
- Tokenizers 0.19.1
|
config.json
CHANGED
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"pooler_size_per_head": 128,
|
| 25 |
"pooler_type": "first_token_transform",
|
| 26 |
"position_embedding_type": "absolute",
|
| 27 |
-
"transformers_version": "4.44.
|
| 28 |
"type_vocab_size": 2,
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 21128
|
|
|
|
| 24 |
"pooler_size_per_head": 128,
|
| 25 |
"pooler_type": "first_token_transform",
|
| 26 |
"position_embedding_type": "absolute",
|
| 27 |
+
"transformers_version": "4.44.0",
|
| 28 |
"type_vocab_size": 2,
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 21128
|
generation_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"pad_token_id": 0,
|
| 4 |
-
"transformers_version": "4.44.
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.44.0"
|
| 5 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 475933304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea6510c049d4c5617ead560ac5812d047d9402f16d572403e1e1d8fdda4f19f0
|
| 3 |
size 475933304
|