Training in progress epoch 0
Browse files- README.md +7 -7
- config.json +3 -2
- tf_model.h5 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +0 -2
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_keras_callback
|
| 4 |
model-index:
|
|
@@ -11,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# CYONG/v2
|
| 13 |
|
| 14 |
-
This model
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Train Loss:
|
| 17 |
-
- Validation Loss:
|
| 18 |
-
- Epoch:
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -41,9 +43,7 @@ The following hyperparameters were used during training:
|
|
| 41 |
|
| 42 |
| Train Loss | Validation Loss | Epoch |
|
| 43 |
|:----------:|:---------------:|:-----:|
|
| 44 |
-
|
|
| 45 |
-
| 4.2775 | 4.1656 | 1 |
|
| 46 |
-
| 4.0073 | 4.1656 | 2 |
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilbert-base-multilingual-cased
|
| 4 |
tags:
|
| 5 |
- generated_from_keras_callback
|
| 6 |
model-index:
|
|
|
|
| 13 |
|
| 14 |
# CYONG/v2
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 3.2713
|
| 19 |
+
- Validation Loss: 2.2642
|
| 20 |
+
- Epoch: 0
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 43 |
|
| 44 |
| Train Loss | Validation Loss | Epoch |
|
| 45 |
|:----------:|:---------------:|:-----:|
|
| 46 |
+
| 3.2713 | 2.2642 | 0 |
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "distilbert-base-
|
| 3 |
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
"DistilBertForQuestionAnswering"
|
|
@@ -13,11 +13,12 @@
|
|
| 13 |
"model_type": "distilbert",
|
| 14 |
"n_heads": 12,
|
| 15 |
"n_layers": 6,
|
|
|
|
| 16 |
"pad_token_id": 0,
|
| 17 |
"qa_dropout": 0.1,
|
| 18 |
"seq_classif_dropout": 0.2,
|
| 19 |
"sinusoidal_pos_embds": false,
|
| 20 |
"tie_weights_": true,
|
| 21 |
"transformers_version": "4.31.0",
|
| 22 |
-
"vocab_size":
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
| 3 |
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
"DistilBertForQuestionAnswering"
|
|
|
|
| 13 |
"model_type": "distilbert",
|
| 14 |
"n_heads": 12,
|
| 15 |
"n_layers": 6,
|
| 16 |
+
"output_past": true,
|
| 17 |
"pad_token_id": 0,
|
| 18 |
"qa_dropout": 0.1,
|
| 19 |
"seq_classif_dropout": 0.2,
|
| 20 |
"sinusoidal_pos_embds": false,
|
| 21 |
"tie_weights_": true,
|
| 22 |
"transformers_version": "4.31.0",
|
| 23 |
+
"vocab_size": 119547
|
| 24 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09917339ae1652a733f8454c60094e54028719aaf891e7e1bd05700e2d91294d
|
| 3 |
+
size 539068392
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
-
"do_basic_tokenize": true,
|
| 5 |
"do_lower_case": false,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
"model_max_length": 512,
|
| 8 |
-
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
"strip_accents": null,
|
|
|
|
| 1 |
{
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
|
|
|
| 4 |
"do_lower_case": false,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"model_max_length": 512,
|
|
|
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
"strip_accents": null,
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|