Training in progress epoch 0
Browse files- README.md +6 -8
- tf_model.h5 +1 -1
- tokenizer_config.json +3 -1
README.md
CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Validation Loss: 1.
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,16 +36,14 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
|
|
47 |
-
| 1.8578 | 1.8098 | 1 |
|
48 |
-
| 1.6098 | 1.8098 | 2 |
|
49 |
|
50 |
|
51 |
### Framework versions
|
@@ -53,4 +51,4 @@ The following hyperparameters were used during training:
|
|
53 |
- Transformers 4.35.2
|
54 |
- TensorFlow 2.15.0
|
55 |
- Datasets 2.16.1
|
56 |
-
- Tokenizers 0.15.
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 2.4444
|
19 |
+
- Validation Loss: 1.8918
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 2.4444 | 1.8918 | 0 |
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
|
|
51 |
- Transformers 4.35.2
|
52 |
- TensorFlow 2.15.0
|
53 |
- Datasets 2.16.1
|
54 |
+
- Tokenizers 0.15.1
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265583592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db6824550f42ffc65eb33d013d5ada5595d77e8344d3740e2d947e810a071567
|
3 |
size 265583592
|
tokenizer_config.json
CHANGED
@@ -43,13 +43,15 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
|
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
"model_max_length": 512,
|
|
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
"unk_token": "[UNK]"
|
57 |
}
|