Training in progress epoch 0
Browse files- README.md +12 -13
- config.json +1 -1
- logs/train/events.out.tfevents.1714812347.8f02ccfbe71c.214.0.v2 +3 -0
- logs/train/events.out.tfevents.1714812493.8f02ccfbe71c.214.1.v2 +3 -0
- logs/train/events.out.tfevents.1714812839.8f02ccfbe71c.509.0.v2 +3 -0
- logs/validation/events.out.tfevents.1714813637.8f02ccfbe71c.509.1.v2 +3 -0
- tf_model.h5 +1 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Train End Logits Accuracy: 0.
|
20 |
-
- Train Start Logits Accuracy: 0.
|
21 |
-
- Validation Loss: 2.
|
22 |
-
- Validation End Logits Accuracy: 0.
|
23 |
-
- Validation Start Logits Accuracy: 0.
|
24 |
-
- Epoch:
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -40,20 +40,19 @@ More information needed
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
-
- 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': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
44 |
- training_precision: float32
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|
49 |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
|
50 |
-
| 2.
|
51 |
-
| 1.7185 | 0.5917 | 0.5638 | 2.0391 | 0.5252 | 0.4886 | 1 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
-
- Transformers 4.
|
57 |
- TensorFlow 2.15.0
|
58 |
-
- Datasets 2.
|
59 |
-
- Tokenizers 0.
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 2.3101
|
19 |
+
- Train End Logits Accuracy: 0.5128
|
20 |
+
- Train Start Logits Accuracy: 0.5040
|
21 |
+
- Validation Loss: 2.0900
|
22 |
+
- Validation End Logits Accuracy: 0.5237
|
23 |
+
- Validation Start Logits Accuracy: 0.4869
|
24 |
+
- Epoch: 0
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
+
- 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': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 22620, '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}
|
44 |
- training_precision: float32
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|
49 |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
|
50 |
+
| 2.3101 | 0.5128 | 0.5040 | 2.0900 | 0.5237 | 0.4869 | 0 |
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
+
- Transformers 4.39.3
|
56 |
- TensorFlow 2.15.0
|
57 |
+
- Datasets 2.18.0
|
58 |
+
- Tokenizers 0.15.2
|
config.json
CHANGED
@@ -19,6 +19,6 @@
|
|
19 |
"seq_classif_dropout": 0.2,
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
-
"transformers_version": "4.
|
23 |
"vocab_size": 28996
|
24 |
}
|
|
|
19 |
"seq_classif_dropout": 0.2,
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
+
"transformers_version": "4.39.3",
|
23 |
"vocab_size": 28996
|
24 |
}
|
logs/train/events.out.tfevents.1714812347.8f02ccfbe71c.214.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdf83fa3c502b6cae61f0a8fb9561bf854aeb9aef5e58f8d204294a3d3fdbd99
|
3 |
+
size 1441201
|
logs/train/events.out.tfevents.1714812493.8f02ccfbe71c.214.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78b5b6042c83cec3acae68c8f1d1c8e7ca4ad03c3da6225e8ca27d9952d5efcd
|
3 |
+
size 1441406
|
logs/train/events.out.tfevents.1714812839.8f02ccfbe71c.509.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f00767c9b41d904f8d3e6597d61436d01cff737a00ce11654764d48c90f5902f
|
3 |
+
size 1441432
|
logs/validation/events.out.tfevents.1714813637.8f02ccfbe71c.509.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9429176b2f9164e22ed3737db063baabb3209b0fef73dd4f89fe4ffb392d5299
|
3 |
+
size 604
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 260895720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c58e00f15ef6d2c0995e6b9074d986b5a4314d5083ea5c760f580fc4e8452ca
|
3 |
size 260895720
|
tokenizer_config.json
CHANGED
@@ -45,7 +45,7 @@
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": false,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"model_max_length":
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": false,
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|