Training in progress epoch 0
Browse files- README.md +5 -24
- checkpoint/extra_data.pickle +3 -0
- checkpoint/weights.h5 +3 -0
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Train Loss:
|
17 |
-
- Validation Loss:
|
18 |
-
- Epoch:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,33 +34,14 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
38 |
- training_precision: mixed_float16
|
39 |
|
40 |
### Training results
|
41 |
|
42 |
| Train Loss | Validation Loss | Epoch |
|
43 |
|:----------:|:---------------:|:-----:|
|
44 |
-
| 4.
|
45 |
-
| 4.2310 | 4.0653 | 1 |
|
46 |
-
| 4.0064 | 3.9325 | 2 |
|
47 |
-
| 3.8931 | 3.8914 | 3 |
|
48 |
-
| 3.7736 | 3.7306 | 4 |
|
49 |
-
| 3.5888 | 3.7033 | 5 |
|
50 |
-
| 3.5368 | 3.6587 | 6 |
|
51 |
-
| 3.4945 | 3.5798 | 7 |
|
52 |
-
| 3.4245 | 3.5234 | 8 |
|
53 |
-
| 3.3508 | 3.4322 | 9 |
|
54 |
-
| 3.2790 | 3.4335 | 10 |
|
55 |
-
| 3.1635 | 3.3848 | 11 |
|
56 |
-
| 3.1446 | 3.3465 | 12 |
|
57 |
-
| 3.0585 | 3.3234 | 13 |
|
58 |
-
| nan | nan | 14 |
|
59 |
-
| nan | nan | 15 |
|
60 |
-
| nan | nan | 16 |
|
61 |
-
| nan | nan | 17 |
|
62 |
-
| nan | nan | 18 |
|
63 |
-
| nan | nan | 19 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 4.6440
|
17 |
+
- Validation Loss: 4.2231
|
18 |
+
- Epoch: 0
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
|
38 |
- training_precision: mixed_float16
|
39 |
|
40 |
### Training results
|
41 |
|
42 |
| Train Loss | Validation Loss | Epoch |
|
43 |
|:----------:|:---------------:|:-----:|
|
44 |
+
| 4.6440 | 4.2231 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
|
47 |
### Framework versions
|
checkpoint/extra_data.pickle
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:962468d06d6a93b7cf28d1a7f1353f8898d951a9c82dee9b2f93a436c30af909
|
3 |
+
size 1080533909
|
checkpoint/weights.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72950c0f718a9ecbe2ac165e6ad2d9f7c715920adb4c99c04ddce7d2ea4a6500
|
3 |
+
size 737947308
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 737947308
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bd46ac4d35396d965abc72789cbfe4cac153106545f663e81b6a8b11376c5a8
|
3 |
size 737947308
|