FredZhang7
commited on
Commit
•
955c23b
1
Parent(s):
4d1bc3b
update params
Browse files
README.md
CHANGED
@@ -75,11 +75,11 @@ Find the v1 (TensorFlow) model on [this page](https://github.com/FredZhang7/tfjs
|
|
75 |
| Framework | PyTorch | TensorFlow |
|
76 |
| Dataset Size | 3.0M | 2.68M |
|
77 |
| Train Split | 80% English<br>20% English + 100% Multilingual | None |
|
78 |
-
| English Train Accuracy | 99.
|
79 |
| Other Train Accuracy | 96.7% | 96.6% |
|
80 |
| Final Val Accuracy | 95.2% | 94.6% |
|
81 |
| Languages | 55 | N/A (≈35) |
|
82 |
-
| Hyperparameters | maxlen=208<br>padding='max_length'<br>batch_size=112<br>optimizer=
|
83 |
| Training Stopped | 7/18/2023 | 9/05/2022 |
|
84 |
|
85 |
<br>
|
|
|
75 |
| Framework | PyTorch | TensorFlow |
|
76 |
| Dataset Size | 3.0M | 2.68M |
|
77 |
| Train Split | 80% English<br>20% English + 100% Multilingual | None |
|
78 |
+
| English Train Accuracy | 99.5% | N/A (≈97.5%) |
|
79 |
| Other Train Accuracy | 96.7% | 96.6% |
|
80 |
| Final Val Accuracy | 95.2% | 94.6% |
|
81 |
| Languages | 55 | N/A (≈35) |
|
82 |
+
| Hyperparameters | maxlen=208<br>padding='max_length'<br>batch_size=112<br>optimizer=AdamW<br>learning_rate=1e-5<br>loss=BCEWithLogitsLoss() | maxlen=192<br>padding='max_length'<br>batch_size=16<br>optimizer=Adam<br>learning_rate=1e-5<br>loss="binary_crossentropy" |
|
83 |
| Training Stopped | 7/18/2023 | 9/05/2022 |
|
84 |
|
85 |
<br>
|