Model save
Browse files
README.md
CHANGED
|
@@ -3,11 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: asapp/sew-d-tiny-100k-ft-ls100h
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
metrics:
|
| 7 |
-
- accuracy
|
| 8 |
-
- precision
|
| 9 |
-
- recall
|
| 10 |
-
- f1
|
| 11 |
model-index:
|
| 12 |
- name: sewd_classifier
|
| 13 |
results: []
|
|
@@ -19,13 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# sewd_classifier
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [asapp/sew-d-tiny-100k-ft-ls100h](https://huggingface.co/asapp/sew-d-tiny-100k-ft-ls100h) on an unknown dataset.
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 3.9535
|
| 24 |
-
- Accuracy: 0.0605
|
| 25 |
-
- Precision: 0.0136
|
| 26 |
-
- Recall: 0.0605
|
| 27 |
-
- F1: 0.0179
|
| 28 |
-
- Binary: 0.3308
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
@@ -44,7 +32,7 @@ More information needed
|
|
| 44 |
### Training hyperparameters
|
| 45 |
|
| 46 |
The following hyperparameters were used during training:
|
| 47 |
-
- learning_rate:
|
| 48 |
- train_batch_size: 32
|
| 49 |
- eval_batch_size: 32
|
| 50 |
- seed: 42
|
|
@@ -55,23 +43,6 @@ The following hyperparameters were used during training:
|
|
| 55 |
- num_epochs: 10
|
| 56 |
- mixed_precision_training: Native AMP
|
| 57 |
|
| 58 |
-
### Training results
|
| 59 |
-
|
| 60 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Binary |
|
| 61 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
|
| 62 |
-
| No log | 0.86 | 50 | 4.4184 | 0.0194 | 0.0009 | 0.0194 | 0.0017 | 0.1934 |
|
| 63 |
-
| 4.4292 | 1.72 | 100 | 4.3532 | 0.0243 | 0.0032 | 0.0243 | 0.0046 | 0.2325 |
|
| 64 |
-
| 4.3785 | 2.59 | 150 | 4.2824 | 0.0267 | 0.0025 | 0.0267 | 0.0040 | 0.2481 |
|
| 65 |
-
| 4.2885 | 3.45 | 200 | 4.2182 | 0.0510 | 0.0310 | 0.0510 | 0.0178 | 0.2917 |
|
| 66 |
-
| 4.2147 | 4.31 | 250 | 4.1618 | 0.0607 | 0.0171 | 0.0607 | 0.0217 | 0.3165 |
|
| 67 |
-
| 4.1553 | 5.17 | 300 | 4.1076 | 0.0631 | 0.0310 | 0.0631 | 0.0243 | 0.3245 |
|
| 68 |
-
| 4.1025 | 6.03 | 350 | 4.0650 | 0.0631 | 0.0285 | 0.0631 | 0.0252 | 0.3282 |
|
| 69 |
-
| 4.1025 | 6.9 | 400 | 4.0315 | 0.0607 | 0.0155 | 0.0607 | 0.0183 | 0.3323 |
|
| 70 |
-
| 4.0669 | 7.76 | 450 | 4.0075 | 0.0607 | 0.0135 | 0.0607 | 0.0173 | 0.3299 |
|
| 71 |
-
| 4.0386 | 8.62 | 500 | 3.9906 | 0.0631 | 0.0181 | 0.0631 | 0.0205 | 0.3337 |
|
| 72 |
-
| 4.0171 | 9.48 | 550 | 3.9803 | 0.0655 | 0.0188 | 0.0655 | 0.0211 | 0.3386 |
|
| 73 |
-
|
| 74 |
-
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
- Transformers 4.38.2
|
|
|
|
| 3 |
base_model: asapp/sew-d-tiny-100k-ft-ls100h
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: sewd_classifier
|
| 8 |
results: []
|
|
|
|
| 14 |
# sewd_classifier
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [asapp/sew-d-tiny-100k-ft-ls100h](https://huggingface.co/asapp/sew-d-tiny-100k-ft-ls100h) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 3e-05
|
| 36 |
- train_batch_size: 32
|
| 37 |
- eval_batch_size: 32
|
| 38 |
- seed: 42
|
|
|
|
| 43 |
- num_epochs: 10
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.38.2
|
runs/Jun17_22-02-21_LAPTOP-1GID9RGH/events.out.tfevents.1718636542.LAPTOP-1GID9RGH.15196.1
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 sha256:2c61f68538d3c31fb04ae799d3942dbb90639aa0b4f9e8a1d9fd8d83b929aa16
|
| 3 |
+
size 17550
|