GQA[:10000]
Browse files- README.md +24 -4
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: dandelin/vilt-b32-mlm
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
datasets:
|
| 7 |
-
- gqa
|
| 8 |
model-index:
|
| 9 |
- name: vilt_finetuned_200
|
| 10 |
results: []
|
|
@@ -15,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# vilt_finetuned_200
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -40,10 +40,30 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
|
|
|
| 3 |
base_model: dandelin/vilt-b32-mlm
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: vilt_finetuned_200
|
| 8 |
results: []
|
|
|
|
| 13 |
|
| 14 |
# vilt_finetuned_200
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 4.3306
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 3
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 363.9675 | 0.16 | 100 | 26.1215 |
|
| 50 |
+
| 11.4975 | 0.32 | 200 | 7.2332 |
|
| 51 |
+
| 6.1909 | 0.48 | 300 | 5.9332 |
|
| 52 |
+
| 5.2134 | 0.64 | 400 | 5.5186 |
|
| 53 |
+
| 5.0189 | 0.8 | 500 | 5.3268 |
|
| 54 |
+
| 4.7551 | 0.96 | 600 | 5.0921 |
|
| 55 |
+
| 4.5394 | 1.12 | 700 | 4.9538 |
|
| 56 |
+
| 4.3441 | 1.28 | 800 | 4.8967 |
|
| 57 |
+
| 4.1436 | 1.44 | 900 | 4.7419 |
|
| 58 |
+
| 4.1847 | 1.6 | 1000 | 4.6581 |
|
| 59 |
+
| 4.0116 | 1.76 | 1100 | 4.5915 |
|
| 60 |
+
| 3.918 | 1.92 | 1200 | 4.5202 |
|
| 61 |
+
| 3.8251 | 2.08 | 1300 | 4.4634 |
|
| 62 |
+
| 3.7981 | 2.24 | 1400 | 4.4169 |
|
| 63 |
+
| 3.7108 | 2.4 | 1500 | 4.3954 |
|
| 64 |
+
| 3.5706 | 2.56 | 1600 | 4.3626 |
|
| 65 |
+
| 3.5559 | 2.72 | 1700 | 4.3374 |
|
| 66 |
+
| 3.6951 | 2.88 | 1800 | 4.3306 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 462520410
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a8239c4dd1e4c7318a4988c6a4de0db7088c7aab853d8e3421d5eec23bf28f7
|
| 3 |
size 462520410
|