End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: dandelin/vilt-b32-finetuned-vqa
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ViLT_FT_Balanced_Binary_Abstract_Scenes
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ViLT_FT_Balanced_Binary_Abstract_Scenes
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [dandelin/vilt-b32-finetuned-vqa](https://huggingface.co/dandelin/vilt-b32-finetuned-vqa) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.3521
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0005
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 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 |
+
| 1.6688 | 0.17 | 200 | 1.6769 |
|
| 50 |
+
| 1.3841 | 0.34 | 400 | 1.6145 |
|
| 51 |
+
| 1.3773 | 0.5 | 600 | 1.5574 |
|
| 52 |
+
| 1.3539 | 0.67 | 800 | 1.5374 |
|
| 53 |
+
| 1.3458 | 0.84 | 1000 | 1.5044 |
|
| 54 |
+
| 1.3653 | 1.01 | 1200 | 1.4956 |
|
| 55 |
+
| 1.3222 | 1.18 | 1400 | 1.4968 |
|
| 56 |
+
| 1.3362 | 1.34 | 1600 | 1.4855 |
|
| 57 |
+
| 1.3557 | 1.51 | 1800 | 1.3809 |
|
| 58 |
+
| 1.3207 | 1.68 | 2000 | 1.3806 |
|
| 59 |
+
| 1.348 | 1.85 | 2200 | 1.3718 |
|
| 60 |
+
| 1.3215 | 2.02 | 2400 | 1.3677 |
|
| 61 |
+
| 1.3299 | 2.18 | 2600 | 1.3793 |
|
| 62 |
+
| 1.335 | 2.35 | 2800 | 1.3662 |
|
| 63 |
+
| 1.3033 | 2.52 | 3000 | 1.3628 |
|
| 64 |
+
| 1.3377 | 2.69 | 3200 | 1.3525 |
|
| 65 |
+
| 1.3001 | 2.85 | 3400 | 1.3521 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.37.2
|
| 71 |
+
- Pytorch 2.1.0+cu121
|
| 72 |
+
- Datasets 2.17.0
|
| 73 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 470378972
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3468d370106eab4033a0e2b1a9c89b6483a2844a3a93d3019d73feca6b126f3
|
| 3 |
size 470378972
|
runs/Feb16_20-00-21_e0a0a9c18c9c/events.out.tfevents.1708113635.e0a0a9c18c9c.5560.4
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 sha256:8853c9d1f59ef3a2ba8255e659206029c4578413bff2e0fe15aee53cfae7cb37
|
| 3 |
+
size 147130
|