End of training
Browse files
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
base_model: microsoft/git-base
|
6 |
datasets:
|
7 |
- imagefolder
|
8 |
model-index:
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Wer Score:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -52,34 +52,34 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
54 |
|:-------------:|:------:|:----:|:---------------:|:---------:|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.41.2
|
83 |
- Pytorch 2.3.0+cu121
|
84 |
-
- Datasets 2.
|
85 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: microsoft/git-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
datasets:
|
7 |
- imagefolder
|
8 |
model-index:
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.3817
|
21 |
+
- Wer Score: 2.8621
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
54 |
|:-------------:|:------:|:----:|:---------------:|:---------:|
|
55 |
+
| 7.3416 | 0.4202 | 50 | 4.5198 | 4.7633 |
|
56 |
+
| 2.4704 | 0.8403 | 100 | 0.7015 | 0.8610 |
|
57 |
+
| 0.4735 | 1.2605 | 150 | 0.3923 | 0.8164 |
|
58 |
+
| 0.3669 | 1.6807 | 200 | 0.3762 | 0.8198 |
|
59 |
+
| 0.3075 | 2.1008 | 250 | 0.3680 | 0.8062 |
|
60 |
+
| 0.2837 | 2.5210 | 300 | 0.3683 | 0.8090 |
|
61 |
+
| 0.274 | 2.9412 | 350 | 0.3640 | 0.8401 |
|
62 |
+
| 0.2393 | 3.3613 | 400 | 0.3692 | 2.8282 |
|
63 |
+
| 0.2498 | 3.7815 | 450 | 0.3655 | 2.0712 |
|
64 |
+
| 0.2198 | 4.2017 | 500 | 0.3698 | 3.2164 |
|
65 |
+
| 0.2034 | 4.6218 | 550 | 0.3688 | 2.5853 |
|
66 |
+
| 0.1925 | 5.0420 | 600 | 0.3698 | 2.9119 |
|
67 |
+
| 0.1779 | 5.4622 | 650 | 0.3729 | 3.1333 |
|
68 |
+
| 0.1734 | 5.8824 | 700 | 0.3727 | 1.7605 |
|
69 |
+
| 0.1696 | 6.3025 | 750 | 0.3749 | 3.5226 |
|
70 |
+
| 0.15 | 6.7227 | 800 | 0.3773 | 2.8932 |
|
71 |
+
| 0.1595 | 7.1429 | 850 | 0.3762 | 2.7842 |
|
72 |
+
| 0.1507 | 7.5630 | 900 | 0.3803 | 1.0266 |
|
73 |
+
| 0.135 | 7.9832 | 950 | 0.3802 | 3.6090 |
|
74 |
+
| 0.1385 | 8.4034 | 1000 | 0.3801 | 3.3169 |
|
75 |
+
| 0.1311 | 8.8235 | 1050 | 0.3800 | 3.3966 |
|
76 |
+
| 0.1398 | 9.2437 | 1100 | 0.3815 | 2.1915 |
|
77 |
+
| 0.1293 | 9.6639 | 1150 | 0.3817 | 2.8621 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.41.2
|
83 |
- Pytorch 2.3.0+cu121
|
84 |
+
- Datasets 2.20.0
|
85 |
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 706516040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84a2e02076cd6806328c1db1b8994501985cd202a83d7450af01c11d330fe6a1
|
3 |
size 706516040
|
runs/Jun20_05-00-43_dab894bb234a/events.out.tfevents.1718859647.dab894bb234a.3323.0
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:c821cc782ff4392bcbb11ab78cb939ec8f87994877d5f70aa224c13acd5b25a9
|
3 |
+
size 17677
|