End of training
Browse files
README.md
CHANGED
@@ -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:
|
21 |
-
- Wer Score:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,11 +38,11 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
-
- train_batch_size:
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
44 |
- gradient_accumulation_steps: 2
|
45 |
-
- total_train_batch_size:
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- num_epochs: 20
|
@@ -51,8 +51,22 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
54 |
-
| No log |
|
55 |
-
| No log |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
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: 0.0157
|
21 |
+
- Wer Score: 3.4082
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 16
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- num_epochs: 20
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
54 |
+
| No log | 1.21 | 20 | 7.3815 | 194.2041 |
|
55 |
+
| No log | 2.42 | 40 | 5.4366 | 0.8878 |
|
56 |
+
| No log | 3.64 | 60 | 3.5512 | 0.7755 |
|
57 |
+
| No log | 4.85 | 80 | 1.8784 | 1.2551 |
|
58 |
+
| No log | 6.06 | 100 | 0.7146 | 21.0918 |
|
59 |
+
| No log | 7.27 | 120 | 0.2174 | 1.4184 |
|
60 |
+
| No log | 8.48 | 140 | 0.0743 | 12.8673 |
|
61 |
+
| No log | 9.7 | 160 | 0.0360 | 0.5510 |
|
62 |
+
| No log | 10.91 | 180 | 0.0265 | 0.4184 |
|
63 |
+
| No log | 12.12 | 200 | 0.0207 | 0.3878 |
|
64 |
+
| No log | 13.33 | 220 | 0.0185 | 0.5 |
|
65 |
+
| No log | 14.55 | 240 | 0.0174 | 4.3571 |
|
66 |
+
| No log | 15.76 | 260 | 0.0166 | 1.2653 |
|
67 |
+
| No log | 16.97 | 280 | 0.0158 | 4.0918 |
|
68 |
+
| No log | 18.18 | 300 | 0.0158 | 3.7959 |
|
69 |
+
| No log | 19.39 | 320 | 0.0157 | 3.4082 |
|
70 |
|
71 |
|
72 |
### Framework versions
|