End of training
Browse files
README.md
CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
-
- Wer Score:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -36,33 +36,24 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 5e-05
|
39 |
-
- train_batch_size:
|
40 |
-
- eval_batch_size:
|
41 |
- seed: 42
|
42 |
- gradient_accumulation_steps: 2
|
43 |
-
- total_train_batch_size:
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
52 |
|:-------------:|:-------:|:----:|:---------------:|:---------:|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.0108 | 18.5185 | 250 | 0.0486 | 0.5161 |
|
58 |
-
| 0.009 | 22.2222 | 300 | 0.0488 | 0.4516 |
|
59 |
-
| 0.0066 | 25.9259 | 350 | 0.0522 | 0.7419 |
|
60 |
-
| 0.0054 | 29.6296 | 400 | 0.0538 | 0.4032 |
|
61 |
-
| 0.0033 | 33.3333 | 450 | 0.0575 | 5.8548 |
|
62 |
-
| 0.0018 | 37.0370 | 500 | 0.0604 | 4.9839 |
|
63 |
-
| 0.0009 | 40.7407 | 550 | 0.0625 | 6.2097 |
|
64 |
-
| 0.0008 | 44.4444 | 600 | 0.0629 | 6.3226 |
|
65 |
-
| 0.0007 | 48.1481 | 650 | 0.0629 | 6.3548 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0481
|
19 |
+
- Wer Score: 3.1327
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
- gradient_accumulation_steps: 2
|
43 |
+
- total_train_batch_size: 16
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 15
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
52 |
|:-------------:|:-------:|:----:|:---------------:|:---------:|
|
53 |
+
| 0.0029 | 3.5714 | 50 | 0.0447 | 3.9381 |
|
54 |
+
| 0.0007 | 7.1429 | 100 | 0.0473 | 3.3097 |
|
55 |
+
| 0.0002 | 10.7143 | 150 | 0.0476 | 4.3274 |
|
56 |
+
| 0.0001 | 14.2857 | 200 | 0.0481 | 3.1327 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
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:cbb81a8b8ea7afa83b07b15ab843e553d9dd2cf7a3058b51872981e71f884052
|
3 |
size 706516040
|
runs/May30_15-00-33_tzuchichen/events.out.tfevents.1717052478.tzuchichen.47.2
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 sha256:9c521da382e296003f0ceca3e16f7993c6ed13e3b43211a226447749d2545f09
|
3 |
+
size 7362
|