End of training
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: microsoft/git-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- imagefolder
|
9 |
+
model-index:
|
10 |
+
- name: git-base-one-entrance-dungeons
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# git-base-one-entrance-dungeons
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 9.6427
|
22 |
+
- Wer Score: 102.0
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 1
|
43 |
+
- eval_batch_size: 1
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 4
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 10
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
56 |
+
|:-------------:|:------:|:----:|:---------------:|:---------:|
|
57 |
+
| 21.0207 | 0.5714 | 1 | 12.1435 | 110.0 |
|
58 |
+
| 9.5856 | 1.7143 | 3 | 10.3902 | 92.4 |
|
59 |
+
| 8.923 | 2.8571 | 5 | 9.9725 | 85.2 |
|
60 |
+
| 8.7018 | 4.0 | 7 | 9.7762 | 97.2 |
|
61 |
+
| 17.1397 | 4.5714 | 8 | 9.7107 | 102.4 |
|
62 |
+
| 6.0772 | 5.7143 | 10 | 9.6427 | 102.0 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.44.2
|
68 |
+
- Pytorch 2.4.1+cu121
|
69 |
+
- Datasets 3.0.1
|
70 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 101,
|
4 |
+
"eos_token_id": 102,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.44.2"
|
7 |
+
}
|
runs/Oct20_12-16-19_b6a20160002a/events.out.tfevents.1729426587.b6a20160002a.1681.0
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:b866cdea200226307e405237aab68329624277e79fb7774a9353970fa2b2f3ba
|
3 |
+
size 8685
|