lenashamseldin
commited on
Commit
•
c659b21
1
Parent(s):
7c739c4
End of training
Browse files- README.md +129 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/git-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: git-base-floors615images
|
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 |
+
# git-base-floors615images
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0139
|
19 |
+
- Wer Score: 0.5837
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 4
|
40 |
+
- eval_batch_size: 4
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 2
|
43 |
+
- total_train_batch_size: 8
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 50
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
53 |
+
| 6.955 | 0.72 | 50 | 4.0586 | 1.6636 |
|
54 |
+
| 1.911 | 1.44 | 100 | 0.2120 | 3.1636 |
|
55 |
+
| 0.0574 | 2.16 | 150 | 0.0130 | 4.5642 |
|
56 |
+
| 0.0118 | 2.88 | 200 | 0.0126 | 2.8213 |
|
57 |
+
| 0.0099 | 3.6 | 250 | 0.0095 | 2.2693 |
|
58 |
+
| 0.0082 | 4.32 | 300 | 0.0089 | 5.0186 |
|
59 |
+
| 0.0077 | 5.04 | 350 | 0.0088 | 5.3560 |
|
60 |
+
| 0.0068 | 5.76 | 400 | 0.0091 | 2.8026 |
|
61 |
+
| 0.0064 | 6.47 | 450 | 0.0082 | 3.4589 |
|
62 |
+
| 0.0063 | 7.19 | 500 | 0.0086 | 4.6660 |
|
63 |
+
| 0.006 | 7.91 | 550 | 0.0082 | 4.8546 |
|
64 |
+
| 0.0056 | 8.63 | 600 | 0.0085 | 3.1033 |
|
65 |
+
| 0.0062 | 9.35 | 650 | 0.0087 | 4.0475 |
|
66 |
+
| 0.0057 | 10.07 | 700 | 0.0086 | 5.4452 |
|
67 |
+
| 0.0054 | 10.79 | 750 | 0.0084 | 4.8614 |
|
68 |
+
| 0.0056 | 11.51 | 800 | 0.0084 | 5.4922 |
|
69 |
+
| 0.005 | 12.23 | 850 | 0.0084 | 5.4324 |
|
70 |
+
| 0.0054 | 12.95 | 900 | 0.0083 | 5.6768 |
|
71 |
+
| 0.0051 | 13.67 | 950 | 0.0086 | 5.1234 |
|
72 |
+
| 0.0052 | 14.39 | 1000 | 0.0091 | 6.0069 |
|
73 |
+
| 0.0053 | 15.11 | 1050 | 0.0085 | 5.0867 |
|
74 |
+
| 0.0049 | 15.83 | 1100 | 0.0092 | 5.4711 |
|
75 |
+
| 0.0051 | 16.55 | 1150 | 0.0087 | 5.7106 |
|
76 |
+
| 0.0048 | 17.27 | 1200 | 0.0086 | 4.0867 |
|
77 |
+
| 0.0047 | 17.99 | 1250 | 0.0087 | 5.0113 |
|
78 |
+
| 0.0048 | 18.71 | 1300 | 0.0088 | 5.9662 |
|
79 |
+
| 0.0046 | 19.42 | 1350 | 0.0091 | 4.5553 |
|
80 |
+
| 0.005 | 20.14 | 1400 | 0.0088 | 6.0235 |
|
81 |
+
| 0.0054 | 20.86 | 1450 | 0.0085 | 6.0230 |
|
82 |
+
| 0.005 | 21.58 | 1500 | 0.0088 | 6.0230 |
|
83 |
+
| 0.0052 | 22.3 | 1550 | 0.0084 | 6.0186 |
|
84 |
+
| 0.0049 | 23.02 | 1600 | 0.0093 | 3.9496 |
|
85 |
+
| 0.005 | 23.74 | 1650 | 0.0089 | 3.9275 |
|
86 |
+
| 0.0046 | 24.46 | 1700 | 0.0085 | 4.7311 |
|
87 |
+
| 0.0049 | 25.18 | 1750 | 0.0089 | 5.2463 |
|
88 |
+
| 0.0045 | 25.9 | 1800 | 0.0088 | 3.8296 |
|
89 |
+
| 0.0044 | 26.62 | 1850 | 0.0088 | 4.5010 |
|
90 |
+
| 0.0043 | 27.34 | 1900 | 0.0090 | 2.7282 |
|
91 |
+
| 0.0045 | 28.06 | 1950 | 0.0089 | 3.4383 |
|
92 |
+
| 0.0038 | 28.78 | 2000 | 0.0094 | 1.3452 |
|
93 |
+
| 0.0042 | 29.5 | 2050 | 0.0089 | 3.1126 |
|
94 |
+
| 0.0039 | 30.22 | 2100 | 0.0092 | 2.4177 |
|
95 |
+
| 0.0042 | 30.94 | 2150 | 0.0092 | 2.7204 |
|
96 |
+
| 0.0037 | 31.65 | 2200 | 0.0092 | 2.6229 |
|
97 |
+
| 0.0039 | 32.37 | 2250 | 0.0095 | 2.3673 |
|
98 |
+
| 0.0038 | 33.09 | 2300 | 0.0102 | 1.4265 |
|
99 |
+
| 0.0034 | 33.81 | 2350 | 0.0098 | 2.4819 |
|
100 |
+
| 0.0032 | 34.53 | 2400 | 0.0110 | 1.9114 |
|
101 |
+
| 0.0034 | 35.25 | 2450 | 0.0111 | 1.4285 |
|
102 |
+
| 0.0031 | 35.97 | 2500 | 0.0108 | 2.0573 |
|
103 |
+
| 0.0027 | 36.69 | 2550 | 0.0109 | 1.6538 |
|
104 |
+
| 0.0028 | 37.41 | 2600 | 0.0114 | 1.9789 |
|
105 |
+
| 0.0029 | 38.13 | 2650 | 0.0108 | 2.1675 |
|
106 |
+
| 0.0026 | 38.85 | 2700 | 0.0112 | 2.3497 |
|
107 |
+
| 0.0026 | 39.57 | 2750 | 0.0124 | 2.1665 |
|
108 |
+
| 0.0026 | 40.29 | 2800 | 0.0119 | 1.4652 |
|
109 |
+
| 0.0024 | 41.01 | 2850 | 0.0119 | 2.0720 |
|
110 |
+
| 0.0022 | 41.73 | 2900 | 0.0122 | 1.2238 |
|
111 |
+
| 0.0022 | 42.45 | 2950 | 0.0128 | 1.5343 |
|
112 |
+
| 0.0021 | 43.17 | 3000 | 0.0121 | 1.3310 |
|
113 |
+
| 0.0019 | 43.88 | 3050 | 0.0131 | 1.3859 |
|
114 |
+
| 0.0018 | 44.6 | 3100 | 0.0131 | 0.8487 |
|
115 |
+
| 0.0017 | 45.32 | 3150 | 0.0133 | 0.9540 |
|
116 |
+
| 0.0016 | 46.04 | 3200 | 0.0131 | 1.0446 |
|
117 |
+
| 0.0014 | 46.76 | 3250 | 0.0135 | 0.6459 |
|
118 |
+
| 0.0014 | 47.48 | 3300 | 0.0137 | 0.6562 |
|
119 |
+
| 0.0013 | 48.2 | 3350 | 0.0135 | 0.5901 |
|
120 |
+
| 0.0012 | 48.92 | 3400 | 0.0139 | 0.5857 |
|
121 |
+
| 0.0012 | 49.64 | 3450 | 0.0139 | 0.5837 |
|
122 |
+
|
123 |
+
|
124 |
+
### Framework versions
|
125 |
+
|
126 |
+
- Transformers 4.38.2
|
127 |
+
- Pytorch 2.0.1
|
128 |
+
- Datasets 2.18.0
|
129 |
+
- Tokenizers 0.15.2
|
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": "4.38.2"
|
7 |
+
}
|
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:dbe7852470006d6de6265a3fe17cd7b1a593c36419188baa551db4dbb1e6cc1f
|
3 |
size 706516040
|