Hugging Face's logo

gokulsabari
/
paligemma-adapter-new

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
paligemma
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
gokulsabari commited on
Commit
7eb1b45
·
verified ·
1 Parent(s): 798b5d2

End of training

Browse files
Files changed (4) hide show
  1. README.md +110 -0
  2. generation_config.json +7 -0
  3. model-00001-of-00002.safetensors +1 -1
  4. runs/Sep10_16-50-50_gangaai-Precision-3660/events.out.tfevents.1725967252.gangaai-Precision-3660.976097.0 +2 -2
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: gemma
4
+ base_model: google/paligemma-3b-pt-224
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: paligemma-adapter-new
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # paligemma-adapter-new
16
+
17
+ This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.9112
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: 2e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
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
+ - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 50
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-------:|:-----:|:---------------:|
53
+ | 1.1672 | 0.9997 | 1682 | 1.1611 |
54
+ | 1.033 | 2.0 | 3365 | 1.0390 |
55
+ | 0.9638 | 2.9997 | 5047 | 0.9879 |
56
+ | 0.9611 | 4.0 | 6730 | 0.9610 |
57
+ | 0.9409 | 4.9997 | 8412 | 0.9443 |
58
+ | 0.9136 | 6.0 | 10095 | 0.9344 |
59
+ | 0.9081 | 6.9997 | 11777 | 0.9271 |
60
+ | 0.9128 | 8.0 | 13460 | 0.9226 |
61
+ | 0.8958 | 8.9997 | 15142 | 0.9195 |
62
+ | 0.91 | 10.0 | 16825 | 0.9177 |
63
+ | 0.9061 | 10.9997 | 18507 | 0.9157 |
64
+ | 0.9013 | 12.0 | 20190 | 0.9144 |
65
+ | 0.9005 | 12.9997 | 21872 | 0.9137 |
66
+ | 0.8874 | 14.0 | 23555 | 0.9130 |
67
+ | 0.9176 | 14.9997 | 25237 | 0.9127 |
68
+ | 0.8866 | 16.0 | 26920 | 0.9125 |
69
+ | 0.8978 | 16.9997 | 28602 | 0.9119 |
70
+ | 0.892 | 18.0 | 30285 | 0.9117 |
71
+ | 0.8945 | 18.9997 | 31967 | 0.9116 |
72
+ | 0.8908 | 20.0 | 33650 | 0.9115 |
73
+ | 0.8837 | 20.9997 | 35332 | 0.9115 |
74
+ | 0.8957 | 22.0 | 37015 | 0.9112 |
75
+ | 0.8887 | 22.9997 | 38697 | 0.9114 |
76
+ | 0.8962 | 24.0 | 40380 | 0.9114 |
77
+ | 0.899 | 24.9997 | 42062 | 0.9114 |
78
+ | 0.9024 | 26.0 | 43745 | 0.9112 |
79
+ | 0.8873 | 26.9997 | 45427 | 0.9112 |
80
+ | 0.9049 | 28.0 | 47110 | 0.9111 |
81
+ | 0.8953 | 28.9997 | 48792 | 0.9113 |
82
+ | 0.8929 | 30.0 | 50475 | 0.9112 |
83
+ | 0.9003 | 30.9997 | 52157 | 0.9111 |
84
+ | 0.8913 | 32.0 | 53840 | 0.9112 |
85
+ | 0.8934 | 32.9997 | 55522 | 0.9111 |
86
+ | 0.9022 | 34.0 | 57205 | 0.9112 |
87
+ | 0.8935 | 34.9997 | 58887 | 0.9112 |
88
+ | 0.8994 | 36.0 | 60570 | 0.9112 |
89
+ | 0.894 | 36.9997 | 62252 | 0.9112 |
90
+ | 0.8938 | 38.0 | 63935 | 0.9112 |
91
+ | 0.8985 | 38.9997 | 65617 | 0.9112 |
92
+ | 0.9013 | 40.0 | 67300 | 0.9111 |
93
+ | 0.9023 | 40.9997 | 68982 | 0.9111 |
94
+ | 0.9065 | 42.0 | 70665 | 0.9110 |
95
+ | 0.9045 | 42.9997 | 72347 | 0.9111 |
96
+ | 0.9013 | 44.0 | 74030 | 0.9112 |
97
+ | 0.8855 | 44.9997 | 75712 | 0.9112 |
98
+ | 0.8864 | 46.0 | 77395 | 0.9110 |
99
+ | 0.9026 | 46.9997 | 79077 | 0.9112 |
100
+ | 0.8979 | 48.0 | 80760 | 0.9111 |
101
+ | 0.9066 | 48.9997 | 82442 | 0.9111 |
102
+ | 0.896 | 49.9851 | 84100 | 0.9112 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.44.2
108
+ - Pytorch 2.4.0+cu118
109
+ - Datasets 2.20.0
110
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.2"
7
+ }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c33b9779c0a39e8b32f6a4a2386b43b6305f222ebb56f130a74e1f3e95c82fa
3
  size 4985044392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771ee7f0ecc4db0bcb667a62f3897367eb399516e4223266b2d527ba6cb3973c
3
  size 4985044392
runs/Sep10_16-50-50_gangaai-Precision-3660/events.out.tfevents.1725967252.gangaai-Precision-3660.976097.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e98d1f15691ca9ee69566ee0eb54641d745efb21afbd031f3021592f511e1aaf
3
- size 198914
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8aa15504c3a719375589b057fe6e63da53ec575744ac26da450c7bc614e709
3
+ size 199550