Hugging Face's logo

BilelDJ
/
clip-hugging-face-finetuned

Zero-Shot Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
BilelDJ commited on
Commit
2da4fb2
•
1 Parent(s): 69261d5

Model save

Browse files
Files changed (8) hide show
  1. README.md +86 -0
  2. config.json +22 -0
  3. model.safetensors +3 -0
  4. runs/May03_14-54-56_b0efebecdfbe/events.out.tfevents.1714748379.b0efebecdfbe.13810.0 +3 -0
  5. runs/May05_10-59-00_bce9b1f2db30/events.out.tfevents.1714906748.bce9b1f2db30.15685.0 +3 -0
  6. runs/May05_11-43-19_bce9b1f2db30/events.out.tfevents.1714909427.bce9b1f2db30.26238.0 +3 -0
  7. runs/May05_15-00-00_cbb6f6ab0fba/events.out.tfevents.1714921955.cbb6f6ab0fba.18514.0 +3 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: clip-hugging-face-finetuned
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # clip-hugging-face-finetuned
13
+
14
+ This model was trained from scratch on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 1.4228
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 64
37
+ - eval_batch_size: 64
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 2.0
42
+
43
+ ### Training results
44
+
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:------:|:----:|:---------------:|
47
+ | 1.8261 | 0.0625 | 1 | 1.7808 |
48
+ | 1.7935 | 0.125 | 2 | 1.6237 |
49
+ | 2.2498 | 0.1875 | 3 | 1.7418 |
50
+ | 1.9536 | 0.25 | 4 | 1.7778 |
51
+ | 2.1207 | 0.3125 | 5 | 1.7882 |
52
+ | 2.1623 | 0.375 | 6 | 1.8578 |
53
+ | 2.0764 | 0.4375 | 7 | 1.8868 |
54
+ | 2.206 | 0.5 | 8 | 1.8571 |
55
+ | 2.2791 | 0.5625 | 9 | 1.8134 |
56
+ | 2.2276 | 0.625 | 10 | 1.7591 |
57
+ | 1.826 | 0.6875 | 11 | 1.6688 |
58
+ | 1.668 | 0.75 | 12 | 1.5710 |
59
+ | 1.8039 | 0.8125 | 13 | 1.5271 |
60
+ | 1.7761 | 0.875 | 14 | 1.4974 |
61
+ | 1.5512 | 0.9375 | 15 | 1.4799 |
62
+ | 1.0115 | 1.0 | 16 | 1.4686 |
63
+ | 0.4346 | 1.0625 | 17 | 1.4616 |
64
+ | 0.3421 | 1.125 | 18 | 1.4560 |
65
+ | 0.3134 | 1.1875 | 19 | 1.4582 |
66
+ | 0.2237 | 1.25 | 20 | 1.4679 |
67
+ | 0.6518 | 1.3125 | 21 | 1.4689 |
68
+ | 0.3559 | 1.375 | 22 | 1.4730 |
69
+ | 0.38 | 1.4375 | 23 | 1.4652 |
70
+ | 0.3887 | 1.5 | 24 | 1.4595 |
71
+ | 0.3202 | 1.5625 | 25 | 1.4468 |
72
+ | 0.2525 | 1.625 | 26 | 1.4385 |
73
+ | 0.5361 | 1.6875 | 27 | 1.4364 |
74
+ | 0.3427 | 1.75 | 28 | 1.4358 |
75
+ | 0.2529 | 1.8125 | 29 | 1.4346 |
76
+ | 0.1857 | 1.875 | 30 | 1.4301 |
77
+ | 0.3143 | 1.9375 | 31 | 1.4248 |
78
+ | 0.1912 | 2.0 | 32 | 1.4228 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.41.0.dev0
84
+ - Pytorch 2.2.1+cu121
85
+ - Datasets 2.19.0
86
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./clip-hugging-face",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "bos_token_id": 0,
12
+ "dropout": 0.0,
13
+ "eos_token_id": 2,
14
+ "model_type": "clip_text_model"
15
+ },
16
+ "torch_dtype": "float32",
17
+ "transformers_version": "4.41.0.dev0",
18
+ "vision_config": {
19
+ "dropout": 0.0,
20
+ "model_type": "clip_vision_model"
21
+ }
22
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82f71df529267e56eae33893a4d28d91c05cb65f7db17341d7e5c46aaccf8a8
3
+ size 605156676
runs/May03_14-54-56_b0efebecdfbe/events.out.tfevents.1714748379.b0efebecdfbe.13810.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3389b6088a6e882773c57edd1a8182f3e2efd1255629ae3a8565b9a1d07e73
3
+ size 4651
runs/May05_10-59-00_bce9b1f2db30/events.out.tfevents.1714906748.bce9b1f2db30.15685.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558f43e4400011771c8be47640bdae83c3b3581c93a3a169b576983eee000045
3
+ size 12693
runs/May05_11-43-19_bce9b1f2db30/events.out.tfevents.1714909427.bce9b1f2db30.26238.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511992c822519597c32baf78bf4c0af71beec87c9778d5c3eadb87b711ad317c
3
+ size 5598
runs/May05_15-00-00_cbb6f6ab0fba/events.out.tfevents.1714921955.cbb6f6ab0fba.18514.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e7591120ff966952fc2c74918a05ec9e67525aff4e13f2c1fcd306bba6afff
3
+ size 20136
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cdc313bc8d04a7aaa7efc5108f96b618a37334d1e657b460d96e257b9dccbe
3
+ size 5112