Hugging Face's logo

christti
/
clip-vit-bert-coco

Feature Extraction
Transformers
Safetensors
vision-text-dual-encoder
Generated from Trainer
Inference Endpoints
Model card Files Community
christti commited on
Commit
465fbee
•
1 Parent(s): e81f6c4

End of training

Browse files
Files changed (5) hide show
  1. README.md +12 -9
  2. all_results.json +4 -4
  3. eval_results.json +4 -4
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -2,7 +2,7 @@
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
- - coco_dataset_script
6
  model-index:
7
  - name: clip-vit-bert-coco
8
  results: []
@@ -13,7 +13,13 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # clip-vit-bert-coco
15
 
16
- This model was trained from scratch on the coco_dataset_script dataset.
 
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -33,16 +39,13 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 5e-05
36
- - train_batch_size: 32
37
- - eval_batch_size: 32
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
- - num_epochs: 3.0
42
-
43
- ### Training results
44
-
45
-
46
 
47
  ### Framework versions
48
 
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
+ - ydshieh/coco_dataset_script
6
  model-index:
7
  - name: clip-vit-bert-coco
8
  results: []
 
13
 
14
  # clip-vit-bert-coco
15
 
16
+ This model was trained from scratch on the ydshieh/coco_dataset_script 2017 dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - eval_loss: 4.2294
19
+ - eval_runtime: 287.7769
20
+ - eval_samples_per_second: 86.921
21
+ - eval_steps_per_second: 0.681
22
+ - step: 0
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
+ - train_batch_size: 128
43
+ - eval_batch_size: 128
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 5.0
48
+ - mixed_precision_training: Native AMP
 
 
 
49
 
50
  ### Framework versions
51
 
all_results.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "eval_loss": 2.8376755714416504,
3
- "eval_runtime": 404.3846,
4
- "eval_samples_per_second": 61.857,
5
- "eval_steps_per_second": 1.934
6
  }
 
1
  {
2
+ "eval_loss": 4.22942590713501,
3
+ "eval_runtime": 287.7769,
4
+ "eval_samples_per_second": 86.921,
5
+ "eval_steps_per_second": 0.681
6
  }
eval_results.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "eval_loss": 2.8376755714416504,
3
- "eval_runtime": 404.3846,
4
- "eval_samples_per_second": 61.857,
5
- "eval_steps_per_second": 1.934
6
  }
 
1
  {
2
+ "eval_loss": 4.22942590713501,
3
+ "eval_runtime": 287.7769,
4
+ "eval_samples_per_second": 86.921,
5
+ "eval_steps_per_second": 0.681
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3d384c956fdd440083a25175b17078a0243d22c080cd02365efe8a6d52cb059
3
  size 1654396092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4ddee26433dc093b909903557586590c975840309b0214169fd912ececcddc
3
  size 1654396092
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a96d6f4e527bea82b61f75f9e6cecdb28abdb3bfdc5fdaabfe6bfffe63aaf9f
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa6dd54b1bc8167c68f8418c863e4ffd44565c8aa2258c5df62a5a4f0bacf481
3
  size 4856