Hugging Face's logo

Ashkchamp
/
blip-finetuned-kag100

Image-Text-to-Text
Transformers
Safetensors
blip
Generated from Trainer
Inference Endpoints
Model card Files Community
Ashkchamp commited on
Commit
d791ad4
·
verified ·
1 Parent(s): cab5988

Ashkchamp/Pokemon-Image-Captioning

Browse files
Files changed (3) hide show
  1. README.md +12 -8
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.7570
20
 
21
  ## Model description
22
 
@@ -35,11 +35,11 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 3e-06
39
- - train_batch_size: 8
40
- - eval_batch_size: 8
41
  - seed: 42
42
- - gradient_accumulation_steps: 2
43
  - total_train_batch_size: 16
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
@@ -51,9 +51,13 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | No log | 2.1277 | 100 | 0.8710 |
55
- | No log | 4.2553 | 200 | 0.7686 |
56
- | No log | 6.3830 | 300 | 0.7570 |
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7098
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 2e-06
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
  - seed: 42
42
+ - gradient_accumulation_steps: 8
43
  - total_train_batch_size: 16
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.3371 | 1.1130 | 50 | 1.0989 |
55
+ | 0.9289 | 2.2260 | 100 | 0.8548 |
56
+ | 0.7662 | 3.3390 | 150 | 0.8150 |
57
+ | 0.677 | 4.4520 | 200 | 0.7596 |
58
+ | 0.6306 | 5.5650 | 250 | 0.7650 |
59
+ | 0.61 | 6.6780 | 300 | 0.7456 |
60
+ | 0.5978 | 7.7910 | 350 | 0.7098 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5f1303175bff20588318a29349ff3c4cddee46d3b10593302ec2dbee566e1dc
3
  size 989717056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc68880c85c895a02953574489fd546430f7ef655a60d15a35604a6e8d5f14ba
3
  size 989717056
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4139f1f28e64b59df96ede484c116447fef86749be869e6caab59f4fa92520af
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1112357f696fc8205962d0b760cd0f98dabebe4188e1cf3c266ba71c35e27c7a
3
  size 5304