Hugging Face's logo

Spalne
/
vit-base-patch16-224-in21k

Image Classification
Transformers
TensorBoard
Safetensors
Habana
vit
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Spalne commited on
Commit
0e25941
•
1 Parent(s): bba3669

End of training

Browse files
Files changed (5) hide show
  1. README.md +4 -4
  2. all_results.json +4 -4
  3. eval_results.json +4 -4
  4. runs/Oct28_23-38-13_800671-5/events.out.tfevents.1730159051.800671-5.490.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the chainyo/rvl-cdip dataset.
20
  It achieves the following results on the evaluation set:
21
  - eval_loss: 2.7757
22
- - eval_model_preparation_time: 0.0146
23
  - eval_accuracy: 0.0567
24
- - eval_runtime: 353.4287
25
- - eval_samples_per_second: 135.812
26
- - eval_steps_per_second: 2.122
27
  - memory_allocated (GB): 0.79
28
  - max_memory_allocated (GB): 0.87
29
  - total_memory_available (GB): 94.62
 
19
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the chainyo/rvl-cdip dataset.
20
  It achieves the following results on the evaluation set:
21
  - eval_loss: 2.7757
22
+ - eval_model_preparation_time: 0.0143
23
  - eval_accuracy: 0.0567
24
+ - eval_runtime: 351.0327
25
+ - eval_samples_per_second: 136.739
26
+ - eval_steps_per_second: 2.137
27
  - memory_allocated (GB): 0.79
28
  - max_memory_allocated (GB): 0.87
29
  - total_memory_available (GB): 94.62
all_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "eval_accuracy": 0.056729166666666664,
3
  "eval_loss": 2.775696277618408,
4
- "eval_model_preparation_time": 0.0146,
5
- "eval_runtime": 353.4287,
6
- "eval_samples_per_second": 135.812,
7
- "eval_steps_per_second": 2.122,
8
  "max_memory_allocated (GB)": 0.87,
9
  "memory_allocated (GB)": 0.79,
10
  "total_memory_available (GB)": 94.62
 
1
  {
2
  "eval_accuracy": 0.056729166666666664,
3
  "eval_loss": 2.775696277618408,
4
+ "eval_model_preparation_time": 0.0143,
5
+ "eval_runtime": 351.0327,
6
+ "eval_samples_per_second": 136.739,
7
+ "eval_steps_per_second": 2.137,
8
  "max_memory_allocated (GB)": 0.87,
9
  "memory_allocated (GB)": 0.79,
10
  "total_memory_available (GB)": 94.62
eval_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "eval_accuracy": 0.056729166666666664,
3
  "eval_loss": 2.775696277618408,
4
- "eval_model_preparation_time": 0.0146,
5
- "eval_runtime": 353.4287,
6
- "eval_samples_per_second": 135.812,
7
- "eval_steps_per_second": 2.122,
8
  "max_memory_allocated (GB)": 0.87,
9
  "memory_allocated (GB)": 0.79,
10
  "total_memory_available (GB)": 94.62
 
1
  {
2
  "eval_accuracy": 0.056729166666666664,
3
  "eval_loss": 2.775696277618408,
4
+ "eval_model_preparation_time": 0.0143,
5
+ "eval_runtime": 351.0327,
6
+ "eval_samples_per_second": 136.739,
7
+ "eval_steps_per_second": 2.137,
8
  "max_memory_allocated (GB)": 0.87,
9
  "memory_allocated (GB)": 0.79,
10
  "total_memory_available (GB)": 94.62
runs/Oct28_23-38-13_800671-5/events.out.tfevents.1730159051.800671-5.490.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c711f4ff1cf4f42246b3a88d8dd057747e4e440ab282da96beeda844a95782c
3
+ size 560
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e49cc21d0f058e33b4fbc6d799a70bb4762616f306c373b3677965d4b36a53a
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfc323517bc9e38c55151bcf9cb85e3128324e70509429fc817e25b5ccc4624
3
  size 5048