Hugging Face's logo

YufeiWeng
/
donut-base-beans

Image Classification
Transformers
Safetensors
beit
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
YufeiWeng commited on
Commit
e676bfe
·
verified ·
1 Parent(s): 0478d52

Model save

Browse files
Files changed (9) hide show
  1. README.md +11 -12
  2. all_results.json +9 -9
  3. command.txt +2 -1
  4. config.json +0 -1
  5. eval_results.json +4 -4
  6. model.safetensors +1 -1
  7. train_results.json +5 -5
  8. trainer_state.json +0 -0
  9. training_args.bin +2 -2
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
- - image-classification
6
- - vision
7
  - generated_from_trainer
8
  metrics:
9
  - f1
@@ -19,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0422
23
  - F1: 0.9705
 
24
 
25
  ## Model description
26
 
@@ -40,8 +38,8 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 3e-05
43
- - train_batch_size: 64
44
- - eval_batch_size: 64
45
  - seed: 1337
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -49,13 +47,14 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | F1 |
53
- |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
- | 0.0659 | 1.0 | 3961 | 0.0543 | 0.9705 |
55
- | 0.08 | 2.0 | 7922 | 0.0514 | 0.9705 |
56
- | 0.0598 | 3.0 | 11883 | 0.0524 | 0.9705 |
57
- | 0.0627 | 4.0 | 15844 | 0.0422 | 0.9705 |
58
- | 0.0622 | 5.0 | 19805 | 0.0446 | 0.9705 |
 
59
 
60
 
61
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - f1
 
17
 
18
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
 
20
  - F1: 0.9705
21
+ - Loss: 0.0429
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 3e-05
41
+ - train_batch_size: 128
42
+ - eval_batch_size: 128
43
  - seed: 1337
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | F1 | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:------:|:---------------:|
52
+ | 0.0796 | 1.0 | 3367 | 0.4973 | 0.0687 |
53
+ | 0.0611 | 2.0 | 6734 | 0.4973 | 0.0585 |
54
+ | 0.0581 | 3.0 | 10101 | 0.4973 | 0.0591 |
55
+ | 0.059 | 4.0 | 13468 | 0.4973 | 0.0550 |
56
+ | 0.0563 | 5.0 | 16835 | 0.4973 | 0.0540 |
57
+ | 0.0532 | 5.0 | 19805 | 0.9705 | 0.0429 |
58
 
59
 
60
  ### Framework versions
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 5.0,
3
  "eval_f1": 0.9705180789481339,
4
- "eval_loss": 0.04224640876054764,
5
- "eval_runtime": 901.493,
6
- "eval_samples_per_second": 228.8,
7
- "eval_steps_per_second": 3.575,
8
- "total_flos": 9.820471825285631e+19,
9
- "train_loss": 0.06684475449172272,
10
- "train_runtime": 18247.0343,
11
- "train_samples_per_second": 69.452,
12
- "train_steps_per_second": 1.085
13
  }
 
1
  {
2
  "epoch": 5.0,
3
  "eval_f1": 0.9705180789481339,
4
+ "eval_loss": 0.04290741682052612,
5
+ "eval_runtime": 939.7613,
6
+ "eval_samples_per_second": 219.483,
7
+ "eval_steps_per_second": 3.43,
8
+ "total_flos": 9.82001462664467e+19,
9
+ "train_loss": 0.0,
10
+ "train_runtime": 0.0662,
11
+ "train_samples_per_second": 19152190.372,
12
+ "train_steps_per_second": 299304.924
13
  }
command.txt CHANGED
@@ -21,4 +21,5 @@ python run_image_classification_val_test.py \
21
  --seed 1337 \
22
  --ignore_mismatched_sizes \
23
  --image_column_name image_url \
24
- --label_column_name label
 
 
21
  --seed 1337 \
22
  --ignore_mismatched_sizes \
23
  --image_column_name image_url \
24
+ --label_column_name label \
25
+ --resume_from_checkpoint /trunk2/yufei/summer24/transformers/examples/pytorch/image-classification/test_default_model/checkpoint-19805
config.json CHANGED
@@ -24,7 +24,6 @@
24
  "num_channels": 3,
25
  "num_hidden_layers": 12,
26
  "patch_size": 16,
27
- "problem_type": "regression",
28
  "qkv_bias": true,
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.43.0.dev0"
 
24
  "num_channels": 3,
25
  "num_hidden_layers": 12,
26
  "patch_size": 16,
 
27
  "qkv_bias": true,
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.43.0.dev0"
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
  "eval_f1": 0.9705180789481339,
4
- "eval_loss": 0.04224640876054764,
5
- "eval_runtime": 901.493,
6
- "eval_samples_per_second": 228.8,
7
- "eval_steps_per_second": 3.575
8
  }
 
1
  {
2
  "epoch": 5.0,
3
  "eval_f1": 0.9705180789481339,
4
+ "eval_loss": 0.04290741682052612,
5
+ "eval_runtime": 939.7613,
6
+ "eval_samples_per_second": 219.483,
7
+ "eval_steps_per_second": 3.43
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:500f0f73dc500410ebd16406eccf35a281a045e2314d6dd422b4a81a518a6a62
3
  size 343220892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472717343c19fb122138fc3fa7339902c64523b4ea7aca0a6a002c718da0878b
3
  size 343220892
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
- "total_flos": 9.820471825285631e+19,
4
- "train_loss": 0.06684475449172272,
5
- "train_runtime": 18247.0343,
6
- "train_samples_per_second": 69.452,
7
- "train_steps_per_second": 1.085
8
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "total_flos": 9.82001462664467e+19,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.0662,
6
+ "train_samples_per_second": 19152190.372,
7
+ "train_steps_per_second": 299304.924
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a48398c5cadfa36edf6a4fd9d2e50dba7cdb9f00316dd4ba7f236ef7fc9f4eb
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfb25f00044de65eddbc5555b76d9d4de4b7dde1e87fa4f820434b1835a3763
3
+ size 5368