sharmajai901
commited on
Commit
•
6344eb9
1
Parent(s):
cf59924
End of training
Browse files- README.md +84 -0
- all_results.json +13 -0
- config.json +66 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Jun19_09-03-53_da3e1e4916a6/events.out.tfevents.1718787852.da3e1e4916a6.1298.0 +3 -0
- runs/Jun19_09-03-53_da3e1e4916a6/events.out.tfevents.1718788926.da3e1e4916a6.1298.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +168 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: UL_interior_classification
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: validation
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.5875912408759124
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# UL_interior_classification
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.2517
|
36 |
+
- Accuracy: 0.5876
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 128
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 7
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
70 |
+
| 2.7547 | 0.9811 | 13 | 2.3422 | 0.3285 |
|
71 |
+
| 1.7119 | 1.9623 | 26 | 1.8850 | 0.4964 |
|
72 |
+
| 1.249 | 2.9434 | 39 | 1.5653 | 0.5292 |
|
73 |
+
| 0.8838 | 4.0 | 53 | 1.3675 | 0.5693 |
|
74 |
+
| 0.8896 | 4.9811 | 66 | 1.2907 | 0.5803 |
|
75 |
+
| 0.7262 | 5.9623 | 79 | 1.2625 | 0.5803 |
|
76 |
+
| 0.6817 | 6.8679 | 91 | 1.2517 | 0.5876 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.41.2
|
82 |
+
- Pytorch 2.3.0+cu121
|
83 |
+
- Datasets 2.20.0
|
84 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.867924528301887,
|
3 |
+
"eval_accuracy": 0.5875912408759124,
|
4 |
+
"eval_loss": 1.251747727394104,
|
5 |
+
"eval_runtime": 9.2712,
|
6 |
+
"eval_samples_per_second": 29.554,
|
7 |
+
"eval_steps_per_second": 0.971,
|
8 |
+
"total_flos": 8.883485181176095e+17,
|
9 |
+
"train_loss": 1.1828759214380284,
|
10 |
+
"train_runtime": 1039.6912,
|
11 |
+
"train_samples_per_second": 11.21,
|
12 |
+
"train_steps_per_second": 0.088
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "bicycle_storage",
|
13 |
+
"1": "building_interiors",
|
14 |
+
"2": "cinema_room",
|
15 |
+
"3": "communal_lounge",
|
16 |
+
"4": "dining_area",
|
17 |
+
"5": "entertainment_area",
|
18 |
+
"6": "fitness_room",
|
19 |
+
"7": "games_area",
|
20 |
+
"8": "gym",
|
21 |
+
"9": "laundry_area",
|
22 |
+
"10": "living_area",
|
23 |
+
"11": "living_area_shared_kitchen",
|
24 |
+
"12": "meeting_room",
|
25 |
+
"13": "parking",
|
26 |
+
"14": "reception",
|
27 |
+
"15": "rooftoop_area",
|
28 |
+
"16": "storage_lockers",
|
29 |
+
"17": "study_area",
|
30 |
+
"18": "swimming_pool"
|
31 |
+
},
|
32 |
+
"image_size": 224,
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"bicycle_storage": 0,
|
37 |
+
"building_interiors": 1,
|
38 |
+
"cinema_room": 2,
|
39 |
+
"communal_lounge": 3,
|
40 |
+
"dining_area": 4,
|
41 |
+
"entertainment_area": 5,
|
42 |
+
"fitness_room": 6,
|
43 |
+
"games_area": 7,
|
44 |
+
"gym": 8,
|
45 |
+
"laundry_area": 9,
|
46 |
+
"living_area": 10,
|
47 |
+
"living_area_shared_kitchen": 11,
|
48 |
+
"meeting_room": 12,
|
49 |
+
"parking": 13,
|
50 |
+
"reception": 14,
|
51 |
+
"rooftoop_area": 15,
|
52 |
+
"storage_lockers": 16,
|
53 |
+
"study_area": 17,
|
54 |
+
"swimming_pool": 18
|
55 |
+
},
|
56 |
+
"layer_norm_eps": 1e-12,
|
57 |
+
"model_type": "vit",
|
58 |
+
"num_attention_heads": 12,
|
59 |
+
"num_channels": 3,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"patch_size": 16,
|
62 |
+
"problem_type": "single_label_classification",
|
63 |
+
"qkv_bias": true,
|
64 |
+
"torch_dtype": "float32",
|
65 |
+
"transformers_version": "4.41.2"
|
66 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.867924528301887,
|
3 |
+
"eval_accuracy": 0.5875912408759124,
|
4 |
+
"eval_loss": 1.251747727394104,
|
5 |
+
"eval_runtime": 9.2712,
|
6 |
+
"eval_samples_per_second": 29.554,
|
7 |
+
"eval_steps_per_second": 0.971
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd6e204db9bd4ee26a44b11d1eb41a56c623af69fc5f24ad264339bde53bdf57
|
3 |
+
size 343276268
|
preprocessor_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTImageProcessor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"resample": 2,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
runs/Jun19_09-03-53_da3e1e4916a6/events.out.tfevents.1718787852.da3e1e4916a6.1298.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7738d4e3dde246d79ee7327081081094cedb7e0d10196f53ef18b412d235d353
|
3 |
+
size 10158
|
runs/Jun19_09-03-53_da3e1e4916a6/events.out.tfevents.1718788926.da3e1e4916a6.1298.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cea746f214435987ba37674ead2bf644e4bc2760c963ff82f977fd5cdde46b3e
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.867924528301887,
|
3 |
+
"total_flos": 8.883485181176095e+17,
|
4 |
+
"train_loss": 1.1828759214380284,
|
5 |
+
"train_runtime": 1039.6912,
|
6 |
+
"train_samples_per_second": 11.21,
|
7 |
+
"train_steps_per_second": 0.088
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5875912408759124,
|
3 |
+
"best_model_checkpoint": "UL_interior_classification/checkpoint-91",
|
4 |
+
"epoch": 6.867924528301887,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 91,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.7547169811320755,
|
13 |
+
"grad_norm": 4.003274440765381,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 2.7547,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9811320754716981,
|
20 |
+
"eval_accuracy": 0.3284671532846715,
|
21 |
+
"eval_loss": 2.342195510864258,
|
22 |
+
"eval_runtime": 10.3898,
|
23 |
+
"eval_samples_per_second": 26.372,
|
24 |
+
"eval_steps_per_second": 0.866,
|
25 |
+
"step": 13
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.509433962264151,
|
29 |
+
"grad_norm": 2.726027011871338,
|
30 |
+
"learning_rate": 4.3827160493827164e-05,
|
31 |
+
"loss": 1.7119,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.9622641509433962,
|
36 |
+
"eval_accuracy": 0.49635036496350365,
|
37 |
+
"eval_loss": 1.8849732875823975,
|
38 |
+
"eval_runtime": 9.8675,
|
39 |
+
"eval_samples_per_second": 27.768,
|
40 |
+
"eval_steps_per_second": 0.912,
|
41 |
+
"step": 26
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.2641509433962264,
|
45 |
+
"grad_norm": 2.424898624420166,
|
46 |
+
"learning_rate": 3.7654320987654326e-05,
|
47 |
+
"loss": 1.249,
|
48 |
+
"step": 30
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.9433962264150946,
|
52 |
+
"eval_accuracy": 0.5291970802919708,
|
53 |
+
"eval_loss": 1.5653367042541504,
|
54 |
+
"eval_runtime": 10.0672,
|
55 |
+
"eval_samples_per_second": 27.217,
|
56 |
+
"eval_steps_per_second": 0.894,
|
57 |
+
"step": 39
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.018867924528302,
|
61 |
+
"grad_norm": 6.8397016525268555,
|
62 |
+
"learning_rate": 3.148148148148148e-05,
|
63 |
+
"loss": 1.0982,
|
64 |
+
"step": 40
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.7735849056603774,
|
68 |
+
"grad_norm": 2.1824584007263184,
|
69 |
+
"learning_rate": 2.5308641975308646e-05,
|
70 |
+
"loss": 0.8838,
|
71 |
+
"step": 50
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.5693430656934306,
|
76 |
+
"eval_loss": 1.36745285987854,
|
77 |
+
"eval_runtime": 10.0511,
|
78 |
+
"eval_samples_per_second": 27.261,
|
79 |
+
"eval_steps_per_second": 0.895,
|
80 |
+
"step": 53
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.528301886792453,
|
84 |
+
"grad_norm": 1.9526816606521606,
|
85 |
+
"learning_rate": 1.91358024691358e-05,
|
86 |
+
"loss": 0.8896,
|
87 |
+
"step": 60
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.981132075471698,
|
91 |
+
"eval_accuracy": 0.5802919708029197,
|
92 |
+
"eval_loss": 1.2906520366668701,
|
93 |
+
"eval_runtime": 11.107,
|
94 |
+
"eval_samples_per_second": 24.669,
|
95 |
+
"eval_steps_per_second": 0.81,
|
96 |
+
"step": 66
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 5.283018867924528,
|
100 |
+
"grad_norm": 2.0880227088928223,
|
101 |
+
"learning_rate": 1.2962962962962962e-05,
|
102 |
+
"loss": 0.7262,
|
103 |
+
"step": 70
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.962264150943396,
|
107 |
+
"eval_accuracy": 0.5802919708029197,
|
108 |
+
"eval_loss": 1.2625008821487427,
|
109 |
+
"eval_runtime": 10.0312,
|
110 |
+
"eval_samples_per_second": 27.315,
|
111 |
+
"eval_steps_per_second": 0.897,
|
112 |
+
"step": 79
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 6.037735849056604,
|
116 |
+
"grad_norm": 1.8009761571884155,
|
117 |
+
"learning_rate": 6.790123456790123e-06,
|
118 |
+
"loss": 0.7061,
|
119 |
+
"step": 80
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 6.7924528301886795,
|
123 |
+
"grad_norm": 1.9284666776657104,
|
124 |
+
"learning_rate": 6.17283950617284e-07,
|
125 |
+
"loss": 0.6817,
|
126 |
+
"step": 90
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.867924528301887,
|
130 |
+
"eval_accuracy": 0.5875912408759124,
|
131 |
+
"eval_loss": 1.251747727394104,
|
132 |
+
"eval_runtime": 9.9685,
|
133 |
+
"eval_samples_per_second": 27.487,
|
134 |
+
"eval_steps_per_second": 0.903,
|
135 |
+
"step": 91
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 6.867924528301887,
|
139 |
+
"step": 91,
|
140 |
+
"total_flos": 8.883485181176095e+17,
|
141 |
+
"train_loss": 1.1828759214380284,
|
142 |
+
"train_runtime": 1039.6912,
|
143 |
+
"train_samples_per_second": 11.21,
|
144 |
+
"train_steps_per_second": 0.088
|
145 |
+
}
|
146 |
+
],
|
147 |
+
"logging_steps": 10,
|
148 |
+
"max_steps": 91,
|
149 |
+
"num_input_tokens_seen": 0,
|
150 |
+
"num_train_epochs": 7,
|
151 |
+
"save_steps": 500,
|
152 |
+
"stateful_callbacks": {
|
153 |
+
"TrainerControl": {
|
154 |
+
"args": {
|
155 |
+
"should_epoch_stop": false,
|
156 |
+
"should_evaluate": false,
|
157 |
+
"should_log": false,
|
158 |
+
"should_save": true,
|
159 |
+
"should_training_stop": true
|
160 |
+
},
|
161 |
+
"attributes": {}
|
162 |
+
}
|
163 |
+
},
|
164 |
+
"total_flos": 8.883485181176095e+17,
|
165 |
+
"train_batch_size": 32,
|
166 |
+
"trial_name": null,
|
167 |
+
"trial_params": null
|
168 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:880333b1a69b402d8beafef381b29aaf91e09aa210d1c606c46c42e975415c6c
|
3 |
+
size 5112
|