fpalffldk
Browse files- README.md +62 -0
- all_results.json +13 -0
- config.json +34 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Jul08_06-47-09_eee4a5b69b15/events.out.tfevents.1720422785.eee4a5b69b15.2703.0 +3 -0
- runs/Jul08_06-47-09_eee4a5b69b15/events.out.tfevents.1720423009.eee4a5b69b15.2703.1 +3 -0
- test_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +242 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: vit-base-beans-demo-v5
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# vit-base-beans-demo-v5
|
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 |
+
- Loss: 0.1263
|
21 |
+
- Accuracy: 0.9688
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0002
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 4
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
53 |
+
| 0.0757 | 1.5385 | 100 | 0.0441 | 0.9925 |
|
54 |
+
| 0.0131 | 3.0769 | 200 | 0.1468 | 0.9624 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.41.2
|
60 |
+
- Pytorch 2.3.0+cu121
|
61 |
+
- Datasets 2.20.0
|
62 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.96875,
|
4 |
+
"eval_loss": 0.12631261348724365,
|
5 |
+
"eval_runtime": 2.932,
|
6 |
+
"eval_samples_per_second": 43.656,
|
7 |
+
"eval_steps_per_second": 5.457,
|
8 |
+
"total_flos": 3.205097416476426e+17,
|
9 |
+
"train_loss": 0.13155597568704533,
|
10 |
+
"train_runtime": 107.1574,
|
11 |
+
"train_samples_per_second": 38.597,
|
12 |
+
"train_steps_per_second": 2.426
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
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": "angular_leaf_spot",
|
13 |
+
"1": "bean_rust",
|
14 |
+
"2": "healthy"
|
15 |
+
},
|
16 |
+
"image_size": 224,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"angular_leaf_spot": "0",
|
21 |
+
"bean_rust": "1",
|
22 |
+
"healthy": "2"
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"model_type": "vit",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_channels": 3,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"patch_size": 16,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"qkv_bias": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.41.2"
|
34 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:572e9533ac40552bee1430a08f7d6b6373d541bf77a4fb52c85d7a05d7fec4fb
|
3 |
+
size 343227052
|
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": "ViTFeatureExtractor",
|
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/Jul08_06-47-09_eee4a5b69b15/events.out.tfevents.1720422785.eee4a5b69b15.2703.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39a135dbe83febcbf7b4eca7f7e57ccee656779ba3498141cbc36c0f625f14d1
|
3 |
+
size 11323
|
runs/Jul08_06-47-09_eee4a5b69b15/events.out.tfevents.1720423009.eee4a5b69b15.2703.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0646205450e01a8e5a7be30476fb89068f04d55ff96a19d9b37b8761705dd274
|
3 |
+
size 411
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.96875,
|
4 |
+
"eval_loss": 0.12631261348724365,
|
5 |
+
"eval_runtime": 2.932,
|
6 |
+
"eval_samples_per_second": 43.656,
|
7 |
+
"eval_steps_per_second": 5.457
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 3.205097416476426e+17,
|
4 |
+
"train_loss": 0.13155597568704533,
|
5 |
+
"train_runtime": 107.1574,
|
6 |
+
"train_samples_per_second": 38.597,
|
7 |
+
"train_steps_per_second": 2.426
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.044119928032159805,
|
3 |
+
"best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-100",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 260,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.15384615384615385,
|
13 |
+
"grad_norm": 2.110915422439575,
|
14 |
+
"learning_rate": 0.00019230769230769233,
|
15 |
+
"loss": 0.8903,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3076923076923077,
|
20 |
+
"grad_norm": 1.4865622520446777,
|
21 |
+
"learning_rate": 0.00018461538461538463,
|
22 |
+
"loss": 0.3935,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.46153846153846156,
|
27 |
+
"grad_norm": 0.5153194665908813,
|
28 |
+
"learning_rate": 0.00017692307692307693,
|
29 |
+
"loss": 0.197,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.6153846153846154,
|
34 |
+
"grad_norm": 3.097721815109253,
|
35 |
+
"learning_rate": 0.00016923076923076923,
|
36 |
+
"loss": 0.2258,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.7692307692307693,
|
41 |
+
"grad_norm": 4.940190315246582,
|
42 |
+
"learning_rate": 0.00016153846153846155,
|
43 |
+
"loss": 0.2628,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.9230769230769231,
|
48 |
+
"grad_norm": 0.6224154829978943,
|
49 |
+
"learning_rate": 0.00015384615384615385,
|
50 |
+
"loss": 0.2031,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0769230769230769,
|
55 |
+
"grad_norm": 1.554422378540039,
|
56 |
+
"learning_rate": 0.00014615384615384615,
|
57 |
+
"loss": 0.248,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.2307692307692308,
|
62 |
+
"grad_norm": 0.161035418510437,
|
63 |
+
"learning_rate": 0.00013846153846153847,
|
64 |
+
"loss": 0.1004,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.3846153846153846,
|
69 |
+
"grad_norm": 7.808058261871338,
|
70 |
+
"learning_rate": 0.00013076923076923077,
|
71 |
+
"loss": 0.0656,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.5384615384615383,
|
76 |
+
"grad_norm": 1.3628555536270142,
|
77 |
+
"learning_rate": 0.0001230769230769231,
|
78 |
+
"loss": 0.0757,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.5384615384615383,
|
83 |
+
"eval_accuracy": 0.9924812030075187,
|
84 |
+
"eval_loss": 0.044119928032159805,
|
85 |
+
"eval_runtime": 1.5577,
|
86 |
+
"eval_samples_per_second": 85.381,
|
87 |
+
"eval_steps_per_second": 10.913,
|
88 |
+
"step": 100
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.6923076923076923,
|
92 |
+
"grad_norm": 2.1813511848449707,
|
93 |
+
"learning_rate": 0.00011538461538461538,
|
94 |
+
"loss": 0.0681,
|
95 |
+
"step": 110
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.8461538461538463,
|
99 |
+
"grad_norm": 0.24909372627735138,
|
100 |
+
"learning_rate": 0.0001076923076923077,
|
101 |
+
"loss": 0.0947,
|
102 |
+
"step": 120
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 2.0,
|
106 |
+
"grad_norm": 0.14786876738071442,
|
107 |
+
"learning_rate": 0.0001,
|
108 |
+
"loss": 0.1183,
|
109 |
+
"step": 130
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 2.1538461538461537,
|
113 |
+
"grad_norm": 0.26466748118400574,
|
114 |
+
"learning_rate": 9.230769230769232e-05,
|
115 |
+
"loss": 0.1728,
|
116 |
+
"step": 140
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.3076923076923075,
|
120 |
+
"grad_norm": 0.2627667784690857,
|
121 |
+
"learning_rate": 8.461538461538461e-05,
|
122 |
+
"loss": 0.063,
|
123 |
+
"step": 150
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.4615384615384617,
|
127 |
+
"grad_norm": 0.10506220906972885,
|
128 |
+
"learning_rate": 7.692307692307693e-05,
|
129 |
+
"loss": 0.0257,
|
130 |
+
"step": 160
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.6153846153846154,
|
134 |
+
"grad_norm": 2.347315549850464,
|
135 |
+
"learning_rate": 6.923076923076924e-05,
|
136 |
+
"loss": 0.0367,
|
137 |
+
"step": 170
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.769230769230769,
|
141 |
+
"grad_norm": 0.6472500562667847,
|
142 |
+
"learning_rate": 6.153846153846155e-05,
|
143 |
+
"loss": 0.0342,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 2.9230769230769234,
|
148 |
+
"grad_norm": 4.727846622467041,
|
149 |
+
"learning_rate": 5.384615384615385e-05,
|
150 |
+
"loss": 0.0425,
|
151 |
+
"step": 190
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 3.076923076923077,
|
155 |
+
"grad_norm": 0.06820247322320938,
|
156 |
+
"learning_rate": 4.615384615384616e-05,
|
157 |
+
"loss": 0.0131,
|
158 |
+
"step": 200
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 3.076923076923077,
|
162 |
+
"eval_accuracy": 0.9624060150375939,
|
163 |
+
"eval_loss": 0.14681094884872437,
|
164 |
+
"eval_runtime": 1.805,
|
165 |
+
"eval_samples_per_second": 73.685,
|
166 |
+
"eval_steps_per_second": 9.418,
|
167 |
+
"step": 200
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 3.230769230769231,
|
171 |
+
"grad_norm": 3.413127899169922,
|
172 |
+
"learning_rate": 3.846153846153846e-05,
|
173 |
+
"loss": 0.0233,
|
174 |
+
"step": 210
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 3.3846153846153846,
|
178 |
+
"grad_norm": 3.6428942680358887,
|
179 |
+
"learning_rate": 3.0769230769230774e-05,
|
180 |
+
"loss": 0.0145,
|
181 |
+
"step": 220
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 3.5384615384615383,
|
185 |
+
"grad_norm": 0.4084061086177826,
|
186 |
+
"learning_rate": 2.307692307692308e-05,
|
187 |
+
"loss": 0.012,
|
188 |
+
"step": 230
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 3.6923076923076925,
|
192 |
+
"grad_norm": 0.06784854084253311,
|
193 |
+
"learning_rate": 1.5384615384615387e-05,
|
194 |
+
"loss": 0.0114,
|
195 |
+
"step": 240
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 3.8461538461538463,
|
199 |
+
"grad_norm": 0.05810296908020973,
|
200 |
+
"learning_rate": 7.692307692307694e-06,
|
201 |
+
"loss": 0.017,
|
202 |
+
"step": 250
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 4.0,
|
206 |
+
"grad_norm": 0.057864416390657425,
|
207 |
+
"learning_rate": 0.0,
|
208 |
+
"loss": 0.011,
|
209 |
+
"step": 260
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 4.0,
|
213 |
+
"step": 260,
|
214 |
+
"total_flos": 3.205097416476426e+17,
|
215 |
+
"train_loss": 0.13155597568704533,
|
216 |
+
"train_runtime": 107.1574,
|
217 |
+
"train_samples_per_second": 38.597,
|
218 |
+
"train_steps_per_second": 2.426
|
219 |
+
}
|
220 |
+
],
|
221 |
+
"logging_steps": 10,
|
222 |
+
"max_steps": 260,
|
223 |
+
"num_input_tokens_seen": 0,
|
224 |
+
"num_train_epochs": 4,
|
225 |
+
"save_steps": 100,
|
226 |
+
"stateful_callbacks": {
|
227 |
+
"TrainerControl": {
|
228 |
+
"args": {
|
229 |
+
"should_epoch_stop": false,
|
230 |
+
"should_evaluate": false,
|
231 |
+
"should_log": false,
|
232 |
+
"should_save": true,
|
233 |
+
"should_training_stop": false
|
234 |
+
},
|
235 |
+
"attributes": {}
|
236 |
+
}
|
237 |
+
},
|
238 |
+
"total_flos": 3.205097416476426e+17,
|
239 |
+
"train_batch_size": 16,
|
240 |
+
"trial_name": null,
|
241 |
+
"trial_params": null
|
242 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ae066d02309be1fbecc3b2f7a8e7f163dff96a7fb9a1dfa4a08cade16b4ccf7
|
3 |
+
size 5112
|