Upload folder using huggingface_hub
Browse files- README.md +42 -0
- checkpoint-129/config.json +37 -0
- checkpoint-129/model.safetensors +3 -0
- checkpoint-129/optimizer.pt +3 -0
- checkpoint-129/rng_state.pth +3 -0
- checkpoint-129/scheduler.pt +3 -0
- checkpoint-129/trainer_state.json +523 -0
- checkpoint-129/training_args.bin +3 -0
- config.json +37 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- image-classification
|
6 |
+
widget:
|
7 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
8 |
+
example_title: Tiger
|
9 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
10 |
+
example_title: Teapot
|
11 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
12 |
+
example_title: Palace
|
13 |
+
datasets:
|
14 |
+
- autotrain-f8u3m-1w0uc/autotrain-data
|
15 |
+
---
|
16 |
+
|
17 |
+
# Model Trained Using AutoTrain
|
18 |
+
|
19 |
+
- Problem type: Image Classification
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
loss: 0.588494598865509
|
23 |
+
|
24 |
+
f1_macro: 0.726419878296146
|
25 |
+
|
26 |
+
f1_micro: 0.7674418604651162
|
27 |
+
|
28 |
+
f1_weighted: 0.7444926647483373
|
29 |
+
|
30 |
+
precision_macro: 0.8743946731234866
|
31 |
+
|
32 |
+
precision_micro: 0.7674418604651163
|
33 |
+
|
34 |
+
precision_weighted: 0.8185567881074384
|
35 |
+
|
36 |
+
recall_macro: 0.6858527131782945
|
37 |
+
|
38 |
+
recall_micro: 0.7674418604651163
|
39 |
+
|
40 |
+
recall_weighted: 0.7674418604651163
|
41 |
+
|
42 |
+
accuracy: 0.7674418604651163
|
checkpoint-129/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
3 |
+
"_num_labels": 4,
|
4 |
+
"architectures": [
|
5 |
+
"ViTForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"encoder_stride": 16,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "blank",
|
14 |
+
"1": "content",
|
15 |
+
"2": "end",
|
16 |
+
"3": "start"
|
17 |
+
},
|
18 |
+
"image_size": 224,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"blank": 0,
|
23 |
+
"content": 1,
|
24 |
+
"end": 2,
|
25 |
+
"start": 3
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"model_type": "vit",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_channels": 3,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"patch_size": 16,
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"qkv_bias": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.39.0"
|
37 |
+
}
|
checkpoint-129/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6cb39e4419595735109964dd5d06982ea0141bd516e365f0c77433ea018e7bd
|
3 |
+
size 343230128
|
checkpoint-129/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2704327f7419c9e23b68834ac0b1aa96c87863523a5e51b42692e0d558b8b98
|
3 |
+
size 686581178
|
checkpoint-129/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f950a96f725d7ae0e18d6a68104201ecfbd07a8263205d8efe7dfa7efc33c8d6
|
3 |
+
size 14244
|
checkpoint-129/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:050bd0dc3838d2e39d3b795937ac070c6d7390f04abec8a76bda56c415eb3a30
|
3 |
+
size 1064
|
checkpoint-129/trainer_state.json
ADDED
@@ -0,0 +1,523 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.588494598865509,
|
3 |
+
"best_model_checkpoint": "autotrain-f8u3m-1w0uc/checkpoint-129",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 129,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"grad_norm": 17.909360885620117,
|
14 |
+
"learning_rate": 3.846153846153847e-06,
|
15 |
+
"loss": 1.7009,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09,
|
20 |
+
"grad_norm": 13.120195388793945,
|
21 |
+
"learning_rate": 7.692307692307694e-06,
|
22 |
+
"loss": 1.4648,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.14,
|
27 |
+
"grad_norm": 14.559846878051758,
|
28 |
+
"learning_rate": 1.5384615384615387e-05,
|
29 |
+
"loss": 1.4937,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.19,
|
34 |
+
"grad_norm": 8.80319881439209,
|
35 |
+
"learning_rate": 2.307692307692308e-05,
|
36 |
+
"loss": 1.1978,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.23,
|
41 |
+
"grad_norm": 10.07514476776123,
|
42 |
+
"learning_rate": 3.0769230769230774e-05,
|
43 |
+
"loss": 1.2436,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.28,
|
48 |
+
"grad_norm": 5.79322624206543,
|
49 |
+
"learning_rate": 3.846153846153846e-05,
|
50 |
+
"loss": 0.8964,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.33,
|
55 |
+
"grad_norm": 15.918188095092773,
|
56 |
+
"learning_rate": 4.615384615384616e-05,
|
57 |
+
"loss": 1.5669,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.37,
|
62 |
+
"grad_norm": 8.671540260314941,
|
63 |
+
"learning_rate": 4.9568965517241384e-05,
|
64 |
+
"loss": 0.9671,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.42,
|
69 |
+
"grad_norm": 6.892113208770752,
|
70 |
+
"learning_rate": 4.870689655172414e-05,
|
71 |
+
"loss": 0.9687,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.47,
|
76 |
+
"grad_norm": 6.245675563812256,
|
77 |
+
"learning_rate": 4.78448275862069e-05,
|
78 |
+
"loss": 0.5675,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.51,
|
83 |
+
"grad_norm": 11.2545804977417,
|
84 |
+
"learning_rate": 4.698275862068966e-05,
|
85 |
+
"loss": 1.2117,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.56,
|
90 |
+
"grad_norm": 5.111425399780273,
|
91 |
+
"learning_rate": 4.612068965517242e-05,
|
92 |
+
"loss": 0.9048,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.6,
|
97 |
+
"grad_norm": 5.0768232345581055,
|
98 |
+
"learning_rate": 4.5258620689655176e-05,
|
99 |
+
"loss": 0.7902,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.65,
|
104 |
+
"grad_norm": 8.407731056213379,
|
105 |
+
"learning_rate": 4.4396551724137933e-05,
|
106 |
+
"loss": 0.941,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.7,
|
111 |
+
"grad_norm": 12.011809349060059,
|
112 |
+
"learning_rate": 4.353448275862069e-05,
|
113 |
+
"loss": 1.1812,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.74,
|
118 |
+
"grad_norm": 6.191880702972412,
|
119 |
+
"learning_rate": 4.267241379310345e-05,
|
120 |
+
"loss": 0.7905,
|
121 |
+
"step": 32
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.79,
|
125 |
+
"grad_norm": 5.270814418792725,
|
126 |
+
"learning_rate": 4.1810344827586205e-05,
|
127 |
+
"loss": 0.7904,
|
128 |
+
"step": 34
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.84,
|
132 |
+
"grad_norm": 5.346973896026611,
|
133 |
+
"learning_rate": 4.094827586206897e-05,
|
134 |
+
"loss": 0.6126,
|
135 |
+
"step": 36
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.88,
|
139 |
+
"grad_norm": 6.431284427642822,
|
140 |
+
"learning_rate": 4.0086206896551726e-05,
|
141 |
+
"loss": 0.9431,
|
142 |
+
"step": 38
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.93,
|
146 |
+
"grad_norm": 5.295109748840332,
|
147 |
+
"learning_rate": 3.922413793103448e-05,
|
148 |
+
"loss": 0.8013,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.98,
|
153 |
+
"grad_norm": 7.394813060760498,
|
154 |
+
"learning_rate": 3.8362068965517246e-05,
|
155 |
+
"loss": 0.5561,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.0,
|
160 |
+
"eval_accuracy": 0.6511627906976745,
|
161 |
+
"eval_f1_macro": 0.5219298245614035,
|
162 |
+
"eval_f1_micro": 0.6511627906976745,
|
163 |
+
"eval_f1_weighted": 0.5661464708282333,
|
164 |
+
"eval_loss": 0.8391300439834595,
|
165 |
+
"eval_precision_macro": 0.5958528951486698,
|
166 |
+
"eval_precision_micro": 0.6511627906976745,
|
167 |
+
"eval_precision_weighted": 0.5547548859045747,
|
168 |
+
"eval_recall_macro": 0.5166666666666667,
|
169 |
+
"eval_recall_micro": 0.6511627906976745,
|
170 |
+
"eval_recall_weighted": 0.6511627906976745,
|
171 |
+
"eval_runtime": 0.5055,
|
172 |
+
"eval_samples_per_second": 170.128,
|
173 |
+
"eval_steps_per_second": 11.869,
|
174 |
+
"step": 43
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.02,
|
178 |
+
"grad_norm": 12.433929443359375,
|
179 |
+
"learning_rate": 3.7500000000000003e-05,
|
180 |
+
"loss": 0.8422,
|
181 |
+
"step": 44
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.07,
|
185 |
+
"grad_norm": 9.662508010864258,
|
186 |
+
"learning_rate": 3.663793103448276e-05,
|
187 |
+
"loss": 0.8562,
|
188 |
+
"step": 46
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.12,
|
192 |
+
"grad_norm": 6.504687309265137,
|
193 |
+
"learning_rate": 3.5775862068965524e-05,
|
194 |
+
"loss": 0.6381,
|
195 |
+
"step": 48
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.16,
|
199 |
+
"grad_norm": 12.690322875976562,
|
200 |
+
"learning_rate": 3.4913793103448275e-05,
|
201 |
+
"loss": 0.5752,
|
202 |
+
"step": 50
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.21,
|
206 |
+
"grad_norm": 5.9632792472839355,
|
207 |
+
"learning_rate": 3.405172413793103e-05,
|
208 |
+
"loss": 0.6849,
|
209 |
+
"step": 52
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.26,
|
213 |
+
"grad_norm": 8.237900733947754,
|
214 |
+
"learning_rate": 3.3189655172413796e-05,
|
215 |
+
"loss": 0.6422,
|
216 |
+
"step": 54
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.3,
|
220 |
+
"grad_norm": 5.977579593658447,
|
221 |
+
"learning_rate": 3.232758620689655e-05,
|
222 |
+
"loss": 0.6344,
|
223 |
+
"step": 56
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.35,
|
227 |
+
"grad_norm": 6.388967037200928,
|
228 |
+
"learning_rate": 3.146551724137931e-05,
|
229 |
+
"loss": 0.6051,
|
230 |
+
"step": 58
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.4,
|
234 |
+
"grad_norm": 6.785774230957031,
|
235 |
+
"learning_rate": 3.060344827586207e-05,
|
236 |
+
"loss": 0.5379,
|
237 |
+
"step": 60
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.44,
|
241 |
+
"grad_norm": 6.693228244781494,
|
242 |
+
"learning_rate": 2.974137931034483e-05,
|
243 |
+
"loss": 0.4483,
|
244 |
+
"step": 62
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.49,
|
248 |
+
"grad_norm": 4.33690071105957,
|
249 |
+
"learning_rate": 2.8879310344827588e-05,
|
250 |
+
"loss": 0.5161,
|
251 |
+
"step": 64
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.53,
|
255 |
+
"grad_norm": 7.381749629974365,
|
256 |
+
"learning_rate": 2.8017241379310345e-05,
|
257 |
+
"loss": 0.7829,
|
258 |
+
"step": 66
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.58,
|
262 |
+
"grad_norm": 11.129793167114258,
|
263 |
+
"learning_rate": 2.7155172413793105e-05,
|
264 |
+
"loss": 0.7715,
|
265 |
+
"step": 68
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.63,
|
269 |
+
"grad_norm": 11.77314281463623,
|
270 |
+
"learning_rate": 2.6293103448275862e-05,
|
271 |
+
"loss": 1.114,
|
272 |
+
"step": 70
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.67,
|
276 |
+
"grad_norm": 7.2926130294799805,
|
277 |
+
"learning_rate": 2.543103448275862e-05,
|
278 |
+
"loss": 0.938,
|
279 |
+
"step": 72
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.72,
|
283 |
+
"grad_norm": 5.774272441864014,
|
284 |
+
"learning_rate": 2.456896551724138e-05,
|
285 |
+
"loss": 0.7925,
|
286 |
+
"step": 74
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.77,
|
290 |
+
"grad_norm": 9.42758560180664,
|
291 |
+
"learning_rate": 2.370689655172414e-05,
|
292 |
+
"loss": 0.6834,
|
293 |
+
"step": 76
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.81,
|
297 |
+
"grad_norm": 7.223062038421631,
|
298 |
+
"learning_rate": 2.2844827586206897e-05,
|
299 |
+
"loss": 0.8257,
|
300 |
+
"step": 78
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.86,
|
304 |
+
"grad_norm": 9.974703788757324,
|
305 |
+
"learning_rate": 2.1982758620689654e-05,
|
306 |
+
"loss": 0.5291,
|
307 |
+
"step": 80
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.91,
|
311 |
+
"grad_norm": 11.898812294006348,
|
312 |
+
"learning_rate": 2.1120689655172415e-05,
|
313 |
+
"loss": 0.8295,
|
314 |
+
"step": 82
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.95,
|
318 |
+
"grad_norm": 5.932551383972168,
|
319 |
+
"learning_rate": 2.0258620689655172e-05,
|
320 |
+
"loss": 0.5594,
|
321 |
+
"step": 84
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 2.0,
|
325 |
+
"grad_norm": 8.01093864440918,
|
326 |
+
"learning_rate": 1.9396551724137932e-05,
|
327 |
+
"loss": 0.7166,
|
328 |
+
"step": 86
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 2.0,
|
332 |
+
"eval_accuracy": 0.7790697674418605,
|
333 |
+
"eval_f1_macro": 0.7326664355062412,
|
334 |
+
"eval_f1_micro": 0.7790697674418605,
|
335 |
+
"eval_f1_weighted": 0.7589375221752733,
|
336 |
+
"eval_loss": 0.6218534708023071,
|
337 |
+
"eval_precision_macro": 0.8907051282051283,
|
338 |
+
"eval_precision_micro": 0.7790697674418605,
|
339 |
+
"eval_precision_weighted": 0.831499701848539,
|
340 |
+
"eval_recall_macro": 0.6805555555555556,
|
341 |
+
"eval_recall_micro": 0.7790697674418605,
|
342 |
+
"eval_recall_weighted": 0.7790697674418605,
|
343 |
+
"eval_runtime": 0.4535,
|
344 |
+
"eval_samples_per_second": 189.622,
|
345 |
+
"eval_steps_per_second": 13.229,
|
346 |
+
"step": 86
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 2.05,
|
350 |
+
"grad_norm": 4.2975664138793945,
|
351 |
+
"learning_rate": 1.8534482758620693e-05,
|
352 |
+
"loss": 0.5073,
|
353 |
+
"step": 88
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 2.09,
|
357 |
+
"grad_norm": 8.290116310119629,
|
358 |
+
"learning_rate": 1.767241379310345e-05,
|
359 |
+
"loss": 0.606,
|
360 |
+
"step": 90
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.14,
|
364 |
+
"grad_norm": 5.366226673126221,
|
365 |
+
"learning_rate": 1.6810344827586207e-05,
|
366 |
+
"loss": 0.4448,
|
367 |
+
"step": 92
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 2.19,
|
371 |
+
"grad_norm": 6.743834495544434,
|
372 |
+
"learning_rate": 1.5948275862068967e-05,
|
373 |
+
"loss": 0.7529,
|
374 |
+
"step": 94
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.23,
|
378 |
+
"grad_norm": 6.312230587005615,
|
379 |
+
"learning_rate": 1.5086206896551724e-05,
|
380 |
+
"loss": 0.662,
|
381 |
+
"step": 96
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.28,
|
385 |
+
"grad_norm": 9.200089454650879,
|
386 |
+
"learning_rate": 1.4224137931034485e-05,
|
387 |
+
"loss": 0.9112,
|
388 |
+
"step": 98
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 2.33,
|
392 |
+
"grad_norm": 3.5302746295928955,
|
393 |
+
"learning_rate": 1.336206896551724e-05,
|
394 |
+
"loss": 0.2405,
|
395 |
+
"step": 100
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.37,
|
399 |
+
"grad_norm": 13.742111206054688,
|
400 |
+
"learning_rate": 1.25e-05,
|
401 |
+
"loss": 0.5303,
|
402 |
+
"step": 102
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.42,
|
406 |
+
"grad_norm": 8.292695045471191,
|
407 |
+
"learning_rate": 1.163793103448276e-05,
|
408 |
+
"loss": 0.5544,
|
409 |
+
"step": 104
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 2.47,
|
413 |
+
"grad_norm": 9.335094451904297,
|
414 |
+
"learning_rate": 1.0775862068965516e-05,
|
415 |
+
"loss": 0.7992,
|
416 |
+
"step": 106
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.51,
|
420 |
+
"grad_norm": 4.947837829589844,
|
421 |
+
"learning_rate": 9.913793103448277e-06,
|
422 |
+
"loss": 0.4896,
|
423 |
+
"step": 108
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 2.56,
|
427 |
+
"grad_norm": 11.157235145568848,
|
428 |
+
"learning_rate": 9.051724137931036e-06,
|
429 |
+
"loss": 0.6746,
|
430 |
+
"step": 110
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 2.6,
|
434 |
+
"grad_norm": 10.61878776550293,
|
435 |
+
"learning_rate": 8.189655172413793e-06,
|
436 |
+
"loss": 0.6722,
|
437 |
+
"step": 112
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 2.65,
|
441 |
+
"grad_norm": 4.7017621994018555,
|
442 |
+
"learning_rate": 7.3275862068965514e-06,
|
443 |
+
"loss": 0.5214,
|
444 |
+
"step": 114
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.7,
|
448 |
+
"grad_norm": 3.746359348297119,
|
449 |
+
"learning_rate": 6.465517241379311e-06,
|
450 |
+
"loss": 0.592,
|
451 |
+
"step": 116
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 2.74,
|
455 |
+
"grad_norm": 5.942258358001709,
|
456 |
+
"learning_rate": 5.603448275862069e-06,
|
457 |
+
"loss": 0.5589,
|
458 |
+
"step": 118
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.79,
|
462 |
+
"grad_norm": 13.716927528381348,
|
463 |
+
"learning_rate": 4.741379310344828e-06,
|
464 |
+
"loss": 1.0046,
|
465 |
+
"step": 120
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.84,
|
469 |
+
"grad_norm": 3.577460765838623,
|
470 |
+
"learning_rate": 3.8793103448275865e-06,
|
471 |
+
"loss": 0.4807,
|
472 |
+
"step": 122
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 2.88,
|
476 |
+
"grad_norm": 6.835740566253662,
|
477 |
+
"learning_rate": 3.017241379310345e-06,
|
478 |
+
"loss": 0.5735,
|
479 |
+
"step": 124
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 2.93,
|
483 |
+
"grad_norm": 7.47273588180542,
|
484 |
+
"learning_rate": 2.1551724137931035e-06,
|
485 |
+
"loss": 0.569,
|
486 |
+
"step": 126
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 2.98,
|
490 |
+
"grad_norm": 6.011229991912842,
|
491 |
+
"learning_rate": 1.293103448275862e-06,
|
492 |
+
"loss": 0.3485,
|
493 |
+
"step": 128
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 3.0,
|
497 |
+
"eval_accuracy": 0.7674418604651163,
|
498 |
+
"eval_f1_macro": 0.726419878296146,
|
499 |
+
"eval_f1_micro": 0.7674418604651162,
|
500 |
+
"eval_f1_weighted": 0.7444926647483373,
|
501 |
+
"eval_loss": 0.588494598865509,
|
502 |
+
"eval_precision_macro": 0.8743946731234866,
|
503 |
+
"eval_precision_micro": 0.7674418604651163,
|
504 |
+
"eval_precision_weighted": 0.8185567881074384,
|
505 |
+
"eval_recall_macro": 0.6858527131782945,
|
506 |
+
"eval_recall_micro": 0.7674418604651163,
|
507 |
+
"eval_recall_weighted": 0.7674418604651163,
|
508 |
+
"eval_runtime": 0.4559,
|
509 |
+
"eval_samples_per_second": 188.618,
|
510 |
+
"eval_steps_per_second": 13.159,
|
511 |
+
"step": 129
|
512 |
+
}
|
513 |
+
],
|
514 |
+
"logging_steps": 2,
|
515 |
+
"max_steps": 129,
|
516 |
+
"num_input_tokens_seen": 0,
|
517 |
+
"num_train_epochs": 3,
|
518 |
+
"save_steps": 500,
|
519 |
+
"total_flos": 7.97406866688983e+16,
|
520 |
+
"train_batch_size": 8,
|
521 |
+
"trial_name": null,
|
522 |
+
"trial_params": null
|
523 |
+
}
|
checkpoint-129/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:373699646c5eae73c7a22630d3eb2d7d5b4ced18a12160daa1913d5e140bdfec
|
3 |
+
size 4920
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
3 |
+
"_num_labels": 4,
|
4 |
+
"architectures": [
|
5 |
+
"ViTForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"encoder_stride": 16,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "blank",
|
14 |
+
"1": "content",
|
15 |
+
"2": "end",
|
16 |
+
"3": "start"
|
17 |
+
},
|
18 |
+
"image_size": 224,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"blank": 0,
|
23 |
+
"content": 1,
|
24 |
+
"end": 2,
|
25 |
+
"start": 3
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"model_type": "vit",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_channels": 3,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"patch_size": 16,
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"qkv_bias": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.39.0"
|
37 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6cb39e4419595735109964dd5d06982ea0141bd516e365f0c77433ea018e7bd
|
3 |
+
size 343230128
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:373699646c5eae73c7a22630d3eb2d7d5b4ced18a12160daa1913d5e140bdfec
|
3 |
+
size 4920
|
training_params.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-f8u3m-1w0uc/autotrain-data",
|
3 |
+
"model": "google/vit-base-patch16-224",
|
4 |
+
"username": "rdmpage",
|
5 |
+
"lr": 5e-05,
|
6 |
+
"epochs": 3,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"logging_steps": -1,
|
18 |
+
"project_name": "autotrain-f8u3m-1w0uc",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"save_total_limit": 1,
|
22 |
+
"save_strategy": "epoch",
|
23 |
+
"push_to_hub": true,
|
24 |
+
"repo_id": "rdmpage/autotrain-f8u3m-1w0uc",
|
25 |
+
"evaluation_strategy": "epoch",
|
26 |
+
"image_column": "autotrain_image",
|
27 |
+
"target_column": "autotrain_label",
|
28 |
+
"log": "none"
|
29 |
+
}
|