Upload folder using huggingface_hub
Browse files- checkpoint-7500/config.json +49 -0
- checkpoint-7500/model.safetensors +3 -0
- checkpoint-7500/optimizer.pt +3 -0
- checkpoint-7500/preprocessor_config.json +22 -0
- checkpoint-7500/rng_state.pth +3 -0
- checkpoint-7500/scheduler.pt +3 -0
- checkpoint-7500/trainer_state.json +228 -0
- checkpoint-7500/training_args.bin +3 -0
- config.json +49 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
checkpoint-7500/config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/resnet-50",
|
3 |
+
"architectures": [
|
4 |
+
"ResNetForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
3,
|
8 |
+
4,
|
9 |
+
6,
|
10 |
+
3
|
11 |
+
],
|
12 |
+
"downsample_in_bottleneck": false,
|
13 |
+
"downsample_in_first_stage": false,
|
14 |
+
"embedding_size": 64,
|
15 |
+
"hidden_act": "relu",
|
16 |
+
"hidden_sizes": [
|
17 |
+
256,
|
18 |
+
512,
|
19 |
+
1024,
|
20 |
+
2048
|
21 |
+
],
|
22 |
+
"id2label": {
|
23 |
+
"0": "REAL",
|
24 |
+
"1": "FAKE"
|
25 |
+
},
|
26 |
+
"label2id": {
|
27 |
+
"FAKE": 1,
|
28 |
+
"REAL": 0
|
29 |
+
},
|
30 |
+
"layer_type": "bottleneck",
|
31 |
+
"model_type": "resnet",
|
32 |
+
"num_channels": 3,
|
33 |
+
"out_features": [
|
34 |
+
"stage4"
|
35 |
+
],
|
36 |
+
"out_indices": [
|
37 |
+
4
|
38 |
+
],
|
39 |
+
"problem_type": "single_label_classification",
|
40 |
+
"stage_names": [
|
41 |
+
"stem",
|
42 |
+
"stage1",
|
43 |
+
"stage2",
|
44 |
+
"stage3",
|
45 |
+
"stage4"
|
46 |
+
],
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.46.3"
|
49 |
+
}
|
checkpoint-7500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf62ea6589fd6fffa30eb1b6c4775d2da8de65e0d420602960f4d0f3397833a6
|
3 |
+
size 94302952
|
checkpoint-7500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79b06917d169c78c07f067154c978b9ad049c66c21276043a4c242183466172a
|
3 |
+
size 188232069
|
checkpoint-7500/preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_pct": 0.875,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.485,
|
8 |
+
0.456,
|
9 |
+
0.406
|
10 |
+
],
|
11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"shortest_edge": 224
|
21 |
+
}
|
22 |
+
}
|
checkpoint-7500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eee0230b2c12193aee2a6065ebea9716d1a04774e36706870db386bc09f5b46a
|
3 |
+
size 14575
|
checkpoint-7500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52b897a14b185f898bec0403b570c6911a55c32f85bd4eab59ba2ffbbd8a7b0e
|
3 |
+
size 627
|
checkpoint-7500/trainer_state.json
ADDED
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.16018521785736084,
|
3 |
+
"best_model_checkpoint": "resnet50_4a_10_epoch_lr1e5/checkpoint-7500",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6666666666666666,
|
13 |
+
"grad_norm": 3.5805983543395996,
|
14 |
+
"learning_rate": 9.395973154362416e-06,
|
15 |
+
"loss": 0.6553,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.821875,
|
21 |
+
"eval_loss": 0.5155154466629028,
|
22 |
+
"eval_runtime": 225.7918,
|
23 |
+
"eval_samples_per_second": 106.293,
|
24 |
+
"eval_steps_per_second": 1.661,
|
25 |
+
"step": 750
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3333333333333333,
|
29 |
+
"grad_norm": 6.772037506103516,
|
30 |
+
"learning_rate": 8.724832214765101e-06,
|
31 |
+
"loss": 0.5278,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"grad_norm": 7.1797895431518555,
|
37 |
+
"learning_rate": 8.053691275167785e-06,
|
38 |
+
"loss": 0.3857,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.0,
|
43 |
+
"eval_accuracy": 0.879,
|
44 |
+
"eval_loss": 0.3160336911678314,
|
45 |
+
"eval_runtime": 100.4203,
|
46 |
+
"eval_samples_per_second": 238.996,
|
47 |
+
"eval_steps_per_second": 3.734,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.6666666666666665,
|
52 |
+
"grad_norm": 8.779245376586914,
|
53 |
+
"learning_rate": 7.382550335570471e-06,
|
54 |
+
"loss": 0.3047,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.9075,
|
60 |
+
"eval_loss": 0.23712438344955444,
|
61 |
+
"eval_runtime": 80.6725,
|
62 |
+
"eval_samples_per_second": 297.499,
|
63 |
+
"eval_steps_per_second": 4.648,
|
64 |
+
"step": 2250
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.3333333333333335,
|
68 |
+
"grad_norm": 9.758003234863281,
|
69 |
+
"learning_rate": 6.711409395973155e-06,
|
70 |
+
"loss": 0.2559,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"grad_norm": 7.47396993637085,
|
76 |
+
"learning_rate": 6.04026845637584e-06,
|
77 |
+
"loss": 0.2298,
|
78 |
+
"step": 3000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 4.0,
|
82 |
+
"eval_accuracy": 0.9228333333333333,
|
83 |
+
"eval_loss": 0.20199613273143768,
|
84 |
+
"eval_runtime": 82.1236,
|
85 |
+
"eval_samples_per_second": 292.242,
|
86 |
+
"eval_steps_per_second": 4.566,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.666666666666667,
|
91 |
+
"grad_norm": 10.239446640014648,
|
92 |
+
"learning_rate": 5.369127516778524e-06,
|
93 |
+
"loss": 0.2128,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.929,
|
99 |
+
"eval_loss": 0.18368670344352722,
|
100 |
+
"eval_runtime": 82.6514,
|
101 |
+
"eval_samples_per_second": 290.376,
|
102 |
+
"eval_steps_per_second": 4.537,
|
103 |
+
"step": 3750
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.333333333333333,
|
107 |
+
"grad_norm": 7.634970188140869,
|
108 |
+
"learning_rate": 4.697986577181208e-06,
|
109 |
+
"loss": 0.2004,
|
110 |
+
"step": 4000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.0,
|
114 |
+
"grad_norm": 8.229543685913086,
|
115 |
+
"learning_rate": 4.026845637583892e-06,
|
116 |
+
"loss": 0.1918,
|
117 |
+
"step": 4500
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 6.0,
|
121 |
+
"eval_accuracy": 0.9323333333333333,
|
122 |
+
"eval_loss": 0.17339174449443817,
|
123 |
+
"eval_runtime": 79.5022,
|
124 |
+
"eval_samples_per_second": 301.879,
|
125 |
+
"eval_steps_per_second": 4.717,
|
126 |
+
"step": 4500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.666666666666667,
|
130 |
+
"grad_norm": 8.368539810180664,
|
131 |
+
"learning_rate": 3.3557046979865777e-06,
|
132 |
+
"loss": 0.1848,
|
133 |
+
"step": 5000
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 7.0,
|
137 |
+
"eval_accuracy": 0.934,
|
138 |
+
"eval_loss": 0.16669026017189026,
|
139 |
+
"eval_runtime": 89.8115,
|
140 |
+
"eval_samples_per_second": 267.226,
|
141 |
+
"eval_steps_per_second": 4.175,
|
142 |
+
"step": 5250
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 7.333333333333333,
|
146 |
+
"grad_norm": 5.3287739753723145,
|
147 |
+
"learning_rate": 2.684563758389262e-06,
|
148 |
+
"loss": 0.181,
|
149 |
+
"step": 5500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 8.0,
|
153 |
+
"grad_norm": 12.32608413696289,
|
154 |
+
"learning_rate": 2.013422818791946e-06,
|
155 |
+
"loss": 0.176,
|
156 |
+
"step": 6000
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 8.0,
|
160 |
+
"eval_accuracy": 0.9349583333333333,
|
161 |
+
"eval_loss": 0.16361936926841736,
|
162 |
+
"eval_runtime": 90.7398,
|
163 |
+
"eval_samples_per_second": 264.493,
|
164 |
+
"eval_steps_per_second": 4.133,
|
165 |
+
"step": 6000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 8.666666666666666,
|
169 |
+
"grad_norm": 10.940423011779785,
|
170 |
+
"learning_rate": 1.342281879194631e-06,
|
171 |
+
"loss": 0.1763,
|
172 |
+
"step": 6500
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 9.0,
|
176 |
+
"eval_accuracy": 0.9363333333333334,
|
177 |
+
"eval_loss": 0.16042540967464447,
|
178 |
+
"eval_runtime": 78.9099,
|
179 |
+
"eval_samples_per_second": 304.144,
|
180 |
+
"eval_steps_per_second": 4.752,
|
181 |
+
"step": 6750
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 9.333333333333334,
|
185 |
+
"grad_norm": 8.731983184814453,
|
186 |
+
"learning_rate": 6.711409395973155e-07,
|
187 |
+
"loss": 0.1731,
|
188 |
+
"step": 7000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 10.0,
|
192 |
+
"grad_norm": 8.042535781860352,
|
193 |
+
"learning_rate": 0.0,
|
194 |
+
"loss": 0.1721,
|
195 |
+
"step": 7500
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 10.0,
|
199 |
+
"eval_accuracy": 0.9371666666666667,
|
200 |
+
"eval_loss": 0.16018521785736084,
|
201 |
+
"eval_runtime": 83.7677,
|
202 |
+
"eval_samples_per_second": 286.507,
|
203 |
+
"eval_steps_per_second": 4.477,
|
204 |
+
"step": 7500
|
205 |
+
}
|
206 |
+
],
|
207 |
+
"logging_steps": 500,
|
208 |
+
"max_steps": 7500,
|
209 |
+
"num_input_tokens_seen": 0,
|
210 |
+
"num_train_epochs": 10,
|
211 |
+
"save_steps": 500,
|
212 |
+
"stateful_callbacks": {
|
213 |
+
"TrainerControl": {
|
214 |
+
"args": {
|
215 |
+
"should_epoch_stop": false,
|
216 |
+
"should_evaluate": false,
|
217 |
+
"should_log": false,
|
218 |
+
"should_save": true,
|
219 |
+
"should_training_stop": true
|
220 |
+
},
|
221 |
+
"attributes": {}
|
222 |
+
}
|
223 |
+
},
|
224 |
+
"total_flos": 2.03859872907264e+19,
|
225 |
+
"train_batch_size": 128,
|
226 |
+
"trial_name": null,
|
227 |
+
"trial_params": null
|
228 |
+
}
|
checkpoint-7500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287fad1ffef17e2aafacc82d0cfe262754323d2a083c87bc80b84ff891d06b22
|
3 |
+
size 4795
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/resnet-50",
|
3 |
+
"architectures": [
|
4 |
+
"ResNetForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
3,
|
8 |
+
4,
|
9 |
+
6,
|
10 |
+
3
|
11 |
+
],
|
12 |
+
"downsample_in_bottleneck": false,
|
13 |
+
"downsample_in_first_stage": false,
|
14 |
+
"embedding_size": 64,
|
15 |
+
"hidden_act": "relu",
|
16 |
+
"hidden_sizes": [
|
17 |
+
256,
|
18 |
+
512,
|
19 |
+
1024,
|
20 |
+
2048
|
21 |
+
],
|
22 |
+
"id2label": {
|
23 |
+
"0": "REAL",
|
24 |
+
"1": "FAKE"
|
25 |
+
},
|
26 |
+
"label2id": {
|
27 |
+
"FAKE": 1,
|
28 |
+
"REAL": 0
|
29 |
+
},
|
30 |
+
"layer_type": "bottleneck",
|
31 |
+
"model_type": "resnet",
|
32 |
+
"num_channels": 3,
|
33 |
+
"out_features": [
|
34 |
+
"stage4"
|
35 |
+
],
|
36 |
+
"out_indices": [
|
37 |
+
4
|
38 |
+
],
|
39 |
+
"problem_type": "single_label_classification",
|
40 |
+
"stage_names": [
|
41 |
+
"stem",
|
42 |
+
"stage1",
|
43 |
+
"stage2",
|
44 |
+
"stage3",
|
45 |
+
"stage4"
|
46 |
+
],
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.46.3"
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf62ea6589fd6fffa30eb1b6c4775d2da8de65e0d420602960f4d0f3397833a6
|
3 |
+
size 94302952
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_pct": 0.875,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.485,
|
8 |
+
0.456,
|
9 |
+
0.406
|
10 |
+
],
|
11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"shortest_edge": 224
|
21 |
+
}
|
22 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287fad1ffef17e2aafacc82d0cfe262754323d2a083c87bc80b84ff891d06b22
|
3 |
+
size 4795
|