Upload folder using huggingface_hub
Browse files- checkpoint-12105/config.json +34 -0
- checkpoint-12105/model.safetensors +3 -0
- checkpoint-12105/optimizer.pt +3 -0
- checkpoint-12105/preprocessor_config.json +22 -0
- checkpoint-12105/rng_state.pth +3 -0
- checkpoint-12105/scheduler.pt +3 -0
- checkpoint-12105/trainer_state.json +211 -0
- checkpoint-12105/training_args.bin +3 -0
- config.json +7 -7
- model.safetensors +1 -1
- training_args.bin +2 -2
checkpoint-12105/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": "E",
|
13 |
+
"1": "S",
|
14 |
+
"2": "SB"
|
15 |
+
},
|
16 |
+
"image_size": 224,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"E": 0,
|
21 |
+
"S": 1,
|
22 |
+
"SB": 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": "4.44.2"
|
34 |
+
}
|
checkpoint-12105/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b33b2b1054d985b32e22181fbf4e011685b83317ec0dac8a1ee688ac78a0142c
|
3 |
+
size 343227052
|
checkpoint-12105/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53c4939c19e28752212e5ab8c3d2f524ecb2a434c556335f768095d1fc441fdd
|
3 |
+
size 686574597
|
checkpoint-12105/preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
checkpoint-12105/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1134a5d235acceaffa481a3ced304b415607b38245b6bc4dd32ed4b161a60938
|
3 |
+
size 14575
|
checkpoint-12105/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c40ca2519339243454f1747334687ba9e05c256d23ca3fa83abba65e3a91ce6a
|
3 |
+
size 627
|
checkpoint-12105/trainer_state.json
ADDED
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5624491572380066,
|
3 |
+
"best_model_checkpoint": "galaxy_type_image_detection/checkpoint-12105",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 12105,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.041305245766212306,
|
13 |
+
"grad_norm": 1.0393656492233276,
|
14 |
+
"learning_rate": 8.66403981750311e-07,
|
15 |
+
"loss": 0.967,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08261049153242461,
|
20 |
+
"grad_norm": 2.2510411739349365,
|
21 |
+
"learning_rate": 8.2907507258399e-07,
|
22 |
+
"loss": 0.8018,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12391573729863693,
|
27 |
+
"grad_norm": 2.212888479232788,
|
28 |
+
"learning_rate": 7.91746163417669e-07,
|
29 |
+
"loss": 0.7377,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16522098306484923,
|
34 |
+
"grad_norm": 2.6769936084747314,
|
35 |
+
"learning_rate": 7.54417254251348e-07,
|
36 |
+
"loss": 0.6944,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.20652622883106153,
|
41 |
+
"grad_norm": 1.5611211061477661,
|
42 |
+
"learning_rate": 7.170883450850269e-07,
|
43 |
+
"loss": 0.6649,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24783147459727387,
|
48 |
+
"grad_norm": 2.753368616104126,
|
49 |
+
"learning_rate": 6.797594359187059e-07,
|
50 |
+
"loss": 0.6495,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.28913672036348614,
|
55 |
+
"grad_norm": 2.5022592544555664,
|
56 |
+
"learning_rate": 6.424305267523848e-07,
|
57 |
+
"loss": 0.6282,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.33044196612969845,
|
62 |
+
"grad_norm": 3.5701966285705566,
|
63 |
+
"learning_rate": 6.051016175860639e-07,
|
64 |
+
"loss": 0.6171,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.37174721189591076,
|
69 |
+
"grad_norm": 2.316419839859009,
|
70 |
+
"learning_rate": 5.677727084197428e-07,
|
71 |
+
"loss": 0.609,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.41305245766212306,
|
76 |
+
"grad_norm": 2.764505624771118,
|
77 |
+
"learning_rate": 5.304437992534219e-07,
|
78 |
+
"loss": 0.5999,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4543577034283354,
|
83 |
+
"grad_norm": 3.0616867542266846,
|
84 |
+
"learning_rate": 4.931148900871008e-07,
|
85 |
+
"loss": 0.5925,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.49566294919454773,
|
90 |
+
"grad_norm": 3.7850115299224854,
|
91 |
+
"learning_rate": 4.557859809207797e-07,
|
92 |
+
"loss": 0.589,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.53696819496076,
|
97 |
+
"grad_norm": 2.5644021034240723,
|
98 |
+
"learning_rate": 4.1845707175445867e-07,
|
99 |
+
"loss": 0.5829,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.5782734407269723,
|
104 |
+
"grad_norm": 2.6693475246429443,
|
105 |
+
"learning_rate": 3.8112816258813767e-07,
|
106 |
+
"loss": 0.5768,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6195786864931846,
|
111 |
+
"grad_norm": 4.514222145080566,
|
112 |
+
"learning_rate": 3.437992534218167e-07,
|
113 |
+
"loss": 0.5728,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6608839322593969,
|
118 |
+
"grad_norm": 3.1888978481292725,
|
119 |
+
"learning_rate": 3.064703442554956e-07,
|
120 |
+
"loss": 0.5698,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.7021891780256092,
|
125 |
+
"grad_norm": 3.4488654136657715,
|
126 |
+
"learning_rate": 2.691414350891746e-07,
|
127 |
+
"loss": 0.5737,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7434944237918215,
|
132 |
+
"grad_norm": 4.471464157104492,
|
133 |
+
"learning_rate": 2.3181252592285358e-07,
|
134 |
+
"loss": 0.5643,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.7847996695580338,
|
139 |
+
"grad_norm": 3.535975217819214,
|
140 |
+
"learning_rate": 1.9448361675653255e-07,
|
141 |
+
"loss": 0.5682,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8261049153242461,
|
146 |
+
"grad_norm": 5.046966075897217,
|
147 |
+
"learning_rate": 1.571547075902115e-07,
|
148 |
+
"loss": 0.5628,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.8674101610904585,
|
153 |
+
"grad_norm": 3.240630626678467,
|
154 |
+
"learning_rate": 1.198257984238905e-07,
|
155 |
+
"loss": 0.5613,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9087154068566708,
|
160 |
+
"grad_norm": 4.973729133605957,
|
161 |
+
"learning_rate": 8.249688925756947e-08,
|
162 |
+
"loss": 0.5602,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.9500206526228832,
|
167 |
+
"grad_norm": 4.114513397216797,
|
168 |
+
"learning_rate": 4.516798009124844e-08,
|
169 |
+
"loss": 0.5622,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.9913258983890955,
|
174 |
+
"grad_norm": 3.011930227279663,
|
175 |
+
"learning_rate": 7.839070924927416e-09,
|
176 |
+
"loss": 0.5592,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"eval_accuracy": 0.7654878108598617,
|
182 |
+
"eval_loss": 0.5624491572380066,
|
183 |
+
"eval_model_preparation_time": 0.006,
|
184 |
+
"eval_runtime": 413.2412,
|
185 |
+
"eval_samples_per_second": 98.669,
|
186 |
+
"eval_steps_per_second": 3.085,
|
187 |
+
"step": 12105
|
188 |
+
}
|
189 |
+
],
|
190 |
+
"logging_steps": 500,
|
191 |
+
"max_steps": 12105,
|
192 |
+
"num_input_tokens_seen": 0,
|
193 |
+
"num_train_epochs": 1,
|
194 |
+
"save_steps": 500,
|
195 |
+
"stateful_callbacks": {
|
196 |
+
"TrainerControl": {
|
197 |
+
"args": {
|
198 |
+
"should_epoch_stop": false,
|
199 |
+
"should_evaluate": false,
|
200 |
+
"should_log": false,
|
201 |
+
"should_save": true,
|
202 |
+
"should_training_stop": true
|
203 |
+
},
|
204 |
+
"attributes": {}
|
205 |
+
}
|
206 |
+
},
|
207 |
+
"total_flos": 6.003272999208671e+19,
|
208 |
+
"train_batch_size": 64,
|
209 |
+
"trial_name": null,
|
210 |
+
"trial_params": null
|
211 |
+
}
|
checkpoint-12105/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6dc03e977829a9fe1632bfde9dc8286b9b4d9e269bca46e17c31045d8f211d2
|
3 |
+
size 4667
|
config.json
CHANGED
@@ -9,17 +9,17 @@
|
|
9 |
"hidden_dropout_prob": 0.0,
|
10 |
"hidden_size": 768,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
-
"2": "
|
15 |
},
|
16 |
"image_size": 224,
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 3072,
|
19 |
"label2id": {
|
20 |
-
"E":
|
21 |
-
"S":
|
22 |
-
"SB":
|
23 |
},
|
24 |
"layer_norm_eps": 1e-12,
|
25 |
"model_type": "vit",
|
@@ -30,5 +30,5 @@
|
|
30 |
"problem_type": "single_label_classification",
|
31 |
"qkv_bias": true,
|
32 |
"torch_dtype": "float32",
|
33 |
-
"transformers_version": "4.
|
34 |
}
|
|
|
9 |
"hidden_dropout_prob": 0.0,
|
10 |
"hidden_size": 768,
|
11 |
"id2label": {
|
12 |
+
"0": "E",
|
13 |
+
"1": "S",
|
14 |
+
"2": "SB"
|
15 |
},
|
16 |
"image_size": 224,
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 3072,
|
19 |
"label2id": {
|
20 |
+
"E": 0,
|
21 |
+
"S": 1,
|
22 |
+
"SB": 2
|
23 |
},
|
24 |
"layer_norm_eps": 1e-12,
|
25 |
"model_type": "vit",
|
|
|
30 |
"problem_type": "single_label_classification",
|
31 |
"qkv_bias": true,
|
32 |
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.44.2"
|
34 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343227052
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b33b2b1054d985b32e22181fbf4e011685b83317ec0dac8a1ee688ac78a0142c
|
3 |
size 343227052
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6dc03e977829a9fe1632bfde9dc8286b9b4d9e269bca46e17c31045d8f211d2
|
3 |
+
size 4667
|