ArtemisTAO commited on
Commit
c2b4059
·
verified ·
1 Parent(s): 86856fa

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +33 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scaler.pt +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +174 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "encoder_stride": 16,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.0,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "None",
12
+ "1": "Roadwork"
13
+ },
14
+ "image_size": 224,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "None": 0,
19
+ "Roadwork": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "model_type": "vit",
23
+ "num_attention_heads": 12,
24
+ "num_channels": 3,
25
+ "num_hidden_layers": 12,
26
+ "patch_size": 16,
27
+ "pooler_act": "tanh",
28
+ "pooler_output_size": 768,
29
+ "problem_type": "single_label_classification",
30
+ "qkv_bias": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.54.1"
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8843c350d99104da5899e9c27ac3380dd82fcc187c2ed546d6f0226b97b0ce05
3
+ size 343223968
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c9f75a3ae0f2f2a51b0f896fdd0a811b4d0e36be555cf30eb362d14cfbbbb34
3
+ size 686569355
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc37bbd2e979f041dfbbb004a5c74bab6cdda159cb18116df728588515a9ef6
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9eb4a7998667daadb245e0bbc5cdaa1499dd6aee017b2c33ea5d2fd3585afcb
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a328c9dba7f609bf83154e6380f5a4065921ba2889951d051233aeb5a023a13a
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.557544757033248,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1278772378516624,
14
+ "grad_norm": 0.15987633168697357,
15
+ "learning_rate": 1.9498721227621484e-05,
16
+ "loss": 0.0362,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.2557544757033248,
21
+ "grad_norm": 0.04608326032757759,
22
+ "learning_rate": 1.8987212276214835e-05,
23
+ "loss": 0.0168,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.3836317135549872,
28
+ "grad_norm": 0.03889036923646927,
29
+ "learning_rate": 1.8475703324808185e-05,
30
+ "loss": 0.0254,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.5115089514066496,
35
+ "grad_norm": 0.05562173202633858,
36
+ "learning_rate": 1.7964194373401536e-05,
37
+ "loss": 0.0502,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.639386189258312,
42
+ "grad_norm": 0.11458363384008408,
43
+ "learning_rate": 1.7452685421994886e-05,
44
+ "loss": 0.0353,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.7672634271099744,
49
+ "grad_norm": 0.0313524566590786,
50
+ "learning_rate": 1.6941176470588237e-05,
51
+ "loss": 0.0423,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.8951406649616368,
56
+ "grad_norm": 0.06919269263744354,
57
+ "learning_rate": 1.6429667519181587e-05,
58
+ "loss": 0.0414,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 1.0230179028132993,
63
+ "grad_norm": 0.04081420600414276,
64
+ "learning_rate": 1.5918158567774937e-05,
65
+ "loss": 0.0444,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 1.1508951406649617,
70
+ "grad_norm": 0.2047465294599533,
71
+ "learning_rate": 1.5406649616368288e-05,
72
+ "loss": 0.0103,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 1.278772378516624,
77
+ "grad_norm": 0.025791389867663383,
78
+ "learning_rate": 1.4895140664961638e-05,
79
+ "loss": 0.0209,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 1.4066496163682864,
84
+ "grad_norm": 0.9749135375022888,
85
+ "learning_rate": 1.4383631713554989e-05,
86
+ "loss": 0.0443,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 1.5345268542199488,
91
+ "grad_norm": 0.049570031464099884,
92
+ "learning_rate": 1.3872122762148339e-05,
93
+ "loss": 0.0334,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 1.6624040920716112,
98
+ "grad_norm": 0.03414261341094971,
99
+ "learning_rate": 1.336061381074169e-05,
100
+ "loss": 0.0263,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 1.7902813299232738,
105
+ "grad_norm": 0.05060505494475365,
106
+ "learning_rate": 1.284910485933504e-05,
107
+ "loss": 0.0324,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 1.918158567774936,
112
+ "grad_norm": 0.02642514370381832,
113
+ "learning_rate": 1.233759590792839e-05,
114
+ "loss": 0.0135,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 2.0460358056265986,
119
+ "grad_norm": 0.025779355317354202,
120
+ "learning_rate": 1.182608695652174e-05,
121
+ "loss": 0.0077,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 2.1739130434782608,
126
+ "grad_norm": 0.02975759282708168,
127
+ "learning_rate": 1.1314578005115091e-05,
128
+ "loss": 0.019,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 2.3017902813299234,
133
+ "grad_norm": 0.022426923736929893,
134
+ "learning_rate": 1.0803069053708442e-05,
135
+ "loss": 0.0122,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 2.4296675191815855,
140
+ "grad_norm": 0.02004999853670597,
141
+ "learning_rate": 1.0291560102301792e-05,
142
+ "loss": 0.0067,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 2.557544757033248,
147
+ "grad_norm": 0.01824093610048294,
148
+ "learning_rate": 9.78005115089514e-06,
149
+ "loss": 0.0266,
150
+ "step": 1000
151
+ }
152
+ ],
153
+ "logging_steps": 50,
154
+ "max_steps": 1955,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 5,
157
+ "save_steps": 500,
158
+ "stateful_callbacks": {
159
+ "TrainerControl": {
160
+ "args": {
161
+ "should_epoch_stop": false,
162
+ "should_evaluate": false,
163
+ "should_log": false,
164
+ "should_save": true,
165
+ "should_training_stop": false
166
+ },
167
+ "attributes": {}
168
+ }
169
+ },
170
+ "total_flos": 1.239096913937326e+18,
171
+ "train_batch_size": 16,
172
+ "trial_name": null,
173
+ "trial_params": null
174
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615105cb107136a134e557122fa967775525dec789d861404c226201990552bb
3
+ size 5713