Hugging Face's logo

Nadav
/
Pixel-real-scans-v2

Transformers
PyTorch
pixel
Model card Files
xet
 Community
Nadav commited on
Commit
27631c9
·
1 Parent(s): c041e8a

Training in progress, step 10000

Browse files
Files changed (12) hide show
  1. .gitignore +1 -0
  2. config.json +31 -0
  3. last-checkpoint/config.json +31 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scaler.pt +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/trainer_state.json +152 -0
  10. last-checkpoint/training_args.bin +3 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Nadav/PretrainedPHD-v2",
3
+ "architectures": [
4
+ "PIXELForPreTraining"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "decoder_hidden_size": 512,
8
+ "decoder_intermediate_size": 2048,
9
+ "decoder_num_attention_heads": 16,
10
+ "decoder_num_hidden_layers": 8,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "image_size": [
15
+ 368,
16
+ 368
17
+ ],
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "layer_norm_eps": 1e-12,
21
+ "mask_ratio": 0.25,
22
+ "model_type": "pixel",
23
+ "norm_pix_loss": true,
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "qkv_bias": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.17.0"
31
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Nadav/PretrainedPHD-v2",
3
+ "architectures": [
4
+ "PIXELForPreTraining"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "decoder_hidden_size": 512,
8
+ "decoder_intermediate_size": 2048,
9
+ "decoder_num_attention_heads": 16,
10
+ "decoder_num_hidden_layers": 8,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "image_size": [
15
+ 368,
16
+ 368
17
+ ],
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "layer_norm_eps": 1e-12,
21
+ "mask_ratio": 0.25,
22
+ "model_type": "pixel",
23
+ "norm_pix_loss": true,
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "qkv_bias": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.17.0"
31
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6efcea1f718e992622738eebec6655b308d8abaef61a2f7a2af6fa93b0ce7b9
3
+ size 893438545
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d606552814a4ba7950abd9e209968958ecfd2f24d817fd26ef28c35737c8054d
3
+ size 449471589
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c1cdccf174ece9de604197435ede54ec32a3b78eb6226070a07ab576a5585d
3
+ size 15523
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4ea5b486ac1940989e451ce41280116176be849f45b93fb6c79bbd63b9b878
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d524b4cb1391ef7e50966a3eef7ac714ecb6ed976eedf165d99a07d29c73b99
3
+ size 623
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.870852564660803,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 0.00010077565027123787,
13
+ "loss": 0.4732,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 0.00010075885246660077,
19
+ "loss": 0.4445,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.13,
24
+ "learning_rate": 0.00010073086073069567,
25
+ "loss": 0.4329,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.17,
30
+ "learning_rate": 0.0001006916819700645,
31
+ "loss": 0.4256,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.22,
36
+ "learning_rate": 0.0001006414377109213,
37
+ "loss": 0.421,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.26,
42
+ "learning_rate": 0.00010057993897463803,
43
+ "loss": 0.4167,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.3,
48
+ "learning_rate": 0.00010050729045131372,
49
+ "loss": 0.4132,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.35,
54
+ "learning_rate": 0.00010042351006588448,
55
+ "loss": 0.4107,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.39,
60
+ "learning_rate": 0.00010032861848990674,
61
+ "loss": 0.4091,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.44,
66
+ "learning_rate": 0.0001002228621438404,
67
+ "loss": 0.4067,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.44,
72
+ "eval_loss": 0.3877949118614197,
73
+ "eval_runtime": 108.0468,
74
+ "eval_samples_per_second": 46.276,
75
+ "eval_steps_per_second": 0.731,
76
+ "step": 5000
77
+ },
78
+ {
79
+ "epoch": 0.48,
80
+ "learning_rate": 0.00010010584325708389,
81
+ "loss": 0.4038,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 0.52,
86
+ "learning_rate": 9.997779155931062e-05,
87
+ "loss": 0.402,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 0.57,
92
+ "learning_rate": 9.983873864536092e-05,
93
+ "loss": 0.401,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 0.61,
98
+ "learning_rate": 9.968871882446063e-05,
99
+ "loss": 0.4001,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 0.65,
104
+ "learning_rate": 9.952776911175577e-05,
105
+ "loss": 0.3987,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 0.7,
110
+ "learning_rate": 9.935592921917959e-05,
111
+ "loss": 0.3974,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 0.74,
116
+ "learning_rate": 9.917361771757108e-05,
117
+ "loss": 0.3954,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 0.78,
122
+ "learning_rate": 9.898014889719868e-05,
123
+ "loss": 0.3945,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 0.83,
128
+ "learning_rate": 9.877592501404869e-05,
129
+ "loss": 0.394,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 0.87,
134
+ "learning_rate": 9.856099645730841e-05,
135
+ "loss": 0.3926,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 0.87,
140
+ "eval_loss": 0.37431180477142334,
141
+ "eval_runtime": 106.4392,
142
+ "eval_samples_per_second": 46.975,
143
+ "eval_steps_per_second": 0.742,
144
+ "step": 10000
145
+ }
146
+ ],
147
+ "max_steps": 100000,
148
+ "num_train_epochs": 9,
149
+ "total_flos": 4.709861347295232e+20,
150
+ "trial_name": null,
151
+ "trial_params": null
152
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd49a349d77c455473f49543bf6e96561e293025b2e65d9b3c90c0be2504db32
3
+ size 5615
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d606552814a4ba7950abd9e209968958ecfd2f24d817fd26ef28c35737c8054d
3
+ size 449471589
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd49a349d77c455473f49543bf6e96561e293025b2e65d9b3c90c0be2504db32
3
+ size 5615