Hugging Face's logo

Nadav
/
PretrainedPHD-v2-all-fonts

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
2
Nadav commited on
Commit
37431cb
•
1 Parent(s): f59762f

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",
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": 0.29,
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",
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": 0.29,
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 sha256:49caf2a8142fb9b42fc301fe94a96cb48e5d4a7756d24b9ce9d339d54621b980
3
+ size 893438545
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827789157924bfd064ba29cacb2c7224c28915242bf8bea1e463bc754d2563f6
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:bcb1f2f3c6553e6af410f9963404e0514ee3675be52a57f773532b5732d735e0
3
+ size 15587
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f62bcce8d52146d097fdece39d912efef3b4e3a86257c80e018dde2c80b6b15
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1128bd62a10e706988856b23de8560c19fdf360d436470289a55f4508a9d3fb8
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": 0.05,
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": 0.0,
12
+ "learning_rate": 0.00010077985004622052,
13
+ "loss": 0.5399,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.00010077565027123787,
19
+ "loss": 0.4951,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 0.00010076865093411392,
25
+ "loss": 0.487,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 0.00010075885246660077,
31
+ "loss": 0.4806,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 0.00010074625547311406,
37
+ "loss": 0.4778,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 0.00010073086073069567,
43
+ "loss": 0.4747,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "learning_rate": 0.00010071266918896582,
49
+ "loss": 0.4732,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.02,
54
+ "learning_rate": 0.0001006916819700645,
55
+ "loss": 0.4724,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.02,
60
+ "learning_rate": 0.00010066790036858225,
61
+ "loss": 0.4708,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.03,
66
+ "learning_rate": 0.00010064132585148025,
67
+ "loss": 0.4677,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.03,
72
+ "eval_loss": 0.4321456551551819,
73
+ "eval_runtime": 334.7353,
74
+ "eval_samples_per_second": 128.46,
75
+ "eval_steps_per_second": 2.008,
76
+ "step": 5000
77
+ },
78
+ {
79
+ "epoch": 0.03,
80
+ "learning_rate": 0.0001006119600579999,
81
+ "loss": 0.4673,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 0.03,
86
+ "learning_rate": 0.00010057980479956167,
87
+ "loss": 0.4649,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 0.03,
92
+ "learning_rate": 0.00010054486205965335,
93
+ "loss": 0.465,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 0.04,
98
+ "learning_rate": 0.00010050713399370776,
99
+ "loss": 0.4644,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 0.04,
104
+ "learning_rate": 0.00010046662292896969,
105
+ "loss": 0.4639,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 0.04,
110
+ "learning_rate": 0.00010042342072067417,
111
+ "loss": 0.4624,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 0.04,
116
+ "learning_rate": 0.00010037735687948529,
117
+ "loss": 0.463,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 0.04,
122
+ "learning_rate": 0.00010032851804476767,
123
+ "loss": 0.4606,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 0.05,
128
+ "learning_rate": 0.00010027690722913066,
129
+ "loss": 0.4595,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 0.05,
134
+ "learning_rate": 0.00010022263913645699,
135
+ "loss": 0.4605,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 0.05,
140
+ "eval_loss": 0.42437314987182617,
141
+ "eval_runtime": 366.557,
142
+ "eval_samples_per_second": 117.308,
143
+ "eval_steps_per_second": 1.833,
144
+ "step": 10000
145
+ }
146
+ ],
147
+ "max_steps": 200000,
148
+ "num_train_epochs": 9223372036854775807,
149
+ "total_flos": 2.354930673647616e+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:a2b52095507afa69b906349b3ac560fe415ed384ba5316ed57dd1ca6c585d042
3
+ size 5551
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827789157924bfd064ba29cacb2c7224c28915242bf8bea1e463bc754d2563f6
3
+ size 449471589
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b52095507afa69b906349b3ac560fe415ed384ba5316ed57dd1ca6c585d042
3
+ size 5551