Transformers
PyTorch
English
pixel
pretraining
Inference Endpoints
plip commited on
Commit
59d4c08
1 Parent(s): bfcfee6

Training in progress, step 10000

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ GoNotoCurrent.ttf filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
GoNotoCurrent.ttf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
3
+ size 15645492
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PIXELForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "decoder_hidden_size": 512,
7
+ "decoder_intermediate_size": 2048,
8
+ "decoder_num_attention_heads": 16,
9
+ "decoder_num_hidden_layers": 8,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "image_size": [
14
+ 16,
15
+ 8464
16
+ ],
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "mask_ratio": 0.25,
21
+ "model_type": "vit_mae",
22
+ "norm_pix_loss": true,
23
+ "num_attention_heads": 12,
24
+ "num_channels": 3,
25
+ "num_hidden_layers": 12,
26
+ "patch_size": 16,
27
+ "qkv_bias": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.17.0"
30
+ }
last-checkpoint/GoNotoCurrent.ttf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
3
+ size 15645492
last-checkpoint/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PIXELForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "decoder_hidden_size": 512,
7
+ "decoder_intermediate_size": 2048,
8
+ "decoder_num_attention_heads": 16,
9
+ "decoder_num_hidden_layers": 8,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "image_size": [
14
+ 16,
15
+ 8464
16
+ ],
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "mask_ratio": 0.25,
21
+ "model_type": "vit_mae",
22
+ "norm_pix_loss": true,
23
+ "num_attention_heads": 12,
24
+ "num_channels": 3,
25
+ "num_hidden_layers": 12,
26
+ "patch_size": 16,
27
+ "qkv_bias": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.17.0"
30
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe1d41121841968447fb336aa28dad25e27dfce742d86e1935552b3a3998fb5
3
+ size 893438545
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d50de73a4b582cc8e43ba0dc54bd470d8cfebded4bc8970956d7cb2d7b0bb31
3
+ size 449471589
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421ae58579f35a00b2415a99cc4838648a03b2fb7fbf0cbc43e22a2df53a9294
3
+ size 14503
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1574767755dbd61dd0f433ae03acfecc74b044e733d9e19d81e1b7b3c223a756
3
+ size 14567
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6a123211cdfaa0afcef7dc225a0ff70c9dd0eeebb385ff55185cd69fa7f690
3
+ size 14503
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bcf5239d9ebda8ce1bd9bba4a25957fe0de3f636d2c412ad5ce7a3755b39cb8
3
+ size 14503
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6647dd16e16d38ed2bd48d2720f065055b2d402dd5cc12bc5f1fbd386132f2a
3
+ size 623
last-checkpoint/text_renderer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": "white",
3
+ "dpi": 120,
4
+ "font_color": "black",
5
+ "font_file": "GoNotoCurrent.ttf",
6
+ "font_size": 8,
7
+ "max_seq_length": 529,
8
+ "pad_size": 3,
9
+ "pixels_per_patch": 16,
10
+ "text_renderer_type": "TextRenderer"
11
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.15270206300487119,
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": 0.02,
12
+ "learning_rate": 2.9999999999999997e-06,
13
+ "loss": 0.8784,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 5.999999999999999e-06,
19
+ "loss": 0.77,
20
+ "step": 2000
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 8.999999999999999e-06,
25
+ "loss": 0.7664,
26
+ "step": 3000
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 1.1999999999999999e-05,
31
+ "loss": 0.7655,
32
+ "step": 4000
33
+ },
34
+ {
35
+ "epoch": 0.08,
36
+ "learning_rate": 1.4999999999999999e-05,
37
+ "loss": 0.765,
38
+ "step": 5000
39
+ },
40
+ {
41
+ "epoch": 0.08,
42
+ "eval_runtime": 1.3797,
43
+ "eval_samples_per_second": 724.791,
44
+ "eval_steps_per_second": 11.597,
45
+ "step": 5000
46
+ },
47
+ {
48
+ "epoch": 0.09,
49
+ "learning_rate": 1.7999999999999997e-05,
50
+ "loss": 0.7647,
51
+ "step": 6000
52
+ },
53
+ {
54
+ "epoch": 0.11,
55
+ "learning_rate": 2.1e-05,
56
+ "loss": 0.7644,
57
+ "step": 7000
58
+ },
59
+ {
60
+ "epoch": 0.12,
61
+ "learning_rate": 2.3999999999999997e-05,
62
+ "loss": 0.7638,
63
+ "step": 8000
64
+ },
65
+ {
66
+ "epoch": 0.14,
67
+ "learning_rate": 2.6999999999999996e-05,
68
+ "loss": 0.7633,
69
+ "step": 9000
70
+ },
71
+ {
72
+ "epoch": 0.15,
73
+ "learning_rate": 2.9999999999999997e-05,
74
+ "loss": 0.76,
75
+ "step": 10000
76
+ },
77
+ {
78
+ "epoch": 0.15,
79
+ "eval_runtime": 1.1376,
80
+ "eval_samples_per_second": 879.066,
81
+ "eval_steps_per_second": 14.065,
82
+ "step": 10000
83
+ }
84
+ ],
85
+ "max_steps": 1000000,
86
+ "num_train_epochs": 16,
87
+ "total_flos": 7.010026103034715e+20,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdc190c32c2fc157093936156e63e0f60bf6e1f2fe248e7ec37847891ea89ae
3
+ size 3183
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d50de73a4b582cc8e43ba0dc54bd470d8cfebded4bc8970956d7cb2d7b0bb31
3
+ size 449471589
text_renderer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": "white",
3
+ "dpi": 120,
4
+ "font_color": "black",
5
+ "font_file": "GoNotoCurrent.ttf",
6
+ "font_size": 8,
7
+ "max_seq_length": 529,
8
+ "pad_size": 3,
9
+ "pixels_per_patch": 16,
10
+ "text_renderer_type": "TextRenderer"
11
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdc190c32c2fc157093936156e63e0f60bf6e1f2fe248e7ec37847891ea89ae
3
+ size 3183