Hugging Face's logo

Nothasan
/
Chessboard

Image Classification
Transformers
Safetensors
vit
vision
Generated from Trainer
Model card Files
xet
Community
Nothasan commited on
Commit
7f5c05f
·
verified ·
1 Parent(s): 62f80ee

Upload 16 files

Browse files
Files changed (16) hide show
  1. checkpoint-10000/config.json +55 -0
  2. checkpoint-10000/model.safetensors +3 -0
  3. checkpoint-10000/optimizer.pt +3 -0
  4. checkpoint-10000/preprocessor_config.json +36 -0
  5. checkpoint-10000/rng_state.pth +3 -0
  6. checkpoint-10000/scheduler.pt +3 -0
  7. checkpoint-10000/trainer_state.json +161 -0
  8. checkpoint-10000/training_args.bin +3 -0
  9. checkpoint-5000/config.json +55 -0
  10. checkpoint-5000/model.safetensors +3 -0
  11. checkpoint-5000/optimizer.pt +3 -0
  12. checkpoint-5000/preprocessor_config.json +36 -0
  13. checkpoint-5000/rng_state.pth +3 -0
  14. checkpoint-5000/scheduler.pt +3 -0
  15. checkpoint-5000/trainer_state.json +91 -0
  16. checkpoint-5000/training_args.bin +3 -0
checkpoint-10000/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "image-classification",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "bb",
14
+ "1": "bk",
15
+ "10": "wp",
16
+ "11": "wq",
17
+ "12": "wr",
18
+ "2": "bn",
19
+ "3": "bp",
20
+ "4": "bq",
21
+ "5": "br",
22
+ "6": "empty",
23
+ "7": "wb",
24
+ "8": "wk",
25
+ "9": "wn"
26
+ },
27
+ "image_size": 224,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "bb": "0",
32
+ "bk": "1",
33
+ "bn": "2",
34
+ "bp": "3",
35
+ "bq": "4",
36
+ "br": "5",
37
+ "empty": "6",
38
+ "wb": "7",
39
+ "wk": "8",
40
+ "wn": "9",
41
+ "wp": "10",
42
+ "wq": "11",
43
+ "wr": "12"
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "model_type": "vit",
47
+ "num_attention_heads": 12,
48
+ "num_channels": 3,
49
+ "num_hidden_layers": 12,
50
+ "patch_size": 16,
51
+ "problem_type": "single_label_classification",
52
+ "qkv_bias": true,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.40.2"
55
+ }
checkpoint-10000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4200bf8a43d782dcf17f7031061239f2a6e53e325f911ca2f729eef0864535
3
+ size 343257812
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75bc7fa0ecbe59eea3c408d98fccde814bba1abb20c4e382134bdddca349c244
3
+ size 686636474
checkpoint-10000/preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "resample": 2,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ce077cdf3c562715e032162388ff80bd70b116278b9fb62a46664bc272e7cb
3
+ size 14244
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614bb5d4e7ff89788d5fafe6c48afcb70252b2c49ca895620357dc0e92c50a5e
3
+ size 1064
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.29411764705882354,
5
+ "eval_steps": 500,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014705882352941176,
13
+ "grad_norm": 0.35731062293052673,
14
+ "learning_rate": 4.975490196078432e-05,
15
+ "loss": 0.5354,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.029411764705882353,
20
+ "grad_norm": 2.1595866680145264,
21
+ "learning_rate": 4.9509803921568634e-05,
22
+ "loss": 0.1627,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.04411764705882353,
27
+ "grad_norm": 0.14825384318828583,
28
+ "learning_rate": 4.9264705882352944e-05,
29
+ "loss": 0.101,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.058823529411764705,
34
+ "grad_norm": 0.07121703773736954,
35
+ "learning_rate": 4.901960784313725e-05,
36
+ "loss": 0.0952,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.07352941176470588,
41
+ "grad_norm": 0.06089532747864723,
42
+ "learning_rate": 4.877450980392157e-05,
43
+ "loss": 0.0881,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.08823529411764706,
48
+ "grad_norm": 0.037034619599580765,
49
+ "learning_rate": 4.8529411764705885e-05,
50
+ "loss": 0.0717,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.10294117647058823,
55
+ "grad_norm": 0.01999847963452339,
56
+ "learning_rate": 4.82843137254902e-05,
57
+ "loss": 0.0848,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.11764705882352941,
62
+ "grad_norm": 0.018650399520993233,
63
+ "learning_rate": 4.803921568627452e-05,
64
+ "loss": 0.068,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.1323529411764706,
69
+ "grad_norm": 0.023023229092359543,
70
+ "learning_rate": 4.7794117647058826e-05,
71
+ "loss": 0.0626,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.14705882352941177,
76
+ "grad_norm": 0.018715515732765198,
77
+ "learning_rate": 4.7549019607843135e-05,
78
+ "loss": 0.0555,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.16176470588235295,
83
+ "grad_norm": 0.11842140555381775,
84
+ "learning_rate": 4.730392156862745e-05,
85
+ "loss": 0.0658,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.17647058823529413,
90
+ "grad_norm": 0.04816881939768791,
91
+ "learning_rate": 4.705882352941177e-05,
92
+ "loss": 0.0648,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.19117647058823528,
97
+ "grad_norm": 0.025240018963813782,
98
+ "learning_rate": 4.681372549019608e-05,
99
+ "loss": 0.0632,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.20588235294117646,
104
+ "grad_norm": 0.007390766404569149,
105
+ "learning_rate": 4.656862745098039e-05,
106
+ "loss": 0.0705,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.22058823529411764,
111
+ "grad_norm": 0.011664963327348232,
112
+ "learning_rate": 4.632352941176471e-05,
113
+ "loss": 0.0552,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.23529411764705882,
118
+ "grad_norm": 39.69175720214844,
119
+ "learning_rate": 4.607843137254902e-05,
120
+ "loss": 0.0686,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.25,
125
+ "grad_norm": 0.007366931065917015,
126
+ "learning_rate": 4.5833333333333334e-05,
127
+ "loss": 0.061,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.2647058823529412,
132
+ "grad_norm": 0.003396671498194337,
133
+ "learning_rate": 4.558823529411765e-05,
134
+ "loss": 0.0464,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.27941176470588236,
139
+ "grad_norm": 0.045366521924734116,
140
+ "learning_rate": 4.5343137254901966e-05,
141
+ "loss": 0.053,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.29411764705882354,
146
+ "grad_norm": 1.137495756149292,
147
+ "learning_rate": 4.5098039215686275e-05,
148
+ "loss": 0.0484,
149
+ "step": 10000
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 102000,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 3,
156
+ "save_steps": 500,
157
+ "total_flos": 6.19997036101632e+18,
158
+ "train_batch_size": 8,
159
+ "trial_name": null,
160
+ "trial_params": null
161
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4d39b2c10c5bbc511dbb6611ec40b6fde59c4b12ef3b86a49c36eefffee464
3
+ size 4984
checkpoint-5000/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "image-classification",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "bb",
14
+ "1": "bk",
15
+ "10": "wp",
16
+ "11": "wq",
17
+ "12": "wr",
18
+ "2": "bn",
19
+ "3": "bp",
20
+ "4": "bq",
21
+ "5": "br",
22
+ "6": "empty",
23
+ "7": "wb",
24
+ "8": "wk",
25
+ "9": "wn"
26
+ },
27
+ "image_size": 224,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "bb": "0",
32
+ "bk": "1",
33
+ "bn": "2",
34
+ "bp": "3",
35
+ "bq": "4",
36
+ "br": "5",
37
+ "empty": "6",
38
+ "wb": "7",
39
+ "wk": "8",
40
+ "wn": "9",
41
+ "wp": "10",
42
+ "wq": "11",
43
+ "wr": "12"
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "model_type": "vit",
47
+ "num_attention_heads": 12,
48
+ "num_channels": 3,
49
+ "num_hidden_layers": 12,
50
+ "patch_size": 16,
51
+ "problem_type": "single_label_classification",
52
+ "qkv_bias": true,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.40.2"
55
+ }
checkpoint-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a00eabd5239de00bfb46a5dcdaaa0466d7efbc9635ab2f5070da8f44e90730
3
+ size 343257812
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f14e50a1ee46d42ec13c6e314a578c82bbe871e233b99c4d532b02275a4a57
3
+ size 686636474
checkpoint-5000/preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "resample": 2,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01768f6651c68282f36282ea1c5c759ca9758d5720de52b20928578feb55565
3
+ size 14244
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d4e0741b99e43f451379859fe83d61ce26d842dd82af6d89375cdee497301c
3
+ size 1064
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.14705882352941177,
5
+ "eval_steps": 500,
6
+ "global_step": 5000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014705882352941176,
13
+ "grad_norm": 0.35731062293052673,
14
+ "learning_rate": 4.975490196078432e-05,
15
+ "loss": 0.5354,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.029411764705882353,
20
+ "grad_norm": 2.1595866680145264,
21
+ "learning_rate": 4.9509803921568634e-05,
22
+ "loss": 0.1627,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.04411764705882353,
27
+ "grad_norm": 0.14825384318828583,
28
+ "learning_rate": 4.9264705882352944e-05,
29
+ "loss": 0.101,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.058823529411764705,
34
+ "grad_norm": 0.07121703773736954,
35
+ "learning_rate": 4.901960784313725e-05,
36
+ "loss": 0.0952,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.07352941176470588,
41
+ "grad_norm": 0.06089532747864723,
42
+ "learning_rate": 4.877450980392157e-05,
43
+ "loss": 0.0881,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.08823529411764706,
48
+ "grad_norm": 0.037034619599580765,
49
+ "learning_rate": 4.8529411764705885e-05,
50
+ "loss": 0.0717,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.10294117647058823,
55
+ "grad_norm": 0.01999847963452339,
56
+ "learning_rate": 4.82843137254902e-05,
57
+ "loss": 0.0848,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.11764705882352941,
62
+ "grad_norm": 0.018650399520993233,
63
+ "learning_rate": 4.803921568627452e-05,
64
+ "loss": 0.068,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.1323529411764706,
69
+ "grad_norm": 0.023023229092359543,
70
+ "learning_rate": 4.7794117647058826e-05,
71
+ "loss": 0.0626,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.14705882352941177,
76
+ "grad_norm": 0.018715515732765198,
77
+ "learning_rate": 4.7549019607843135e-05,
78
+ "loss": 0.0555,
79
+ "step": 5000
80
+ }
81
+ ],
82
+ "logging_steps": 500,
83
+ "max_steps": 102000,
84
+ "num_input_tokens_seen": 0,
85
+ "num_train_epochs": 3,
86
+ "save_steps": 500,
87
+ "total_flos": 3.09998518050816e+18,
88
+ "train_batch_size": 8,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4d39b2c10c5bbc511dbb6611ec40b6fde59c4b12ef3b86a49c36eefffee464
3
+ size 4984