Hugging Face's logo

heyitsjearbear
/
moldy-strawberries

Image Classification
Transformers
Safetensors
vit
Inference Endpoints
Model card Files Community
6
heyitsjearbear commited on
Commit
d3c42a7
•
1 Parent(s): 91e4067

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. all_results.json +8 -0
  2. checkpoint-120/config.json +32 -0
  3. checkpoint-120/model.safetensors +3 -0
  4. checkpoint-120/optimizer.pt +3 -0
  5. checkpoint-120/preprocessor_config.json +36 -0
  6. checkpoint-120/rng_state.pth +3 -0
  7. checkpoint-120/scheduler.pt +3 -0
  8. checkpoint-120/trainer_state.json +132 -0
  9. checkpoint-120/training_args.bin +3 -0
  10. checkpoint-160/config.json +32 -0
  11. checkpoint-160/model.safetensors +3 -0
  12. checkpoint-160/optimizer.pt +3 -0
  13. checkpoint-160/preprocessor_config.json +36 -0
  14. checkpoint-160/rng_state.pth +3 -0
  15. checkpoint-160/scheduler.pt +3 -0
  16. checkpoint-160/trainer_state.json +169 -0
  17. checkpoint-160/training_args.bin +3 -0
  18. config.json +32 -0
  19. model.safetensors +3 -0
  20. preprocessor_config.json +36 -0
  21. train_results.json +8 -0
  22. trainer_state.json +178 -0
  23. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 32.0,
3
+ "total_flos": 1.8350103140735386e+17,
4
+ "train_loss": 0.03308067205362022,
5
+ "train_runtime": 121.1399,
6
+ "train_samples_per_second": 19.548,
7
+ "train_steps_per_second": 1.321
8
+ }
checkpoint-120/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "mold",
13
+ "1": "non-mold"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "mold": "0",
20
+ "non-mold": "1"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.40.1"
32
+ }
checkpoint-120/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8957d0a669550e5402b43df5e7727b6ddc09e4784fe83eec8b0c3afe5486bda1
3
+ size 343223968
checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64723caebe47a46d2229b0824556e27b48cb37973a53fc3462e1861f5a4973fe
3
+ size 686568890
checkpoint-120/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": "ViTFeatureExtractor",
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-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3bd3cafcd141485c5526689e7070ba65dab1e4639fbae44141ae41439003c1f
3
+ size 14244
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e330a80cd73509e4d36a2e26bc84533f25e1b9420ada1a46870d473f74e7d8
3
+ size 1064
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.018665345385670662,
3
+ "best_model_checkpoint": "./vit-strawberries/checkpoint-120",
4
+ "epoch": 24.0,
5
+ "eval_steps": 40,
6
+ "global_step": 120,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.0,
13
+ "grad_norm": 0.6030758023262024,
14
+ "learning_rate": 0.0001875,
15
+ "loss": 0.3813,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 4.0,
20
+ "grad_norm": 0.19357694685459137,
21
+ "learning_rate": 0.000175,
22
+ "loss": 0.0627,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 6.0,
27
+ "grad_norm": 0.09823369234800339,
28
+ "learning_rate": 0.00016250000000000002,
29
+ "loss": 0.0166,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 8.0,
34
+ "grad_norm": 0.06956500560045242,
35
+ "learning_rate": 0.00015000000000000001,
36
+ "loss": 0.0102,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 8.0,
41
+ "eval_accuracy": 1.0,
42
+ "eval_loss": 0.021412454545497894,
43
+ "eval_runtime": 0.4006,
44
+ "eval_samples_per_second": 64.901,
45
+ "eval_steps_per_second": 9.985,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 10.0,
50
+ "grad_norm": 0.059710320085287094,
51
+ "learning_rate": 0.0001375,
52
+ "loss": 0.0078,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 12.0,
57
+ "grad_norm": 0.04971468821167946,
58
+ "learning_rate": 0.000125,
59
+ "loss": 0.0065,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 14.0,
64
+ "grad_norm": 0.044971030205488205,
65
+ "learning_rate": 0.00011250000000000001,
66
+ "loss": 0.0058,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 16.0,
71
+ "grad_norm": 0.04283370077610016,
72
+ "learning_rate": 0.0001,
73
+ "loss": 0.0052,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 16.0,
78
+ "eval_accuracy": 1.0,
79
+ "eval_loss": 0.019078843295574188,
80
+ "eval_runtime": 0.4188,
81
+ "eval_samples_per_second": 62.087,
82
+ "eval_steps_per_second": 9.552,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 18.0,
87
+ "grad_norm": 0.03907443583011627,
88
+ "learning_rate": 8.75e-05,
89
+ "loss": 0.0048,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 20.0,
94
+ "grad_norm": 0.03701604902744293,
95
+ "learning_rate": 7.500000000000001e-05,
96
+ "loss": 0.0045,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 22.0,
101
+ "grad_norm": 0.03528870269656181,
102
+ "learning_rate": 6.25e-05,
103
+ "loss": 0.0043,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 24.0,
108
+ "grad_norm": 0.033964332193136215,
109
+ "learning_rate": 5e-05,
110
+ "loss": 0.0041,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 24.0,
115
+ "eval_accuracy": 1.0,
116
+ "eval_loss": 0.018665345385670662,
117
+ "eval_runtime": 0.4061,
118
+ "eval_samples_per_second": 64.02,
119
+ "eval_steps_per_second": 9.849,
120
+ "step": 120
121
+ }
122
+ ],
123
+ "logging_steps": 10,
124
+ "max_steps": 160,
125
+ "num_input_tokens_seen": 0,
126
+ "num_train_epochs": 32,
127
+ "save_steps": 40,
128
+ "total_flos": 1.376257735555154e+17,
129
+ "train_batch_size": 16,
130
+ "trial_name": null,
131
+ "trial_params": null
132
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb496ae4ef9baef4da454a5aeb81107fc1c8c5186e0e0e4558b603478a5db94
3
+ size 4984
checkpoint-160/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "mold",
13
+ "1": "non-mold"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "mold": "0",
20
+ "non-mold": "1"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.40.1"
32
+ }
checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2dec449c03a6a4a335f6706b8121a11f67349c62f865dc61bebeab88fcc1f9d
3
+ size 343223968
checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5058d92612251a9c59fb5caa74cdf04a9cf374e124467191f87f6175c4207b
3
+ size 686568890
checkpoint-160/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": "ViTFeatureExtractor",
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-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86f749dc73bc16a2502fef2f98f5c00b4400cb2c67fbe62653b7ed104d13779
3
+ size 14244
checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec82b88d9fc1851330cce56bddf8838806450e0dcb4ecdc26493c05dc810338d
3
+ size 1064
checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.018665345385670662,
3
+ "best_model_checkpoint": "./vit-strawberries/checkpoint-120",
4
+ "epoch": 32.0,
5
+ "eval_steps": 40,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.0,
13
+ "grad_norm": 0.6030758023262024,
14
+ "learning_rate": 0.0001875,
15
+ "loss": 0.3813,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 4.0,
20
+ "grad_norm": 0.19357694685459137,
21
+ "learning_rate": 0.000175,
22
+ "loss": 0.0627,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 6.0,
27
+ "grad_norm": 0.09823369234800339,
28
+ "learning_rate": 0.00016250000000000002,
29
+ "loss": 0.0166,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 8.0,
34
+ "grad_norm": 0.06956500560045242,
35
+ "learning_rate": 0.00015000000000000001,
36
+ "loss": 0.0102,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 8.0,
41
+ "eval_accuracy": 1.0,
42
+ "eval_loss": 0.021412454545497894,
43
+ "eval_runtime": 0.4006,
44
+ "eval_samples_per_second": 64.901,
45
+ "eval_steps_per_second": 9.985,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 10.0,
50
+ "grad_norm": 0.059710320085287094,
51
+ "learning_rate": 0.0001375,
52
+ "loss": 0.0078,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 12.0,
57
+ "grad_norm": 0.04971468821167946,
58
+ "learning_rate": 0.000125,
59
+ "loss": 0.0065,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 14.0,
64
+ "grad_norm": 0.044971030205488205,
65
+ "learning_rate": 0.00011250000000000001,
66
+ "loss": 0.0058,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 16.0,
71
+ "grad_norm": 0.04283370077610016,
72
+ "learning_rate": 0.0001,
73
+ "loss": 0.0052,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 16.0,
78
+ "eval_accuracy": 1.0,
79
+ "eval_loss": 0.019078843295574188,
80
+ "eval_runtime": 0.4188,
81
+ "eval_samples_per_second": 62.087,
82
+ "eval_steps_per_second": 9.552,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 18.0,
87
+ "grad_norm": 0.03907443583011627,
88
+ "learning_rate": 8.75e-05,
89
+ "loss": 0.0048,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 20.0,
94
+ "grad_norm": 0.03701604902744293,
95
+ "learning_rate": 7.500000000000001e-05,
96
+ "loss": 0.0045,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 22.0,
101
+ "grad_norm": 0.03528870269656181,
102
+ "learning_rate": 6.25e-05,
103
+ "loss": 0.0043,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 24.0,
108
+ "grad_norm": 0.033964332193136215,
109
+ "learning_rate": 5e-05,
110
+ "loss": 0.0041,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 24.0,
115
+ "eval_accuracy": 1.0,
116
+ "eval_loss": 0.018665345385670662,
117
+ "eval_runtime": 0.4061,
118
+ "eval_samples_per_second": 64.02,
119
+ "eval_steps_per_second": 9.849,
120
+ "step": 120
121
+ },
122
+ {
123
+ "epoch": 26.0,
124
+ "grad_norm": 0.03315058350563049,
125
+ "learning_rate": 3.7500000000000003e-05,
126
+ "loss": 0.004,
127
+ "step": 130
128
+ },
129
+ {
130
+ "epoch": 28.0,
131
+ "grad_norm": 0.031990278512239456,
132
+ "learning_rate": 2.5e-05,
133
+ "loss": 0.0039,
134
+ "step": 140
135
+ },
136
+ {
137
+ "epoch": 30.0,
138
+ "grad_norm": 0.031738851219415665,
139
+ "learning_rate": 1.25e-05,
140
+ "loss": 0.0038,
141
+ "step": 150
142
+ },
143
+ {
144
+ "epoch": 32.0,
145
+ "grad_norm": 0.03203798457980156,
146
+ "learning_rate": 0.0,
147
+ "loss": 0.0038,
148
+ "step": 160
149
+ },
150
+ {
151
+ "epoch": 32.0,
152
+ "eval_accuracy": 1.0,
153
+ "eval_loss": 0.01877218298614025,
154
+ "eval_runtime": 0.485,
155
+ "eval_samples_per_second": 53.611,
156
+ "eval_steps_per_second": 8.248,
157
+ "step": 160
158
+ }
159
+ ],
160
+ "logging_steps": 10,
161
+ "max_steps": 160,
162
+ "num_input_tokens_seen": 0,
163
+ "num_train_epochs": 32,
164
+ "save_steps": 40,
165
+ "total_flos": 1.8350103140735386e+17,
166
+ "train_batch_size": 16,
167
+ "trial_name": null,
168
+ "trial_params": null
169
+ }
checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb496ae4ef9baef4da454a5aeb81107fc1c8c5186e0e0e4558b603478a5db94
3
+ size 4984
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "mold",
13
+ "1": "non-mold"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "mold": "0",
20
+ "non-mold": "1"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.40.1"
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8957d0a669550e5402b43df5e7727b6ddc09e4784fe83eec8b0c3afe5486bda1
3
+ size 343223968
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": "ViTFeatureExtractor",
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
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 32.0,
3
+ "total_flos": 1.8350103140735386e+17,
4
+ "train_loss": 0.03308067205362022,
5
+ "train_runtime": 121.1399,
6
+ "train_samples_per_second": 19.548,
7
+ "train_steps_per_second": 1.321
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.018665345385670662,
3
+ "best_model_checkpoint": "./vit-strawberries/checkpoint-120",
4
+ "epoch": 32.0,
5
+ "eval_steps": 40,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.0,
13
+ "grad_norm": 0.6030758023262024,
14
+ "learning_rate": 0.0001875,
15
+ "loss": 0.3813,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 4.0,
20
+ "grad_norm": 0.19357694685459137,
21
+ "learning_rate": 0.000175,
22
+ "loss": 0.0627,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 6.0,
27
+ "grad_norm": 0.09823369234800339,
28
+ "learning_rate": 0.00016250000000000002,
29
+ "loss": 0.0166,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 8.0,
34
+ "grad_norm": 0.06956500560045242,
35
+ "learning_rate": 0.00015000000000000001,
36
+ "loss": 0.0102,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 8.0,
41
+ "eval_accuracy": 1.0,
42
+ "eval_loss": 0.021412454545497894,
43
+ "eval_runtime": 0.4006,
44
+ "eval_samples_per_second": 64.901,
45
+ "eval_steps_per_second": 9.985,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 10.0,
50
+ "grad_norm": 0.059710320085287094,
51
+ "learning_rate": 0.0001375,
52
+ "loss": 0.0078,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 12.0,
57
+ "grad_norm": 0.04971468821167946,
58
+ "learning_rate": 0.000125,
59
+ "loss": 0.0065,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 14.0,
64
+ "grad_norm": 0.044971030205488205,
65
+ "learning_rate": 0.00011250000000000001,
66
+ "loss": 0.0058,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 16.0,
71
+ "grad_norm": 0.04283370077610016,
72
+ "learning_rate": 0.0001,
73
+ "loss": 0.0052,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 16.0,
78
+ "eval_accuracy": 1.0,
79
+ "eval_loss": 0.019078843295574188,
80
+ "eval_runtime": 0.4188,
81
+ "eval_samples_per_second": 62.087,
82
+ "eval_steps_per_second": 9.552,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 18.0,
87
+ "grad_norm": 0.03907443583011627,
88
+ "learning_rate": 8.75e-05,
89
+ "loss": 0.0048,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 20.0,
94
+ "grad_norm": 0.03701604902744293,
95
+ "learning_rate": 7.500000000000001e-05,
96
+ "loss": 0.0045,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 22.0,
101
+ "grad_norm": 0.03528870269656181,
102
+ "learning_rate": 6.25e-05,
103
+ "loss": 0.0043,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 24.0,
108
+ "grad_norm": 0.033964332193136215,
109
+ "learning_rate": 5e-05,
110
+ "loss": 0.0041,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 24.0,
115
+ "eval_accuracy": 1.0,
116
+ "eval_loss": 0.018665345385670662,
117
+ "eval_runtime": 0.4061,
118
+ "eval_samples_per_second": 64.02,
119
+ "eval_steps_per_second": 9.849,
120
+ "step": 120
121
+ },
122
+ {
123
+ "epoch": 26.0,
124
+ "grad_norm": 0.03315058350563049,
125
+ "learning_rate": 3.7500000000000003e-05,
126
+ "loss": 0.004,
127
+ "step": 130
128
+ },
129
+ {
130
+ "epoch": 28.0,
131
+ "grad_norm": 0.031990278512239456,
132
+ "learning_rate": 2.5e-05,
133
+ "loss": 0.0039,
134
+ "step": 140
135
+ },
136
+ {
137
+ "epoch": 30.0,
138
+ "grad_norm": 0.031738851219415665,
139
+ "learning_rate": 1.25e-05,
140
+ "loss": 0.0038,
141
+ "step": 150
142
+ },
143
+ {
144
+ "epoch": 32.0,
145
+ "grad_norm": 0.03203798457980156,
146
+ "learning_rate": 0.0,
147
+ "loss": 0.0038,
148
+ "step": 160
149
+ },
150
+ {
151
+ "epoch": 32.0,
152
+ "eval_accuracy": 1.0,
153
+ "eval_loss": 0.01877218298614025,
154
+ "eval_runtime": 0.485,
155
+ "eval_samples_per_second": 53.611,
156
+ "eval_steps_per_second": 8.248,
157
+ "step": 160
158
+ },
159
+ {
160
+ "epoch": 32.0,
161
+ "step": 160,
162
+ "total_flos": 1.8350103140735386e+17,
163
+ "train_loss": 0.03308067205362022,
164
+ "train_runtime": 121.1399,
165
+ "train_samples_per_second": 19.548,
166
+ "train_steps_per_second": 1.321
167
+ }
168
+ ],
169
+ "logging_steps": 10,
170
+ "max_steps": 160,
171
+ "num_input_tokens_seen": 0,
172
+ "num_train_epochs": 32,
173
+ "save_steps": 40,
174
+ "total_flos": 1.8350103140735386e+17,
175
+ "train_batch_size": 16,
176
+ "trial_name": null,
177
+ "trial_params": null
178
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb496ae4ef9baef4da454a5aeb81107fc1c8c5186e0e0e4558b603478a5db94
3
+ size 4984