Hugging Face's logo

2nzi
/
videomae-surf-analytics

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2nzi commited on
Commit
861f70b
·
verified ·
1 Parent(s): 1d5be31

Training in progress, epoch 0

Browse files
Files changed (9) hide show
  1. all_results.json +6 -6
  2. config.json +8 -4
  3. model.safetensors +2 -2
  4. runs/May16_18-59-46_MSI/events.out.tfevents.1715883082.MSI.22228.1 +2 -2
  5. runs/May16_21-50-47_MSI/events.out.tfevents.1715889052.MSI.22228.2 +3 -0
  6. runs/May17_01-25-40_MSI/events.out.tfevents.1715901945.MSI.2780.0 +3 -0
  7. test_results.json +6 -6
  8. trainer_state.json +98 -138
  9. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.22972972972973,
3
- "eval_accuracy": 0.6956521739130435,
4
- "eval_loss": 0.6255780458450317,
5
- "eval_runtime": 237.0624,
6
- "eval_samples_per_second": 0.291,
7
- "eval_steps_per_second": 0.076
8
  }
 
1
  {
2
+ "epoch": 1.4864864864864864,
3
+ "eval_accuracy": 0.5942028985507246,
4
+ "eval_loss": 0.6942497491836548,
5
+ "eval_runtime": 230.5496,
6
+ "eval_samples_per_second": 0.299,
7
+ "eval_steps_per_second": 0.078
8
  }
config.json CHANGED
@@ -12,15 +12,19 @@
12
  "hidden_dropout_prob": 0.0,
13
  "hidden_size": 768,
14
  "id2label": {
15
- "0": "cutback-frontside",
16
- "1": "roller"
 
 
17
  },
18
  "image_size": 224,
19
  "initializer_range": 0.02,
20
  "intermediate_size": 3072,
21
  "label2id": {
22
- "cutback-frontside": 0,
23
- "roller": 1
 
 
24
  },
25
  "layer_norm_eps": 1e-12,
26
  "model_type": "videomae",
 
12
  "hidden_dropout_prob": 0.0,
13
  "hidden_size": 768,
14
  "id2label": {
15
+ "0": "360",
16
+ "1": "cutback-frontside",
17
+ "2": "roller",
18
+ "3": "take-off"
19
  },
20
  "image_size": 224,
21
  "initializer_range": 0.02,
22
  "intermediate_size": 3072,
23
  "label2id": {
24
+ "360": 0,
25
+ "cutback-frontside": 1,
26
+ "roller": 2,
27
+ "take-off": 3
28
  },
29
  "layer_norm_eps": 1e-12,
30
  "model_type": "videomae",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d82b1e517ace738d4b2d76647cff44c0845a3bf614b8d6afa3ab588c620bc448
3
- size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af85c78b34aee269d970962ce4c41ddd8befc9506e1e39f8e38d8b1cffa4c060
3
+ size 344943528
runs/May16_18-59-46_MSI/events.out.tfevents.1715883082.MSI.22228.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85058443c0f7288d1374f6ad9f0c5ec3853069bbd7d5b191e63a1002a34a8201
3
- size 1356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8c518e08c2f05e791cd5955bd208d29dba35c6ae4cc95b626a15d6992ccb41
3
+ size 1673
runs/May16_21-50-47_MSI/events.out.tfevents.1715889052.MSI.22228.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0547263154d3528f80a85216eae79f7158dd3540c85c85fdf12bbfadc18f75
3
+ size 4951
runs/May17_01-25-40_MSI/events.out.tfevents.1715901945.MSI.2780.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8601cd6ea2789c01915a4cfc76ca8267595ae6337a7a66cd55813e51d0b3bd7f
3
+ size 9093
test_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.22972972972973,
3
- "eval_accuracy": 0.6956521739130435,
4
- "eval_loss": 0.6255780458450317,
5
- "eval_runtime": 237.0624,
6
- "eval_samples_per_second": 0.291,
7
- "eval_steps_per_second": 0.076
8
  }
 
1
  {
2
+ "epoch": 1.4864864864864864,
3
+ "eval_accuracy": 0.5942028985507246,
4
+ "eval_loss": 0.6942497491836548,
5
+ "eval_runtime": 230.5496,
6
+ "eval_samples_per_second": 0.299,
7
+ "eval_steps_per_second": 0.078
8
  }
trainer_state.json CHANGED
@@ -1,181 +1,141 @@
1
  {
2
- "best_metric": 0.6727272727272727,
3
- "best_model_checkpoint": "videomae-base-finetuned-2\\checkpoint-114",
4
- "epoch": 3.22972972972973,
5
  "eval_steps": 500,
6
- "global_step": 148,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.06756756756756757,
13
- "grad_norm": 10.621135711669922,
14
- "learning_rate": 3.3333333333333335e-05,
15
- "loss": 0.7046,
16
  "step": 10
17
  },
18
  {
19
- "epoch": 0.13513513513513514,
20
- "grad_norm": 15.56004524230957,
21
- "learning_rate": 4.81203007518797e-05,
22
- "loss": 0.6959,
23
  "step": 20
24
  },
25
  {
26
- "epoch": 0.20270270270270271,
27
- "grad_norm": 12.019503593444824,
28
- "learning_rate": 4.43609022556391e-05,
29
- "loss": 0.6924,
30
  "step": 30
31
  },
32
  {
33
- "epoch": 0.25675675675675674,
34
- "eval_accuracy": 0.5454545454545454,
35
- "eval_loss": 0.6671423316001892,
36
- "eval_runtime": 167.6467,
37
- "eval_samples_per_second": 0.328,
38
- "eval_steps_per_second": 0.084,
39
  "step": 38
40
  },
41
  {
42
- "epoch": 1.0135135135135136,
43
- "grad_norm": 5.8651123046875,
44
- "learning_rate": 4.0601503759398494e-05,
45
- "loss": 0.7766,
46
  "step": 40
47
  },
48
  {
49
- "epoch": 1.0810810810810811,
50
- "grad_norm": 4.48609733581543,
51
- "learning_rate": 3.6842105263157895e-05,
52
- "loss": 0.7431,
53
  "step": 50
54
  },
55
  {
56
- "epoch": 1.1486486486486487,
57
- "grad_norm": 17.070894241333008,
58
- "learning_rate": 3.3082706766917295e-05,
59
- "loss": 0.7388,
60
  "step": 60
61
  },
62
  {
63
- "epoch": 1.2162162162162162,
64
- "grad_norm": 5.109278678894043,
65
- "learning_rate": 2.9323308270676693e-05,
66
- "loss": 0.6664,
67
  "step": 70
68
  },
69
  {
70
- "epoch": 1.2567567567567568,
71
- "eval_accuracy": 0.6181818181818182,
72
- "eval_loss": 0.6748194694519043,
73
- "eval_runtime": 170.038,
74
- "eval_samples_per_second": 0.323,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  "eval_steps_per_second": 0.082,
76
- "step": 76
77
- },
78
- {
79
- "epoch": 2.027027027027027,
80
- "grad_norm": 8.704899787902832,
81
- "learning_rate": 2.556390977443609e-05,
82
- "loss": 0.7082,
83
- "step": 80
84
- },
85
- {
86
- "epoch": 2.0945945945945947,
87
- "grad_norm": 7.929505825042725,
88
- "learning_rate": 2.1804511278195487e-05,
89
- "loss": 0.6429,
90
- "step": 90
91
- },
92
- {
93
- "epoch": 2.1621621621621623,
94
- "grad_norm": 17.118267059326172,
95
- "learning_rate": 1.8045112781954888e-05,
96
- "loss": 0.8039,
97
- "step": 100
98
- },
99
- {
100
- "epoch": 2.22972972972973,
101
- "grad_norm": 7.988255500793457,
102
- "learning_rate": 1.4285714285714285e-05,
103
- "loss": 0.5947,
104
- "step": 110
105
- },
106
- {
107
- "epoch": 2.2567567567567566,
108
- "eval_accuracy": 0.6727272727272727,
109
- "eval_loss": 0.6094833612442017,
110
- "eval_runtime": 168.4773,
111
- "eval_samples_per_second": 0.326,
112
- "eval_steps_per_second": 0.083,
113
- "step": 114
114
- },
115
- {
116
- "epoch": 3.0405405405405403,
117
- "grad_norm": 7.859794616699219,
118
- "learning_rate": 1.0526315789473684e-05,
119
- "loss": 0.5892,
120
- "step": 120
121
- },
122
- {
123
- "epoch": 3.108108108108108,
124
- "grad_norm": 12.87205982208252,
125
- "learning_rate": 6.766917293233083e-06,
126
- "loss": 0.5001,
127
- "step": 130
128
- },
129
- {
130
- "epoch": 3.175675675675676,
131
- "grad_norm": 13.842416763305664,
132
- "learning_rate": 3.007518796992481e-06,
133
- "loss": 0.5049,
134
- "step": 140
135
- },
136
- {
137
- "epoch": 3.22972972972973,
138
- "eval_accuracy": 0.6181818181818182,
139
- "eval_loss": 0.6914771199226379,
140
- "eval_runtime": 166.1396,
141
- "eval_samples_per_second": 0.331,
142
- "eval_steps_per_second": 0.084,
143
- "step": 148
144
- },
145
- {
146
- "epoch": 3.22972972972973,
147
- "step": 148,
148
- "total_flos": 7.264556556620268e+17,
149
- "train_loss": 0.6650454998016357,
150
- "train_runtime": 4992.096,
151
- "train_samples_per_second": 0.119,
152
- "train_steps_per_second": 0.03
153
- },
154
- {
155
- "epoch": 3.22972972972973,
156
- "eval_accuracy": 0.6956521739130435,
157
- "eval_loss": 0.6255781054496765,
158
- "eval_runtime": 189.5334,
159
- "eval_samples_per_second": 0.364,
160
- "eval_steps_per_second": 0.095,
161
- "step": 148
162
  },
163
  {
164
- "epoch": 3.22972972972973,
165
- "eval_accuracy": 0.6956521739130435,
166
- "eval_loss": 0.6255780458450317,
167
- "eval_runtime": 237.0624,
168
- "eval_samples_per_second": 0.291,
169
- "eval_steps_per_second": 0.076,
170
- "step": 148
171
  }
172
  ],
173
  "logging_steps": 10,
174
- "max_steps": 148,
175
  "num_input_tokens_seen": 0,
176
  "num_train_epochs": 9223372036854775807,
177
  "save_steps": 500,
178
- "total_flos": 7.264556556620268e+17,
179
  "train_batch_size": 4,
180
  "trial_name": null,
181
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6363636363636364,
3
+ "best_model_checkpoint": "videomae-base-finetuned-2\\checkpoint-74",
4
+ "epoch": 1.4864864864864864,
5
  "eval_steps": 500,
6
+ "global_step": 74,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.13513513513513514,
13
+ "grad_norm": 13.06977367401123,
14
+ "learning_rate": 4.848484848484849e-05,
15
+ "loss": 0.7158,
16
  "step": 10
17
  },
18
  {
19
+ "epoch": 0.2702702702702703,
20
+ "grad_norm": 11.546745300292969,
21
+ "learning_rate": 4.0909090909090915e-05,
22
+ "loss": 0.6967,
23
  "step": 20
24
  },
25
  {
26
+ "epoch": 0.40540540540540543,
27
+ "grad_norm": 13.410033226013184,
28
+ "learning_rate": 3.3333333333333335e-05,
29
+ "loss": 0.6252,
30
  "step": 30
31
  },
32
  {
33
+ "epoch": 0.5135135135135135,
34
+ "eval_accuracy": 0.6181818181818182,
35
+ "eval_loss": 0.6595810055732727,
36
+ "eval_runtime": 150.5547,
37
+ "eval_samples_per_second": 0.365,
38
+ "eval_steps_per_second": 0.093,
39
  "step": 38
40
  },
41
  {
42
+ "epoch": 1.027027027027027,
43
+ "grad_norm": 6.076575756072998,
44
+ "learning_rate": 2.575757575757576e-05,
45
+ "loss": 0.6072,
46
  "step": 40
47
  },
48
  {
49
+ "epoch": 1.1621621621621623,
50
+ "grad_norm": 2.566138982772827,
51
+ "learning_rate": 1.8181818181818182e-05,
52
+ "loss": 0.5134,
53
  "step": 50
54
  },
55
  {
56
+ "epoch": 1.2972972972972974,
57
+ "grad_norm": 14.576709747314453,
58
+ "learning_rate": 1.0606060606060607e-05,
59
+ "loss": 0.4588,
60
  "step": 60
61
  },
62
  {
63
+ "epoch": 1.4324324324324325,
64
+ "grad_norm": 22.475860595703125,
65
+ "learning_rate": 3.0303030303030305e-06,
66
+ "loss": 0.5187,
67
  "step": 70
68
  },
69
  {
70
+ "epoch": 1.4864864864864864,
71
+ "eval_accuracy": 0.6363636363636364,
72
+ "eval_loss": 0.7526556253433228,
73
+ "eval_runtime": 149.6048,
74
+ "eval_samples_per_second": 0.368,
75
+ "eval_steps_per_second": 0.094,
76
+ "step": 74
77
+ },
78
+ {
79
+ "epoch": 1.4864864864864864,
80
+ "step": 74,
81
+ "total_flos": 3.65096924715221e+17,
82
+ "train_loss": 0.5808639623023368,
83
+ "train_runtime": 2222.6393,
84
+ "train_samples_per_second": 0.133,
85
+ "train_steps_per_second": 0.033
86
+ },
87
+ {
88
+ "epoch": 1.4864864864864864,
89
+ "eval_accuracy": 0.8322147651006712,
90
+ "eval_loss": 0.3304717242717743,
91
+ "eval_runtime": 358.1284,
92
+ "eval_samples_per_second": 0.416,
93
+ "eval_steps_per_second": 0.106,
94
+ "step": 74
95
+ },
96
+ {
97
+ "epoch": 1.4864864864864864,
98
+ "eval_accuracy": 0.5942028985507246,
99
+ "eval_loss": 0.6942497491836548,
100
+ "eval_runtime": 179.9904,
101
+ "eval_samples_per_second": 0.383,
102
+ "eval_steps_per_second": 0.1,
103
+ "step": 74
104
+ },
105
+ {
106
+ "epoch": 1.4864864864864864,
107
+ "eval_accuracy": 0.6363636363636364,
108
+ "eval_loss": 0.7526556253433228,
109
+ "eval_runtime": 136.5776,
110
+ "eval_samples_per_second": 0.403,
111
+ "eval_steps_per_second": 0.103,
112
+ "step": 74
113
+ },
114
+ {
115
+ "epoch": 1.4864864864864864,
116
+ "eval_accuracy": 0.6363636363636364,
117
+ "eval_loss": 0.752655565738678,
118
+ "eval_runtime": 171.0609,
119
+ "eval_samples_per_second": 0.322,
120
  "eval_steps_per_second": 0.082,
121
+ "step": 74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
122
  },
123
  {
124
+ "epoch": 1.4864864864864864,
125
+ "eval_accuracy": 0.5942028985507246,
126
+ "eval_loss": 0.6942497491836548,
127
+ "eval_runtime": 230.5496,
128
+ "eval_samples_per_second": 0.299,
129
+ "eval_steps_per_second": 0.078,
130
+ "step": 74
131
  }
132
  ],
133
  "logging_steps": 10,
134
+ "max_steps": 74,
135
  "num_input_tokens_seen": 0,
136
  "num_train_epochs": 9223372036854775807,
137
  "save_steps": 500,
138
+ "total_flos": 3.65096924715221e+17,
139
  "train_batch_size": 4,
140
  "trial_name": null,
141
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:498bb098c9e8befc320966c8d6858e42030b47f82ab4d7282188f2c749102de0
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99430f942125dacb32fad24aa279c4516536bd138df92cf1268d99fde0fca48b
3
  size 4984