Hugging Face's logo

minhah
/
vivit-b-16x2-kinetics400-finetuned-ucf101-subset

Video Classification
Transformers
Safetensors
vivit
Generated from Trainer
Inference Endpoints
Model card Files Community
minhah commited on
Commit
48de180
•
1 Parent(s): 7fbe5ca

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. test_results.json +8 -0
  3. trainer_state.json +182 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.23,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.2172325998544693,
5
+ "eval_runtime": 199.0471,
6
+ "eval_samples_per_second": 0.437,
7
+ "eval_steps_per_second": 0.055
8
+ }
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.23,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.2172325998544693,
5
+ "eval_runtime": 199.0471,
6
+ "eval_samples_per_second": 0.437,
7
+ "eval_steps_per_second": 0.055
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "vivit-b-16x2-kinetics400-finetuned-ucf101-subset/checkpoint-38",
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": 0.07,
13
+ "grad_norm": 11.20502758026123,
14
+ "learning_rate": 3.3333333333333335e-05,
15
+ "loss": 2.4387,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.14,
20
+ "grad_norm": 7.179543495178223,
21
+ "learning_rate": 4.81203007518797e-05,
22
+ "loss": 1.4999,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.2,
27
+ "grad_norm": 5.833919525146484,
28
+ "learning_rate": 4.43609022556391e-05,
29
+ "loss": 0.7382,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.26,
34
+ "eval_accuracy": 1.0,
35
+ "eval_loss": 0.2207001894712448,
36
+ "eval_runtime": 85.8262,
37
+ "eval_samples_per_second": 0.431,
38
+ "eval_steps_per_second": 0.058,
39
+ "step": 38
40
+ },
41
+ {
42
+ "epoch": 1.01,
43
+ "grad_norm": 2.8914296627044678,
44
+ "learning_rate": 4.0601503759398494e-05,
45
+ "loss": 0.4191,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 1.08,
50
+ "grad_norm": 1.2957464456558228,
51
+ "learning_rate": 3.6842105263157895e-05,
52
+ "loss": 0.1263,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.15,
57
+ "grad_norm": 7.1389689445495605,
58
+ "learning_rate": 3.3082706766917295e-05,
59
+ "loss": 0.1227,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.22,
64
+ "grad_norm": 0.3911808133125305,
65
+ "learning_rate": 2.9323308270676693e-05,
66
+ "loss": 0.0404,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.26,
71
+ "eval_accuracy": 0.972972972972973,
72
+ "eval_loss": 0.054861173033714294,
73
+ "eval_runtime": 86.2035,
74
+ "eval_samples_per_second": 0.429,
75
+ "eval_steps_per_second": 0.058,
76
+ "step": 76
77
+ },
78
+ {
79
+ "epoch": 2.03,
80
+ "grad_norm": 0.20817312598228455,
81
+ "learning_rate": 2.556390977443609e-05,
82
+ "loss": 0.0473,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 2.09,
87
+ "grad_norm": 0.41731318831443787,
88
+ "learning_rate": 2.1804511278195487e-05,
89
+ "loss": 0.0191,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 2.16,
94
+ "grad_norm": 0.8074580430984497,
95
+ "learning_rate": 1.8045112781954888e-05,
96
+ "loss": 0.0182,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.23,
101
+ "grad_norm": 0.2408752292394638,
102
+ "learning_rate": 1.4285714285714285e-05,
103
+ "loss": 0.0115,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.26,
108
+ "eval_accuracy": 1.0,
109
+ "eval_loss": 0.028172966092824936,
110
+ "eval_runtime": 85.2593,
111
+ "eval_samples_per_second": 0.434,
112
+ "eval_steps_per_second": 0.059,
113
+ "step": 114
114
+ },
115
+ {
116
+ "epoch": 3.04,
117
+ "grad_norm": 0.14038172364234924,
118
+ "learning_rate": 1.0526315789473684e-05,
119
+ "loss": 0.0097,
120
+ "step": 120
121
+ },
122
+ {
123
+ "epoch": 3.11,
124
+ "grad_norm": 0.15160618722438812,
125
+ "learning_rate": 6.766917293233083e-06,
126
+ "loss": 0.0085,
127
+ "step": 130
128
+ },
129
+ {
130
+ "epoch": 3.18,
131
+ "grad_norm": 0.0902809351682663,
132
+ "learning_rate": 3.007518796992481e-06,
133
+ "loss": 0.0172,
134
+ "step": 140
135
+ },
136
+ {
137
+ "epoch": 3.23,
138
+ "eval_accuracy": 1.0,
139
+ "eval_loss": 0.0235783401876688,
140
+ "eval_runtime": 86.3082,
141
+ "eval_samples_per_second": 0.429,
142
+ "eval_steps_per_second": 0.058,
143
+ "step": 148
144
+ },
145
+ {
146
+ "epoch": 3.23,
147
+ "step": 148,
148
+ "total_flos": 3.0029279215406285e+18,
149
+ "train_loss": 0.3731363031107026,
150
+ "train_runtime": 6285.1813,
151
+ "train_samples_per_second": 0.188,
152
+ "train_steps_per_second": 0.024
153
+ },
154
+ {
155
+ "epoch": 3.23,
156
+ "eval_accuracy": 1.0,
157
+ "eval_loss": 0.2172325849533081,
158
+ "eval_runtime": 200.1151,
159
+ "eval_samples_per_second": 0.435,
160
+ "eval_steps_per_second": 0.055,
161
+ "step": 148
162
+ },
163
+ {
164
+ "epoch": 3.23,
165
+ "eval_accuracy": 1.0,
166
+ "eval_loss": 0.2172325998544693,
167
+ "eval_runtime": 199.0471,
168
+ "eval_samples_per_second": 0.437,
169
+ "eval_steps_per_second": 0.055,
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": 3.0029279215406285e+18,
179
+ "train_batch_size": 8,
180
+ "trial_name": null,
181
+ "trial_params": null
182
+ }