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
vivit-b-16x2-kinetics400-finetuned-ucf101-subset
File size: 4,421 Bytes 
48de180
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
 
{
  "best_metric": 1.0,
  "best_model_checkpoint": "vivit-b-16x2-kinetics400-finetuned-ucf101-subset/checkpoint-38",
  "epoch": 3.22972972972973,
  "eval_steps": 500,
  "global_step": 148,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "grad_norm": 11.20502758026123,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.4387,
      "step": 10
    },
    {
      "epoch": 0.14,
      "grad_norm": 7.179543495178223,
      "learning_rate": 4.81203007518797e-05,
      "loss": 1.4999,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 5.833919525146484,
      "learning_rate": 4.43609022556391e-05,
      "loss": 0.7382,
      "step": 30
    },
    {
      "epoch": 0.26,
      "eval_accuracy": 1.0,
      "eval_loss": 0.2207001894712448,
      "eval_runtime": 85.8262,
      "eval_samples_per_second": 0.431,
      "eval_steps_per_second": 0.058,
      "step": 38
    },
    {
      "epoch": 1.01,
      "grad_norm": 2.8914296627044678,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 0.4191,
      "step": 40
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.2957464456558228,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 0.1263,
      "step": 50
    },
    {
      "epoch": 1.15,
      "grad_norm": 7.1389689445495605,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 0.1227,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.3911808133125305,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.0404,
      "step": 70
    },
    {
      "epoch": 1.26,
      "eval_accuracy": 0.972972972972973,
      "eval_loss": 0.054861173033714294,
      "eval_runtime": 86.2035,
      "eval_samples_per_second": 0.429,
      "eval_steps_per_second": 0.058,
      "step": 76
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.20817312598228455,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.0473,
      "step": 80
    },
    {
      "epoch": 2.09,
      "grad_norm": 0.41731318831443787,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.0191,
      "step": 90
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.8074580430984497,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.0182,
      "step": 100
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.2408752292394638,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.0115,
      "step": 110
    },
    {
      "epoch": 2.26,
      "eval_accuracy": 1.0,
      "eval_loss": 0.028172966092824936,
      "eval_runtime": 85.2593,
      "eval_samples_per_second": 0.434,
      "eval_steps_per_second": 0.059,
      "step": 114
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.14038172364234924,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.0097,
      "step": 120
    },
    {
      "epoch": 3.11,
      "grad_norm": 0.15160618722438812,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.0085,
      "step": 130
    },
    {
      "epoch": 3.18,
      "grad_norm": 0.0902809351682663,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.0172,
      "step": 140
    },
    {
      "epoch": 3.23,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0235783401876688,
      "eval_runtime": 86.3082,
      "eval_samples_per_second": 0.429,
      "eval_steps_per_second": 0.058,
      "step": 148
    },
    {
      "epoch": 3.23,
      "step": 148,
      "total_flos": 3.0029279215406285e+18,
      "train_loss": 0.3731363031107026,
      "train_runtime": 6285.1813,
      "train_samples_per_second": 0.188,
      "train_steps_per_second": 0.024
    },
    {
      "epoch": 3.23,
      "eval_accuracy": 1.0,
      "eval_loss": 0.2172325849533081,
      "eval_runtime": 200.1151,
      "eval_samples_per_second": 0.435,
      "eval_steps_per_second": 0.055,
      "step": 148
    },
    {
      "epoch": 3.23,
      "eval_accuracy": 1.0,
      "eval_loss": 0.2172325998544693,
      "eval_runtime": 199.0471,
      "eval_samples_per_second": 0.437,
      "eval_steps_per_second": 0.055,
      "step": 148
    }
  ],
  "logging_steps": 10,
  "max_steps": 148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 3.0029279215406285e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}