Hugging Face's logo

Shawon16
/
ViViT_lsa64_coR

Video Classification
Transformers
Safetensors
vivit
Generated from Trainer
Model card Files
xet
Community
ViViT_lsa64_coR
File size: 4,434 Bytes
124ec6b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.0,
  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/ViViT_lsa64_coR/checkpoint-864",
  "epoch": 7.1,
  "eval_steps": 500,
  "global_step": 2304,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 34.6246223449707,
      "learning_rate": 4.930555555555556e-05,
      "loss": 12.7049,
      "step": 288
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.84375,
      "eval_loss": 1.3316307067871094,
      "eval_runtime": 289.0213,
      "eval_samples_per_second": 0.886,
      "eval_steps_per_second": 0.443,
      "step": 288
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.3600924015045166,
      "learning_rate": 4.4521604938271604e-05,
      "loss": 1.4335,
      "step": 576
    },
    {
      "epoch": 1.1,
      "eval_accuracy": 0.9921875,
      "eval_loss": 0.08541239798069,
      "eval_runtime": 353.5336,
      "eval_samples_per_second": 0.724,
      "eval_steps_per_second": 0.362,
      "step": 576
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.12772603332996368,
      "learning_rate": 3.8966049382716055e-05,
      "loss": 0.0869,
      "step": 864
    },
    {
      "epoch": 2.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.00544479675590992,
      "eval_runtime": 303.6919,
      "eval_samples_per_second": 0.843,
      "eval_steps_per_second": 0.421,
      "step": 864
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.10945271700620651,
      "learning_rate": 3.341049382716049e-05,
      "loss": 0.0225,
      "step": 1152
    },
    {
      "epoch": 3.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.002123473212122917,
      "eval_runtime": 394.5624,
      "eval_samples_per_second": 0.649,
      "eval_steps_per_second": 0.324,
      "step": 1152
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.0422612763941288,
      "learning_rate": 2.785493827160494e-05,
      "loss": 0.0057,
      "step": 1440
    },
    {
      "epoch": 4.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0011819098144769669,
      "eval_runtime": 324.5781,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.394,
      "step": 1440
    },
    {
      "epoch": 5.1,
      "grad_norm": 0.026100359857082367,
      "learning_rate": 2.2299382716049384e-05,
      "loss": 0.0038,
      "step": 1728
    },
    {
      "epoch": 5.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0009726639837026596,
      "eval_runtime": 354.0444,
      "eval_samples_per_second": 0.723,
      "eval_steps_per_second": 0.362,
      "step": 1728
    },
    {
      "epoch": 6.1,
      "grad_norm": 0.02095157280564308,
      "learning_rate": 1.674382716049383e-05,
      "loss": 0.0024,
      "step": 2016
    },
    {
      "epoch": 6.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0008304659277200699,
      "eval_runtime": 359.9913,
      "eval_samples_per_second": 0.711,
      "eval_steps_per_second": 0.356,
      "step": 2016
    },
    {
      "epoch": 7.1,
      "grad_norm": 0.028533462435007095,
      "learning_rate": 1.1188271604938271e-05,
      "loss": 0.0016,
      "step": 2304
    },
    {
      "epoch": 7.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0007986431010067463,
      "eval_runtime": 294.083,
      "eval_samples_per_second": 0.871,
      "eval_steps_per_second": 0.435,
      "step": 2304
    },
    {
      "epoch": 7.1,
      "step": 2304,
      "total_flos": 4.72490560063663e+19,
      "train_loss": 1.7826555360419054,
      "train_runtime": 26105.5788,
      "train_samples_per_second": 0.883,
      "train_steps_per_second": 0.11
    }
  ],
  "logging_steps": 500,
  "max_steps": 2880,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.72490560063663e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}