Hugging Face's logo

latif98
/
videomae-base-finetuned-numbers

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
latif98 commited on
Commit
c12e8ea
•
1 Parent(s): d506e49

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +11 -0
  2. runs/Apr28_03-32-49_blackhorse/events.out.tfevents.1714258486.blackhorse.2381173.4 +2 -2
  3. test_results.json +11 -0
  4. trainer_state.json +221 -0
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.25,
3
+ "eval_accuracy": 0.8222222222222222,
4
+ "eval_f1": 0.8014692378328742,
5
+ "eval_loss": 0.3432573974132538,
6
+ "eval_precision": 0.8761904761904762,
7
+ "eval_recall": 0.8181818181818182,
8
+ "eval_runtime": 76.5031,
9
+ "eval_samples_per_second": 0.588,
10
+ "eval_steps_per_second": 0.157
11
+ }
runs/Apr28_03-32-49_blackhorse/events.out.tfevents.1714258486.blackhorse.2381173.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01dfbd307d1a37854fa9142596d7529444bdb175fffa01c9e7ca551cefbb2d6d
3
- size 560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed413321f23882e1d446681ea3f4ca8a4578060b5f485f19e5effd6ce6f8a175
3
+ size 1032
test_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.25,
3
+ "eval_accuracy": 0.8222222222222222,
4
+ "eval_f1": 0.8014692378328742,
5
+ "eval_loss": 0.3432573974132538,
6
+ "eval_precision": 0.8761904761904762,
7
+ "eval_recall": 0.8181818181818182,
8
+ "eval_runtime": 76.5031,
9
+ "eval_samples_per_second": 0.588,
10
+ "eval_steps_per_second": 0.157
11
+ }
trainer_state.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9743589743589743,
3
+ "best_model_checkpoint": "videomae-base-finetuned-numbers/checkpoint-176",
4
+ "epoch": 3.25,
5
+ "eval_steps": 500,
6
+ "global_step": 176,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.056818181818181816,
13
+ "grad_norm": 13.327278137207031,
14
+ "learning_rate": 2.777777777777778e-05,
15
+ "loss": 0.8601,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.11363636363636363,
20
+ "grad_norm": 18.073780059814453,
21
+ "learning_rate": 4.936708860759494e-05,
22
+ "loss": 0.7637,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.17045454545454544,
27
+ "grad_norm": 21.950044631958008,
28
+ "learning_rate": 4.6202531645569625e-05,
29
+ "loss": 0.8635,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.22727272727272727,
34
+ "grad_norm": 11.889289855957031,
35
+ "learning_rate": 4.3037974683544305e-05,
36
+ "loss": 0.7592,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.25,
41
+ "eval_accuracy": 0.8461538461538461,
42
+ "eval_f1": 0.8479076479076479,
43
+ "eval_loss": 0.6377912759780884,
44
+ "eval_precision": 0.8757575757575757,
45
+ "eval_recall": 0.8560606060606059,
46
+ "eval_runtime": 77.2345,
47
+ "eval_samples_per_second": 0.505,
48
+ "eval_steps_per_second": 0.129,
49
+ "step": 44
50
+ },
51
+ {
52
+ "epoch": 1.0340909090909092,
53
+ "grad_norm": 6.685118198394775,
54
+ "learning_rate": 3.987341772151899e-05,
55
+ "loss": 0.6971,
56
+ "step": 50
57
+ },
58
+ {
59
+ "epoch": 1.0909090909090908,
60
+ "grad_norm": 5.797889232635498,
61
+ "learning_rate": 3.670886075949367e-05,
62
+ "loss": 0.4348,
63
+ "step": 60
64
+ },
65
+ {
66
+ "epoch": 1.1477272727272727,
67
+ "grad_norm": 2.289470672607422,
68
+ "learning_rate": 3.354430379746836e-05,
69
+ "loss": 0.4708,
70
+ "step": 70
71
+ },
72
+ {
73
+ "epoch": 1.2045454545454546,
74
+ "grad_norm": 1.6386131048202515,
75
+ "learning_rate": 3.0379746835443042e-05,
76
+ "loss": 0.296,
77
+ "step": 80
78
+ },
79
+ {
80
+ "epoch": 1.25,
81
+ "eval_accuracy": 0.8974358974358975,
82
+ "eval_f1": 0.8805194805194806,
83
+ "eval_loss": 0.3026905655860901,
84
+ "eval_precision": 0.9090909090909091,
85
+ "eval_recall": 0.8863636363636362,
86
+ "eval_runtime": 76.9133,
87
+ "eval_samples_per_second": 0.507,
88
+ "eval_steps_per_second": 0.13,
89
+ "step": 88
90
+ },
91
+ {
92
+ "epoch": 2.0113636363636362,
93
+ "grad_norm": 0.7323519587516785,
94
+ "learning_rate": 2.7215189873417722e-05,
95
+ "loss": 0.4399,
96
+ "step": 90
97
+ },
98
+ {
99
+ "epoch": 2.0681818181818183,
100
+ "grad_norm": 7.895605564117432,
101
+ "learning_rate": 2.4050632911392405e-05,
102
+ "loss": 0.2948,
103
+ "step": 100
104
+ },
105
+ {
106
+ "epoch": 2.125,
107
+ "grad_norm": 27.428850173950195,
108
+ "learning_rate": 2.088607594936709e-05,
109
+ "loss": 0.3388,
110
+ "step": 110
111
+ },
112
+ {
113
+ "epoch": 2.1818181818181817,
114
+ "grad_norm": 0.781851053237915,
115
+ "learning_rate": 1.7721518987341772e-05,
116
+ "loss": 0.2823,
117
+ "step": 120
118
+ },
119
+ {
120
+ "epoch": 2.2386363636363638,
121
+ "grad_norm": 22.52676773071289,
122
+ "learning_rate": 1.4556962025316457e-05,
123
+ "loss": 0.2144,
124
+ "step": 130
125
+ },
126
+ {
127
+ "epoch": 2.25,
128
+ "eval_accuracy": 0.9487179487179487,
129
+ "eval_f1": 0.9376623376623378,
130
+ "eval_loss": 0.12886768579483032,
131
+ "eval_precision": 0.9545454545454546,
132
+ "eval_recall": 0.9393939393939393,
133
+ "eval_runtime": 65.5077,
134
+ "eval_samples_per_second": 0.595,
135
+ "eval_steps_per_second": 0.153,
136
+ "step": 132
137
+ },
138
+ {
139
+ "epoch": 3.0454545454545454,
140
+ "grad_norm": 16.04294204711914,
141
+ "learning_rate": 1.139240506329114e-05,
142
+ "loss": 0.2912,
143
+ "step": 140
144
+ },
145
+ {
146
+ "epoch": 3.102272727272727,
147
+ "grad_norm": 0.34404367208480835,
148
+ "learning_rate": 8.227848101265822e-06,
149
+ "loss": 0.0882,
150
+ "step": 150
151
+ },
152
+ {
153
+ "epoch": 3.159090909090909,
154
+ "grad_norm": 0.7014194130897522,
155
+ "learning_rate": 5.063291139240506e-06,
156
+ "loss": 0.083,
157
+ "step": 160
158
+ },
159
+ {
160
+ "epoch": 3.215909090909091,
161
+ "grad_norm": 22.440013885498047,
162
+ "learning_rate": 1.8987341772151901e-06,
163
+ "loss": 0.1331,
164
+ "step": 170
165
+ },
166
+ {
167
+ "epoch": 3.25,
168
+ "eval_accuracy": 0.9743589743589743,
169
+ "eval_f1": 0.9688311688311688,
170
+ "eval_loss": 0.09583019465208054,
171
+ "eval_precision": 0.9772727272727273,
172
+ "eval_recall": 0.9696969696969696,
173
+ "eval_runtime": 66.5184,
174
+ "eval_samples_per_second": 0.586,
175
+ "eval_steps_per_second": 0.15,
176
+ "step": 176
177
+ },
178
+ {
179
+ "epoch": 3.25,
180
+ "step": 176,
181
+ "total_flos": 8.922538555213087e+17,
182
+ "train_loss": 0.41998768225312233,
183
+ "train_runtime": 1661.3641,
184
+ "train_samples_per_second": 0.424,
185
+ "train_steps_per_second": 0.106
186
+ },
187
+ {
188
+ "epoch": 3.25,
189
+ "eval_accuracy": 0.8222222222222222,
190
+ "eval_f1": 0.8014692378328742,
191
+ "eval_loss": 0.3432573676109314,
192
+ "eval_precision": 0.8761904761904762,
193
+ "eval_recall": 0.8181818181818182,
194
+ "eval_runtime": 74.9292,
195
+ "eval_samples_per_second": 0.601,
196
+ "eval_steps_per_second": 0.16,
197
+ "step": 176
198
+ },
199
+ {
200
+ "epoch": 3.25,
201
+ "eval_accuracy": 0.8222222222222222,
202
+ "eval_f1": 0.8014692378328742,
203
+ "eval_loss": 0.3432573974132538,
204
+ "eval_precision": 0.8761904761904762,
205
+ "eval_recall": 0.8181818181818182,
206
+ "eval_runtime": 76.5031,
207
+ "eval_samples_per_second": 0.588,
208
+ "eval_steps_per_second": 0.157,
209
+ "step": 176
210
+ }
211
+ ],
212
+ "logging_steps": 10,
213
+ "max_steps": 176,
214
+ "num_input_tokens_seen": 0,
215
+ "num_train_epochs": 9223372036854775807,
216
+ "save_steps": 500,
217
+ "total_flos": 8.922538555213087e+17,
218
+ "train_batch_size": 4,
219
+ "trial_name": null,
220
+ "trial_params": null
221
+ }