Hugging Face's logo

Salvatore
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
Salvatore commited on
Commit
0cc16d4
•
1 Parent(s): 413831a

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +9 -0
  2. test_results.json +9 -0
  3. trainer_state.json +200 -0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.22972972972973,
3
+ "eval_accuracy": 0.9161290322580645,
4
+ "eval_loss": 0.37556546926498413,
5
+ "eval_model_preparation_time": 0.0017,
6
+ "eval_runtime": 9.9597,
7
+ "eval_samples_per_second": 15.563,
8
+ "eval_steps_per_second": 2.008
9
+ }
test_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.22972972972973,
3
+ "eval_accuracy": 0.9161290322580645,
4
+ "eval_loss": 0.37556546926498413,
5
+ "eval_model_preparation_time": 0.0017,
6
+ "eval_runtime": 9.9597,
7
+ "eval_samples_per_second": 15.563,
8
+ "eval_steps_per_second": 2.008
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7714285714285715,
3
+ "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/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": 8.911906242370605,
14
+ "learning_rate": 3.3333333333333335e-05,
15
+ "loss": 2.2939,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.13513513513513514,
20
+ "grad_norm": 7.693809509277344,
21
+ "learning_rate": 4.81203007518797e-05,
22
+ "loss": 2.1937,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.20270270270270271,
27
+ "grad_norm": 7.856507778167725,
28
+ "learning_rate": 4.43609022556391e-05,
29
+ "loss": 2.1284,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.25675675675675674,
34
+ "eval_accuracy": 0.42857142857142855,
35
+ "eval_loss": 1.8425960540771484,
36
+ "eval_model_preparation_time": 0.0017,
37
+ "eval_runtime": 4.7396,
38
+ "eval_samples_per_second": 14.769,
39
+ "eval_steps_per_second": 1.899,
40
+ "step": 38
41
+ },
42
+ {
43
+ "epoch": 1.0135135135135136,
44
+ "grad_norm": 8.737997055053711,
45
+ "learning_rate": 4.0601503759398494e-05,
46
+ "loss": 1.9138,
47
+ "step": 40
48
+ },
49
+ {
50
+ "epoch": 1.0810810810810811,
51
+ "grad_norm": 9.056952476501465,
52
+ "learning_rate": 3.6842105263157895e-05,
53
+ "loss": 1.3965,
54
+ "step": 50
55
+ },
56
+ {
57
+ "epoch": 1.1486486486486487,
58
+ "grad_norm": 9.419984817504883,
59
+ "learning_rate": 3.3082706766917295e-05,
60
+ "loss": 1.0866,
61
+ "step": 60
62
+ },
63
+ {
64
+ "epoch": 1.2162162162162162,
65
+ "grad_norm": 5.51899528503418,
66
+ "learning_rate": 2.9323308270676693e-05,
67
+ "loss": 0.8904,
68
+ "step": 70
69
+ },
70
+ {
71
+ "epoch": 1.2567567567567568,
72
+ "eval_accuracy": 0.7428571428571429,
73
+ "eval_loss": 0.7788430452346802,
74
+ "eval_model_preparation_time": 0.0017,
75
+ "eval_runtime": 4.6999,
76
+ "eval_samples_per_second": 14.894,
77
+ "eval_steps_per_second": 1.915,
78
+ "step": 76
79
+ },
80
+ {
81
+ "epoch": 2.027027027027027,
82
+ "grad_norm": 6.201491832733154,
83
+ "learning_rate": 2.556390977443609e-05,
84
+ "loss": 0.6935,
85
+ "step": 80
86
+ },
87
+ {
88
+ "epoch": 2.0945945945945947,
89
+ "grad_norm": 12.898451805114746,
90
+ "learning_rate": 2.1804511278195487e-05,
91
+ "loss": 0.5538,
92
+ "step": 90
93
+ },
94
+ {
95
+ "epoch": 2.1621621621621623,
96
+ "grad_norm": 9.50394058227539,
97
+ "learning_rate": 1.8045112781954888e-05,
98
+ "loss": 0.5005,
99
+ "step": 100
100
+ },
101
+ {
102
+ "epoch": 2.22972972972973,
103
+ "grad_norm": 10.287944793701172,
104
+ "learning_rate": 1.4285714285714285e-05,
105
+ "loss": 0.3888,
106
+ "step": 110
107
+ },
108
+ {
109
+ "epoch": 2.2567567567567566,
110
+ "eval_accuracy": 0.7714285714285715,
111
+ "eval_loss": 0.4577937126159668,
112
+ "eval_model_preparation_time": 0.0017,
113
+ "eval_runtime": 4.8277,
114
+ "eval_samples_per_second": 14.5,
115
+ "eval_steps_per_second": 1.864,
116
+ "step": 114
117
+ },
118
+ {
119
+ "epoch": 3.0405405405405403,
120
+ "grad_norm": 5.723540306091309,
121
+ "learning_rate": 1.0526315789473684e-05,
122
+ "loss": 0.3792,
123
+ "step": 120
124
+ },
125
+ {
126
+ "epoch": 3.108108108108108,
127
+ "grad_norm": 3.536975383758545,
128
+ "learning_rate": 6.766917293233083e-06,
129
+ "loss": 0.2719,
130
+ "step": 130
131
+ },
132
+ {
133
+ "epoch": 3.175675675675676,
134
+ "grad_norm": 6.4476141929626465,
135
+ "learning_rate": 3.007518796992481e-06,
136
+ "loss": 0.2734,
137
+ "step": 140
138
+ },
139
+ {
140
+ "epoch": 3.22972972972973,
141
+ "eval_accuracy": 0.7571428571428571,
142
+ "eval_loss": 0.39962273836135864,
143
+ "eval_model_preparation_time": 0.0017,
144
+ "eval_runtime": 4.7855,
145
+ "eval_samples_per_second": 14.627,
146
+ "eval_steps_per_second": 1.881,
147
+ "step": 148
148
+ },
149
+ {
150
+ "epoch": 3.22972972972973,
151
+ "step": 148,
152
+ "total_flos": 1.460491890402263e+18,
153
+ "train_loss": 1.0221337974071503,
154
+ "train_runtime": 165.2475,
155
+ "train_samples_per_second": 7.165,
156
+ "train_steps_per_second": 0.896
157
+ },
158
+ {
159
+ "epoch": 3.22972972972973,
160
+ "eval_accuracy": 0.9161290322580645,
161
+ "eval_loss": 0.3755654990673065,
162
+ "eval_model_preparation_time": 0.0017,
163
+ "eval_runtime": 9.8886,
164
+ "eval_samples_per_second": 15.675,
165
+ "eval_steps_per_second": 2.023,
166
+ "step": 148
167
+ },
168
+ {
169
+ "epoch": 3.22972972972973,
170
+ "eval_accuracy": 0.9161290322580645,
171
+ "eval_loss": 0.37556546926498413,
172
+ "eval_model_preparation_time": 0.0017,
173
+ "eval_runtime": 9.9597,
174
+ "eval_samples_per_second": 15.563,
175
+ "eval_steps_per_second": 2.008,
176
+ "step": 148
177
+ }
178
+ ],
179
+ "logging_steps": 10,
180
+ "max_steps": 148,
181
+ "num_input_tokens_seen": 0,
182
+ "num_train_epochs": 9223372036854775807,
183
+ "save_steps": 500,
184
+ "stateful_callbacks": {
185
+ "TrainerControl": {
186
+ "args": {
187
+ "should_epoch_stop": false,
188
+ "should_evaluate": false,
189
+ "should_log": false,
190
+ "should_save": true,
191
+ "should_training_stop": true
192
+ },
193
+ "attributes": {}
194
+ }
195
+ },
196
+ "total_flos": 1.460491890402263e+18,
197
+ "train_batch_size": 8,
198
+ "trial_name": null,
199
+ "trial_params": null
200
+ }