Hugging Face's logo

cccchristopher
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Model card Files
xet
 Metrics Community
cccchristopher commited on
Commit
7a726a5
·
verified ·
1 Parent(s): fbe754e

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +8 -0
  2. runs/Apr08_22-32-06_51e754e7eecc/events.out.tfevents.1744152365.51e754e7eecc.4471.1 +2 -2
  3. test_results.json +8 -0
  4. trainer_state.json +195 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.22972972972973,
3
+ "eval_accuracy": 0.8193548387096774,
4
+ "eval_loss": 0.4802559018135071,
5
+ "eval_runtime": 37.3836,
6
+ "eval_samples_per_second": 4.146,
7
+ "eval_steps_per_second": 0.535
8
+ }
runs/Apr08_22-32-06_51e754e7eecc/events.out.tfevents.1744152365.51e754e7eecc.4471.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fad01a255b5b34f59c45b884953545bcdf60ddde3565b55064e43465f7e010af
3
- size 411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e67b68ec9ff4a41c2303a05e803f1a304937bb5b8d00a89be1e0618c5f333cb
3
+ size 734
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.22972972972973,
3
+ "eval_accuracy": 0.8193548387096774,
4
+ "eval_loss": 0.4802559018135071,
5
+ "eval_runtime": 37.3836,
6
+ "eval_samples_per_second": 4.146,
7
+ "eval_steps_per_second": 0.535
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 148,
3
+ "best_metric": 0.9142857142857143,
4
+ "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
5
+ "epoch": 3.22972972972973,
6
+ "eval_steps": 500,
7
+ "global_step": 148,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06756756756756757,
14
+ "grad_norm": 7.40066385269165,
15
+ "learning_rate": 3.3333333333333335e-05,
16
+ "loss": 2.283,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.13513513513513514,
21
+ "grad_norm": 7.144842147827148,
22
+ "learning_rate": 4.81203007518797e-05,
23
+ "loss": 2.2444,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.20270270270270271,
28
+ "grad_norm": 6.828388214111328,
29
+ "learning_rate": 4.43609022556391e-05,
30
+ "loss": 2.0763,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.25675675675675674,
35
+ "eval_accuracy": 0.5857142857142857,
36
+ "eval_loss": 1.6526830196380615,
37
+ "eval_runtime": 18.1085,
38
+ "eval_samples_per_second": 3.866,
39
+ "eval_steps_per_second": 0.497,
40
+ "step": 38
41
+ },
42
+ {
43
+ "epoch": 1.0135135135135136,
44
+ "grad_norm": 9.339892387390137,
45
+ "learning_rate": 4.0601503759398494e-05,
46
+ "loss": 1.8731,
47
+ "step": 40
48
+ },
49
+ {
50
+ "epoch": 1.0810810810810811,
51
+ "grad_norm": 11.664366722106934,
52
+ "learning_rate": 3.6842105263157895e-05,
53
+ "loss": 1.3972,
54
+ "step": 50
55
+ },
56
+ {
57
+ "epoch": 1.1486486486486487,
58
+ "grad_norm": 16.482961654663086,
59
+ "learning_rate": 3.3082706766917295e-05,
60
+ "loss": 1.0329,
61
+ "step": 60
62
+ },
63
+ {
64
+ "epoch": 1.2162162162162162,
65
+ "grad_norm": 5.483195781707764,
66
+ "learning_rate": 2.9323308270676693e-05,
67
+ "loss": 0.6845,
68
+ "step": 70
69
+ },
70
+ {
71
+ "epoch": 1.2567567567567568,
72
+ "eval_accuracy": 0.8,
73
+ "eval_loss": 0.6961432695388794,
74
+ "eval_runtime": 18.1176,
75
+ "eval_samples_per_second": 3.864,
76
+ "eval_steps_per_second": 0.497,
77
+ "step": 76
78
+ },
79
+ {
80
+ "epoch": 2.027027027027027,
81
+ "grad_norm": 6.847842693328857,
82
+ "learning_rate": 2.556390977443609e-05,
83
+ "loss": 0.7041,
84
+ "step": 80
85
+ },
86
+ {
87
+ "epoch": 2.0945945945945947,
88
+ "grad_norm": 4.047189235687256,
89
+ "learning_rate": 2.1804511278195487e-05,
90
+ "loss": 0.5721,
91
+ "step": 90
92
+ },
93
+ {
94
+ "epoch": 2.1621621621621623,
95
+ "grad_norm": 9.763541221618652,
96
+ "learning_rate": 1.8045112781954888e-05,
97
+ "loss": 0.5223,
98
+ "step": 100
99
+ },
100
+ {
101
+ "epoch": 2.22972972972973,
102
+ "grad_norm": 7.095814228057861,
103
+ "learning_rate": 1.4285714285714285e-05,
104
+ "loss": 0.5159,
105
+ "step": 110
106
+ },
107
+ {
108
+ "epoch": 2.2567567567567566,
109
+ "eval_accuracy": 0.8285714285714286,
110
+ "eval_loss": 0.45256105065345764,
111
+ "eval_runtime": 18.9877,
112
+ "eval_samples_per_second": 3.687,
113
+ "eval_steps_per_second": 0.474,
114
+ "step": 114
115
+ },
116
+ {
117
+ "epoch": 3.0405405405405403,
118
+ "grad_norm": 2.604196786880493,
119
+ "learning_rate": 1.0526315789473684e-05,
120
+ "loss": 0.3598,
121
+ "step": 120
122
+ },
123
+ {
124
+ "epoch": 3.108108108108108,
125
+ "grad_norm": 2.877445936203003,
126
+ "learning_rate": 6.766917293233083e-06,
127
+ "loss": 0.2583,
128
+ "step": 130
129
+ },
130
+ {
131
+ "epoch": 3.175675675675676,
132
+ "grad_norm": 7.803931713104248,
133
+ "learning_rate": 3.007518796992481e-06,
134
+ "loss": 0.2407,
135
+ "step": 140
136
+ },
137
+ {
138
+ "epoch": 3.22972972972973,
139
+ "eval_accuracy": 0.9142857142857143,
140
+ "eval_loss": 0.37618494033813477,
141
+ "eval_runtime": 16.478,
142
+ "eval_samples_per_second": 4.248,
143
+ "eval_steps_per_second": 0.546,
144
+ "step": 148
145
+ },
146
+ {
147
+ "epoch": 3.22972972972973,
148
+ "step": 148,
149
+ "total_flos": 1.460491890402263e+18,
150
+ "train_loss": 1.0104753785842173,
151
+ "train_runtime": 782.0727,
152
+ "train_samples_per_second": 1.514,
153
+ "train_steps_per_second": 0.189
154
+ },
155
+ {
156
+ "epoch": 3.22972972972973,
157
+ "eval_accuracy": 0.8193548387096774,
158
+ "eval_loss": 0.4802559018135071,
159
+ "eval_runtime": 37.4049,
160
+ "eval_samples_per_second": 4.144,
161
+ "eval_steps_per_second": 0.535,
162
+ "step": 148
163
+ },
164
+ {
165
+ "epoch": 3.22972972972973,
166
+ "eval_accuracy": 0.8193548387096774,
167
+ "eval_loss": 0.4802559018135071,
168
+ "eval_runtime": 37.3836,
169
+ "eval_samples_per_second": 4.146,
170
+ "eval_steps_per_second": 0.535,
171
+ "step": 148
172
+ }
173
+ ],
174
+ "logging_steps": 10,
175
+ "max_steps": 148,
176
+ "num_input_tokens_seen": 0,
177
+ "num_train_epochs": 9223372036854775807,
178
+ "save_steps": 500,
179
+ "stateful_callbacks": {
180
+ "TrainerControl": {
181
+ "args": {
182
+ "should_epoch_stop": false,
183
+ "should_evaluate": false,
184
+ "should_log": false,
185
+ "should_save": true,
186
+ "should_training_stop": true
187
+ },
188
+ "attributes": {}
189
+ }
190
+ },
191
+ "total_flos": 1.460491890402263e+18,
192
+ "train_batch_size": 8,
193
+ "trial_name": null,
194
+ "trial_params": null
195
+ }