Hugging Face's logo

AC-1ML
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
AC-1ML commited on
Commit
635d7e9
·
verified ·
1 Parent(s): ac50ee7

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +8 -0
  2. runs/Oct30_18-41-52_ARNAB-PC/events.out.tfevents.1730297606.ARNAB-PC.4712.1 +2 -2
  3. test_results.json +8 -0
  4. trainer_state.json +201 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.230769230769231,
3
+ "eval_accuracy": 0.4925373134328358,
4
+ "eval_loss": 2.203362226486206,
5
+ "eval_runtime": 52.0119,
6
+ "eval_samples_per_second": 1.288,
7
+ "eval_steps_per_second": 0.173
8
+ }
runs/Oct30_18-41-52_ARNAB-PC/events.out.tfevents.1730297606.ARNAB-PC.4712.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff8e54d27fed56dd070e7667b310ecec7625b0b0e9c2e8814f879e1bc11ee089
3
- size 411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b99b410ae8ca93c56dc3fafccecdb6f3839e6e89ab3b2f2b280a06a47c0f08
3
+ size 734
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.230769230769231,
3
+ "eval_accuracy": 0.4925373134328358,
4
+ "eval_loss": 2.203362226486206,
5
+ "eval_runtime": 52.0119,
6
+ "eval_samples_per_second": 1.288,
7
+ "eval_steps_per_second": 0.173
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9076923076923077,
3
+ "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\checkpoint-80",
4
+ "epoch": 3.230769230769231,
5
+ "eval_steps": 500,
6
+ "global_step": 156,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0641025641025641,
13
+ "grad_norm": 4.394412994384766,
14
+ "learning_rate": 3.125e-05,
15
+ "loss": 1.0132,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.1282051282051282,
20
+ "grad_norm": 5.420567989349365,
21
+ "learning_rate": 4.8571428571428576e-05,
22
+ "loss": 0.8683,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.19230769230769232,
27
+ "grad_norm": 6.78421688079834,
28
+ "learning_rate": 4.5e-05,
29
+ "loss": 0.5054,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.2564102564102564,
34
+ "grad_norm": 6.155091762542725,
35
+ "learning_rate": 4.1428571428571437e-05,
36
+ "loss": 0.5439,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.2564102564102564,
41
+ "eval_accuracy": 0.8153846153846154,
42
+ "eval_loss": 0.34107062220573425,
43
+ "eval_runtime": 71.8323,
44
+ "eval_samples_per_second": 0.905,
45
+ "eval_steps_per_second": 0.125,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 1.064102564102564,
50
+ "grad_norm": 5.863360404968262,
51
+ "learning_rate": 3.785714285714286e-05,
52
+ "loss": 0.3668,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.1282051282051282,
57
+ "grad_norm": 9.200115203857422,
58
+ "learning_rate": 3.428571428571429e-05,
59
+ "loss": 0.2457,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.1923076923076923,
64
+ "grad_norm": 5.0272040367126465,
65
+ "learning_rate": 3.071428571428572e-05,
66
+ "loss": 0.1767,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.2564102564102564,
71
+ "grad_norm": 16.482421875,
72
+ "learning_rate": 2.714285714285714e-05,
73
+ "loss": 0.4475,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.2564102564102564,
78
+ "eval_accuracy": 0.9076923076923077,
79
+ "eval_loss": 0.24450990557670593,
80
+ "eval_runtime": 67.8827,
81
+ "eval_samples_per_second": 0.958,
82
+ "eval_steps_per_second": 0.133,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 2.064102564102564,
87
+ "grad_norm": 0.37460148334503174,
88
+ "learning_rate": 2.357142857142857e-05,
89
+ "loss": 0.2746,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 2.128205128205128,
94
+ "grad_norm": 10.542753219604492,
95
+ "learning_rate": 2e-05,
96
+ "loss": 0.1803,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.1923076923076925,
101
+ "grad_norm": 1.9386680126190186,
102
+ "learning_rate": 1.642857142857143e-05,
103
+ "loss": 0.0729,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.2564102564102564,
108
+ "grad_norm": 1.4239801168441772,
109
+ "learning_rate": 1.2857142857142857e-05,
110
+ "loss": 0.151,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 2.2564102564102564,
115
+ "eval_accuracy": 0.8615384615384616,
116
+ "eval_loss": 0.4069540798664093,
117
+ "eval_runtime": 67.5775,
118
+ "eval_samples_per_second": 0.962,
119
+ "eval_steps_per_second": 0.133,
120
+ "step": 120
121
+ },
122
+ {
123
+ "epoch": 3.064102564102564,
124
+ "grad_norm": 0.11065883934497833,
125
+ "learning_rate": 9.285714285714286e-06,
126
+ "loss": 0.136,
127
+ "step": 130
128
+ },
129
+ {
130
+ "epoch": 3.128205128205128,
131
+ "grad_norm": 0.9843647480010986,
132
+ "learning_rate": 5.7142857142857145e-06,
133
+ "loss": 0.0397,
134
+ "step": 140
135
+ },
136
+ {
137
+ "epoch": 3.1923076923076925,
138
+ "grad_norm": 0.10109780728816986,
139
+ "learning_rate": 2.142857142857143e-06,
140
+ "loss": 0.0314,
141
+ "step": 150
142
+ },
143
+ {
144
+ "epoch": 3.230769230769231,
145
+ "eval_accuracy": 0.8769230769230769,
146
+ "eval_loss": 0.4337887167930603,
147
+ "eval_runtime": 72.43,
148
+ "eval_samples_per_second": 0.897,
149
+ "eval_steps_per_second": 0.124,
150
+ "step": 156
151
+ },
152
+ {
153
+ "epoch": 3.230769230769231,
154
+ "step": 156,
155
+ "total_flos": 1.5476260219471135e+18,
156
+ "train_loss": 0.32558026298498494,
157
+ "train_runtime": 3518.9902,
158
+ "train_samples_per_second": 0.355,
159
+ "train_steps_per_second": 0.044
160
+ },
161
+ {
162
+ "epoch": 3.230769230769231,
163
+ "eval_accuracy": 0.4925373134328358,
164
+ "eval_loss": 2.203362226486206,
165
+ "eval_runtime": 169.2326,
166
+ "eval_samples_per_second": 0.396,
167
+ "eval_steps_per_second": 0.053,
168
+ "step": 156
169
+ },
170
+ {
171
+ "epoch": 3.230769230769231,
172
+ "eval_accuracy": 0.4925373134328358,
173
+ "eval_loss": 2.203362226486206,
174
+ "eval_runtime": 52.0119,
175
+ "eval_samples_per_second": 1.288,
176
+ "eval_steps_per_second": 0.173,
177
+ "step": 156
178
+ }
179
+ ],
180
+ "logging_steps": 10,
181
+ "max_steps": 156,
182
+ "num_input_tokens_seen": 0,
183
+ "num_train_epochs": 9223372036854775807,
184
+ "save_steps": 500,
185
+ "stateful_callbacks": {
186
+ "TrainerControl": {
187
+ "args": {
188
+ "should_epoch_stop": false,
189
+ "should_evaluate": false,
190
+ "should_log": false,
191
+ "should_save": true,
192
+ "should_training_stop": true
193
+ },
194
+ "attributes": {}
195
+ }
196
+ },
197
+ "total_flos": 1.5476260219471135e+18,
198
+ "train_batch_size": 8,
199
+ "trial_name": null,
200
+ "trial_params": null
201
+ }