Hugging Face's logo

mjahmadi
/
timesformer-base-finetuned-k400-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
timesformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mjahmadi commited on
Commit
6a8468e
•
1 Parent(s): c8287c5

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +8 -0
  2. runs/May16_12-11-01_af0e0407b4ff/events.out.tfevents.1715862474.af0e0407b4ff.1146.1 +2 -2
  3. test_results.json +8 -0
  4. trainer_state.json +133 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.2083333333333335,
3
+ "eval_accuracy": 0.8125,
4
+ "eval_loss": 0.462173730134964,
5
+ "eval_runtime": 113.0732,
6
+ "eval_samples_per_second": 2.547,
7
+ "eval_steps_per_second": 0.318
8
+ }
runs/May16_12-11-01_af0e0407b4ff/events.out.tfevents.1715862474.af0e0407b4ff.1146.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76948bd47e8e0bd0a8d1ec76a007d7484dc29085a81ae4d6ef5fbccfacc9ac9b
3
- size 405
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd0819d32d582eec51394eaa5cc62be481091486b7a0b4b079e8f54d5c7202c
3
+ size 722
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.2083333333333335,
3
+ "eval_accuracy": 0.8125,
4
+ "eval_loss": 0.462173730134964,
5
+ "eval_runtime": 113.0732,
6
+ "eval_samples_per_second": 2.547,
7
+ "eval_steps_per_second": 0.318
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8571428571428571,
3
+ "best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-ucf101-subset/checkpoint-19",
4
+ "epoch": 3.2083333333333335,
5
+ "eval_steps": 500,
6
+ "global_step": 72,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1388888888888889,
13
+ "grad_norm": 11.173284530639648,
14
+ "learning_rate": 4.8437500000000005e-05,
15
+ "loss": 0.8729,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.2638888888888889,
20
+ "eval_accuracy": 0.8571428571428571,
21
+ "eval_loss": 0.41932326555252075,
22
+ "eval_runtime": 147.7861,
23
+ "eval_samples_per_second": 2.558,
24
+ "eval_steps_per_second": 0.325,
25
+ "step": 19
26
+ },
27
+ {
28
+ "epoch": 1.0138888888888888,
29
+ "grad_norm": 4.447381019592285,
30
+ "learning_rate": 4.0625000000000005e-05,
31
+ "loss": 0.4879,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 1.1527777777777777,
36
+ "grad_norm": 3.373873233795166,
37
+ "learning_rate": 3.2812500000000005e-05,
38
+ "loss": 0.5106,
39
+ "step": 30
40
+ },
41
+ {
42
+ "epoch": 1.2638888888888888,
43
+ "eval_accuracy": 0.8571428571428571,
44
+ "eval_loss": 0.45790210366249084,
45
+ "eval_runtime": 146.1696,
46
+ "eval_samples_per_second": 2.586,
47
+ "eval_steps_per_second": 0.328,
48
+ "step": 38
49
+ },
50
+ {
51
+ "epoch": 2.0277777777777777,
52
+ "grad_norm": 0.6665381193161011,
53
+ "learning_rate": 2.5e-05,
54
+ "loss": 0.2482,
55
+ "step": 40
56
+ },
57
+ {
58
+ "epoch": 2.1666666666666665,
59
+ "grad_norm": 8.423311233520508,
60
+ "learning_rate": 1.71875e-05,
61
+ "loss": 0.4699,
62
+ "step": 50
63
+ },
64
+ {
65
+ "epoch": 2.263888888888889,
66
+ "eval_accuracy": 0.8571428571428571,
67
+ "eval_loss": 0.4250260889530182,
68
+ "eval_runtime": 146.1132,
69
+ "eval_samples_per_second": 2.587,
70
+ "eval_steps_per_second": 0.329,
71
+ "step": 57
72
+ },
73
+ {
74
+ "epoch": 3.0416666666666665,
75
+ "grad_norm": 0.42366838455200195,
76
+ "learning_rate": 9.375000000000001e-06,
77
+ "loss": 0.0982,
78
+ "step": 60
79
+ },
80
+ {
81
+ "epoch": 3.1805555555555554,
82
+ "grad_norm": 4.436389446258545,
83
+ "learning_rate": 1.5625e-06,
84
+ "loss": 0.109,
85
+ "step": 70
86
+ },
87
+ {
88
+ "epoch": 3.2083333333333335,
89
+ "eval_accuracy": 0.8571428571428571,
90
+ "eval_loss": 0.5306517481803894,
91
+ "eval_runtime": 145.944,
92
+ "eval_samples_per_second": 2.59,
93
+ "eval_steps_per_second": 0.329,
94
+ "step": 72
95
+ },
96
+ {
97
+ "epoch": 3.2083333333333335,
98
+ "step": 72,
99
+ "total_flos": 4.967755240837939e+17,
100
+ "train_loss": 0.3919994781414668,
101
+ "train_runtime": 877.0447,
102
+ "train_samples_per_second": 0.657,
103
+ "train_steps_per_second": 0.082
104
+ },
105
+ {
106
+ "epoch": 3.2083333333333335,
107
+ "eval_accuracy": 0.8125,
108
+ "eval_loss": 0.4621736705303192,
109
+ "eval_runtime": 114.6382,
110
+ "eval_samples_per_second": 2.512,
111
+ "eval_steps_per_second": 0.314,
112
+ "step": 72
113
+ },
114
+ {
115
+ "epoch": 3.2083333333333335,
116
+ "eval_accuracy": 0.8125,
117
+ "eval_loss": 0.462173730134964,
118
+ "eval_runtime": 113.0732,
119
+ "eval_samples_per_second": 2.547,
120
+ "eval_steps_per_second": 0.318,
121
+ "step": 72
122
+ }
123
+ ],
124
+ "logging_steps": 10,
125
+ "max_steps": 72,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 9223372036854775807,
128
+ "save_steps": 500,
129
+ "total_flos": 4.967755240837939e+17,
130
+ "train_batch_size": 8,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }