sayakpaul HF staff commited on
Commit
60d2897
1 Parent(s): e3ebcb5

End of training

Browse files
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.23,
3
- "eval_accuracy": 0.8698224852071006,
4
- "eval_loss": 0.4558912515640259,
5
- "eval_runtime": 14.3413,
6
- "eval_samples_per_second": 11.784,
7
- "eval_steps_per_second": 1.534
8
  }
 
1
  {
2
  "epoch": 3.23,
3
+ "eval_accuracy": 0.864516129032258,
4
+ "eval_loss": 0.3992488980293274,
5
+ "eval_runtime": 13.7986,
6
+ "eval_samples_per_second": 11.233,
7
+ "eval_steps_per_second": 1.449
8
  }
runs/Nov10_08-33-15_c4cf3c5cebad/events.out.tfevents.1668069624.c4cf3c5cebad.106.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fda87ea3894e70cd4b7ac80d185c598a6b8521eafc20581ceb42867494b4b44
3
- size 363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def6ccc8a665dfe287bebd0058f98facdb692c8daa39629792cd745da16ed40b
3
+ size 686
test_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.23,
3
- "eval_accuracy": 0.8698224852071006,
4
- "eval_loss": 0.4558912515640259,
5
- "eval_runtime": 14.3413,
6
- "eval_samples_per_second": 11.784,
7
- "eval_steps_per_second": 1.534
8
  }
 
1
  {
2
  "epoch": 3.23,
3
+ "eval_accuracy": 0.864516129032258,
4
+ "eval_loss": 0.3992488980293274,
5
+ "eval_runtime": 13.7986,
6
+ "eval_samples_per_second": 11.233,
7
+ "eval_steps_per_second": 1.449
8
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.8243243243243243,
3
- "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-114",
4
  "epoch": 3.22972972972973,
5
  "global_step": 148,
6
  "is_hyper_param_search": false,
@@ -10,148 +10,148 @@
10
  {
11
  "epoch": 0.07,
12
  "learning_rate": 3.3333333333333335e-05,
13
- "loss": 2.3253,
14
  "step": 10
15
  },
16
  {
17
  "epoch": 0.14,
18
  "learning_rate": 4.81203007518797e-05,
19
- "loss": 2.2018,
20
  "step": 20
21
  },
22
  {
23
  "epoch": 0.2,
24
  "learning_rate": 4.43609022556391e-05,
25
- "loss": 2.1321,
26
  "step": 30
27
  },
28
  {
29
  "epoch": 0.26,
30
- "eval_accuracy": 0.5,
31
- "eval_loss": 1.7063186168670654,
32
- "eval_runtime": 6.3814,
33
- "eval_samples_per_second": 11.596,
34
- "eval_steps_per_second": 1.567,
35
  "step": 38
36
  },
37
  {
38
  "epoch": 1.01,
39
  "learning_rate": 4.0601503759398494e-05,
40
- "loss": 1.8954,
41
  "step": 40
42
  },
43
  {
44
  "epoch": 1.08,
45
  "learning_rate": 3.6842105263157895e-05,
46
- "loss": 1.4623,
47
  "step": 50
48
  },
49
  {
50
  "epoch": 1.15,
51
  "learning_rate": 3.3082706766917295e-05,
52
- "loss": 1.1013,
53
  "step": 60
54
  },
55
  {
56
  "epoch": 1.22,
57
  "learning_rate": 2.9323308270676693e-05,
58
- "loss": 0.7513,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 1.26,
63
- "eval_accuracy": 0.6756756756756757,
64
- "eval_loss": 0.8875435590744019,
65
- "eval_runtime": 6.6832,
66
- "eval_samples_per_second": 11.073,
67
- "eval_steps_per_second": 1.496,
68
  "step": 76
69
  },
70
  {
71
  "epoch": 2.03,
72
  "learning_rate": 2.556390977443609e-05,
73
- "loss": 0.7555,
74
  "step": 80
75
  },
76
  {
77
  "epoch": 2.09,
78
  "learning_rate": 2.1804511278195487e-05,
79
- "loss": 0.531,
80
  "step": 90
81
  },
82
  {
83
  "epoch": 2.16,
84
  "learning_rate": 1.8045112781954888e-05,
85
- "loss": 0.5464,
86
  "step": 100
87
  },
88
  {
89
  "epoch": 2.23,
90
  "learning_rate": 1.4285714285714285e-05,
91
- "loss": 0.3882,
92
  "step": 110
93
  },
94
  {
95
  "epoch": 2.26,
96
- "eval_accuracy": 0.8243243243243243,
97
- "eval_loss": 0.46954473853111267,
98
- "eval_runtime": 6.7034,
99
- "eval_samples_per_second": 11.039,
100
- "eval_steps_per_second": 1.492,
101
  "step": 114
102
  },
103
  {
104
  "epoch": 3.04,
105
  "learning_rate": 1.0526315789473684e-05,
106
- "loss": 0.271,
107
  "step": 120
108
  },
109
  {
110
  "epoch": 3.11,
111
  "learning_rate": 6.766917293233083e-06,
112
- "loss": 0.2625,
113
  "step": 130
114
  },
115
  {
116
  "epoch": 3.18,
117
  "learning_rate": 3.007518796992481e-06,
118
- "loss": 0.2671,
119
  "step": 140
120
  },
121
  {
122
  "epoch": 3.23,
123
- "eval_accuracy": 0.8243243243243243,
124
- "eval_loss": 0.3919770121574402,
125
- "eval_runtime": 6.5967,
126
- "eval_samples_per_second": 11.218,
127
- "eval_steps_per_second": 1.516,
128
  "step": 148
129
  },
130
  {
131
  "epoch": 3.23,
132
  "step": 148,
133
  "total_flos": 1.460491890402263e+18,
134
- "train_loss": 1.0175014428190283,
135
- "train_runtime": 239.3713,
136
- "train_samples_per_second": 4.946,
137
- "train_steps_per_second": 0.618
138
  },
139
  {
140
  "epoch": 3.23,
141
- "eval_accuracy": 0.8698224852071006,
142
- "eval_loss": 0.4558912515640259,
143
- "eval_runtime": 15.206,
144
- "eval_samples_per_second": 11.114,
145
- "eval_steps_per_second": 1.447,
146
  "step": 148
147
  },
148
  {
149
  "epoch": 3.23,
150
- "eval_accuracy": 0.8698224852071006,
151
- "eval_loss": 0.4558912515640259,
152
- "eval_runtime": 14.3413,
153
- "eval_samples_per_second": 11.784,
154
- "eval_steps_per_second": 1.534,
155
  "step": 148
156
  }
157
  ],
 
1
  {
2
+ "best_metric": 0.9285714285714286,
3
+ "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
4
  "epoch": 3.22972972972973,
5
  "global_step": 148,
6
  "is_hyper_param_search": false,
 
10
  {
11
  "epoch": 0.07,
12
  "learning_rate": 3.3333333333333335e-05,
13
+ "loss": 2.3623,
14
  "step": 10
15
  },
16
  {
17
  "epoch": 0.14,
18
  "learning_rate": 4.81203007518797e-05,
19
+ "loss": 2.2155,
20
  "step": 20
21
  },
22
  {
23
  "epoch": 0.2,
24
  "learning_rate": 4.43609022556391e-05,
25
+ "loss": 2.1374,
26
  "step": 30
27
  },
28
  {
29
  "epoch": 0.26,
30
+ "eval_accuracy": 0.5714285714285714,
31
+ "eval_loss": 1.7412834167480469,
32
+ "eval_runtime": 6.1835,
33
+ "eval_samples_per_second": 11.32,
34
+ "eval_steps_per_second": 1.455,
35
  "step": 38
36
  },
37
  {
38
  "epoch": 1.01,
39
  "learning_rate": 4.0601503759398494e-05,
40
+ "loss": 1.9183,
41
  "step": 40
42
  },
43
  {
44
  "epoch": 1.08,
45
  "learning_rate": 3.6842105263157895e-05,
46
+ "loss": 1.4923,
47
  "step": 50
48
  },
49
  {
50
  "epoch": 1.15,
51
  "learning_rate": 3.3082706766917295e-05,
52
+ "loss": 1.2149,
53
  "step": 60
54
  },
55
  {
56
  "epoch": 1.22,
57
  "learning_rate": 2.9323308270676693e-05,
58
+ "loss": 0.7949,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 1.26,
63
+ "eval_accuracy": 0.8,
64
+ "eval_loss": 0.7746667265892029,
65
+ "eval_runtime": 6.3565,
66
+ "eval_samples_per_second": 11.012,
67
+ "eval_steps_per_second": 1.416,
68
  "step": 76
69
  },
70
  {
71
  "epoch": 2.03,
72
  "learning_rate": 2.556390977443609e-05,
73
+ "loss": 0.8088,
74
  "step": 80
75
  },
76
  {
77
  "epoch": 2.09,
78
  "learning_rate": 2.1804511278195487e-05,
79
+ "loss": 0.535,
80
  "step": 90
81
  },
82
  {
83
  "epoch": 2.16,
84
  "learning_rate": 1.8045112781954888e-05,
85
+ "loss": 0.5405,
86
  "step": 100
87
  },
88
  {
89
  "epoch": 2.23,
90
  "learning_rate": 1.4285714285714285e-05,
91
+ "loss": 0.4279,
92
  "step": 110
93
  },
94
  {
95
  "epoch": 2.26,
96
+ "eval_accuracy": 0.9142857142857143,
97
+ "eval_loss": 0.4053409993648529,
98
+ "eval_runtime": 6.2263,
99
+ "eval_samples_per_second": 11.243,
100
+ "eval_steps_per_second": 1.445,
101
  "step": 114
102
  },
103
  {
104
  "epoch": 3.04,
105
  "learning_rate": 1.0526315789473684e-05,
106
+ "loss": 0.3461,
107
  "step": 120
108
  },
109
  {
110
  "epoch": 3.11,
111
  "learning_rate": 6.766917293233083e-06,
112
+ "loss": 0.2509,
113
  "step": 130
114
  },
115
  {
116
  "epoch": 3.18,
117
  "learning_rate": 3.007518796992481e-06,
118
+ "loss": 0.291,
119
  "step": 140
120
  },
121
  {
122
  "epoch": 3.23,
123
+ "eval_accuracy": 0.9285714285714286,
124
+ "eval_loss": 0.3428815007209778,
125
+ "eval_runtime": 6.583,
126
+ "eval_samples_per_second": 10.633,
127
+ "eval_steps_per_second": 1.367,
128
  "step": 148
129
  },
130
  {
131
  "epoch": 3.23,
132
  "step": 148,
133
  "total_flos": 1.460491890402263e+18,
134
+ "train_loss": 1.0492687128685616,
135
+ "train_runtime": 239.2161,
136
+ "train_samples_per_second": 4.949,
137
+ "train_steps_per_second": 0.619
138
  },
139
  {
140
  "epoch": 3.23,
141
+ "eval_accuracy": 0.864516129032258,
142
+ "eval_loss": 0.3992488980293274,
143
+ "eval_runtime": 14.1288,
144
+ "eval_samples_per_second": 10.971,
145
+ "eval_steps_per_second": 1.416,
146
  "step": 148
147
  },
148
  {
149
  "epoch": 3.23,
150
+ "eval_accuracy": 0.864516129032258,
151
+ "eval_loss": 0.3992488980293274,
152
+ "eval_runtime": 13.7986,
153
+ "eval_samples_per_second": 11.233,
154
+ "eval_steps_per_second": 1.449,
155
  "step": 148
156
  }
157
  ],