shivarama23 commited on
Commit
d4de32a
1 Parent(s): c6f116f

End of training

Browse files
all_results.json CHANGED
@@ -1,8 +1,13 @@
1
  {
2
- "epoch": 3.0,
3
- "total_flos": 6711117026181120.0,
4
- "train_loss": 0.5747490723927816,
5
- "train_runtime": 22.6294,
6
- "train_samples_per_second": 11.931,
7
- "train_steps_per_second": 0.133
 
 
 
 
 
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.9090909090909091,
4
+ "eval_loss": 0.5242365002632141,
5
+ "eval_runtime": 0.3661,
6
+ "eval_samples_per_second": 30.05,
7
+ "eval_steps_per_second": 2.732,
8
+ "total_flos": 2.23703900872704e+16,
9
+ "train_loss": 0.4094994068145752,
10
+ "train_runtime": 71.4678,
11
+ "train_samples_per_second": 12.593,
12
+ "train_steps_per_second": 0.14
13
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.9090909090909091,
4
+ "eval_loss": 0.5242365002632141,
5
+ "eval_runtime": 0.3661,
6
+ "eval_samples_per_second": 30.05,
7
+ "eval_steps_per_second": 2.732
8
+ }
runs/Jun11_11-45-15_65ae023a8309/events.out.tfevents.1654948435.65ae023a8309.80.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b6489722dc0897044417a639cf104a283feda87a965c6e3d7aae4fc73af0fb
3
+ size 357
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "total_flos": 6711117026181120.0,
4
- "train_loss": 0.5747490723927816,
5
- "train_runtime": 22.6294,
6
- "train_samples_per_second": 11.931,
7
- "train_steps_per_second": 0.133
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "total_flos": 2.23703900872704e+16,
4
+ "train_loss": 0.4094994068145752,
5
+ "train_runtime": 71.4678,
6
+ "train_samples_per_second": 12.593,
7
+ "train_steps_per_second": 0.14
8
  }
trainer_state.json CHANGED
@@ -1,52 +1,121 @@
1
  {
2
- "best_metric": 0.6363636363636364,
3
- "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-image_quality/checkpoint-3",
4
- "epoch": 3.0,
5
- "global_step": 3,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "eval_accuracy": 0.45454545454545453,
13
- "eval_loss": 0.7566965222358704,
14
- "eval_runtime": 0.3201,
15
- "eval_samples_per_second": 34.368,
16
- "eval_steps_per_second": 3.124,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 2.0,
21
- "eval_accuracy": 0.5454545454545454,
22
- "eval_loss": 0.67878258228302,
23
- "eval_runtime": 0.4855,
24
- "eval_samples_per_second": 22.659,
25
- "eval_steps_per_second": 2.06,
26
  "step": 2
27
  },
28
  {
29
  "epoch": 3.0,
30
  "eval_accuracy": 0.6363636363636364,
31
- "eval_loss": 0.6762338280677795,
32
- "eval_runtime": 0.3259,
33
- "eval_samples_per_second": 33.75,
34
- "eval_steps_per_second": 3.068,
35
  "step": 3
36
  },
37
  {
38
- "epoch": 3.0,
39
- "step": 3,
40
- "total_flos": 6711117026181120.0,
41
- "train_loss": 0.5747490723927816,
42
- "train_runtime": 22.6294,
43
- "train_samples_per_second": 11.931,
44
- "train_steps_per_second": 0.133
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  }
46
  ],
47
- "max_steps": 3,
48
- "num_train_epochs": 3,
49
- "total_flos": 6711117026181120.0,
50
  "trial_name": null,
51
  "trial_params": null
52
  }
 
1
  {
2
+ "best_metric": 0.9090909090909091,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-image_quality/checkpoint-6",
4
+ "epoch": 10.0,
5
+ "global_step": 10,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "eval_accuracy": 0.6363636363636364,
13
+ "eval_loss": 0.6762338280677795,
14
+ "eval_runtime": 0.2955,
15
+ "eval_samples_per_second": 37.225,
16
+ "eval_steps_per_second": 3.384,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 2.0,
21
+ "eval_accuracy": 0.7272727272727273,
22
+ "eval_loss": 0.6309272050857544,
23
+ "eval_runtime": 0.2998,
24
+ "eval_samples_per_second": 36.688,
25
+ "eval_steps_per_second": 3.335,
26
  "step": 2
27
  },
28
  {
29
  "epoch": 3.0,
30
  "eval_accuracy": 0.6363636363636364,
31
+ "eval_loss": 0.609474241733551,
32
+ "eval_runtime": 0.3499,
33
+ "eval_samples_per_second": 31.437,
34
+ "eval_steps_per_second": 2.858,
35
  "step": 3
36
  },
37
  {
38
+ "epoch": 4.0,
39
+ "eval_accuracy": 0.6363636363636364,
40
+ "eval_loss": 0.5775323510169983,
41
+ "eval_runtime": 0.3517,
42
+ "eval_samples_per_second": 31.276,
43
+ "eval_steps_per_second": 2.843,
44
+ "step": 4
45
+ },
46
+ {
47
+ "epoch": 5.0,
48
+ "eval_accuracy": 0.8181818181818182,
49
+ "eval_loss": 0.5443004965782166,
50
+ "eval_runtime": 0.4331,
51
+ "eval_samples_per_second": 25.399,
52
+ "eval_steps_per_second": 2.309,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 6.0,
57
+ "eval_accuracy": 0.9090909090909091,
58
+ "eval_loss": 0.5242365002632141,
59
+ "eval_runtime": 0.3235,
60
+ "eval_samples_per_second": 34.003,
61
+ "eval_steps_per_second": 3.091,
62
+ "step": 6
63
+ },
64
+ {
65
+ "epoch": 7.0,
66
+ "eval_accuracy": 0.8181818181818182,
67
+ "eval_loss": 0.5149173140525818,
68
+ "eval_runtime": 0.3418,
69
+ "eval_samples_per_second": 32.183,
70
+ "eval_steps_per_second": 2.926,
71
+ "step": 7
72
+ },
73
+ {
74
+ "epoch": 8.0,
75
+ "eval_accuracy": 0.8181818181818182,
76
+ "eval_loss": 0.509437620639801,
77
+ "eval_runtime": 0.3412,
78
+ "eval_samples_per_second": 32.243,
79
+ "eval_steps_per_second": 2.931,
80
+ "step": 8
81
+ },
82
+ {
83
+ "epoch": 9.0,
84
+ "eval_accuracy": 0.8181818181818182,
85
+ "eval_loss": 0.5037996172904968,
86
+ "eval_runtime": 0.3235,
87
+ "eval_samples_per_second": 33.998,
88
+ "eval_steps_per_second": 3.091,
89
+ "step": 9
90
+ },
91
+ {
92
+ "epoch": 10.0,
93
+ "learning_rate": 0.0,
94
+ "loss": 0.4095,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 10.0,
99
+ "eval_accuracy": 0.8181818181818182,
100
+ "eval_loss": 0.4992285668849945,
101
+ "eval_runtime": 0.3365,
102
+ "eval_samples_per_second": 32.694,
103
+ "eval_steps_per_second": 2.972,
104
+ "step": 10
105
+ },
106
+ {
107
+ "epoch": 10.0,
108
+ "step": 10,
109
+ "total_flos": 2.23703900872704e+16,
110
+ "train_loss": 0.4094994068145752,
111
+ "train_runtime": 71.4678,
112
+ "train_samples_per_second": 12.593,
113
+ "train_steps_per_second": 0.14
114
  }
115
  ],
116
+ "max_steps": 10,
117
+ "num_train_epochs": 10,
118
+ "total_flos": 2.23703900872704e+16,
119
  "trial_name": null,
120
  "trial_params": null
121
  }