jayanthspratap commited on
Commit
fcfb4cd
1 Parent(s): 89475a5

End of training

Browse files
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6046
36
  - Accuracy: 0.7209
37
 
38
  ## Model description
 
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5932
36
  - Accuracy: 0.7209
37
 
38
  ## Model description
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 9.6,
3
- "eval_accuracy": 0.7441860465116279,
4
- "eval_loss": 0.5859283208847046,
5
- "eval_runtime": 0.3168,
6
- "eval_samples_per_second": 135.736,
7
- "eval_steps_per_second": 34.723,
8
- "total_flos": 7.3694882123477e+16,
9
- "train_loss": 0.5492916504542033,
10
- "train_runtime": 34.9653,
11
- "train_samples_per_second": 28.314,
12
- "train_steps_per_second": 1.716
13
  }
 
1
  {
2
  "epoch": 9.6,
3
+ "eval_accuracy": 0.7209302325581395,
4
+ "eval_loss": 0.5932016372680664,
5
+ "eval_runtime": 0.4968,
6
+ "eval_samples_per_second": 86.55,
7
+ "eval_steps_per_second": 22.141,
8
+ "total_flos": 9.748371434294477e+16,
9
+ "train_loss": 0.5804096937179566,
10
+ "train_runtime": 57.1953,
11
+ "train_samples_per_second": 17.309,
12
+ "train_steps_per_second": 1.049
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 9.6,
3
- "eval_accuracy": 0.7441860465116279,
4
- "eval_loss": 0.5859283208847046,
5
- "eval_runtime": 0.3168,
6
- "eval_samples_per_second": 135.736,
7
- "eval_steps_per_second": 34.723
8
  }
 
1
  {
2
  "epoch": 9.6,
3
+ "eval_accuracy": 0.7209302325581395,
4
+ "eval_loss": 0.5932016372680664,
5
+ "eval_runtime": 0.4968,
6
+ "eval_samples_per_second": 86.55,
7
+ "eval_steps_per_second": 22.141
8
  }
runs/Aug10_00-26-27_EMIMDGXA100GPU1/events.out.tfevents.1723264067.EMIMDGXA100GPU1.4104023.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8bb608305f1d975331400478e43662715f6b23b73697208b1785abf6ac4249
3
+ size 405
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 9.6,
3
- "total_flos": 7.3694882123477e+16,
4
- "train_loss": 0.5492916504542033,
5
- "train_runtime": 34.9653,
6
- "train_samples_per_second": 28.314,
7
- "train_steps_per_second": 1.716
8
  }
 
1
  {
2
  "epoch": 9.6,
3
+ "total_flos": 9.748371434294477e+16,
4
+ "train_loss": 0.5804096937179566,
5
+ "train_runtime": 57.1953,
6
+ "train_samples_per_second": 17.309,
7
+ "train_steps_per_second": 1.049
8
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.7441860465116279,
3
- "best_model_checkpoint": "vit-base-patch16-224/checkpoint-6",
4
  "epoch": 9.6,
5
  "eval_steps": 500,
6
  "global_step": 60,
@@ -10,144 +10,144 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.96,
13
- "eval_accuracy": 0.7441860465116279,
14
- "eval_loss": 0.5859283208847046,
15
- "eval_runtime": 0.2566,
16
- "eval_samples_per_second": 167.599,
17
- "eval_steps_per_second": 42.874,
18
  "step": 6
19
  },
20
  {
21
  "epoch": 1.6,
22
- "grad_norm": 3.7175180912017822,
23
  "learning_rate": 4.62962962962963e-06,
24
- "loss": 0.605,
25
  "step": 10
26
  },
27
  {
28
  "epoch": 1.92,
29
- "eval_accuracy": 0.7441860465116279,
30
- "eval_loss": 0.5841977000236511,
31
- "eval_runtime": 0.2709,
32
- "eval_samples_per_second": 158.721,
33
- "eval_steps_per_second": 40.603,
34
  "step": 12
35
  },
36
  {
37
  "epoch": 2.88,
38
- "eval_accuracy": 0.7441860465116279,
39
- "eval_loss": 0.5918598771095276,
40
- "eval_runtime": 0.2627,
41
- "eval_samples_per_second": 163.663,
42
- "eval_steps_per_second": 41.867,
43
  "step": 18
44
  },
45
  {
46
  "epoch": 3.2,
47
- "grad_norm": 2.415996551513672,
48
  "learning_rate": 3.7037037037037037e-06,
49
- "loss": 0.5428,
50
  "step": 20
51
  },
52
  {
53
  "epoch": 4.0,
54
- "eval_accuracy": 0.7441860465116279,
55
- "eval_loss": 0.5884882807731628,
56
- "eval_runtime": 0.9618,
57
- "eval_samples_per_second": 44.706,
58
- "eval_steps_per_second": 11.436,
59
  "step": 25
60
  },
61
  {
62
  "epoch": 4.8,
63
- "grad_norm": 2.7047529220581055,
64
  "learning_rate": 2.7777777777777783e-06,
65
- "loss": 0.5584,
66
  "step": 30
67
  },
68
  {
69
  "epoch": 4.96,
70
- "eval_accuracy": 0.7441860465116279,
71
- "eval_loss": 0.588610827922821,
72
- "eval_runtime": 0.2732,
73
- "eval_samples_per_second": 157.373,
74
- "eval_steps_per_second": 40.258,
75
  "step": 31
76
  },
77
  {
78
  "epoch": 5.92,
79
- "eval_accuracy": 0.7441860465116279,
80
- "eval_loss": 0.5914657711982727,
81
- "eval_runtime": 0.2503,
82
- "eval_samples_per_second": 171.764,
83
- "eval_steps_per_second": 43.94,
84
  "step": 37
85
  },
86
  {
87
  "epoch": 6.4,
88
- "grad_norm": 3.9282095432281494,
89
  "learning_rate": 1.8518518518518519e-06,
90
- "loss": 0.5593,
91
  "step": 40
92
  },
93
  {
94
  "epoch": 6.88,
95
- "eval_accuracy": 0.7441860465116279,
96
- "eval_loss": 0.5934743881225586,
97
- "eval_runtime": 0.2654,
98
- "eval_samples_per_second": 162.014,
99
- "eval_steps_per_second": 41.446,
100
  "step": 43
101
  },
102
  {
103
  "epoch": 8.0,
104
- "grad_norm": 2.82995343208313,
105
  "learning_rate": 9.259259259259259e-07,
106
- "loss": 0.5097,
107
  "step": 50
108
  },
109
  {
110
  "epoch": 8.0,
111
- "eval_accuracy": 0.7441860465116279,
112
- "eval_loss": 0.5947032570838928,
113
- "eval_runtime": 0.2582,
114
- "eval_samples_per_second": 166.523,
115
- "eval_steps_per_second": 42.599,
116
  "step": 50
117
  },
118
  {
119
  "epoch": 8.96,
120
- "eval_accuracy": 0.7441860465116279,
121
- "eval_loss": 0.594927966594696,
122
- "eval_runtime": 0.2847,
123
- "eval_samples_per_second": 151.012,
124
- "eval_steps_per_second": 38.631,
125
  "step": 56
126
  },
127
  {
128
  "epoch": 9.6,
129
- "grad_norm": 3.3591854572296143,
130
  "learning_rate": 0.0,
131
- "loss": 0.5205,
132
  "step": 60
133
  },
134
  {
135
  "epoch": 9.6,
136
- "eval_accuracy": 0.7441860465116279,
137
- "eval_loss": 0.5949187874794006,
138
- "eval_runtime": 0.2565,
139
- "eval_samples_per_second": 167.627,
140
- "eval_steps_per_second": 42.881,
141
  "step": 60
142
  },
143
  {
144
  "epoch": 9.6,
145
  "step": 60,
146
- "total_flos": 7.3694882123477e+16,
147
- "train_loss": 0.5492916504542033,
148
- "train_runtime": 34.9653,
149
- "train_samples_per_second": 28.314,
150
- "train_steps_per_second": 1.716
151
  }
152
  ],
153
  "logging_steps": 10,
@@ -167,7 +167,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 7.3694882123477e+16,
171
  "train_batch_size": 4,
172
  "trial_name": null,
173
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7209302325581395,
3
+ "best_model_checkpoint": "vit-base-patch16-224/checkpoint-12",
4
  "epoch": 9.6,
5
  "eval_steps": 500,
6
  "global_step": 60,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.96,
13
+ "eval_accuracy": 0.3488372093023256,
14
+ "eval_loss": 0.742401123046875,
15
+ "eval_runtime": 0.4622,
16
+ "eval_samples_per_second": 93.03,
17
+ "eval_steps_per_second": 23.798,
18
  "step": 6
19
  },
20
  {
21
  "epoch": 1.6,
22
+ "grad_norm": 6.224728107452393,
23
  "learning_rate": 4.62962962962963e-06,
24
+ "loss": 0.7374,
25
  "step": 10
26
  },
27
  {
28
  "epoch": 1.92,
29
+ "eval_accuracy": 0.7209302325581395,
30
+ "eval_loss": 0.5932016372680664,
31
+ "eval_runtime": 0.5117,
32
+ "eval_samples_per_second": 84.03,
33
+ "eval_steps_per_second": 21.496,
34
  "step": 12
35
  },
36
  {
37
  "epoch": 2.88,
38
+ "eval_accuracy": 0.7209302325581395,
39
+ "eval_loss": 0.5843029618263245,
40
+ "eval_runtime": 0.5094,
41
+ "eval_samples_per_second": 84.414,
42
+ "eval_steps_per_second": 21.594,
43
  "step": 18
44
  },
45
  {
46
  "epoch": 3.2,
47
+ "grad_norm": 6.278665065765381,
48
  "learning_rate": 3.7037037037037037e-06,
49
+ "loss": 0.5783,
50
  "step": 20
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.7209302325581395,
55
+ "eval_loss": 0.599581241607666,
56
+ "eval_runtime": 0.5003,
57
+ "eval_samples_per_second": 85.944,
58
+ "eval_steps_per_second": 21.986,
59
  "step": 25
60
  },
61
  {
62
  "epoch": 4.8,
63
+ "grad_norm": 12.106355667114258,
64
  "learning_rate": 2.7777777777777783e-06,
65
+ "loss": 0.5358,
66
  "step": 30
67
  },
68
  {
69
  "epoch": 4.96,
70
+ "eval_accuracy": 0.7209302325581395,
71
+ "eval_loss": 0.6146759986877441,
72
+ "eval_runtime": 0.5458,
73
+ "eval_samples_per_second": 78.786,
74
+ "eval_steps_per_second": 20.154,
75
  "step": 31
76
  },
77
  {
78
  "epoch": 5.92,
79
+ "eval_accuracy": 0.7209302325581395,
80
+ "eval_loss": 0.6159453988075256,
81
+ "eval_runtime": 0.4886,
82
+ "eval_samples_per_second": 88.012,
83
+ "eval_steps_per_second": 22.515,
84
  "step": 37
85
  },
86
  {
87
  "epoch": 6.4,
88
+ "grad_norm": 6.217154502868652,
89
  "learning_rate": 1.8518518518518519e-06,
90
+ "loss": 0.5745,
91
  "step": 40
92
  },
93
  {
94
  "epoch": 6.88,
95
+ "eval_accuracy": 0.7209302325581395,
96
+ "eval_loss": 0.6090837121009827,
97
+ "eval_runtime": 0.4608,
98
+ "eval_samples_per_second": 93.312,
99
+ "eval_steps_per_second": 23.871,
100
  "step": 43
101
  },
102
  {
103
  "epoch": 8.0,
104
+ "grad_norm": 6.606484413146973,
105
  "learning_rate": 9.259259259259259e-07,
106
+ "loss": 0.5325,
107
  "step": 50
108
  },
109
  {
110
  "epoch": 8.0,
111
+ "eval_accuracy": 0.7209302325581395,
112
+ "eval_loss": 0.6066591739654541,
113
+ "eval_runtime": 0.5381,
114
+ "eval_samples_per_second": 79.913,
115
+ "eval_steps_per_second": 20.443,
116
  "step": 50
117
  },
118
  {
119
  "epoch": 8.96,
120
+ "eval_accuracy": 0.7209302325581395,
121
+ "eval_loss": 0.6046953797340393,
122
+ "eval_runtime": 0.5485,
123
+ "eval_samples_per_second": 78.392,
124
+ "eval_steps_per_second": 20.054,
125
  "step": 56
126
  },
127
  {
128
  "epoch": 9.6,
129
+ "grad_norm": 4.127104759216309,
130
  "learning_rate": 0.0,
131
+ "loss": 0.524,
132
  "step": 60
133
  },
134
  {
135
  "epoch": 9.6,
136
+ "eval_accuracy": 0.7209302325581395,
137
+ "eval_loss": 0.6046017408370972,
138
+ "eval_runtime": 0.7447,
139
+ "eval_samples_per_second": 57.745,
140
+ "eval_steps_per_second": 14.772,
141
  "step": 60
142
  },
143
  {
144
  "epoch": 9.6,
145
  "step": 60,
146
+ "total_flos": 9.748371434294477e+16,
147
+ "train_loss": 0.5804096937179566,
148
+ "train_runtime": 57.1953,
149
+ "train_samples_per_second": 17.309,
150
+ "train_steps_per_second": 1.049
151
  }
152
  ],
153
  "logging_steps": 10,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 9.748371434294477e+16,
171
  "train_batch_size": 4,
172
  "trial_name": null,
173
  "trial_params": null