NDSrex commited on
Commit
a7d8d7b
·
1 Parent(s): cbe9d15

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. optimizer.pt +1 -1
  2. pytorch_model.bin +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. trainer_state.json +93 -15
  6. training_args.bin +1 -1
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7a14d94cef04785d9ab0085ea466fed726ace6e947d692853e497bd3dd0d8ba
3
  size 686518725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22666f5905d107b8d5563f4da23b6ba468b2792972fc19057e26c575916ddedd
3
  size 686518725
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6353a925cafe8840c2c126fba9edb0694908d92f0bfda785ecea8be80740660
3
  size 343268717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e000e536345028f0b070576e3b623b25524c2a5a51a0fe58bfd85e12eafaa994
3
  size 343268717
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6869750f95a25c4e970298a33adf90e2d7ab52680bf3317239bff1b10103235
3
  size 14575
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab96bad09d57829f7b90b937a32bb83fb6a93bd7e03359b05ae3cd25a9340380
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ff558059fa499586e4a8c58395be208b37c7150858880034600454791a5754
3
  size 627
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.0557590089738369,
3
- "best_model_checkpoint": "./vit-base-beans/checkpoint-50",
4
- "epoch": 1.1627906976744187,
5
- "global_step": 50,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -10,46 +10,124 @@
10
  {
11
  "epoch": 0.23,
12
  "learning_rate": 0.00018837209302325584,
13
- "loss": 0.4497,
14
  "step": 10
15
  },
16
  {
17
  "epoch": 0.47,
18
  "learning_rate": 0.00017674418604651164,
19
- "loss": 0.1718,
20
  "step": 20
21
  },
22
  {
23
  "epoch": 0.7,
24
  "learning_rate": 0.00016511627906976747,
25
- "loss": 0.1226,
26
  "step": 30
27
  },
28
  {
29
  "epoch": 0.93,
30
  "learning_rate": 0.00015348837209302327,
31
- "loss": 0.2082,
32
  "step": 40
33
  },
34
  {
35
  "epoch": 1.16,
36
  "learning_rate": 0.0001418604651162791,
37
- "loss": 0.0393,
38
  "step": 50
39
  },
40
  {
41
  "epoch": 1.16,
42
- "eval_accuracy": 0.9895287958115183,
43
- "eval_loss": 0.0557590089738369,
44
- "eval_runtime": 3.165,
45
- "eval_samples_per_second": 60.347,
46
- "eval_steps_per_second": 7.583,
47
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "max_steps": 172,
51
  "num_train_epochs": 4,
52
- "total_flos": 6.19935916916736e+16,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
 
1
  {
2
+ "best_metric": 0.031983137130737305,
3
+ "best_model_checkpoint": "./vit-base-beans/checkpoint-150",
4
+ "epoch": 3.488372093023256,
5
+ "global_step": 150,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
10
  {
11
  "epoch": 0.23,
12
  "learning_rate": 0.00018837209302325584,
13
+ "loss": 0.4709,
14
  "step": 10
15
  },
16
  {
17
  "epoch": 0.47,
18
  "learning_rate": 0.00017674418604651164,
19
+ "loss": 0.1674,
20
  "step": 20
21
  },
22
  {
23
  "epoch": 0.7,
24
  "learning_rate": 0.00016511627906976747,
25
+ "loss": 0.166,
26
  "step": 30
27
  },
28
  {
29
  "epoch": 0.93,
30
  "learning_rate": 0.00015348837209302327,
31
+ "loss": 0.1066,
32
  "step": 40
33
  },
34
  {
35
  "epoch": 1.16,
36
  "learning_rate": 0.0001418604651162791,
37
+ "loss": 0.0363,
38
  "step": 50
39
  },
40
  {
41
  "epoch": 1.16,
42
+ "eval_accuracy": 0.9842931937172775,
43
+ "eval_loss": 0.05189552530646324,
44
+ "eval_runtime": 3.2845,
45
+ "eval_samples_per_second": 58.151,
46
+ "eval_steps_per_second": 7.307,
47
  "step": 50
48
+ },
49
+ {
50
+ "epoch": 1.4,
51
+ "learning_rate": 0.0001302325581395349,
52
+ "loss": 0.0399,
53
+ "step": 60
54
+ },
55
+ {
56
+ "epoch": 1.63,
57
+ "learning_rate": 0.00011860465116279071,
58
+ "loss": 0.0512,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.86,
63
+ "learning_rate": 0.00010697674418604651,
64
+ "loss": 0.0703,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 2.09,
69
+ "learning_rate": 9.534883720930233e-05,
70
+ "loss": 0.0224,
71
+ "step": 90
72
+ },
73
+ {
74
+ "epoch": 2.33,
75
+ "learning_rate": 8.372093023255814e-05,
76
+ "loss": 0.0225,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 2.33,
81
+ "eval_accuracy": 0.9842931937172775,
82
+ "eval_loss": 0.056159574538469315,
83
+ "eval_runtime": 3.4745,
84
+ "eval_samples_per_second": 54.972,
85
+ "eval_steps_per_second": 6.908,
86
+ "step": 100
87
+ },
88
+ {
89
+ "epoch": 2.56,
90
+ "learning_rate": 7.209302325581396e-05,
91
+ "loss": 0.0112,
92
+ "step": 110
93
+ },
94
+ {
95
+ "epoch": 2.79,
96
+ "learning_rate": 6.0465116279069765e-05,
97
+ "loss": 0.0087,
98
+ "step": 120
99
+ },
100
+ {
101
+ "epoch": 3.02,
102
+ "learning_rate": 4.883720930232558e-05,
103
+ "loss": 0.0059,
104
+ "step": 130
105
+ },
106
+ {
107
+ "epoch": 3.26,
108
+ "learning_rate": 3.7209302325581394e-05,
109
+ "loss": 0.0055,
110
+ "step": 140
111
+ },
112
+ {
113
+ "epoch": 3.49,
114
+ "learning_rate": 2.5581395348837212e-05,
115
+ "loss": 0.0053,
116
+ "step": 150
117
+ },
118
+ {
119
+ "epoch": 3.49,
120
+ "eval_accuracy": 0.9947643979057592,
121
+ "eval_loss": 0.031983137130737305,
122
+ "eval_runtime": 3.2734,
123
+ "eval_samples_per_second": 58.348,
124
+ "eval_steps_per_second": 7.332,
125
+ "step": 150
126
  }
127
  ],
128
  "max_steps": 172,
129
  "num_train_epochs": 4,
130
+ "total_flos": 1.859807750750208e+17,
131
  "trial_name": null,
132
  "trial_params": null
133
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:020d05f87f714abeb0eae454cd2eb3d07174ad2523c1db5d3bae5f87cfef750d
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37da18ed758395c47df20de75ab7403f6e8e6609ebe6ec88bb3c851e36d73985
3
  size 3899