NDSrex commited on
Commit
70c3ef6
·
1 Parent(s): 3de00c7

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 +17 -47
  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:dda8980d7671d127b0f541a0ae725c3006551050749393d32d1f18d210eb3c75
3
  size 686518725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a14d94cef04785d9ab0085ea466fed726ace6e947d692853e497bd3dd0d8ba
3
  size 686518725
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a846d790851e45d2f0d3cae2ed550c915e3ef9153a0e709fcf580f393bfbb77
3
  size 343268717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6353a925cafe8840c2c126fba9edb0694908d92f0bfda785ecea8be80740660
3
  size 343268717
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2bad8ffde323ea4d873d4ea6f601f2ad8074201b415660915f2d39a92b3907b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
  size 14575
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a04b7ca52e62c545329902f7405b02b6f23d0e3265cf861e921213663d499ef
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab96bad09d57829f7b90b937a32bb83fb6a93bd7e03359b05ae3cd25a9340380
3
  size 627
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.03398842737078667,
3
- "best_model_checkpoint": "./vit-base-beans/checkpoint-100",
4
- "epoch": 2.3255813953488373,
5
- "global_step": 100,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -10,76 +10,46 @@
10
  {
11
  "epoch": 0.23,
12
  "learning_rate": 0.00018837209302325584,
13
- "loss": 0.4916,
14
  "step": 10
15
  },
16
  {
17
  "epoch": 0.47,
18
  "learning_rate": 0.00017674418604651164,
19
- "loss": 0.1876,
20
  "step": 20
21
  },
22
  {
23
  "epoch": 0.7,
24
  "learning_rate": 0.00016511627906976747,
25
- "loss": 0.2071,
26
  "step": 30
27
  },
28
  {
29
  "epoch": 0.93,
30
  "learning_rate": 0.00015348837209302327,
31
- "loss": 0.1312,
32
  "step": 40
33
  },
34
  {
35
  "epoch": 1.16,
36
  "learning_rate": 0.0001418604651162791,
37
- "loss": 0.0352,
38
  "step": 50
39
  },
40
  {
41
- "epoch": 1.4,
42
- "learning_rate": 0.0001302325581395349,
43
- "loss": 0.0399,
44
- "step": 60
45
- },
46
- {
47
- "epoch": 1.63,
48
- "learning_rate": 0.00011860465116279071,
49
- "loss": 0.0131,
50
- "step": 70
51
- },
52
- {
53
- "epoch": 1.86,
54
- "learning_rate": 0.00010697674418604651,
55
- "loss": 0.068,
56
- "step": 80
57
- },
58
- {
59
- "epoch": 2.09,
60
- "learning_rate": 9.534883720930233e-05,
61
- "loss": 0.0105,
62
- "step": 90
63
- },
64
- {
65
- "epoch": 2.33,
66
- "learning_rate": 8.372093023255814e-05,
67
- "loss": 0.0083,
68
- "step": 100
69
- },
70
- {
71
- "epoch": 2.33,
72
- "eval_accuracy": 0.9842931937172775,
73
- "eval_loss": 0.03398842737078667,
74
- "eval_runtime": 3.2659,
75
- "eval_samples_per_second": 58.484,
76
- "eval_steps_per_second": 7.349,
77
- "step": 100
78
  }
79
  ],
80
  "max_steps": 172,
81
  "num_train_epochs": 4,
82
- "total_flos": 1.239871833833472e+17,
83
  "trial_name": null,
84
  "trial_params": null
85
  }
 
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
  {
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9a45514ed7ce9c3bcd8ff62e497208fb4c074b81a735559b25781feab1174ff
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020d05f87f714abeb0eae454cd2eb3d07174ad2523c1db5d3bae5f87cfef750d
3
  size 3899