dima806 commited on
Commit
5b43d69
1 Parent(s): 3c9d9f2

Upload folder using huggingface_hub

Browse files
checkpoint-3083/config.json CHANGED
@@ -28,5 +28,5 @@
28
  "problem_type": "single_label_classification",
29
  "qkv_bias": true,
30
  "torch_dtype": "float32",
31
- "transformers_version": "4.36.2"
32
  }
 
28
  "problem_type": "single_label_classification",
29
  "qkv_bias": true,
30
  "torch_dtype": "float32",
31
+ "transformers_version": "4.38.1"
32
  }
checkpoint-3083/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52086aa16a0e53e76b5784b7d988db288488bdfbb39ec5091336774078a0db7d
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3a80f5c706bca73ca214109bf83b272fca7f90ee9a6d205be513a9376317d1
3
  size 343223968
checkpoint-3083/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02d4ecfae19c8535542f4fe9da532367c586895ad8ae988f9a3d26a329e715a5
3
- size 686568453
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eec085e0540c0de44a4fb182dd1fe4a92666b36a05b9351020353d6d757df6b
3
+ size 686568890
checkpoint-3083/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69b162c02e967df6c30d2992f889a341e337cd98122ef045821cff41ce24f93a
3
- size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc4283a115199ee7bf1c952aee6079e4cbfe30fe75b04b54e426b009e600e7f
3
+ size 14244
checkpoint-3083/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74c1465b7ec7760d31a35532f7949881605ce9fd3fd8dc2de409151d75509d99
3
- size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ab7441b7e56f11f9b21b2f7a84e78331ef7bc6964005b79e8d38df2cfec818
3
+ size 1064
checkpoint-3083/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.33903706073760986,
3
  "best_model_checkpoint": "attractive_faces_celebs_detection/checkpoint-3083",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,47 +10,53 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.16,
13
- "learning_rate": 8.516320474777447e-07,
14
- "loss": 0.3642,
 
15
  "step": 500
16
  },
17
  {
18
  "epoch": 0.32,
19
- "learning_rate": 6.867787668974612e-07,
20
- "loss": 0.3589,
 
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 0.49,
25
- "learning_rate": 5.219254863171777e-07,
26
- "loss": 0.3581,
 
27
  "step": 1500
28
  },
29
  {
30
  "epoch": 0.65,
31
- "learning_rate": 3.5707220573689416e-07,
32
- "loss": 0.3551,
 
33
  "step": 2000
34
  },
35
  {
36
  "epoch": 0.81,
37
- "learning_rate": 1.9221892515661062e-07,
38
- "loss": 0.357,
 
39
  "step": 2500
40
  },
41
  {
42
  "epoch": 0.97,
43
- "learning_rate": 2.7365644576327068e-08,
44
- "loss": 0.3562,
 
45
  "step": 3000
46
  },
47
  {
48
  "epoch": 1.0,
49
- "eval_accuracy": 0.8429314329738059,
50
- "eval_loss": 0.33903706073760986,
51
- "eval_runtime": 98.4909,
52
- "eval_samples_per_second": 105.431,
53
- "eval_steps_per_second": 3.3,
54
  "step": 3083
55
  }
56
  ],
 
1
  {
2
+ "best_metric": 0.34020188450813293,
3
  "best_model_checkpoint": "attractive_faces_celebs_detection/checkpoint-3083",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.16,
13
+ "grad_norm": 1.2501987218856812,
14
+ "learning_rate": 2.5548961424332345e-07,
15
+ "loss": 0.3544,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.32,
20
+ "grad_norm": 1.8902180194854736,
21
+ "learning_rate": 2.060336300692384e-07,
22
+ "loss": 0.3567,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.49,
27
+ "grad_norm": 1.0417747497558594,
28
+ "learning_rate": 1.565776458951533e-07,
29
+ "loss": 0.3574,
30
  "step": 1500
31
  },
32
  {
33
  "epoch": 0.65,
34
+ "grad_norm": 1.3442531824111938,
35
+ "learning_rate": 1.0712166172106825e-07,
36
+ "loss": 0.3558,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.81,
41
+ "grad_norm": 1.7245718240737915,
42
+ "learning_rate": 5.766567754698319e-08,
43
+ "loss": 0.3562,
44
  "step": 2500
45
  },
46
  {
47
  "epoch": 0.97,
48
+ "grad_norm": 1.2036902904510498,
49
+ "learning_rate": 8.20969337289812e-09,
50
+ "loss": 0.3545,
51
  "step": 3000
52
  },
53
  {
54
  "epoch": 1.0,
55
+ "eval_accuracy": 0.8378274268104776,
56
+ "eval_loss": 0.34020188450813293,
57
+ "eval_runtime": 95.2822,
58
+ "eval_samples_per_second": 108.982,
59
+ "eval_steps_per_second": 3.411,
60
  "step": 3083
61
  }
62
  ],
checkpoint-3083/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d1c7fe3249808625e105f85d80f7a9525b21d12cee2a508a7eb95ae620eedd6
3
- size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a379e76c753034f1463de1c22bf9fc150d5ba8468f84ab8a5d6735a57468aa24
3
+ size 4856
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58c4ab4867f7ffb1a9f0d962842bc5e4a0ae7f27e6fb71f876c535ba58a7a61f
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3a80f5c706bca73ca214109bf83b272fca7f90ee9a6d205be513a9376317d1
3
  size 343223968