dima806 commited on
Commit
603589a
·
verified ·
1 Parent(s): 372e951

Upload folder using huggingface_hub

Browse files
checkpoint-4989/config.json CHANGED
@@ -60,5 +60,5 @@
60
  "problem_type": "single_label_classification",
61
  "qkv_bias": true,
62
  "torch_dtype": "float32",
63
- "transformers_version": "4.41.1"
64
  }
 
60
  "problem_type": "single_label_classification",
61
  "qkv_bias": true,
62
  "torch_dtype": "float32",
63
+ "transformers_version": "4.41.2"
64
  }
checkpoint-4989/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6e3797aab8b8cd941fae1aa768972dd05068d1dbec02ba376c498d5f8d5a10
3
  size 343273192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6572381f0d82e49d8ffa641a16d527ee697ad7e8498c672b03c60fda1e399b36
3
  size 343273192
checkpoint-4989/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62e66bbfccd83b044162eb5b1d594efdbf258e99331b726e95d906dcd9c2dd87
3
  size 686666885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1c622b82a8f810d1ec287ed9b58aa24acd92ad360242d3aa120025c7739edd
3
  size 686666885
checkpoint-4989/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.3838658332824707,
3
  "best_model_checkpoint": "hand_gestures_image_detection/checkpoint-4989",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,74 +10,74 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.10022048506714773,
13
- "grad_norm": 4.403792381286621,
14
  "learning_rate": 1.817776877910508e-07,
15
- "loss": 0.3862,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.20044097013429546,
20
- "grad_norm": 3.355459690093994,
21
  "learning_rate": 1.6153067422555175e-07,
22
- "loss": 0.3863,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.30066145520144316,
27
- "grad_norm": 2.863913059234619,
28
  "learning_rate": 1.4128366066005264e-07,
29
- "loss": 0.3806,
30
  "step": 1500
31
  },
32
  {
33
  "epoch": 0.4008819402685909,
34
- "grad_norm": 3.9345569610595703,
35
  "learning_rate": 1.2103664709455354e-07,
36
- "loss": 0.3765,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.5011024253357387,
41
- "grad_norm": 4.702720642089844,
42
  "learning_rate": 1.0078963352905445e-07,
43
- "loss": 0.3703,
44
  "step": 2500
45
  },
46
  {
47
  "epoch": 0.6013229104028863,
48
- "grad_norm": 3.5991787910461426,
49
  "learning_rate": 8.054261996355537e-08,
50
- "loss": 0.3719,
51
  "step": 3000
52
  },
53
  {
54
  "epoch": 0.7015433954700341,
55
- "grad_norm": 2.9875855445861816,
56
  "learning_rate": 6.029560639805629e-08,
57
- "loss": 0.3694,
58
  "step": 3500
59
  },
60
  {
61
  "epoch": 0.8017638805371818,
62
- "grad_norm": 4.093947887420654,
63
  "learning_rate": 4.00485928325572e-08,
64
- "loss": 0.3689,
65
  "step": 4000
66
  },
67
  {
68
  "epoch": 0.9019843656043295,
69
- "grad_norm": 2.9663009643554688,
70
  "learning_rate": 1.980157926705811e-08,
71
- "loss": 0.3698,
72
  "step": 4500
73
  },
74
  {
75
  "epoch": 1.0,
76
- "eval_accuracy": 0.9586631651641212,
77
- "eval_loss": 0.3838658332824707,
78
- "eval_runtime": 2604.9028,
79
- "eval_samples_per_second": 81.716,
80
- "eval_steps_per_second": 2.554,
81
  "step": 4989
82
  }
83
  ],
 
1
  {
2
+ "best_metric": 0.3653666079044342,
3
  "best_model_checkpoint": "hand_gestures_image_detection/checkpoint-4989",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.10022048506714773,
13
+ "grad_norm": 4.143678188323975,
14
  "learning_rate": 1.817776877910508e-07,
15
+ "loss": 0.369,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.20044097013429546,
20
+ "grad_norm": 1.583790898323059,
21
  "learning_rate": 1.6153067422555175e-07,
22
+ "loss": 0.3611,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.30066145520144316,
27
+ "grad_norm": 4.256168365478516,
28
  "learning_rate": 1.4128366066005264e-07,
29
+ "loss": 0.3609,
30
  "step": 1500
31
  },
32
  {
33
  "epoch": 0.4008819402685909,
34
+ "grad_norm": 2.3767576217651367,
35
  "learning_rate": 1.2103664709455354e-07,
36
+ "loss": 0.3581,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.5011024253357387,
41
+ "grad_norm": 4.901381015777588,
42
  "learning_rate": 1.0078963352905445e-07,
43
+ "loss": 0.3564,
44
  "step": 2500
45
  },
46
  {
47
  "epoch": 0.6013229104028863,
48
+ "grad_norm": 2.049335479736328,
49
  "learning_rate": 8.054261996355537e-08,
50
+ "loss": 0.3457,
51
  "step": 3000
52
  },
53
  {
54
  "epoch": 0.7015433954700341,
55
+ "grad_norm": 4.378603935241699,
56
  "learning_rate": 6.029560639805629e-08,
57
+ "loss": 0.3495,
58
  "step": 3500
59
  },
60
  {
61
  "epoch": 0.8017638805371818,
62
+ "grad_norm": 3.5756170749664307,
63
  "learning_rate": 4.00485928325572e-08,
64
+ "loss": 0.3545,
65
  "step": 4000
66
  },
67
  {
68
  "epoch": 0.9019843656043295,
69
+ "grad_norm": 4.958667755126953,
70
  "learning_rate": 1.980157926705811e-08,
71
+ "loss": 0.3484,
72
  "step": 4500
73
  },
74
  {
75
  "epoch": 1.0,
76
+ "eval_accuracy": 0.9589215497437295,
77
+ "eval_loss": 0.3653666079044342,
78
+ "eval_runtime": 2787.3216,
79
+ "eval_samples_per_second": 76.368,
80
+ "eval_steps_per_second": 2.387,
81
  "step": 4989
82
  }
83
  ],
config.json CHANGED
@@ -60,5 +60,5 @@
60
  "problem_type": "single_label_classification",
61
  "qkv_bias": true,
62
  "torch_dtype": "float32",
63
- "transformers_version": "4.41.1"
64
  }
 
60
  "problem_type": "single_label_classification",
61
  "qkv_bias": true,
62
  "torch_dtype": "float32",
63
+ "transformers_version": "4.41.2"
64
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6e3797aab8b8cd941fae1aa768972dd05068d1dbec02ba376c498d5f8d5a10
3
  size 343273192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6572381f0d82e49d8ffa641a16d527ee697ad7e8498c672b03c60fda1e399b36
3
  size 343273192