dima806 commited on
Commit
889ed6e
1 Parent(s): ed98492

Upload folder using huggingface_hub

Browse files
checkpoint-3811/config.json CHANGED
@@ -120,5 +120,5 @@
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
- "transformers_version": "4.37.2"
124
  }
 
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
+ "transformers_version": "4.38.1"
124
  }
checkpoint-3811/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf5f6f1dfd2ccde0d7a7a24e1e6044f20ebc081c27c4474c0901aeeec0ac23f
3
  size 343365480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9449fd2d1966756ea426a5eaed7016b0a2b06e90c9b93c5c152101c63e800467
3
  size 343365480
checkpoint-3811/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d362186704f9c56250778b57f1ea20edfb0596a177fadcd6898a087c34ec3d94
3
  size 686851461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6722a5f10822f8dd81119396666550fca6614bebaaf4c062fafa0e1c32ff9786
3
  size 686851461
checkpoint-3811/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b668fdb5dc699008b82d229ecd74c73544a23840131a335df22bdecd69c9d0f8
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47937116bc899ee0e8d20f420e26be61bf299bdf92003f1cac432d282b42481f
3
  size 14575
checkpoint-3811/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 2.5512685775756836,
3
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-3811",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,53 +10,60 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13,
 
13
  "learning_rate": 2.641052911459718e-07,
14
- "loss": 2.5439,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 0.26,
 
19
  "learning_rate": 2.2422228130816273e-07,
20
- "loss": 2.5463,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 0.39,
 
25
  "learning_rate": 1.8433927147035363e-07,
26
- "loss": 2.5467,
27
  "step": 1500
28
  },
29
  {
30
  "epoch": 0.52,
 
31
  "learning_rate": 1.444562616325445e-07,
32
- "loss": 2.5433,
33
  "step": 2000
34
  },
35
  {
36
  "epoch": 0.66,
 
37
  "learning_rate": 1.0457325179473543e-07,
38
- "loss": 2.5426,
39
  "step": 2500
40
  },
41
  {
42
  "epoch": 0.79,
 
43
  "learning_rate": 6.469024195692635e-08,
44
- "loss": 2.5382,
45
  "step": 3000
46
  },
47
  {
48
  "epoch": 0.92,
 
49
  "learning_rate": 2.4807232119117254e-08,
50
- "loss": 2.5352,
51
  "step": 3500
52
  },
53
  {
54
  "epoch": 1.0,
55
- "eval_accuracy": 0.4089533510481252,
56
- "eval_loss": 2.5512685775756836,
57
- "eval_runtime": 320.305,
58
- "eval_samples_per_second": 84.594,
59
- "eval_steps_per_second": 2.644,
60
  "step": 3811
61
  }
62
  ],
 
1
  {
2
+ "best_metric": 2.530700206756592,
3
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-3811",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13,
13
+ "grad_norm": 2.8601508140563965,
14
  "learning_rate": 2.641052911459718e-07,
15
+ "loss": 2.5249,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.26,
20
+ "grad_norm": 2.4823763370513916,
21
  "learning_rate": 2.2422228130816273e-07,
22
+ "loss": 2.5332,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.39,
27
+ "grad_norm": 3.0686984062194824,
28
  "learning_rate": 1.8433927147035363e-07,
29
+ "loss": 2.5257,
30
  "step": 1500
31
  },
32
  {
33
  "epoch": 0.52,
34
+ "grad_norm": 2.4510738849639893,
35
  "learning_rate": 1.444562616325445e-07,
36
+ "loss": 2.5138,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.66,
41
+ "grad_norm": 2.1571173667907715,
42
  "learning_rate": 1.0457325179473543e-07,
43
+ "loss": 2.521,
44
  "step": 2500
45
  },
46
  {
47
  "epoch": 0.79,
48
+ "grad_norm": 2.9375104904174805,
49
  "learning_rate": 6.469024195692635e-08,
50
+ "loss": 2.5142,
51
  "step": 3000
52
  },
53
  {
54
  "epoch": 0.92,
55
+ "grad_norm": 3.093559503555298,
56
  "learning_rate": 2.4807232119117254e-08,
57
+ "loss": 2.5058,
58
  "step": 3500
59
  },
60
  {
61
  "epoch": 1.0,
62
+ "eval_accuracy": 0.41552258635961026,
63
+ "eval_loss": 2.530700206756592,
64
+ "eval_runtime": 299.6579,
65
+ "eval_samples_per_second": 90.423,
66
+ "eval_steps_per_second": 2.827,
67
  "step": 3811
68
  }
69
  ],
checkpoint-3811/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06011ad1af114029fbc190c3719d27b6d4c4854d6a202ffb9e678265e68cb0ee
3
- size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3778b54042e77bf37dd5c8d74f4432f27fcc27b31fdf7ef4e19085906e116ef3
3
+ size 4411
config.json CHANGED
@@ -120,5 +120,5 @@
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
- "transformers_version": "4.37.2"
124
  }
 
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
+ "transformers_version": "4.38.1"
124
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf5f6f1dfd2ccde0d7a7a24e1e6044f20ebc081c27c4474c0901aeeec0ac23f
3
  size 343365480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9449fd2d1966756ea426a5eaed7016b0a2b06e90c9b93c5c152101c63e800467
3
  size 343365480
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06011ad1af114029fbc190c3719d27b6d4c4854d6a202ffb9e678265e68cb0ee
3
- size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3778b54042e77bf37dd5c8d74f4432f27fcc27b31fdf7ef4e19085906e116ef3
3
+ size 4411