Hugging Face's logo

HorcruxNo13
/
beit-base-patch16-224-pt22k-ft22k

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
HorcruxNo13 commited on
Commit
682f8c0
•
1 Parent(s): b7b0f4c

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. all_results.json +5 -5
  2. pytorch_model.bin +1 -1
  3. train_results.json +5 -5
  4. trainer_state.json +25 -25
  5. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "total_flos": 2.32376605913088e+17,
4
- "train_loss": 3.054683963457743,
5
- "train_runtime": 175.6001,
6
- "train_samples_per_second": 17.084,
7
- "train_steps_per_second": 0.137
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "total_flos": 2.77880533604352e+17,
4
+ "train_loss": 3.9848953088124595,
5
+ "train_runtime": 321.3932,
6
+ "train_samples_per_second": 9.334,
7
+ "train_steps_per_second": 0.075
8
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbb51149e3ab4f2462ff4ccfc4d640ed7e6145853f9787eff19d9f50af37b271
3
  size 410307017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77fba285dba7d46bf2f67eb1461d08ebd2c08fcc74c440915984b64121049bb9
3
  size 410307017
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "total_flos": 2.32376605913088e+17,
4
- "train_loss": 3.054683963457743,
5
- "train_runtime": 175.6001,
6
- "train_samples_per_second": 17.084,
7
- "train_steps_per_second": 0.137
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "total_flos": 2.77880533604352e+17,
4
+ "train_loss": 3.9848953088124595,
5
+ "train_runtime": 321.3932,
6
+ "train_samples_per_second": 9.334,
7
+ "train_steps_per_second": 0.075
8
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.7333333333333333,
3
- "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k/checkpoint-8",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
  "global_step": 24,
@@ -10,58 +10,58 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7333333333333333,
14
- "eval_loss": 3.1590805053710938,
15
- "eval_runtime": 3.4474,
16
- "eval_samples_per_second": 69.617,
17
- "eval_steps_per_second": 2.321,
18
  "step": 8
19
  },
20
  {
21
  "epoch": 1.25,
22
  "learning_rate": 0.03333333333333333,
23
- "loss": 5.12,
24
  "step": 10
25
  },
26
  {
27
  "epoch": 2.0,
28
- "eval_accuracy": 0.26666666666666666,
29
- "eval_loss": 2.633744716644287,
30
- "eval_runtime": 3.2534,
31
- "eval_samples_per_second": 73.768,
32
- "eval_steps_per_second": 2.459,
33
  "step": 16
34
  },
35
  {
36
  "epoch": 2.5,
37
  "learning_rate": 0.009523809523809525,
38
- "loss": 1.8305,
39
  "step": 20
40
  },
41
  {
42
  "epoch": 3.0,
43
- "eval_accuracy": 0.7333333333333333,
44
- "eval_loss": 0.6371921300888062,
45
- "eval_runtime": 3.6339,
46
- "eval_samples_per_second": 66.045,
47
- "eval_steps_per_second": 2.202,
48
  "step": 24
49
  },
50
  {
51
  "epoch": 3.0,
52
  "step": 24,
53
- "total_flos": 2.32376605913088e+17,
54
- "train_loss": 3.054683963457743,
55
- "train_runtime": 175.6001,
56
- "train_samples_per_second": 17.084,
57
- "train_steps_per_second": 0.137
58
  }
59
  ],
60
  "logging_steps": 10,
61
  "max_steps": 24,
62
  "num_train_epochs": 3,
63
  "save_steps": 500,
64
- "total_flos": 2.32376605913088e+17,
65
  "trial_name": null,
66
  "trial_params": null
67
  }
 
1
  {
2
+ "best_metric": 0.725,
3
+ "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k/checkpoint-16",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
  "global_step": 24,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.275,
14
+ "eval_loss": 2.470369815826416,
15
+ "eval_runtime": 66.8165,
16
+ "eval_samples_per_second": 3.592,
17
+ "eval_steps_per_second": 0.12,
18
  "step": 8
19
  },
20
  {
21
  "epoch": 1.25,
22
  "learning_rate": 0.03333333333333333,
23
+ "loss": 8.3532,
24
  "step": 10
25
  },
26
  {
27
  "epoch": 2.0,
28
+ "eval_accuracy": 0.725,
29
+ "eval_loss": 0.685380756855011,
30
+ "eval_runtime": 3.4245,
31
+ "eval_samples_per_second": 70.083,
32
+ "eval_steps_per_second": 2.336,
33
  "step": 16
34
  },
35
  {
36
  "epoch": 2.5,
37
  "learning_rate": 0.009523809523809525,
38
+ "loss": 0.9363,
39
  "step": 20
40
  },
41
  {
42
  "epoch": 3.0,
43
+ "eval_accuracy": 0.725,
44
+ "eval_loss": 0.6314295530319214,
45
+ "eval_runtime": 3.2582,
46
+ "eval_samples_per_second": 73.66,
47
+ "eval_steps_per_second": 2.455,
48
  "step": 24
49
  },
50
  {
51
  "epoch": 3.0,
52
  "step": 24,
53
+ "total_flos": 2.77880533604352e+17,
54
+ "train_loss": 3.9848953088124595,
55
+ "train_runtime": 321.3932,
56
+ "train_samples_per_second": 9.334,
57
+ "train_steps_per_second": 0.075
58
  }
59
  ],
60
  "logging_steps": 10,
61
  "max_steps": 24,
62
  "num_train_epochs": 3,
63
  "save_steps": 500,
64
+ "total_flos": 2.77880533604352e+17,
65
  "trial_name": null,
66
  "trial_params": null
67
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:482cb12aab0ceded9970fba68a99a0c3a084beb389d5b2767c37c56bc1db311c
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffbd9d796cc5934996b0bcbde90a6dbdde8985ee8ab80ff909927fdec9534de7
3
  size 4091