Hugging Face's logo

DanJoshua
/
profesor_MViT_S_VIOPERU

Transformers
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
 Metrics Community
DanJoshua commited on
Commit
094d5c5
·
verified ·
1 Parent(s): b27c169

Model save

Browse files
Files changed (4) hide show
  1. README.md +19 -17
  2. all_results.json +5 -5
  3. model.safetensors +1 -1
  4. train_results.json +5 -5
README.md CHANGED
@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6168
23
- - Accuracy: 0.8304
24
- - F1: 0.8303
25
- - Precision: 0.8305
26
- - Recall: 0.8304
27
- - Roc Auc: 0.8836
28
 
29
  ## Model description
30
 
@@ -44,26 +44,28 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 1e-05
47
- - train_batch_size: 20
48
- - eval_batch_size: 20
49
  - seed: 42
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
- - lr_scheduler_warmup_steps: 44
53
- - training_steps: 440
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc |
59
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------:|
60
- | 0.6732 | 3.0182 | 44 | 0.6748 | 0.7321 | 0.7321 | 0.7324 | 0.7321 | 0.7564 |
61
- | 0.6421 | 7.0091 | 88 | 0.6404 | 0.8036 | 0.8035 | 0.8040 | 0.8036 | 0.8482 |
62
- | 0.6014 | 10.0273 | 132 | 0.6064 | 0.8036 | 0.8035 | 0.8040 | 0.8036 | 0.8673 |
63
- | 0.5425 | 14.0182 | 176 | 0.5740 | 0.8036 | 0.8035 | 0.8040 | 0.8036 | 0.8776 |
64
- | 0.4931 | 18.0091 | 220 | 0.5276 | 0.7857 | 0.7846 | 0.7917 | 0.7857 | 0.8852 |
65
- | 0.4091 | 21.0273 | 264 | 0.4804 | 0.8036 | 0.8030 | 0.8071 | 0.8036 | 0.9018 |
66
- | 0.3446 | 25.0182 | 308 | 0.4592 | 0.8036 | 0.8020 | 0.8136 | 0.8036 | 0.8967 |
 
 
67
 
68
 
69
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.4191
23
+ - Accuracy: 0.8929
24
+ - F1: 0.8927
25
+ - Precision: 0.8949
26
+ - Recall: 0.8929
27
+ - Roc Auc: 0.9783
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 1e-05
47
+ - train_batch_size: 23
48
+ - eval_batch_size: 23
49
  - seed: 42
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 81
53
+ - training_steps: 810
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc |
59
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------:|
60
+ | 0.6473 | 6.0111 | 81 | 0.6350 | 0.75 | 0.7497 | 0.7513 | 0.75 | 0.8418 |
61
+ | 0.5438 | 13.0074 | 162 | 0.5559 | 0.7857 | 0.7857 | 0.7857 | 0.7857 | 0.8980 |
62
+ | 0.4124 | 20.0037 | 243 | 0.4445 | 0.8571 | 0.8564 | 0.8646 | 0.8571 | 0.9439 |
63
+ | 0.2958 | 26.0148 | 324 | 0.3501 | 0.8929 | 0.8927 | 0.8949 | 0.8929 | 0.9745 |
64
+ | 0.2126 | 33.0111 | 405 | 0.2827 | 0.8929 | 0.8927 | 0.8949 | 0.8929 | 0.9745 |
65
+ | 0.1469 | 40.0074 | 486 | 0.3615 | 0.875 | 0.8746 | 0.8794 | 0.875 | 0.9732 |
66
+ | 0.1063 | 47.0037 | 567 | 0.3208 | 0.8929 | 0.8927 | 0.8949 | 0.8929 | 0.9783 |
67
+ | 0.0883 | 53.0148 | 648 | 0.4270 | 0.875 | 0.8746 | 0.8794 | 0.875 | 0.9745 |
68
+ | 0.0631 | 60.0111 | 729 | 0.4191 | 0.8929 | 0.8927 | 0.8949 | 0.8929 | 0.9783 |
69
 
70
 
71
  ### Framework versions
all_results.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "epoch": 25.01818181818182,
3
  "eval_accuracy": 0.8303571428571429,
4
  "eval_f1": 0.8303436179542373,
5
  "eval_loss": 0.6168394088745117,
@@ -10,8 +10,8 @@
10
  "eval_samples_per_second": 1.451,
11
  "eval_steps_per_second": 0.078,
12
  "total_flos": 0.0,
13
- "train_loss": 0.5427347839652717,
14
- "train_runtime": 4082.9807,
15
- "train_samples_per_second": 2.155,
16
- "train_steps_per_second": 0.108
17
  }
 
1
  {
2
+ "epoch": 60.01111111111111,
3
  "eval_accuracy": 0.8303571428571429,
4
  "eval_f1": 0.8303436179542373,
5
  "eval_loss": 0.6168394088745117,
 
10
  "eval_samples_per_second": 1.451,
11
  "eval_steps_per_second": 0.078,
12
  "total_flos": 0.0,
13
+ "train_loss": 0.2925308818516254,
14
+ "train_runtime": 9457.9204,
15
+ "train_samples_per_second": 1.97,
16
+ "train_steps_per_second": 0.086
17
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ae84d1fe48109b3ca34d56c0a0b215aad6905f78dee594dc29670655a155cbf
3
  size 137270032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f4937332b094511b38eacee170c24e6f2d018b827f1855cc92f24e5b989bb0
3
  size 137270032
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 25.01818181818182,
3
  "total_flos": 0.0,
4
- "train_loss": 0.5427347839652717,
5
- "train_runtime": 4082.9807,
6
- "train_samples_per_second": 2.155,
7
- "train_steps_per_second": 0.108
8
  }
 
1
  {
2
+ "epoch": 60.01111111111111,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.2925308818516254,
5
+ "train_runtime": 9457.9204,
6
+ "train_samples_per_second": 1.97,
7
+ "train_steps_per_second": 0.086
8
  }