Hugging Face's logo

DanJoshua
/
estudiante_S3D_RWF2000

Transformers
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
 Metrics Community
DanJoshua commited on
Commit
bcf9028
·
verified ·
1 Parent(s): a4e9307

Model save

Browse files
Files changed (4) hide show
  1. README.md +87 -0
  2. all_results.json +8 -0
  3. model.safetensors +1 -1
  4. train_results.json +8 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - f1
8
+ - precision
9
+ - recall
10
+ model-index:
11
+ - name: estudiante_S3D_RWF2000
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # estudiante_S3D_RWF2000
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: 0.4603
23
+ - Accuracy: 0.8975
24
+ - F1: 0.8975
25
+ - Precision: 0.8980
26
+ - Recall: 0.8975
27
+ - Roc Auc: 0.9484
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 1e-05
47
+ - train_batch_size: 75
48
+ - eval_batch_size: 75
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: 189
53
+ - training_steps: 1890
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
+ | 0.4756 | 3.0116 | 94 | 0.4573 | 0.77 | 0.7623 | 0.8102 | 0.77 | 0.9241 |
61
+ | 0.3034 | 7.0106 | 188 | 0.4936 | 0.775 | 0.7641 | 0.8374 | 0.775 | 0.9375 |
62
+ | 0.2149 | 11.0095 | 282 | 0.7740 | 0.77 | 0.7583 | 0.8348 | 0.77 | 0.9408 |
63
+ | 0.1536 | 15.0085 | 376 | 0.7817 | 0.795 | 0.7877 | 0.8418 | 0.795 | 0.9405 |
64
+ | 0.1242 | 19.0074 | 470 | 0.7977 | 0.7875 | 0.7793 | 0.8375 | 0.7875 | 0.9390 |
65
+ | 0.0884 | 23.0063 | 564 | 0.7113 | 0.83 | 0.8263 | 0.8603 | 0.83 | 0.9438 |
66
+ | 0.0742 | 27.0053 | 658 | 0.6809 | 0.8325 | 0.8290 | 0.8619 | 0.8325 | 0.9446 |
67
+ | 0.055 | 31.0042 | 752 | 0.5733 | 0.835 | 0.8319 | 0.8613 | 0.835 | 0.9422 |
68
+ | 0.0441 | 35.0032 | 846 | 0.5877 | 0.85 | 0.8485 | 0.8646 | 0.85 | 0.9428 |
69
+ | 0.0304 | 39.0021 | 940 | 0.4630 | 0.865 | 0.8641 | 0.8746 | 0.865 | 0.9444 |
70
+ | 0.0242 | 43.0011 | 1034 | 0.5108 | 0.8675 | 0.8667 | 0.8765 | 0.8675 | 0.9440 |
71
+ | 0.0201 | 46.0127 | 1128 | 0.5144 | 0.87 | 0.8694 | 0.8774 | 0.87 | 0.9451 |
72
+ | 0.0165 | 50.0116 | 1222 | 0.3905 | 0.8825 | 0.8822 | 0.8860 | 0.8825 | 0.9463 |
73
+ | 0.0232 | 54.0106 | 1316 | 0.4735 | 0.8825 | 0.8822 | 0.8860 | 0.8825 | 0.9466 |
74
+ | 0.0098 | 58.0095 | 1410 | 0.4823 | 0.8825 | 0.8823 | 0.8847 | 0.8825 | 0.9457 |
75
+ | 0.0132 | 62.0085 | 1504 | 0.4508 | 0.88 | 0.8798 | 0.8824 | 0.88 | 0.9475 |
76
+ | 0.0105 | 66.0074 | 1598 | 0.4055 | 0.885 | 0.8849 | 0.8869 | 0.885 | 0.9477 |
77
+ | 0.0082 | 70.0063 | 1692 | 0.4190 | 0.885 | 0.8849 | 0.8869 | 0.885 | 0.9464 |
78
+ | 0.0072 | 74.0053 | 1786 | 0.4812 | 0.8875 | 0.8874 | 0.8891 | 0.8875 | 0.9476 |
79
+ | 0.0056 | 78.0042 | 1880 | 0.4603 | 0.8975 | 0.8975 | 0.8980 | 0.8975 | 0.9484 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.46.1
85
+ - Pytorch 2.0.1+cu118
86
+ - Datasets 3.1.0
87
+ - Tokenizers 0.20.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 78.00952380952381,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.09421822984835931,
5
+ "train_runtime": 45989.911,
6
+ "train_samples_per_second": 3.082,
7
+ "train_steps_per_second": 0.041
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6c31ee08109ff008d8d0e0b4192e3f6bf2e6e17d537285351132501b70e33b3
3
  size 31782968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2a07970c2d2f9c79b4971337098d48e710aabdfa6f800bd15427022bd8e40b
3
  size 31782968
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 78.00952380952381,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.09421822984835931,
5
+ "train_runtime": 45989.911,
6
+ "train_samples_per_second": 3.082,
7
+ "train_steps_per_second": 0.041
8
+ }