pabRomero commited on
Commit
107ade2
·
verified ·
1 Parent(s): 2b4b742

Training complete

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: FacebookAI/roberta-large
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: RoBERTa-Large-full-finetuned-ner-pablo
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # RoBERTa-Large-full-finetuned-ner-pablo
20
+
21
+ This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1030
24
+ - Precision: 0.8060
25
+ - Recall: 0.7767
26
+ - F1: 0.7910
27
+ - Accuracy: 0.9711
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: 0.0002
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
+ - seed: 42
50
+ - gradient_accumulation_steps: 4
51
+ - total_train_batch_size: 64
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_ratio: 0.05
55
+ - num_epochs: 5
56
+ - mixed_precision_training: Native AMP
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
+ | 0.3288 | 0.9996 | 652 | 0.1883 | 0.6920 | 0.6017 | 0.6437 | 0.9526 |
63
+ | 0.1779 | 1.9992 | 1304 | 0.1474 | 0.6717 | 0.7175 | 0.6939 | 0.9600 |
64
+ | 0.1471 | 2.9989 | 1956 | 0.1193 | 0.7544 | 0.7445 | 0.7494 | 0.9666 |
65
+ | 0.1029 | 4.0 | 2609 | 0.1109 | 0.7757 | 0.7709 | 0.7733 | 0.9693 |
66
+ | 0.0818 | 4.9981 | 3260 | 0.1030 | 0.8060 | 0.7767 | 0.7910 | 0.9711 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.44.0
72
+ - Pytorch 2.4.0+cu124
73
+ - Datasets 2.21.0
74
+ - Tokenizers 0.19.1