rollerhafeezh-amikom
commited on
Commit
•
14c209a
1
Parent(s):
16eea98
Training complete
Browse files
README.md
CHANGED
@@ -25,16 +25,16 @@ model-index:
|
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
-
value: 0.
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
-
value: 0.
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
-
value: 0.
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
44 |
|
45 |
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the wikiann dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
-
- Loss: 0.
|
48 |
-
- Precision: 0.
|
49 |
-
- Recall: 0.
|
50 |
-
- F1: 0.
|
51 |
-
- Accuracy: 0.
|
52 |
|
53 |
## Model description
|
54 |
|
@@ -67,12 +67,12 @@ More information needed
|
|
67 |
### Training hyperparameters
|
68 |
|
69 |
The following hyperparameters were used during training:
|
70 |
-
- learning_rate:
|
71 |
-
- train_batch_size:
|
72 |
- eval_batch_size: 8
|
73 |
- seed: 42
|
74 |
- gradient_accumulation_steps: 4
|
75 |
-
- total_train_batch_size:
|
76 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
77 |
- lr_scheduler_type: linear
|
78 |
- num_epochs: 3
|
@@ -81,9 +81,9 @@ The following hyperparameters were used during training:
|
|
81 |
|
82 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
83 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
84 |
-
| No log | 1.0 |
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
|
88 |
|
89 |
### Framework versions
|
|
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
+
value: 0.969802244788883
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
+
value: 0.9789587267332075
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
+
value: 0.9743589743589745
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9894519740718916
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
44 |
|
45 |
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the wikiann dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.0686
|
48 |
+
- Precision: 0.9698
|
49 |
+
- Recall: 0.9790
|
50 |
+
- F1: 0.9744
|
51 |
+
- Accuracy: 0.9895
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
67 |
### Training hyperparameters
|
68 |
|
69 |
The following hyperparameters were used during training:
|
70 |
+
- learning_rate: 2e-05
|
71 |
+
- train_batch_size: 4
|
72 |
- eval_batch_size: 8
|
73 |
- seed: 42
|
74 |
- gradient_accumulation_steps: 4
|
75 |
+
- total_train_batch_size: 16
|
76 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
77 |
- lr_scheduler_type: linear
|
78 |
- num_epochs: 3
|
|
|
81 |
|
82 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
83 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
84 |
+
| No log | 1.0 | 427 | 0.0717 | 0.9367 | 0.9701 | 0.9531 | 0.9862 |
|
85 |
+
| 0.0221 | 2.0 | 855 | 0.0715 | 0.9560 | 0.9733 | 0.9646 | 0.9880 |
|
86 |
+
| 0.0113 | 3.0 | 1281 | 0.0686 | 0.9698 | 0.9790 | 0.9744 | 0.9895 |
|
87 |
|
88 |
|
89 |
### Framework versions
|