Model save
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ base_model: xlm-roberta-base
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
-
|
8 |
metrics:
|
9 |
- precision
|
10 |
- recall
|
@@ -17,24 +17,24 @@ model-index:
|
|
17 |
name: Token Classification
|
18 |
type: token-classification
|
19 |
dataset:
|
20 |
-
name:
|
21 |
-
type:
|
22 |
config: en_ewt
|
23 |
split: validation
|
24 |
args: en_ewt
|
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
|
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
42 |
|
43 |
# UNER_subword_tk_en_lora_alpha_64_drop_0.3_rank_32_seed_42
|
44 |
|
45 |
-
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the
|
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 |
|
@@ -69,7 +69,7 @@ More information needed
|
|
69 |
The following hyperparameters were used during training:
|
70 |
- learning_rate: 0.0001
|
71 |
- train_batch_size: 32
|
72 |
-
- eval_batch_size:
|
73 |
- seed: 42
|
74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
- lr_scheduler_type: linear
|
@@ -79,26 +79,26 @@ The following hyperparameters were used during training:
|
|
79 |
|
80 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
-
| No log | 1.0 | 392 | 0.
|
83 |
-
| 0.1782 | 2.0 | 784 | 0.
|
84 |
-
| 0.0539 | 3.0 | 1176 | 0.
|
85 |
-
| 0.0435 | 4.0 | 1568 | 0.
|
86 |
-
| 0.0435 | 5.0 | 1960 | 0.
|
87 |
-
| 0.0385 | 6.0 | 2352 | 0.
|
88 |
-
| 0.0342 | 7.0 | 2744 | 0.
|
89 |
-
| 0.0313 | 8.0 | 3136 | 0.
|
90 |
-
| 0.0295 | 9.0 | 3528 | 0.
|
91 |
-
| 0.0295 | 10.0 | 3920 | 0.
|
92 |
-
| 0.0272 | 11.0 | 4312 | 0.
|
93 |
-
| 0.0256 | 12.0 | 4704 | 0.
|
94 |
-
| 0.0248 | 13.0 | 5096 | 0.
|
95 |
-
| 0.0248 | 14.0 | 5488 | 0.
|
96 |
-
| 0.023 | 15.0 | 5880 | 0.
|
97 |
-
| 0.0222 | 16.0 | 6272 | 0.
|
98 |
-
| 0.0205 | 17.0 | 6664 | 0.
|
99 |
-
| 0.0207 | 18.0 | 7056 | 0.
|
100 |
-
| 0.0207 | 19.0 | 7448 | 0.
|
101 |
-
| 0.0203 | 20.0 | 7840 | 0.
|
102 |
|
103 |
|
104 |
### Framework versions
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- universal_ner
|
8 |
metrics:
|
9 |
- precision
|
10 |
- recall
|
|
|
17 |
name: Token Classification
|
18 |
type: token-classification
|
19 |
dataset:
|
20 |
+
name: universal_ner
|
21 |
+
type: universal_ner
|
22 |
config: en_ewt
|
23 |
split: validation
|
24 |
args: en_ewt
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
+
value: 0.7735665694849369
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
+
value: 0.8240165631469979
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
+
value: 0.7979949874686717
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9840550320092251
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
42 |
|
43 |
# UNER_subword_tk_en_lora_alpha_64_drop_0.3_rank_32_seed_42
|
44 |
|
45 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the universal_ner dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.0607
|
48 |
+
- Precision: 0.7736
|
49 |
+
- Recall: 0.8240
|
50 |
+
- F1: 0.7980
|
51 |
+
- Accuracy: 0.9841
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
69 |
The following hyperparameters were used during training:
|
70 |
- learning_rate: 0.0001
|
71 |
- train_batch_size: 32
|
72 |
+
- eval_batch_size: 32
|
73 |
- seed: 42
|
74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
- lr_scheduler_type: linear
|
|
|
79 |
|
80 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| No log | 1.0 | 392 | 0.0899 | 0.5755 | 0.7143 | 0.6374 | 0.9740 |
|
83 |
+
| 0.1782 | 2.0 | 784 | 0.0651 | 0.6961 | 0.7919 | 0.7409 | 0.9799 |
|
84 |
+
| 0.0539 | 3.0 | 1176 | 0.0664 | 0.7144 | 0.8209 | 0.7640 | 0.9815 |
|
85 |
+
| 0.0435 | 4.0 | 1568 | 0.0581 | 0.7170 | 0.8209 | 0.7654 | 0.9821 |
|
86 |
+
| 0.0435 | 5.0 | 1960 | 0.0584 | 0.7321 | 0.8261 | 0.7763 | 0.9820 |
|
87 |
+
| 0.0385 | 6.0 | 2352 | 0.0571 | 0.7409 | 0.8230 | 0.7798 | 0.9827 |
|
88 |
+
| 0.0342 | 7.0 | 2744 | 0.0580 | 0.7433 | 0.8333 | 0.7857 | 0.9829 |
|
89 |
+
| 0.0313 | 8.0 | 3136 | 0.0578 | 0.7744 | 0.8282 | 0.8004 | 0.9846 |
|
90 |
+
| 0.0295 | 9.0 | 3528 | 0.0566 | 0.7588 | 0.8271 | 0.7915 | 0.9835 |
|
91 |
+
| 0.0295 | 10.0 | 3920 | 0.0564 | 0.7756 | 0.8302 | 0.8020 | 0.9848 |
|
92 |
+
| 0.0272 | 11.0 | 4312 | 0.0557 | 0.7597 | 0.8344 | 0.7953 | 0.9835 |
|
93 |
+
| 0.0256 | 12.0 | 4704 | 0.0585 | 0.7787 | 0.8157 | 0.7968 | 0.9841 |
|
94 |
+
| 0.0248 | 13.0 | 5096 | 0.0574 | 0.7812 | 0.8240 | 0.8020 | 0.9845 |
|
95 |
+
| 0.0248 | 14.0 | 5488 | 0.0577 | 0.7604 | 0.8344 | 0.7957 | 0.9836 |
|
96 |
+
| 0.023 | 15.0 | 5880 | 0.0583 | 0.7812 | 0.8282 | 0.8040 | 0.9845 |
|
97 |
+
| 0.0222 | 16.0 | 6272 | 0.0595 | 0.7733 | 0.8333 | 0.8022 | 0.9841 |
|
98 |
+
| 0.0205 | 17.0 | 6664 | 0.0603 | 0.7755 | 0.8261 | 0.8 | 0.9839 |
|
99 |
+
| 0.0207 | 18.0 | 7056 | 0.0605 | 0.7744 | 0.8282 | 0.8004 | 0.9840 |
|
100 |
+
| 0.0207 | 19.0 | 7448 | 0.0611 | 0.7770 | 0.8333 | 0.8042 | 0.9842 |
|
101 |
+
| 0.0203 | 20.0 | 7840 | 0.0607 | 0.7736 | 0.8240 | 0.7980 | 0.9841 |
|
102 |
|
103 |
|
104 |
### Framework versions
|