khalidrajan
commited on
Commit
•
5cbc615
1
Parent(s):
d80bcaf
End of training
Browse files- README.md +22 -14
- model.safetensors +1 -1
- special_tokens_map.json +6 -42
- tokenizer_config.json +0 -7
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# roberta_crf_ner_finetuned
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss:
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -43,21 +43,29 @@ More information needed
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
-
- learning_rate:
|
47 |
-
- train_batch_size:
|
48 |
-
- eval_batch_size:
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
-
|
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: FacebookAI/roberta-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
18 |
|
19 |
# roberta_crf_ner_finetuned
|
20 |
|
21 |
+
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: nan
|
24 |
+
- Precision: 0.8044
|
25 |
+
- Recall: 0.6309
|
26 |
+
- F1: 0.7014
|
27 |
+
- Accuracy: 0.8064
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_steps: 500
|
53 |
+
- num_epochs: 10
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 0.0 | 1.0 | 85 | nan | 1.0 | 0.0 | 0.0 | 0.7707 |
|
60 |
+
| 0.0 | 2.0 | 170 | nan | 0.5105 | 0.1412 | 0.1284 | 0.8910 |
|
61 |
+
| 0.0 | 3.0 | 255 | nan | 0.3443 | 0.3458 | 0.3346 | 0.9210 |
|
62 |
+
| 0.0 | 4.0 | 340 | nan | 0.5898 | 0.5990 | 0.5930 | 0.9423 |
|
63 |
+
| 0.0 | 5.0 | 425 | nan | 0.5650 | 0.5795 | 0.5606 | 0.9421 |
|
64 |
+
| 0.0 | 6.0 | 510 | nan | 0.6261 | 0.6867 | 0.6515 | 0.9470 |
|
65 |
+
| 0.0 | 7.0 | 595 | nan | 0.6874 | 0.6640 | 0.6724 | 0.9457 |
|
66 |
+
| 0.0 | 8.0 | 680 | nan | 0.6825 | 0.7224 | 0.7011 | 0.9549 |
|
67 |
+
| 0.0 | 9.0 | 765 | nan | 0.6744 | 0.7224 | 0.6972 | 0.9551 |
|
68 |
+
| 0.0 | 10.0 | 850 | nan | 0.7020 | 0.7062 | 0.7035 | 0.9552 |
|
69 |
|
70 |
|
71 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 496273984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:996c81c4c002120e76fa2fa5d95e9ddd639e6131735c934c7068ddeac5db1f20
|
3 |
size 496273984
|
special_tokens_map.json
CHANGED
@@ -1,25 +1,7 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "<s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "</s>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"mask_token": {
|
24 |
"content": "<mask>",
|
25 |
"lstrip": true,
|
@@ -27,25 +9,7 @@
|
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
-
"pad_token":
|
31 |
-
|
32 |
-
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "</s>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": true,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
-
"unk_token": {
|
45 |
-
"content": "<unk>",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": true,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false
|
50 |
-
}
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
tokenizer_config.json
CHANGED
@@ -48,17 +48,10 @@
|
|
48 |
"eos_token": "</s>",
|
49 |
"errors": "replace",
|
50 |
"mask_token": "<mask>",
|
51 |
-
"max_length": 512,
|
52 |
"model_max_length": 512,
|
53 |
-
"pad_to_multiple_of": null,
|
54 |
"pad_token": "<pad>",
|
55 |
-
"pad_token_type_id": 0,
|
56 |
-
"padding_side": "right",
|
57 |
"sep_token": "</s>",
|
58 |
-
"stride": 0,
|
59 |
"tokenizer_class": "RobertaTokenizer",
|
60 |
"trim_offsets": true,
|
61 |
-
"truncation_side": "right",
|
62 |
-
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "<unk>"
|
64 |
}
|
|
|
48 |
"eos_token": "</s>",
|
49 |
"errors": "replace",
|
50 |
"mask_token": "<mask>",
|
|
|
51 |
"model_max_length": 512,
|
|
|
52 |
"pad_token": "<pad>",
|
|
|
|
|
53 |
"sep_token": "</s>",
|
|
|
54 |
"tokenizer_class": "RobertaTokenizer",
|
55 |
"trim_offsets": true,
|
|
|
|
|
56 |
"unk_token": "<unk>"
|
57 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01eea6c2b72a7dbcae7fb6a6ce419fa6ffc52a1947e1038276d30adf795d5b12
|
3 |
+
size 5176
|