End of training
Browse files- README.md +21 -15
- config.json +29 -21
- merges.txt +0 -0
- model.safetensors +2 -2
- special_tokens_map.json +11 -11
- tokenizer.json +0 -0
- tokenizer_config.json +22 -23
- training_args.bin +2 -2
- vocab.json +0 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,17 +13,21 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# output
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
-
- Name Student Precision: 0.
|
20 |
- Name Student Recall: 1.0
|
21 |
-
- Name Student F1: 0.
|
22 |
-
- Name Student Number:
|
23 |
-
-
|
24 |
-
-
|
25 |
-
-
|
26 |
-
-
|
|
|
|
|
|
|
|
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -46,6 +50,8 @@ The following hyperparameters were used during training:
|
|
46 |
- train_batch_size: 2
|
47 |
- eval_batch_size: 4
|
48 |
- seed: 42
|
|
|
|
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -54,10 +60,10 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
-
| Training Loss | Epoch | Step | Validation Loss | Name Student Precision | Name Student Recall | Name Student F1 | Name Student Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
58 |
-
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: allenai/longformer-base-4096
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# output
|
15 |
|
16 |
+
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0554
|
19 |
+
- Name Student Precision: 0.9535
|
20 |
- Name Student Recall: 1.0
|
21 |
+
- Name Student F1: 0.9762
|
22 |
+
- Name Student Number: 41
|
23 |
+
- Url Personal Precision: 0.0
|
24 |
+
- Url Personal Recall: 0.0
|
25 |
+
- Url Personal F1: 0.0
|
26 |
+
- Url Personal Number: 1
|
27 |
+
- Overall Precision: 0.9535
|
28 |
+
- Overall Recall: 0.9762
|
29 |
+
- Overall F1: 0.9647
|
30 |
+
- Overall Accuracy: 0.9925
|
31 |
|
32 |
## Model description
|
33 |
|
|
|
50 |
- train_batch_size: 2
|
51 |
- eval_batch_size: 4
|
52 |
- seed: 42
|
53 |
+
- gradient_accumulation_steps: 4
|
54 |
+
- total_train_batch_size: 8
|
55 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
- lr_scheduler_type: linear
|
57 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Name Student Precision | Name Student Recall | Name Student F1 | Name Student Number | Url Personal Precision | Url Personal Recall | Url Personal F1 | Url Personal Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
64 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
65 |
+
| 0.0023 | 1.0 | 100 | 0.0549 | 0.9535 | 1.0 | 0.9762 | 41 | 0.0 | 0.0 | 0.0 | 1 | 0.9535 | 0.9762 | 0.9647 | 0.9925 |
|
66 |
+
| 0.0009 | 2.0 | 200 | 0.0554 | 0.9535 | 1.0 | 0.9762 | 41 | 0.0 | 0.0 | 0.0 | 1 | 0.9535 | 0.9762 | 0.9647 | 0.9925 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
config.json
CHANGED
@@ -1,9 +1,27 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
|
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
"hidden_size": 768,
|
@@ -22,6 +40,7 @@
|
|
22 |
"11": "I-URL_PERSONAL",
|
23 |
"12": "O"
|
24 |
},
|
|
|
25 |
"initializer_range": 0.02,
|
26 |
"intermediate_size": 3072,
|
27 |
"label2id": {
|
@@ -39,27 +58,16 @@
|
|
39 |
"I-URL_PERSONAL": 11,
|
40 |
"O": 12
|
41 |
},
|
42 |
-
"layer_norm_eps": 1e-
|
43 |
-
"max_position_embeddings":
|
44 |
-
"
|
45 |
-
"model_type": "deberta-v2",
|
46 |
-
"norm_rel_ebd": "layer_norm",
|
47 |
"num_attention_heads": 12,
|
48 |
"num_hidden_layers": 12,
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"pooler_hidden_size": 768,
|
53 |
-
"pos_att_type": [
|
54 |
-
"p2c",
|
55 |
-
"c2p"
|
56 |
-
],
|
57 |
-
"position_biased_input": false,
|
58 |
-
"position_buckets": 256,
|
59 |
-
"relative_attention": true,
|
60 |
-
"share_att_key": true,
|
61 |
"torch_dtype": "float32",
|
62 |
"transformers_version": "4.38.1",
|
63 |
-
"type_vocab_size":
|
64 |
-
"vocab_size":
|
65 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
3 |
"architectures": [
|
4 |
+
"LongformerForTokenClassification"
|
5 |
],
|
6 |
+
"attention_mode": "longformer",
|
7 |
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_window": [
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
"hidden_act": "gelu",
|
26 |
"hidden_dropout_prob": 0.1,
|
27 |
"hidden_size": 768,
|
|
|
40 |
"11": "I-URL_PERSONAL",
|
41 |
"12": "O"
|
42 |
},
|
43 |
+
"ignore_attention_mask": false,
|
44 |
"initializer_range": 0.02,
|
45 |
"intermediate_size": 3072,
|
46 |
"label2id": {
|
|
|
58 |
"I-URL_PERSONAL": 11,
|
59 |
"O": 12
|
60 |
},
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"max_position_embeddings": 4098,
|
63 |
+
"model_type": "longformer",
|
|
|
|
|
64 |
"num_attention_heads": 12,
|
65 |
"num_hidden_layers": 12,
|
66 |
+
"onnx_export": false,
|
67 |
+
"pad_token_id": 1,
|
68 |
+
"sep_token_id": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
"torch_dtype": "float32",
|
70 |
"transformers_version": "4.38.1",
|
71 |
+
"type_vocab_size": 1,
|
72 |
+
"vocab_size": 50688
|
73 |
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
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 sha256:57f481f6cca419d995a782136b2b9c72bd262b7877ba2e639e40f8d34079ee4f
|
3 |
+
size 593648892
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"bos_token": "
|
3 |
-
"cls_token": "
|
4 |
-
"eos_token": "
|
5 |
-
"mask_token":
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"content": "[UNK]",
|
10 |
-
"lstrip": false,
|
11 |
-
"normalized": true,
|
12 |
"rstrip": false,
|
13 |
"single_word": false
|
14 |
-
}
|
|
|
|
|
|
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
|
|
|
|
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,58 +1,57 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
-
"normalized":
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
-
"normalized":
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
-
"normalized":
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
"3": {
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": true,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip":
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"bos_token": "
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
-
"cls_token": "
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"mask_token": "
|
50 |
-
"model_max_length":
|
51 |
-
"pad_token": "
|
52 |
-
"sep_token": "
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"unk_token": "[UNK]",
|
57 |
-
"vocab_type": "spm"
|
58 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
+
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
"2": {
|
21 |
+
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
"normalized": true,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
"normalized": false,
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
}
|
44 |
},
|
45 |
+
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 4096,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "LongformerTokenizer",
|
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:ac423cb02aadebb07017fcd28a0ce79ad4e5a16ce750832bf14b5b45897e48bf
|
3 |
+
size 4920
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|