End of training
Browse files- .gitattributes +1 -0
- README.md +14 -16
- added_tokens.json +4 -0
- config.json +19 -14
- entity_vocab.json +3 -0
- model.safetensors +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +43 -5
- tokenizer_config.json +66 -19
- training_args.bin +2 -2
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
entity_vocab.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# exp_number1
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,28 +34,26 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate:
|
38 |
-
- train_batch_size:
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
|
|
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
-
|
|
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.149 | 6.0 | 2658 | 0.2398 |
|
55 |
-
| 0.1102 | 7.0 | 3101 | 0.2547 |
|
56 |
-
| 0.0479 | 8.0 | 3544 | 0.2352 |
|
57 |
-
| 0.0651 | 9.0 | 3987 | 0.2485 |
|
58 |
-
| 0.0806 | 10.0 | 4430 | 0.2623 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: studio-ousia/mluke-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# exp_number1
|
15 |
|
16 |
+
This model is a fine-tuned version of [studio-ousia/mluke-base](https://huggingface.co/studio-ousia/mluke-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2131
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 4
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 4
|
42 |
+
- total_train_batch_size: 16
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_ratio: 0.1
|
46 |
+
- num_epochs: 5
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 0.4351 | 1.0 | 221 | 0.5519 |
|
53 |
+
| 0.3954 | 2.0 | 443 | 0.3151 |
|
54 |
+
| 0.2607 | 3.0 | 664 | 0.3064 |
|
55 |
+
| 0.222 | 4.0 | 886 | 0.2342 |
|
56 |
+
| 0.1296 | 4.99 | 1105 | 0.2131 |
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<ent2>": 250003,
|
3 |
+
"<ent>": 250002
|
4 |
+
}
|
config.json
CHANGED
@@ -1,32 +1,37 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
|
|
|
|
|
|
|
|
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-
|
15 |
-
"max_position_embeddings":
|
16 |
-
"model_type": "
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"pooler_num_attention_heads": 12,
|
22 |
-
"pooler_num_fc_layers": 3,
|
23 |
-
"pooler_size_per_head": 128,
|
24 |
-
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
26 |
"problem_type": "single_label_classification",
|
27 |
"torch_dtype": "float32",
|
28 |
"transformers_version": "4.39.3",
|
29 |
-
"type_vocab_size":
|
30 |
"use_cache": true,
|
31 |
-
"
|
|
|
|
|
32 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "studio-ousia/mluke-base",
|
3 |
"architectures": [
|
4 |
+
"LukeForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bert_model_name": "xlm-roberta-base",
|
8 |
+
"bos_token_id": 0,
|
9 |
"classifier_dropout": null,
|
10 |
+
"cls_entity_prediction": false,
|
11 |
+
"deepspeed_transformer_layer_args": {},
|
12 |
+
"entity_emb_size": 256,
|
13 |
+
"entity_vocab_size": 1200001,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"gradient_checkpointing": false,
|
16 |
"hidden_act": "gelu",
|
17 |
"hidden_dropout_prob": 0.1,
|
18 |
"hidden_size": 768,
|
19 |
"initializer_range": 0.02,
|
20 |
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-05,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "luke",
|
24 |
"num_attention_heads": 12,
|
25 |
"num_hidden_layers": 12,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 1,
|
|
|
|
|
|
|
|
|
28 |
"position_embedding_type": "absolute",
|
29 |
"problem_type": "single_label_classification",
|
30 |
"torch_dtype": "float32",
|
31 |
"transformers_version": "4.39.3",
|
32 |
+
"type_vocab_size": 1,
|
33 |
"use_cache": true,
|
34 |
+
"use_deepspeed_transformer_layer": false,
|
35 |
+
"use_entity_aware_attention": false,
|
36 |
+
"vocab_size": 250004
|
37 |
}
|
entity_vocab.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebeabade0acbb5f6fb6562490c081441746f7bf9bd06a3fa8d86b0bce7461c8d
|
3 |
+
size 336948106
|
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:a8eb5efbee3c159e9bfe0f109f5bf50badf6de76910b6f5f20adc7abd2f7c600
|
3 |
+
size 2343386936
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,45 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<ent>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<ent2>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<ent>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "<ent2>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"cls_token": "<s>",
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"mask_token": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false
|
41 |
+
},
|
42 |
+
"pad_token": "<pad>",
|
43 |
+
"sep_token": "</s>",
|
44 |
+
"unk_token": "<unk>"
|
45 |
}
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,102 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
"lstrip": false,
|
38 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
-
"
|
47 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
"model_max_length": 512,
|
49 |
-
"pad_token": "
|
50 |
-
"sep_token": "
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"tokenizer_class": "
|
54 |
-
"unk_token": "
|
55 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
+
"content": "<s>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"250002": {
|
44 |
+
"content": "<ent>",
|
45 |
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"250003": {
|
52 |
+
"content": "<ent2>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
"rstrip": false,
|
56 |
"single_word": false,
|
57 |
"special": true
|
58 |
}
|
59 |
},
|
60 |
+
"additional_special_tokens": [
|
61 |
+
"<ent>",
|
62 |
+
"<ent2>",
|
63 |
+
"<ent>",
|
64 |
+
"<ent2>"
|
65 |
+
],
|
66 |
+
"bos_token": "<s>",
|
67 |
"clean_up_tokenization_spaces": true,
|
68 |
+
"cls_token": "<s>",
|
69 |
+
"entity_mask2_token": "[MASK2]",
|
70 |
+
"entity_mask_token": "[MASK]",
|
71 |
+
"entity_pad_token": "[PAD]",
|
72 |
+
"entity_token_1": {
|
73 |
+
"__type": "AddedToken",
|
74 |
+
"content": "<ent>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": true,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false,
|
79 |
+
"special": false
|
80 |
+
},
|
81 |
+
"entity_token_2": {
|
82 |
+
"__type": "AddedToken",
|
83 |
+
"content": "<ent2>",
|
84 |
+
"lstrip": false,
|
85 |
+
"normalized": true,
|
86 |
+
"rstrip": false,
|
87 |
+
"single_word": false,
|
88 |
+
"special": false
|
89 |
+
},
|
90 |
+
"entity_unk_token": "[UNK]",
|
91 |
+
"eos_token": "</s>",
|
92 |
+
"mask_token": "<mask>",
|
93 |
+
"max_entity_length": 32,
|
94 |
+
"max_mention_length": 30,
|
95 |
"model_max_length": 512,
|
96 |
+
"pad_token": "<pad>",
|
97 |
+
"sep_token": "</s>",
|
98 |
+
"sp_model_kwargs": {},
|
99 |
+
"task": null,
|
100 |
+
"tokenizer_class": "MLukeTokenizer",
|
101 |
+
"unk_token": "<unk>"
|
102 |
}
|
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 sha256:5e6e2251e262f9cd187f4ffee4f240581585b807a7b2e3491f7a8b515338a391
|
3 |
+
size 4920
|