silviacamplani
commited on
Commit
•
05b2396
1
Parent(s):
b475981
Training in progress epoch 0
Browse files- README.md +57 -0
- config.json +81 -0
- logs/train/events.out.tfevents.1661703305.3e81d4e42f0b.17.0.v2 +3 -0
- logs/train/events.out.tfevents.1661703320.3e81d4e42f0b.profile-empty +3 -0
- logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.input_pipeline.pb +3 -0
- logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.kernel_stats.pb +3 -0
- logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.memory_profile.json.gz +3 -0
- logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.overview_page.pb +3 -0
- logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.tensorflow_stats.pb +3 -0
- logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.trace.json.gz +3 -0
- logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.xplane.pb +3 -0
- logs/validation/events.out.tfevents.1661703324.3e81d4e42f0b.17.1.v2 +3 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: silviacamplani/distilbert-finetuned-dapt-ner-music
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# silviacamplani/distilbert-finetuned-dapt-ner-music
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [silviacamplani/distilbert-finetuned-dapt-lm-ai](https://huggingface.co/silviacamplani/distilbert-finetuned-dapt-lm-ai) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 2.5668
|
18 |
+
- Validation Loss: 1.9780
|
19 |
+
- Train Precision: 0.0
|
20 |
+
- Train Recall: 0.0
|
21 |
+
- Train F1: 0.0
|
22 |
+
- Train Accuracy: 0.5482
|
23 |
+
- Epoch: 0
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 370, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
|
43 |
+
- training_precision: mixed_float16
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|
48 |
+
|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
|
49 |
+
| 2.5668 | 1.9780 | 0.0 | 0.0 | 0.0 | 0.5482 | 0 |
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.20.1
|
55 |
+
- TensorFlow 2.6.4
|
56 |
+
- Datasets 2.1.0
|
57 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "silviacamplani/distilbert-finetuned-dapt-lm-ai",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-album",
|
14 |
+
"2": "I-album",
|
15 |
+
"3": "B-award",
|
16 |
+
"4": "I-award",
|
17 |
+
"5": "B-band",
|
18 |
+
"6": "I-band",
|
19 |
+
"7": "B-country",
|
20 |
+
"8": "I-country",
|
21 |
+
"9": "B-event",
|
22 |
+
"10": "I-event",
|
23 |
+
"11": "B-location",
|
24 |
+
"12": "I-location",
|
25 |
+
"13": "B-misc",
|
26 |
+
"14": "I-misc",
|
27 |
+
"15": "B-musicalartist",
|
28 |
+
"16": "I-musicalartist",
|
29 |
+
"17": "B-musicalinstrument",
|
30 |
+
"18": "I-musicalinstrument",
|
31 |
+
"19": "B-musicgenre",
|
32 |
+
"20": "I-musicgenre",
|
33 |
+
"21": "B-organisation",
|
34 |
+
"22": "I-organisation",
|
35 |
+
"23": "B-person",
|
36 |
+
"24": "I-person",
|
37 |
+
"25": "B-song",
|
38 |
+
"26": "I-song"
|
39 |
+
},
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"label2id": {
|
42 |
+
"B-album": 1,
|
43 |
+
"B-award": 3,
|
44 |
+
"B-band": 5,
|
45 |
+
"B-country": 7,
|
46 |
+
"B-event": 9,
|
47 |
+
"B-location": 11,
|
48 |
+
"B-misc": 13,
|
49 |
+
"B-musicalartist": 15,
|
50 |
+
"B-musicalinstrument": 17,
|
51 |
+
"B-musicgenre": 19,
|
52 |
+
"B-organisation": 21,
|
53 |
+
"B-person": 23,
|
54 |
+
"B-song": 25,
|
55 |
+
"I-album": 2,
|
56 |
+
"I-award": 4,
|
57 |
+
"I-band": 6,
|
58 |
+
"I-country": 8,
|
59 |
+
"I-event": 10,
|
60 |
+
"I-location": 12,
|
61 |
+
"I-misc": 14,
|
62 |
+
"I-musicalartist": 16,
|
63 |
+
"I-musicalinstrument": 18,
|
64 |
+
"I-musicgenre": 20,
|
65 |
+
"I-organisation": 22,
|
66 |
+
"I-person": 24,
|
67 |
+
"I-song": 26,
|
68 |
+
"O": 0
|
69 |
+
},
|
70 |
+
"max_position_embeddings": 512,
|
71 |
+
"model_type": "distilbert",
|
72 |
+
"n_heads": 12,
|
73 |
+
"n_layers": 6,
|
74 |
+
"pad_token_id": 0,
|
75 |
+
"qa_dropout": 0.1,
|
76 |
+
"seq_classif_dropout": 0.2,
|
77 |
+
"sinusoidal_pos_embds": false,
|
78 |
+
"tie_weights_": true,
|
79 |
+
"transformers_version": "4.20.1",
|
80 |
+
"vocab_size": 30522
|
81 |
+
}
|
logs/train/events.out.tfevents.1661703305.3e81d4e42f0b.17.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf3cd17ada4cf14a9b5c4e4a3f89e792a946641a8b42d1b7ed5b0833089fe32
|
3 |
+
size 1867008
|
logs/train/events.out.tfevents.1661703320.3e81d4e42f0b.profile-empty
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fc134edc9618ac86aa4973346da1a0a8f0fec7b1beefda613446761779e33d4
|
3 |
+
size 40
|
logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.input_pipeline.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30601cafb1aa6e095e1aa6c55d03e249fec6f4a48178cbeb72f412c0d16963d0
|
3 |
+
size 3066
|
logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.kernel_stats.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:219a9e4016012df3434ec83b4a6f11be8d61ded9d7e0addaaddd061bbf925778
|
3 |
+
size 318992
|
logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.memory_profile.json.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e0c6b1798309f917c26914bc4349422eeea964422ad393e050baee4999a0d9e
|
3 |
+
size 38597
|
logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.overview_page.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8723a63eb138f1332e4d29a2228059ef44299a7dac639c6c15209336910f80b
|
3 |
+
size 6253
|
logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.tensorflow_stats.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d95c61c6f01e207f4501ffbb6e46f67af0e6fbdabc2d166adfc6bd50b3b14a2
|
3 |
+
size 191527
|
logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.trace.json.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:632c80bdf53e044b4fea24eb03a9b41f35d23a69aef0cce374c9ea7e3409cffe
|
3 |
+
size 217054
|
logs/train/plugins/profile/2022_08_28_16_15_20/3e81d4e42f0b.xplane.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79bea4168f73b6285831a89c7634aa129059e10eb51f0a696571e05c4c7a88f4
|
3 |
+
size 1671675
|
logs/validation/events.out.tfevents.1661703324.3e81d4e42f0b.17.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6015cc698395c6fe386c093d2e074c83ef98f698fe9cba4161ecd2d77d05896d
|
3 |
+
size 193
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25761d79d09588baf32444825414e55385d2a35a9b7cddc36720b7bb3fd56853
|
3 |
+
size 265660768
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "silviacamplani/distilbert-finetuned-dapt-lm-ai",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|