silviacamplani commited on
Commit
19f7ae7
1 Parent(s): 6d01abb

Training in progress epoch 0

Browse files
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-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-ner-music
14
+
15
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.6671
18
+ - Validation Loss: 2.0032
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
+ | 2.6671 | 2.0032 | 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": "distilbert-base-uncased",
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.1661683261.ba7ce45e5513.17.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85852cd7b216ed7dd2d1cd99b6893c645344bc6b92ca8a5e8f2901c67d1d0640
3
+ size 1867008
logs/train/events.out.tfevents.1661683276.ba7ce45e5513.profile-empty ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4d20d1abc03cf61404c8b2c0195c6d16641e86de9206734c3c32c56e2731df
3
+ size 40
logs/train/plugins/profile/2022_08_28_10_41_16/ba7ce45e5513.input_pipeline.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3614538ff2500292ce02b133df6385aa85ce01cab310f1dca3bdf82de98873b
3
+ size 3066
logs/train/plugins/profile/2022_08_28_10_41_16/ba7ce45e5513.kernel_stats.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba02c2af1411104f8b379af32f9d01428a165e541ffdf0ffce8f15f96d538f6
3
+ size 315928
logs/train/plugins/profile/2022_08_28_10_41_16/ba7ce45e5513.memory_profile.json.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0544b48637a34380ff7a5e945e417063d5db432759498f28a347cc7461c9e5ec
3
+ size 38851
logs/train/plugins/profile/2022_08_28_10_41_16/ba7ce45e5513.overview_page.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eeddcdc250ed08a68f3125a2311b02e4a73e1c940089e2b6c3d9f159c3dfd0d
3
+ size 6232
logs/train/plugins/profile/2022_08_28_10_41_16/ba7ce45e5513.tensorflow_stats.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6bc7a3409e00d402604ca9f3ca48efffeedde682d4bdf74664cdb7787d8eda
3
+ size 191521
logs/train/plugins/profile/2022_08_28_10_41_16/ba7ce45e5513.trace.json.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e605fce0cac0898989e3f8d4697e563b16591db2032c31e25ea97f158fa43c4
3
+ size 216919
logs/train/plugins/profile/2022_08_28_10_41_16/ba7ce45e5513.xplane.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656b1b1ebae550b80e271383519b676b00c147a0c04b6f018e22d1a38503e701
3
+ size 1678409
logs/validation/events.out.tfevents.1661683280.ba7ce45e5513.17.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a9d04cf58082715da8cf2b4bab7412e533cd8762cb18c5afa248b3d6c759da
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 sha256:4333834f57c5b18215ef1578eb54fc15fcf10d6404532bb303fa93fb271947bc
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": "distilbert-base-uncased",
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