Hugging Face's logo

haryoaw
/
scenario-kd-po-ner-full-mdeberta_data-univner_full66

Transformers
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
9d36ead
•
1 Parent(s): c7eb554

Initial Commit

Browse files
Files changed (5) hide show
  1. README.md +102 -0
  2. config.json +53 -0
  3. eval_result_ner.json +1 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: haryoaw/scenario-TCR-NER_data-univner_full
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: scenario-kd-po-ner-full-mdeberta_data-univner_full66
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # scenario-kd-po-ner-full-mdeberta_data-univner_full66
21
+
22
+ This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_full](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_full) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.2476
25
+ - Precision: 0.8200
26
+ - Recall: 0.8197
27
+ - F1: 0.8198
28
+ - Accuracy: 0.9813
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 3e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 32
50
+ - seed: 66
51
+ - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 32
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: linear
55
+ - num_epochs: 10
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
+ |:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | 1.199 | 0.2911 | 500 | 0.6605 | 0.5339 | 0.5311 | 0.5325 | 0.9554 |
62
+ | 0.5861 | 0.5822 | 1000 | 0.4717 | 0.6657 | 0.6788 | 0.6722 | 0.9691 |
63
+ | 0.4428 | 0.8732 | 1500 | 0.4097 | 0.7062 | 0.7338 | 0.7197 | 0.9729 |
64
+ | 0.3682 | 1.1643 | 2000 | 0.3621 | 0.7544 | 0.7599 | 0.7571 | 0.9759 |
65
+ | 0.3192 | 1.4554 | 2500 | 0.3490 | 0.7587 | 0.7756 | 0.7671 | 0.9767 |
66
+ | 0.2984 | 1.7465 | 3000 | 0.3384 | 0.7618 | 0.7767 | 0.7692 | 0.9768 |
67
+ | 0.2751 | 2.0375 | 3500 | 0.3231 | 0.7827 | 0.7869 | 0.7848 | 0.9782 |
68
+ | 0.2403 | 2.3286 | 4000 | 0.3070 | 0.7924 | 0.8033 | 0.7978 | 0.9794 |
69
+ | 0.2399 | 2.6197 | 4500 | 0.3047 | 0.7893 | 0.7950 | 0.7921 | 0.9793 |
70
+ | 0.2299 | 2.9108 | 5000 | 0.2929 | 0.7895 | 0.8129 | 0.8010 | 0.9796 |
71
+ | 0.2065 | 3.2019 | 5500 | 0.2914 | 0.7978 | 0.8098 | 0.8038 | 0.9800 |
72
+ | 0.2009 | 3.4929 | 6000 | 0.2837 | 0.8048 | 0.8016 | 0.8032 | 0.9800 |
73
+ | 0.1956 | 3.7840 | 6500 | 0.2817 | 0.7960 | 0.8195 | 0.8076 | 0.9798 |
74
+ | 0.1914 | 4.0751 | 7000 | 0.2772 | 0.8027 | 0.8114 | 0.8071 | 0.9804 |
75
+ | 0.1789 | 4.3662 | 7500 | 0.2737 | 0.8046 | 0.8163 | 0.8104 | 0.9805 |
76
+ | 0.1769 | 4.6573 | 8000 | 0.2748 | 0.8108 | 0.8104 | 0.8106 | 0.9805 |
77
+ | 0.1739 | 4.9483 | 8500 | 0.2659 | 0.8093 | 0.8124 | 0.8109 | 0.9805 |
78
+ | 0.1655 | 5.2394 | 9000 | 0.2669 | 0.8033 | 0.8178 | 0.8105 | 0.9806 |
79
+ | 0.1638 | 5.5305 | 9500 | 0.2633 | 0.8051 | 0.8153 | 0.8102 | 0.9805 |
80
+ | 0.1612 | 5.8216 | 10000 | 0.2612 | 0.8129 | 0.8181 | 0.8155 | 0.9810 |
81
+ | 0.1574 | 6.1126 | 10500 | 0.2564 | 0.8108 | 0.8269 | 0.8188 | 0.9811 |
82
+ | 0.1534 | 6.4037 | 11000 | 0.2593 | 0.8163 | 0.8106 | 0.8134 | 0.9809 |
83
+ | 0.153 | 6.6948 | 11500 | 0.2542 | 0.8125 | 0.8215 | 0.8170 | 0.9811 |
84
+ | 0.1511 | 6.9859 | 12000 | 0.2545 | 0.8137 | 0.8218 | 0.8177 | 0.9809 |
85
+ | 0.1464 | 7.2770 | 12500 | 0.2534 | 0.8120 | 0.8264 | 0.8192 | 0.9813 |
86
+ | 0.1466 | 7.5680 | 13000 | 0.2516 | 0.8181 | 0.8259 | 0.8219 | 0.9813 |
87
+ | 0.1455 | 7.8591 | 13500 | 0.2513 | 0.8168 | 0.8212 | 0.8190 | 0.9813 |
88
+ | 0.1445 | 8.1502 | 14000 | 0.2514 | 0.8270 | 0.8133 | 0.8201 | 0.9811 |
89
+ | 0.1406 | 8.4413 | 14500 | 0.2492 | 0.8157 | 0.8254 | 0.8205 | 0.9813 |
90
+ | 0.141 | 8.7324 | 15000 | 0.2483 | 0.8243 | 0.8228 | 0.8235 | 0.9815 |
91
+ | 0.1423 | 9.0234 | 15500 | 0.2469 | 0.8210 | 0.8155 | 0.8182 | 0.9812 |
92
+ | 0.1408 | 9.3145 | 16000 | 0.2462 | 0.8236 | 0.8221 | 0.8229 | 0.9817 |
93
+ | 0.1387 | 9.6056 | 16500 | 0.2475 | 0.8204 | 0.8227 | 0.8216 | 0.9814 |
94
+ | 0.1387 | 9.8967 | 17000 | 0.2476 | 0.8200 | 0.8197 | 0.8198 | 0.9813 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - Transformers 4.44.2
100
+ - Pytorch 2.1.1+cu121
101
+ - Datasets 2.14.5
102
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_full",
3
+ "architectures": [
4
+ "DebertaForTokenClassificationKD"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3,
26
+ "LABEL_4": 4,
27
+ "LABEL_5": 5,
28
+ "LABEL_6": 6
29
+ },
30
+ "layer_norm_eps": 1e-07,
31
+ "max_position_embeddings": 512,
32
+ "max_relative_positions": -1,
33
+ "model_type": "deberta-v2",
34
+ "norm_rel_ebd": "layer_norm",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 6,
37
+ "pad_token_id": 0,
38
+ "pooler_dropout": 0,
39
+ "pooler_hidden_act": "gelu",
40
+ "pooler_hidden_size": 768,
41
+ "pos_att_type": [
42
+ "p2c",
43
+ "c2p"
44
+ ],
45
+ "position_biased_input": false,
46
+ "position_buckets": 256,
47
+ "relative_attention": true,
48
+ "share_att_key": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.44.2",
51
+ "type_vocab_size": 0,
52
+ "vocab_size": 251000
53
+ }
eval_result_ner.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"ceb_gja": {"precision": 0.6060606060606061, "recall": 0.8163265306122449, "f1": 0.6956521739130436, "accuracy": 0.972972972972973}, "en_pud": {"precision": 0.7842565597667639, "recall": 0.7506976744186047, "f1": 0.7671102661596959, "accuracy": 0.9774272761616924}, "de_pud": {"precision": 0.7373447946513849, "recall": 0.7430221366698749, "f1": 0.7401725790987536, "accuracy": 0.9728564061694248}, "pt_pud": {"precision": 0.832, "recall": 0.8516833484986351, "f1": 0.841726618705036, "accuracy": 0.9845345409492887}, "ru_pud": {"precision": 0.669452181987001, "recall": 0.6959459459459459, "f1": 0.6824420255560815, "accuracy": 0.9682252647894601}, "sv_pud": {"precision": 0.8427991886409736, "recall": 0.8075801749271136, "f1": 0.8248138957816376, "accuracy": 0.982543510169847}, "tl_trg": {"precision": 0.5806451612903226, "recall": 0.782608695652174, "f1": 0.6666666666666667, "accuracy": 0.9795640326975477}, "tl_ugnayan": {"precision": 0.5111111111111111, "recall": 0.696969696969697, "f1": 0.5897435897435898, "accuracy": 0.9690063810391978}, "zh_gsd": {"precision": 0.8, "recall": 0.8135593220338984, "f1": 0.8067226890756303, "accuracy": 0.9732767232767233}, "zh_gsdsimp": {"precision": 0.7976653696498055, "recall": 0.8060288335517694, "f1": 0.8018252933507172, "accuracy": 0.9726107226107226}, "hr_set": {"precision": 0.8831808585503167, "recall": 0.894511760513186, "f1": 0.8888101983002833, "accuracy": 0.9865622423742787}, "da_ddt": {"precision": 0.8619854721549637, "recall": 0.796420581655481, "f1": 0.827906976744186, "accuracy": 0.9866307492766637}, "en_ewt": {"precision": 0.8189823874755382, "recall": 0.7693014705882353, "f1": 0.7933649289099527, "accuracy": 0.9778459576841854}, "pt_bosque": {"precision": 0.8421913327882257, "recall": 0.8477366255144033, "f1": 0.844954881050041, "accuracy": 0.9858353861759165}, "sr_set": {"precision": 0.9253554502369669, "recall": 0.922077922077922, "f1": 0.9237137788290953, "accuracy": 0.9881796690307328}, "sk_snk": {"precision": 0.7959667852906287, "recall": 0.7333333333333333, "f1": 0.7633674630261661, "accuracy": 0.9673366834170855}, "sv_talbanken": {"precision": 0.8446601941747572, "recall": 0.8877551020408163, "f1": 0.8656716417910448, "accuracy": 0.997399028316239}}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99bb9dd2f2a8347137be9a8b99683d69b1d676121cb1c98b9385b5efe556edd
3
+ size 944366708
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965e521a6547268d6d304ac2b2a6812c6ae6c70defcac10c4b79df7b7214a53b
3
+ size 5304