Initial Commit
Browse files- README.md +60 -51
- config.json +3 -3
- eval_result_ner.json +1 -1
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: haryoaw/scenario-TCR-NER_data-univner_half
|
| 3 |
library_name: transformers
|
| 4 |
license: mit
|
|
|
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- precision
|
| 7 |
- recall
|
| 8 |
- f1
|
| 9 |
- accuracy
|
| 10 |
-
tags:
|
| 11 |
-
- generated_from_trainer
|
| 12 |
model-index:
|
| 13 |
- name: scenario-non-kd-pre-ner-full-mdeberta_data-univner_half66
|
| 14 |
results: []
|
|
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
# scenario-non-kd-pre-ner-full-mdeberta_data-univner_half66
|
| 21 |
|
| 22 |
-
This model is a fine-tuned version of [
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 0.
|
| 25 |
-
- Precision: 0.
|
| 26 |
-
- Recall: 0.
|
| 27 |
-
- F1: 0.
|
| 28 |
-
- Accuracy: 0.
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
@@ -56,48 +56,57 @@ The following hyperparameters were used during training:
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
|
| 102 |
|
| 103 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
license: mit
|
| 4 |
+
base_model: microsoft/mdeberta-v3-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- precision
|
| 9 |
- recall
|
| 10 |
- f1
|
| 11 |
- accuracy
|
|
|
|
|
|
|
| 12 |
model-index:
|
| 13 |
- name: scenario-non-kd-pre-ner-full-mdeberta_data-univner_half66
|
| 14 |
results: []
|
|
|
|
| 19 |
|
| 20 |
# scenario-non-kd-pre-ner-full-mdeberta_data-univner_half66
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.1996
|
| 25 |
+
- Precision: 0.7561
|
| 26 |
+
- Recall: 0.7723
|
| 27 |
+
- F1: 0.7641
|
| 28 |
+
- Accuracy: 0.9755
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 59 |
+
| 0.304 | 0.5828 | 500 | 0.1829 | 0.3627 | 0.3414 | 0.3517 | 0.9389 |
|
| 60 |
+
| 0.155 | 1.1655 | 1000 | 0.1258 | 0.5315 | 0.6722 | 0.5937 | 0.9577 |
|
| 61 |
+
| 0.0973 | 1.7483 | 1500 | 0.1032 | 0.6320 | 0.7086 | 0.6681 | 0.9670 |
|
| 62 |
+
| 0.0707 | 2.3310 | 2000 | 0.1055 | 0.6478 | 0.7443 | 0.6927 | 0.9683 |
|
| 63 |
+
| 0.0584 | 2.9138 | 2500 | 0.1007 | 0.6755 | 0.7436 | 0.7079 | 0.9698 |
|
| 64 |
+
| 0.0431 | 3.4965 | 3000 | 0.1186 | 0.6613 | 0.7552 | 0.7051 | 0.9686 |
|
| 65 |
+
| 0.0392 | 4.0793 | 3500 | 0.1087 | 0.6946 | 0.7627 | 0.7270 | 0.9718 |
|
| 66 |
+
| 0.0273 | 4.6620 | 4000 | 0.1095 | 0.7451 | 0.7286 | 0.7367 | 0.9736 |
|
| 67 |
+
| 0.0233 | 5.2448 | 4500 | 0.1259 | 0.6876 | 0.7772 | 0.7297 | 0.9719 |
|
| 68 |
+
| 0.0189 | 5.8275 | 5000 | 0.1201 | 0.7222 | 0.7526 | 0.7371 | 0.9730 |
|
| 69 |
+
| 0.0161 | 6.4103 | 5500 | 0.1339 | 0.7334 | 0.7342 | 0.7338 | 0.9734 |
|
| 70 |
+
| 0.0153 | 6.9930 | 6000 | 0.1338 | 0.7226 | 0.7533 | 0.7376 | 0.9737 |
|
| 71 |
+
| 0.0109 | 7.5758 | 6500 | 0.1320 | 0.7345 | 0.7634 | 0.7486 | 0.9742 |
|
| 72 |
+
| 0.0108 | 8.1585 | 7000 | 0.1427 | 0.7189 | 0.7617 | 0.7397 | 0.9728 |
|
| 73 |
+
| 0.0089 | 8.7413 | 7500 | 0.1423 | 0.7268 | 0.7647 | 0.7453 | 0.9738 |
|
| 74 |
+
| 0.0075 | 9.3240 | 8000 | 0.1471 | 0.7332 | 0.7638 | 0.7482 | 0.9740 |
|
| 75 |
+
| 0.0071 | 9.9068 | 8500 | 0.1501 | 0.7502 | 0.7466 | 0.7484 | 0.9744 |
|
| 76 |
+
| 0.0064 | 10.4895 | 9000 | 0.1558 | 0.7133 | 0.7813 | 0.7458 | 0.9734 |
|
| 77 |
+
| 0.0058 | 11.0723 | 9500 | 0.1495 | 0.7514 | 0.7599 | 0.7556 | 0.9750 |
|
| 78 |
+
| 0.0047 | 11.6550 | 10000 | 0.1632 | 0.7146 | 0.7627 | 0.7379 | 0.9727 |
|
| 79 |
+
| 0.0043 | 12.2378 | 10500 | 0.1707 | 0.7259 | 0.7699 | 0.7472 | 0.9740 |
|
| 80 |
+
| 0.0039 | 12.8205 | 11000 | 0.1648 | 0.7415 | 0.7608 | 0.7510 | 0.9742 |
|
| 81 |
+
| 0.0041 | 13.4033 | 11500 | 0.1717 | 0.7247 | 0.7693 | 0.7463 | 0.9739 |
|
| 82 |
+
| 0.0036 | 13.9860 | 12000 | 0.1711 | 0.7251 | 0.7687 | 0.7463 | 0.9737 |
|
| 83 |
+
| 0.0029 | 14.5688 | 12500 | 0.1757 | 0.7275 | 0.7751 | 0.7505 | 0.9741 |
|
| 84 |
+
| 0.0026 | 15.1515 | 13000 | 0.1817 | 0.7527 | 0.7563 | 0.7545 | 0.9744 |
|
| 85 |
+
| 0.0027 | 15.7343 | 13500 | 0.1779 | 0.7534 | 0.7554 | 0.7544 | 0.9750 |
|
| 86 |
+
| 0.0028 | 16.3170 | 14000 | 0.1826 | 0.7505 | 0.7578 | 0.7541 | 0.9747 |
|
| 87 |
+
| 0.0026 | 16.8998 | 14500 | 0.1793 | 0.7573 | 0.7681 | 0.7627 | 0.9755 |
|
| 88 |
+
| 0.0022 | 17.4825 | 15000 | 0.1803 | 0.7460 | 0.7722 | 0.7589 | 0.9753 |
|
| 89 |
+
| 0.002 | 18.0653 | 15500 | 0.1858 | 0.7331 | 0.7807 | 0.7561 | 0.9746 |
|
| 90 |
+
| 0.0018 | 18.6480 | 16000 | 0.1875 | 0.7451 | 0.7624 | 0.7536 | 0.9740 |
|
| 91 |
+
| 0.0018 | 19.2308 | 16500 | 0.1896 | 0.7484 | 0.7661 | 0.7572 | 0.9749 |
|
| 92 |
+
| 0.0014 | 19.8135 | 17000 | 0.1862 | 0.7592 | 0.7689 | 0.7640 | 0.9755 |
|
| 93 |
+
| 0.0018 | 20.3963 | 17500 | 0.1936 | 0.7559 | 0.7567 | 0.7563 | 0.9749 |
|
| 94 |
+
| 0.0014 | 20.9790 | 18000 | 0.1908 | 0.7514 | 0.7680 | 0.7596 | 0.9751 |
|
| 95 |
+
| 0.0012 | 21.5618 | 18500 | 0.1956 | 0.7464 | 0.7692 | 0.7576 | 0.9751 |
|
| 96 |
+
| 0.0015 | 22.1445 | 19000 | 0.1986 | 0.7352 | 0.7751 | 0.7546 | 0.9746 |
|
| 97 |
+
| 0.0012 | 22.7273 | 19500 | 0.1936 | 0.7277 | 0.7804 | 0.7531 | 0.9746 |
|
| 98 |
+
| 0.001 | 23.3100 | 20000 | 0.1975 | 0.7358 | 0.7781 | 0.7564 | 0.9749 |
|
| 99 |
+
| 0.0011 | 23.8928 | 20500 | 0.1956 | 0.7485 | 0.7749 | 0.7615 | 0.9754 |
|
| 100 |
+
| 0.001 | 24.4755 | 21000 | 0.1950 | 0.7522 | 0.7728 | 0.7624 | 0.9754 |
|
| 101 |
+
| 0.0009 | 25.0583 | 21500 | 0.1958 | 0.7522 | 0.7713 | 0.7616 | 0.9755 |
|
| 102 |
+
| 0.0006 | 25.6410 | 22000 | 0.1998 | 0.7454 | 0.7741 | 0.7595 | 0.9751 |
|
| 103 |
+
| 0.0006 | 26.2238 | 22500 | 0.2026 | 0.7496 | 0.7725 | 0.7609 | 0.9753 |
|
| 104 |
+
| 0.0008 | 26.8065 | 23000 | 0.1991 | 0.7609 | 0.7638 | 0.7623 | 0.9755 |
|
| 105 |
+
| 0.0006 | 27.3893 | 23500 | 0.1962 | 0.7547 | 0.7772 | 0.7658 | 0.9758 |
|
| 106 |
+
| 0.0006 | 27.9720 | 24000 | 0.1995 | 0.7551 | 0.7728 | 0.7638 | 0.9755 |
|
| 107 |
+
| 0.0005 | 28.5548 | 24500 | 0.2003 | 0.7538 | 0.7738 | 0.7636 | 0.9754 |
|
| 108 |
+
| 0.0006 | 29.1375 | 25000 | 0.1996 | 0.7574 | 0.7694 | 0.7634 | 0.9755 |
|
| 109 |
+
| 0.0005 | 29.7203 | 25500 | 0.1996 | 0.7561 | 0.7723 | 0.7641 | 0.9755 |
|
| 110 |
|
| 111 |
|
| 112 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
|
@@ -33,7 +33,7 @@
|
|
| 33 |
"model_type": "deberta-v2",
|
| 34 |
"norm_rel_ebd": "layer_norm",
|
| 35 |
"num_attention_heads": 12,
|
| 36 |
-
"num_hidden_layers":
|
| 37 |
"pad_token_id": 0,
|
| 38 |
"pooler_dropout": 0,
|
| 39 |
"pooler_hidden_act": "gelu",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/mdeberta-v3-base",
|
| 3 |
"architectures": [
|
| 4 |
+
"DebertaForTokenClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
|
|
|
| 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",
|
eval_result_ner.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"ceb_gja": {"precision": 0.
|
|
|
|
| 1 |
+
{"ceb_gja": {"precision": 0.4864864864864865, "recall": 0.7346938775510204, "f1": 0.5853658536585366, "accuracy": 0.9583011583011583}, "en_pud": {"precision": 0.7389597644749755, "recall": 0.7004651162790698, "f1": 0.7191977077363897, "accuracy": 0.97369663770306}, "de_pud": {"precision": 0.6733067729083665, "recall": 0.6506256015399422, "f1": 0.661771904062653, "accuracy": 0.964699263981998}, "pt_pud": {"precision": 0.6958614051973051, "recall": 0.6578707916287534, "f1": 0.676333021515435, "accuracy": 0.9695817490494296}, "ru_pud": {"precision": 0.6028571428571429, "recall": 0.611003861003861, "f1": 0.6069031639501438, "accuracy": 0.9617669852751227}, "sv_pud": {"precision": 0.7585492227979275, "recall": 0.7113702623906706, "f1": 0.7342026078234705, "accuracy": 0.9749947578108619}, "tl_trg": {"precision": 0.425, "recall": 0.7391304347826086, "f1": 0.5396825396825397, "accuracy": 0.9550408719346049}, "tl_ugnayan": {"precision": 0.45098039215686275, "recall": 0.696969696969697, "f1": 0.5476190476190477, "accuracy": 0.9608021877848678}, "zh_gsd": {"precision": 0.7667560321715817, "recall": 0.7457627118644068, "f1": 0.7561136814276272, "accuracy": 0.9676157176157176}, "zh_gsdsimp": {"precision": 0.776, "recall": 0.762778505897772, "f1": 0.7693324520819564, "accuracy": 0.9708624708624709}, "hr_set": {"precision": 0.8520055325034578, "recall": 0.8781183178902352, "f1": 0.8648648648648648, "accuracy": 0.9834707337180544}, "da_ddt": {"precision": 0.7322834645669292, "recall": 0.6241610738255033, "f1": 0.6739130434782609, "accuracy": 0.976154843859124}, "en_ewt": {"precision": 0.7760467380720545, "recall": 0.7325367647058824, "f1": 0.7536643026004729, "accuracy": 0.9758138422919074}, "pt_bosque": {"precision": 0.6792975970425139, "recall": 0.6049382716049383, "f1": 0.6399651719634306, "accuracy": 0.9674322561947544}, "sr_set": {"precision": 0.8651162790697674, "recall": 0.8783943329397875, "f1": 0.8717047451669595, "accuracy": 0.9826635145784082}, "sk_snk": {"precision": 0.654292343387471, "recall": 0.6163934426229508, "f1": 0.634777715250422, "accuracy": 0.9520257537688442}, "sv_talbanken": {"precision": 0.8109452736318408, "recall": 0.8316326530612245, "f1": 0.8211586901763225, "accuracy": 0.9966629042547971}}
|
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 sha256:360b3cdf67db34474d0f73560495b58f1c3ab576204323d8b26923f5fa93e01f
|
| 3 |
+
size 944366708
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecc396eabbe7cbc981aa7e4804a3c44f5acb4ba9bee40799bad7496c45bb8ac1
|
| 3 |
size 5304
|