Initial Commit
Browse files- README.md +89 -0
- config.json +46 -0
- eval_result_ner.json +1 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: haryoaw/scenario-TCR-NER_data-univner_half
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: scenario-non-kd-po-ner-full-xlmr_data-univner_half66
|
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-non-kd-po-ner-full-xlmr_data-univner_half66
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_half](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_half) on the None dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.1331
|
25 |
+
- Precision: 0.8406
|
26 |
+
- Recall: 0.8491
|
27 |
+
- F1: 0.8448
|
28 |
+
- Accuracy: 0.9836
|
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: 32
|
49 |
+
- eval_batch_size: 32
|
50 |
+
- seed: 66
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 30
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 0.0102 | 0.5828 | 500 | 0.0979 | 0.8297 | 0.8550 | 0.8422 | 0.9832 |
|
60 |
+
| 0.0109 | 1.1655 | 1000 | 0.0889 | 0.8346 | 0.8466 | 0.8406 | 0.9835 |
|
61 |
+
| 0.0084 | 1.7483 | 1500 | 0.0932 | 0.8491 | 0.8462 | 0.8477 | 0.9839 |
|
62 |
+
| 0.0075 | 2.3310 | 2000 | 0.0919 | 0.8434 | 0.8437 | 0.8436 | 0.9835 |
|
63 |
+
| 0.0072 | 2.9138 | 2500 | 0.1043 | 0.8278 | 0.8380 | 0.8329 | 0.9826 |
|
64 |
+
| 0.0058 | 3.4965 | 3000 | 0.1020 | 0.8370 | 0.8468 | 0.8419 | 0.9832 |
|
65 |
+
| 0.0059 | 4.0793 | 3500 | 0.1030 | 0.8467 | 0.8458 | 0.8463 | 0.9839 |
|
66 |
+
| 0.005 | 4.6620 | 4000 | 0.1182 | 0.8492 | 0.8326 | 0.8408 | 0.9830 |
|
67 |
+
| 0.005 | 5.2448 | 4500 | 0.1141 | 0.8235 | 0.8510 | 0.8370 | 0.9821 |
|
68 |
+
| 0.0044 | 5.8275 | 5000 | 0.1184 | 0.8273 | 0.8572 | 0.8420 | 0.9828 |
|
69 |
+
| 0.0045 | 6.4103 | 5500 | 0.1213 | 0.8417 | 0.8494 | 0.8455 | 0.9833 |
|
70 |
+
| 0.0048 | 6.9930 | 6000 | 0.1126 | 0.8413 | 0.8413 | 0.8413 | 0.9835 |
|
71 |
+
| 0.0043 | 7.5758 | 6500 | 0.1240 | 0.8363 | 0.8472 | 0.8417 | 0.9830 |
|
72 |
+
| 0.0036 | 8.1585 | 7000 | 0.1185 | 0.8470 | 0.8450 | 0.8460 | 0.9838 |
|
73 |
+
| 0.0032 | 8.7413 | 7500 | 0.1249 | 0.8338 | 0.8391 | 0.8365 | 0.9828 |
|
74 |
+
| 0.0022 | 9.3240 | 8000 | 0.1260 | 0.8351 | 0.8499 | 0.8425 | 0.9835 |
|
75 |
+
| 0.003 | 9.9068 | 8500 | 0.1208 | 0.8273 | 0.8420 | 0.8346 | 0.9827 |
|
76 |
+
| 0.0024 | 10.4895 | 9000 | 0.1216 | 0.8451 | 0.8463 | 0.8457 | 0.9836 |
|
77 |
+
| 0.0027 | 11.0723 | 9500 | 0.1214 | 0.8410 | 0.8390 | 0.8400 | 0.9832 |
|
78 |
+
| 0.0019 | 11.6550 | 10000 | 0.1234 | 0.8419 | 0.8458 | 0.8438 | 0.9833 |
|
79 |
+
| 0.0023 | 12.2378 | 10500 | 0.1289 | 0.8339 | 0.8502 | 0.8420 | 0.9830 |
|
80 |
+
| 0.0019 | 12.8205 | 11000 | 0.1286 | 0.8400 | 0.8401 | 0.8401 | 0.9832 |
|
81 |
+
| 0.002 | 13.4033 | 11500 | 0.1331 | 0.8406 | 0.8491 | 0.8448 | 0.9836 |
|
82 |
+
|
83 |
+
|
84 |
+
### Framework versions
|
85 |
+
|
86 |
+
- Transformers 4.44.2
|
87 |
+
- Pytorch 2.1.1+cu121
|
88 |
+
- Datasets 2.14.5
|
89 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_half",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
30 |
+
"LABEL_5": 5,
|
31 |
+
"LABEL_6": 6
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-05,
|
34 |
+
"max_position_embeddings": 514,
|
35 |
+
"model_type": "xlm-roberta",
|
36 |
+
"num_attention_heads": 12,
|
37 |
+
"num_hidden_layers": 12,
|
38 |
+
"output_past": true,
|
39 |
+
"pad_token_id": 1,
|
40 |
+
"position_embedding_type": "absolute",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.44.2",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 250002
|
46 |
+
}
|
eval_result_ner.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ceb_gja": {"precision": 0.6515151515151515, "recall": 0.8775510204081632, "f1": 0.7478260869565216, "accuracy": 0.9783783783783784}, "en_pud": {"precision": 0.8212237093690249, "recall": 0.7990697674418604, "f1": 0.8099952852428101, "accuracy": 0.9802134491877598}, "de_pud": {"precision": 0.8014981273408239, "recall": 0.8238691049085659, "f1": 0.8125296630280019, "accuracy": 0.9786226618536402}, "pt_pud": {"precision": 0.8650137741046832, "recall": 0.8571428571428571, "f1": 0.8610603290676416, "accuracy": 0.9854317084632802}, "ru_pud": {"precision": 0.7129798903107861, "recall": 0.752895752895753, "f1": 0.732394366197183, "accuracy": 0.9727202273314389}, "sv_pud": {"precision": 0.859086491739553, "recall": 0.859086491739553, "f1": 0.859086491739553, "accuracy": 0.9858985112182848}, "tl_trg": {"precision": 0.9166666666666666, "recall": 0.9565217391304348, "f1": 0.9361702127659574, "accuracy": 0.9959128065395095}, "tl_ugnayan": {"precision": 0.6923076923076923, "recall": 0.8181818181818182, "f1": 0.7500000000000001, "accuracy": 0.9808568824065633}, "zh_gsd": {"precision": 0.8350785340314136, "recall": 0.8318122555410691, "f1": 0.8334421946440235, "accuracy": 0.9779387279387279}, "zh_gsdsimp": {"precision": 0.8398950131233596, "recall": 0.8387942332896461, "f1": 0.839344262295082, "accuracy": 0.9781884781884782}, "hr_set": {"precision": 0.9279151943462898, "recall": 0.9358517462580185, "f1": 0.9318665720369056, "accuracy": 0.9912613355317395}, "da_ddt": {"precision": 0.8275058275058275, "recall": 0.7941834451901566, "f1": 0.8105022831050228, "accuracy": 0.9857328145265889}, "en_ewt": {"precision": 0.8248587570621468, "recall": 0.8051470588235294, "f1": 0.8148837209302325, "accuracy": 0.9815914252699526}, "pt_bosque": {"precision": 0.8616636528028933, "recall": 0.7843621399176954, "f1": 0.8211977595863852, "accuracy": 0.982393855962904}, "sr_set": {"precision": 0.9475566150178785, "recall": 0.9386068476977568, "f1": 0.9430604982206405, "accuracy": 0.9908939672533054}, "sk_snk": {"precision": 0.7965554359526372, "recall": 0.8087431693989071, "f1": 0.8026030368763557, "accuracy": 0.9722047738693468}, "sv_talbanken": {"precision": 0.8786407766990292, "recall": 0.923469387755102, "f1": 0.900497512437811, "accuracy": 0.9979388526279629}}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f50f430da50b680235f848e1ea5b0620a758b589440b255bca07bbdc851ec3ec
|
3 |
+
size 1109857804
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fe61d3e7057e3174f4b11fbb2a0ff7fe202e2eafe3273cac41093da663e0043
|
3 |
+
size 5304
|