Initial Commit
Browse files- README.md +96 -0
- config.json +159 -0
- eval_results_ml.json +1 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/mdeberta-v3-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- massive
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: scenario-MDBT-TCR_data-AmazonScience_massive_all_1_1
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Text Classification
|
16 |
+
type: text-classification
|
17 |
+
dataset:
|
18 |
+
name: massive
|
19 |
+
type: massive
|
20 |
+
config: all_1.1
|
21 |
+
split: validation
|
22 |
+
args: all_1.1
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.8643440917174317
|
27 |
+
- name: F1
|
28 |
+
type: f1
|
29 |
+
value: 0.8368032657773605
|
30 |
+
---
|
31 |
+
|
32 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
33 |
+
should probably proofread and complete it, then remove this comment. -->
|
34 |
+
|
35 |
+
# scenario-MDBT-TCR_data-AmazonScience_massive_all_1_1
|
36 |
+
|
37 |
+
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the massive dataset.
|
38 |
+
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 1.0026
|
40 |
+
- Accuracy: 0.8643
|
41 |
+
- F1: 0.8368
|
42 |
+
|
43 |
+
## Model description
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Intended uses & limitations
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training and evaluation data
|
52 |
+
|
53 |
+
More information needed
|
54 |
+
|
55 |
+
## Training procedure
|
56 |
+
|
57 |
+
### Training hyperparameters
|
58 |
+
|
59 |
+
The following hyperparameters were used during training:
|
60 |
+
- learning_rate: 5e-05
|
61 |
+
- train_batch_size: 32
|
62 |
+
- eval_batch_size: 64
|
63 |
+
- seed: 66
|
64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
+
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 5
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
71 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
72 |
+
| 0.5131 | 0.27 | 5000 | 0.6674 | 0.8368 | 0.7780 |
|
73 |
+
| 0.3715 | 0.53 | 10000 | 0.6554 | 0.8527 | 0.8145 |
|
74 |
+
| 0.3066 | 0.8 | 15000 | 0.6924 | 0.8471 | 0.8103 |
|
75 |
+
| 0.2194 | 1.07 | 20000 | 0.7348 | 0.8548 | 0.8238 |
|
76 |
+
| 0.2112 | 1.34 | 25000 | 0.7297 | 0.8581 | 0.8288 |
|
77 |
+
| 0.1907 | 1.6 | 30000 | 0.7308 | 0.8558 | 0.8288 |
|
78 |
+
| 0.1816 | 1.87 | 35000 | 0.7785 | 0.8565 | 0.8281 |
|
79 |
+
| 0.1297 | 2.14 | 40000 | 0.8493 | 0.8567 | 0.8278 |
|
80 |
+
| 0.127 | 2.41 | 45000 | 0.8757 | 0.8576 | 0.8310 |
|
81 |
+
| 0.1148 | 2.67 | 50000 | 0.8581 | 0.8577 | 0.8300 |
|
82 |
+
| 0.1287 | 2.94 | 55000 | 0.8479 | 0.8597 | 0.8341 |
|
83 |
+
| 0.0875 | 3.21 | 60000 | 0.8763 | 0.8656 | 0.8392 |
|
84 |
+
| 0.0832 | 3.47 | 65000 | 0.9379 | 0.8620 | 0.8341 |
|
85 |
+
| 0.0837 | 3.74 | 70000 | 0.9044 | 0.8625 | 0.8339 |
|
86 |
+
| 0.0617 | 4.01 | 75000 | 0.9840 | 0.8618 | 0.8352 |
|
87 |
+
| 0.0524 | 4.28 | 80000 | 0.9955 | 0.8639 | 0.8385 |
|
88 |
+
| 0.0496 | 4.54 | 85000 | 1.0026 | 0.8643 | 0.8368 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.33.3
|
94 |
+
- Pytorch 2.1.1+cu121
|
95 |
+
- Datasets 2.14.5
|
96 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/mdeberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
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 |
+
"7": "LABEL_7",
|
19 |
+
"8": "LABEL_8",
|
20 |
+
"9": "LABEL_9",
|
21 |
+
"10": "LABEL_10",
|
22 |
+
"11": "LABEL_11",
|
23 |
+
"12": "LABEL_12",
|
24 |
+
"13": "LABEL_13",
|
25 |
+
"14": "LABEL_14",
|
26 |
+
"15": "LABEL_15",
|
27 |
+
"16": "LABEL_16",
|
28 |
+
"17": "LABEL_17",
|
29 |
+
"18": "LABEL_18",
|
30 |
+
"19": "LABEL_19",
|
31 |
+
"20": "LABEL_20",
|
32 |
+
"21": "LABEL_21",
|
33 |
+
"22": "LABEL_22",
|
34 |
+
"23": "LABEL_23",
|
35 |
+
"24": "LABEL_24",
|
36 |
+
"25": "LABEL_25",
|
37 |
+
"26": "LABEL_26",
|
38 |
+
"27": "LABEL_27",
|
39 |
+
"28": "LABEL_28",
|
40 |
+
"29": "LABEL_29",
|
41 |
+
"30": "LABEL_30",
|
42 |
+
"31": "LABEL_31",
|
43 |
+
"32": "LABEL_32",
|
44 |
+
"33": "LABEL_33",
|
45 |
+
"34": "LABEL_34",
|
46 |
+
"35": "LABEL_35",
|
47 |
+
"36": "LABEL_36",
|
48 |
+
"37": "LABEL_37",
|
49 |
+
"38": "LABEL_38",
|
50 |
+
"39": "LABEL_39",
|
51 |
+
"40": "LABEL_40",
|
52 |
+
"41": "LABEL_41",
|
53 |
+
"42": "LABEL_42",
|
54 |
+
"43": "LABEL_43",
|
55 |
+
"44": "LABEL_44",
|
56 |
+
"45": "LABEL_45",
|
57 |
+
"46": "LABEL_46",
|
58 |
+
"47": "LABEL_47",
|
59 |
+
"48": "LABEL_48",
|
60 |
+
"49": "LABEL_49",
|
61 |
+
"50": "LABEL_50",
|
62 |
+
"51": "LABEL_51",
|
63 |
+
"52": "LABEL_52",
|
64 |
+
"53": "LABEL_53",
|
65 |
+
"54": "LABEL_54",
|
66 |
+
"55": "LABEL_55",
|
67 |
+
"56": "LABEL_56",
|
68 |
+
"57": "LABEL_57",
|
69 |
+
"58": "LABEL_58",
|
70 |
+
"59": "LABEL_59"
|
71 |
+
},
|
72 |
+
"initializer_range": 0.02,
|
73 |
+
"intermediate_size": 3072,
|
74 |
+
"label2id": {
|
75 |
+
"LABEL_0": 0,
|
76 |
+
"LABEL_1": 1,
|
77 |
+
"LABEL_10": 10,
|
78 |
+
"LABEL_11": 11,
|
79 |
+
"LABEL_12": 12,
|
80 |
+
"LABEL_13": 13,
|
81 |
+
"LABEL_14": 14,
|
82 |
+
"LABEL_15": 15,
|
83 |
+
"LABEL_16": 16,
|
84 |
+
"LABEL_17": 17,
|
85 |
+
"LABEL_18": 18,
|
86 |
+
"LABEL_19": 19,
|
87 |
+
"LABEL_2": 2,
|
88 |
+
"LABEL_20": 20,
|
89 |
+
"LABEL_21": 21,
|
90 |
+
"LABEL_22": 22,
|
91 |
+
"LABEL_23": 23,
|
92 |
+
"LABEL_24": 24,
|
93 |
+
"LABEL_25": 25,
|
94 |
+
"LABEL_26": 26,
|
95 |
+
"LABEL_27": 27,
|
96 |
+
"LABEL_28": 28,
|
97 |
+
"LABEL_29": 29,
|
98 |
+
"LABEL_3": 3,
|
99 |
+
"LABEL_30": 30,
|
100 |
+
"LABEL_31": 31,
|
101 |
+
"LABEL_32": 32,
|
102 |
+
"LABEL_33": 33,
|
103 |
+
"LABEL_34": 34,
|
104 |
+
"LABEL_35": 35,
|
105 |
+
"LABEL_36": 36,
|
106 |
+
"LABEL_37": 37,
|
107 |
+
"LABEL_38": 38,
|
108 |
+
"LABEL_39": 39,
|
109 |
+
"LABEL_4": 4,
|
110 |
+
"LABEL_40": 40,
|
111 |
+
"LABEL_41": 41,
|
112 |
+
"LABEL_42": 42,
|
113 |
+
"LABEL_43": 43,
|
114 |
+
"LABEL_44": 44,
|
115 |
+
"LABEL_45": 45,
|
116 |
+
"LABEL_46": 46,
|
117 |
+
"LABEL_47": 47,
|
118 |
+
"LABEL_48": 48,
|
119 |
+
"LABEL_49": 49,
|
120 |
+
"LABEL_5": 5,
|
121 |
+
"LABEL_50": 50,
|
122 |
+
"LABEL_51": 51,
|
123 |
+
"LABEL_52": 52,
|
124 |
+
"LABEL_53": 53,
|
125 |
+
"LABEL_54": 54,
|
126 |
+
"LABEL_55": 55,
|
127 |
+
"LABEL_56": 56,
|
128 |
+
"LABEL_57": 57,
|
129 |
+
"LABEL_58": 58,
|
130 |
+
"LABEL_59": 59,
|
131 |
+
"LABEL_6": 6,
|
132 |
+
"LABEL_7": 7,
|
133 |
+
"LABEL_8": 8,
|
134 |
+
"LABEL_9": 9
|
135 |
+
},
|
136 |
+
"layer_norm_eps": 1e-07,
|
137 |
+
"max_position_embeddings": 512,
|
138 |
+
"max_relative_positions": -1,
|
139 |
+
"model_type": "deberta-v2",
|
140 |
+
"norm_rel_ebd": "layer_norm",
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_hidden_layers": 12,
|
143 |
+
"pad_token_id": 0,
|
144 |
+
"pooler_dropout": 0,
|
145 |
+
"pooler_hidden_act": "gelu",
|
146 |
+
"pooler_hidden_size": 768,
|
147 |
+
"pos_att_type": [
|
148 |
+
"p2c",
|
149 |
+
"c2p"
|
150 |
+
],
|
151 |
+
"position_biased_input": false,
|
152 |
+
"position_buckets": 256,
|
153 |
+
"relative_attention": true,
|
154 |
+
"share_att_key": true,
|
155 |
+
"torch_dtype": "float32",
|
156 |
+
"transformers_version": "4.33.3",
|
157 |
+
"type_vocab_size": 0,
|
158 |
+
"vocab_size": 251000
|
159 |
+
}
|
eval_results_ml.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"nb-NO": {"f1": 0.012019000889607884, "accuracy": 0.04606590450571621}, "fr-FR": {"f1": 0.008492272469929457, "accuracy": 0.03396099529253531}, "bn-BD": {"f1": 0.011669300004516788, "accuracy": 0.03160726294552791}, "es-ES": {"f1": 0.008853805126984126, "accuracy": 0.02925353059852051}, "az-AZ": {"f1": 0.010558384042046117, "accuracy": 0.03799596503026227}, "da-DK": {"f1": 0.010996445282701498, "accuracy": 0.03396099529253531}, "ca-ES": {"f1": 0.01053840581306283, "accuracy": 0.03833221250840619}, "it-IT": {"f1": 0.008757670724817408, "accuracy": 0.02824478816408877}, "km-KH": {"f1": 0.009853364760794375, "accuracy": 0.03261600537995965}, "sw-KE": {"f1": 0.011783894093590699, "accuracy": 0.03967720242098184}, "te-IN": {"f1": 0.009750077470156559, "accuracy": 0.03328850033624748}, "jv-ID": {"f1": 0.00799501062964386, "accuracy": 0.0265635507733692}, "zh-CN": {"f1": 0.0197456686345654, "accuracy": 0.03900470746469401}, "pt-PT": {"f1": 0.010875702201031696, "accuracy": 0.03227975790181574}, "ms-MY": {"f1": 0.01012587752844684, "accuracy": 0.03261600537995965}, "sl-SL": {"f1": 0.012555716255058707, "accuracy": 0.03463349024882313}, "mn-MN": {"f1": 0.013568313518437566, "accuracy": 0.03160726294552791}, "de-DE": {"f1": 0.0069720410655382085, "accuracy": 0.02757229320780094}, "ml-IN": {"f1": 0.009160751677700333, "accuracy": 0.03665097511768662}, "ar-SA": {"f1": 0.012684188466879902, "accuracy": 0.04001344989912576}, "kn-IN": {"f1": 0.00952656251000866, "accuracy": 0.03665097511768662}, "en-US": {"f1": 0.008731659647542273, "accuracy": 0.03026227303295225}, "sq-AL": {"f1": 0.009970924011615138, "accuracy": 0.03530598520511096}, "fi-FI": {"f1": 0.014044420411004292, "accuracy": 0.03564223268325487}, "hu-HU": {"f1": 0.009665474803596693, "accuracy": 0.03328850033624748}, "hi-IN": {"f1": 0.01074810249615481, "accuracy": 0.03597848016139879}, "tr-TR": {"f1": 0.011151460004962033, "accuracy": 0.03732347007397444}, "hy-AM": {"f1": 0.009265220307715923, "accuracy": 0.03026227303295225}, "cy-GB": {"f1": 0.009505542593050928, "accuracy": 0.03530598520511096}, "ru-RU": {"f1": 0.012416071180966824, "accuracy": 0.04707464694014795}, "pl-PL": {"f1": 0.009144975000210326, "accuracy": 0.03362474781439139}, "my-MM": {"f1": 0.008002815385973736, "accuracy": 0.03429724277067922}, "el-GR": {"f1": 0.01184212226127579, "accuracy": 0.03194351042367182}, "nl-NL": {"f1": 0.010436582741691213, "accuracy": 0.02992602555480834}, "ro-RO": {"f1": 0.01358534277436384, "accuracy": 0.0363147276395427}, "am-ET": {"f1": 0.009739568306955259, "accuracy": 0.03396099529253531}, "he-IL": {"f1": 0.018400371623280478, "accuracy": 0.04270342972427707}, "tl-PH": {"f1": 0.006592469092758274, "accuracy": 0.02757229320780094}, "ja-JP": {"f1": 0.008992306835998559, "accuracy": 0.03026227303295225}, "zh-TW": {"f1": 0.014292726906824335, "accuracy": 0.04135843981170141}, "th-TH": {"f1": 0.013199423521434325, "accuracy": 0.03833221250840619}, "is-IS": {"f1": 0.011853149379817367, "accuracy": 0.03967720242098184}, "ur-PK": {"f1": 0.011806200948505038, "accuracy": 0.03093476798924008}, "sv-SE": {"f1": 0.008811447003744699, "accuracy": 0.03429724277067922}, "ka-GE": {"f1": 0.009232359052637066, "accuracy": 0.03530598520511096}, "ko-KR": {"f1": 0.01185008113889738, "accuracy": 0.0386684599865501}, "fa-IR": {"f1": 0.012507857873278714, "accuracy": 0.03362474781439139}, "id-ID": {"f1": 0.011101287684256701, "accuracy": 0.026899798251513115}, "af-ZA": {"f1": 0.01583713548548105, "accuracy": 0.03698722259583053}, "ta-IN": {"f1": 0.010373316679240534, "accuracy": 0.03295225285810356}, "vi-VN": {"f1": 0.01239755184988743, "accuracy": 0.03362474781439139}, "lv-LV": {"f1": 0.008380076420249592, "accuracy": 0.026227303295225286}, "all": {"f1": 0.01140940497830658, "accuracy": 0.03447183280740779}}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:506df72e2493e99a486892572960c8338b65e7b58483cdacf25fd6f3fd7ca0ca
|
3 |
+
size 1115491954
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f4e69fea42866e66f9d49628bd0241dbac660172cd3c2a027dba6a98a4cebf0
|
3 |
+
size 4600
|