distilbert_cheat_massive
Browse files- README.md +95 -0
- config.json +161 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert/distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- massive
|
8 |
+
metrics:
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: results
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: massive
|
18 |
+
type: massive
|
19 |
+
config: en-US
|
20 |
+
split: test
|
21 |
+
args: en-US
|
22 |
+
metrics:
|
23 |
+
- name: F1
|
24 |
+
type: f1
|
25 |
+
value: 0.9734295558770142
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# results
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the massive dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.0231
|
36 |
+
- F1: 0.9734
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 8
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 500
|
62 |
+
- num_epochs: 10
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
+
| 3.8235 | 0.5 | 185 | 3.7551 | 0.0022 |
|
69 |
+
| 3.5949 | 0.99 | 370 | 3.1246 | 0.0454 |
|
70 |
+
| 2.8705 | 1.49 | 555 | 2.4379 | 0.1543 |
|
71 |
+
| 2.3444 | 1.99 | 740 | 1.7732 | 0.2967 |
|
72 |
+
| 1.7151 | 2.49 | 925 | 1.2983 | 0.4403 |
|
73 |
+
| 1.3959 | 2.98 | 1110 | 0.9965 | 0.5490 |
|
74 |
+
| 0.9919 | 3.48 | 1295 | 0.7098 | 0.6880 |
|
75 |
+
| 0.9495 | 3.98 | 1480 | 0.5798 | 0.7014 |
|
76 |
+
| 0.6 | 4.48 | 1665 | 0.4419 | 0.7408 |
|
77 |
+
| 0.5952 | 4.97 | 1850 | 0.3653 | 0.7522 |
|
78 |
+
| 0.3715 | 5.47 | 2035 | 0.3077 | 0.7957 |
|
79 |
+
| 0.3783 | 5.97 | 2220 | 0.2050 | 0.8453 |
|
80 |
+
| 0.196 | 6.47 | 2405 | 0.1532 | 0.8386 |
|
81 |
+
| 0.22 | 6.96 | 2590 | 0.0968 | 0.8871 |
|
82 |
+
| 0.1117 | 7.46 | 2775 | 0.0725 | 0.9057 |
|
83 |
+
| 0.1065 | 7.96 | 2960 | 0.0458 | 0.9265 |
|
84 |
+
| 0.0644 | 8.45 | 3145 | 0.0378 | 0.9336 |
|
85 |
+
| 0.0526 | 8.95 | 3330 | 0.0324 | 0.9616 |
|
86 |
+
| 0.0521 | 9.45 | 3515 | 0.0251 | 0.9708 |
|
87 |
+
| 0.0302 | 9.95 | 3700 | 0.0231 | 0.9734 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.38.1
|
93 |
+
- Pytorch 2.1.0+cu121
|
94 |
+
- Datasets 2.18.0
|
95 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"dim": 768,
|
11 |
+
"dropout": 0.1,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dim": 3072,
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4",
|
22 |
+
"5": "LABEL_5",
|
23 |
+
"6": "LABEL_6",
|
24 |
+
"7": "LABEL_7",
|
25 |
+
"8": "LABEL_8",
|
26 |
+
"9": "LABEL_9",
|
27 |
+
"10": "LABEL_10",
|
28 |
+
"11": "LABEL_11",
|
29 |
+
"12": "LABEL_12",
|
30 |
+
"13": "LABEL_13",
|
31 |
+
"14": "LABEL_14",
|
32 |
+
"15": "LABEL_15",
|
33 |
+
"16": "LABEL_16",
|
34 |
+
"17": "LABEL_17",
|
35 |
+
"18": "LABEL_18",
|
36 |
+
"19": "LABEL_19",
|
37 |
+
"20": "LABEL_20",
|
38 |
+
"21": "LABEL_21",
|
39 |
+
"22": "LABEL_22",
|
40 |
+
"23": "LABEL_23",
|
41 |
+
"24": "LABEL_24",
|
42 |
+
"25": "LABEL_25",
|
43 |
+
"26": "LABEL_26",
|
44 |
+
"27": "LABEL_27",
|
45 |
+
"28": "LABEL_28",
|
46 |
+
"29": "LABEL_29",
|
47 |
+
"30": "LABEL_30",
|
48 |
+
"31": "LABEL_31",
|
49 |
+
"32": "LABEL_32",
|
50 |
+
"33": "LABEL_33",
|
51 |
+
"34": "LABEL_34",
|
52 |
+
"35": "LABEL_35",
|
53 |
+
"36": "LABEL_36",
|
54 |
+
"37": "LABEL_37",
|
55 |
+
"38": "LABEL_38",
|
56 |
+
"39": "LABEL_39",
|
57 |
+
"40": "LABEL_40",
|
58 |
+
"41": "LABEL_41",
|
59 |
+
"42": "LABEL_42",
|
60 |
+
"43": "LABEL_43",
|
61 |
+
"44": "LABEL_44",
|
62 |
+
"45": "LABEL_45",
|
63 |
+
"46": "LABEL_46",
|
64 |
+
"47": "LABEL_47",
|
65 |
+
"48": "LABEL_48",
|
66 |
+
"49": "LABEL_49",
|
67 |
+
"50": "LABEL_50",
|
68 |
+
"51": "LABEL_51",
|
69 |
+
"52": "LABEL_52",
|
70 |
+
"53": "LABEL_53",
|
71 |
+
"54": "LABEL_54",
|
72 |
+
"55": "LABEL_55",
|
73 |
+
"56": "LABEL_56",
|
74 |
+
"57": "LABEL_57",
|
75 |
+
"58": "LABEL_58",
|
76 |
+
"59": "LABEL_59"
|
77 |
+
},
|
78 |
+
"initializer_range": 0.02,
|
79 |
+
"intermediate_size": 3072,
|
80 |
+
"label2id": {
|
81 |
+
"LABEL_0": 0,
|
82 |
+
"LABEL_1": 1,
|
83 |
+
"LABEL_10": 10,
|
84 |
+
"LABEL_11": 11,
|
85 |
+
"LABEL_12": 12,
|
86 |
+
"LABEL_13": 13,
|
87 |
+
"LABEL_14": 14,
|
88 |
+
"LABEL_15": 15,
|
89 |
+
"LABEL_16": 16,
|
90 |
+
"LABEL_17": 17,
|
91 |
+
"LABEL_18": 18,
|
92 |
+
"LABEL_19": 19,
|
93 |
+
"LABEL_2": 2,
|
94 |
+
"LABEL_20": 20,
|
95 |
+
"LABEL_21": 21,
|
96 |
+
"LABEL_22": 22,
|
97 |
+
"LABEL_23": 23,
|
98 |
+
"LABEL_24": 24,
|
99 |
+
"LABEL_25": 25,
|
100 |
+
"LABEL_26": 26,
|
101 |
+
"LABEL_27": 27,
|
102 |
+
"LABEL_28": 28,
|
103 |
+
"LABEL_29": 29,
|
104 |
+
"LABEL_3": 3,
|
105 |
+
"LABEL_30": 30,
|
106 |
+
"LABEL_31": 31,
|
107 |
+
"LABEL_32": 32,
|
108 |
+
"LABEL_33": 33,
|
109 |
+
"LABEL_34": 34,
|
110 |
+
"LABEL_35": 35,
|
111 |
+
"LABEL_36": 36,
|
112 |
+
"LABEL_37": 37,
|
113 |
+
"LABEL_38": 38,
|
114 |
+
"LABEL_39": 39,
|
115 |
+
"LABEL_4": 4,
|
116 |
+
"LABEL_40": 40,
|
117 |
+
"LABEL_41": 41,
|
118 |
+
"LABEL_42": 42,
|
119 |
+
"LABEL_43": 43,
|
120 |
+
"LABEL_44": 44,
|
121 |
+
"LABEL_45": 45,
|
122 |
+
"LABEL_46": 46,
|
123 |
+
"LABEL_47": 47,
|
124 |
+
"LABEL_48": 48,
|
125 |
+
"LABEL_49": 49,
|
126 |
+
"LABEL_5": 5,
|
127 |
+
"LABEL_50": 50,
|
128 |
+
"LABEL_51": 51,
|
129 |
+
"LABEL_52": 52,
|
130 |
+
"LABEL_53": 53,
|
131 |
+
"LABEL_54": 54,
|
132 |
+
"LABEL_55": 55,
|
133 |
+
"LABEL_56": 56,
|
134 |
+
"LABEL_57": 57,
|
135 |
+
"LABEL_58": 58,
|
136 |
+
"LABEL_59": 59,
|
137 |
+
"LABEL_6": 6,
|
138 |
+
"LABEL_7": 7,
|
139 |
+
"LABEL_8": 8,
|
140 |
+
"LABEL_9": 9
|
141 |
+
},
|
142 |
+
"layer_norm_eps": 1e-12,
|
143 |
+
"max_position_embeddings": 512,
|
144 |
+
"model_type": "bert",
|
145 |
+
"n_heads": 12,
|
146 |
+
"n_layers": 6,
|
147 |
+
"num_attention_heads": 12,
|
148 |
+
"num_hidden_layers": 12,
|
149 |
+
"pad_token_id": 0,
|
150 |
+
"position_embedding_type": "absolute",
|
151 |
+
"problem_type": "single_label_classification",
|
152 |
+
"qa_dropout": 0.1,
|
153 |
+
"seq_classif_dropout": 0.2,
|
154 |
+
"sinusoidal_pos_embds": false,
|
155 |
+
"tie_weights_": true,
|
156 |
+
"torch_dtype": "float32",
|
157 |
+
"transformers_version": "4.38.1",
|
158 |
+
"type_vocab_size": 2,
|
159 |
+
"use_cache": true,
|
160 |
+
"vocab_size": 30522
|
161 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e0d5a42409f25cca84b32fbd3e5a7ef4e01b1c777c638e4d0730ed0fe53f3f
|
3 |
+
size 438137056
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0e5ef26ac2667f1eda020d60129cda16aec5b65b71529d3378dce4d8b763604
|
3 |
+
size 4792
|