Publish verified antielite_classifier_013_s43
Browse files- config.json +43 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_metadata.json +65 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"directionality": "bidi",
|
| 10 |
+
"dtype": "float32",
|
| 11 |
+
"eos_token_id": null,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "not_antielite",
|
| 17 |
+
"1": "antielite"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"is_decoder": false,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"antielite": 1,
|
| 24 |
+
"not_antielite": 0
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"pooler_fc_size": 768,
|
| 33 |
+
"pooler_num_attention_heads": 12,
|
| 34 |
+
"pooler_num_fc_layers": 3,
|
| 35 |
+
"pooler_size_per_head": 128,
|
| 36 |
+
"pooler_type": "first_token_transform",
|
| 37 |
+
"problem_type": "single_label_classification",
|
| 38 |
+
"tie_word_embeddings": true,
|
| 39 |
+
"transformers_version": "5.19.0",
|
| 40 |
+
"type_vocab_size": 2,
|
| 41 |
+
"use_cache": false,
|
| 42 |
+
"vocab_size": 119547
|
| 43 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b451167acd0d92b8c1b5737f5fd34d3e67ba198e07046f99a6b26ddb263bfbfb
|
| 3 |
+
size 711443432
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
training_metadata.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"identity": {
|
| 3 |
+
"base_model": "google-bert/bert-base-multilingual-cased",
|
| 4 |
+
"batch_size": 64,
|
| 5 |
+
"class_weights": "balanced",
|
| 6 |
+
"data_sha256": {
|
| 7 |
+
"All_test_posts.csv": "4d3f03fc89175a6ccc6c70f79bd36365900209a2dbbb713571e39a9b535186f8",
|
| 8 |
+
"All_train_posts.csv": "5a70a8f267a577bbc4b7e4a761a97aa60b5c305d3da7eacd7d29f191352a82f8"
|
| 9 |
+
},
|
| 10 |
+
"device_batch": 64,
|
| 11 |
+
"distribution": "original",
|
| 12 |
+
"environment": {
|
| 13 |
+
"accelerate": "1.15.0",
|
| 14 |
+
"datasets": "5.1.0",
|
| 15 |
+
"huggingface_hub": "2.2.0",
|
| 16 |
+
"numpy": "2.5.4",
|
| 17 |
+
"pandas": "3.0.6",
|
| 18 |
+
"scikit-learn": "1.9.1",
|
| 19 |
+
"torch": "2.14.1",
|
| 20 |
+
"transformers": "5.19.0"
|
| 21 |
+
},
|
| 22 |
+
"epochs": 20,
|
| 23 |
+
"label": "antielite",
|
| 24 |
+
"learning_rate": 1e-05,
|
| 25 |
+
"max_length": 512,
|
| 26 |
+
"model_n": 13,
|
| 27 |
+
"patience": 2,
|
| 28 |
+
"precision": "bf16",
|
| 29 |
+
"revision": "3f076fdb1ab68d5b2880cb87a0886f315b8146f8",
|
| 30 |
+
"seed": 43,
|
| 31 |
+
"split_seed": 42,
|
| 32 |
+
"test_mode": false,
|
| 33 |
+
"tf32": true,
|
| 34 |
+
"train_lang": "Greek",
|
| 35 |
+
"val_size": 0.2,
|
| 36 |
+
"warmup_ratio": 0.0,
|
| 37 |
+
"weight_decay": 0.01
|
| 38 |
+
},
|
| 39 |
+
"name": "antielite_classifier_013_s43",
|
| 40 |
+
"private": false,
|
| 41 |
+
"repo_id": "AnonymousCS/antielite_classifier_013_s43",
|
| 42 |
+
"results": {
|
| 43 |
+
"data/antielite/classified_testset/antielite_classifier_013_s43.csv": {
|
| 44 |
+
"sha256": "2e200645bd7d4a8aeacced9316140c915aef03ab17ed0ed1528ee409a9042bd3",
|
| 45 |
+
"size": 625708
|
| 46 |
+
},
|
| 47 |
+
"data/antielite/classified_valset/antielite_classifier_013_s43.csv": {
|
| 48 |
+
"sha256": "26d0170b76b08657fe59397fc907d44760f2f790c9d8467d05e9d1c791da6945",
|
| 49 |
+
"size": 28154
|
| 50 |
+
},
|
| 51 |
+
"data/antielite/final_test_results/antielite_classifier_013_s43.csv": {
|
| 52 |
+
"sha256": "900b6411772ff2e1cdf39e9a7fb9a4a7cea9dde500b5a0cd618e21277ae423aa",
|
| 53 |
+
"size": 7818
|
| 54 |
+
},
|
| 55 |
+
"data/antielite/timing/antielite_classifier_013_s43.csv": {
|
| 56 |
+
"sha256": "4326f681cc781c4d66d06110bb91c0999ab6755f784804bb1a5795d1b0e9b83a",
|
| 57 |
+
"size": 334
|
| 58 |
+
},
|
| 59 |
+
"data/antielite/training_logs/antielite_classifier_013_s43.csv": {
|
| 60 |
+
"sha256": "6605c4af72bbd1d59b23e4b5e88189d8a759abe21bf6696c8559b688d7a4a294",
|
| 61 |
+
"size": 3446
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"status": "pending"
|
| 65 |
+
}
|