Add distilbert_optuna weights + eval metrics
Browse files
weights/distilbert_optuna/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"dtype": "float32",
|
| 11 |
+
"eos_token_id": null,
|
| 12 |
+
"hidden_dim": 3072,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "safe",
|
| 15 |
+
"1": "unsafe"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"safe": 0,
|
| 20 |
+
"unsafe": 1
|
| 21 |
+
},
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "distilbert",
|
| 24 |
+
"n_heads": 12,
|
| 25 |
+
"n_layers": 6,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"qa_dropout": 0.1,
|
| 29 |
+
"seq_classif_dropout": 0.2,
|
| 30 |
+
"sinusoidal_pos_embds": false,
|
| 31 |
+
"tie_weights_": true,
|
| 32 |
+
"tie_word_embeddings": true,
|
| 33 |
+
"transformers_version": "5.6.2",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
weights/distilbert_optuna/eval_plot.png
ADDED
|
weights/distilbert_optuna/metrics.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "distilbert_optuna",
|
| 3 |
+
"hf_id": "distilbert-base-uncased",
|
| 4 |
+
"metrics": {
|
| 5 |
+
"f1": 0.9486,
|
| 6 |
+
"f1_macro": 0.9483,
|
| 7 |
+
"accuracy": 0.9486,
|
| 8 |
+
"roc_auc": 0.9882,
|
| 9 |
+
"pr_auc": 0.9903,
|
| 10 |
+
"fpr_pct": 5.27,
|
| 11 |
+
"fnr_pct": 5.03,
|
| 12 |
+
"threshold": 0.6
|
| 13 |
+
},
|
| 14 |
+
"params": {
|
| 15 |
+
"name": "distilbert_optuna",
|
| 16 |
+
"hf_id": "distilbert-base-uncased",
|
| 17 |
+
"epochs": 5,
|
| 18 |
+
"lr": 2.3628864184236417e-05,
|
| 19 |
+
"batch": 32,
|
| 20 |
+
"weight_decay": 0.01129013355909268,
|
| 21 |
+
"unsafe_weight": 1.8803049874792026,
|
| 22 |
+
"label_smooth": 0.012203823484477884,
|
| 23 |
+
"warmup_ratio": 0.12427653651669054
|
| 24 |
+
}
|
| 25 |
+
}
|
weights/distilbert_optuna/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86ab68c2c39462e2c371b7fdab5ab18388d552d7fb18068c0504446ef161375a
|
| 3 |
+
size 267832560
|
weights/distilbert_optuna/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
weights/distilbert_optuna/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 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 |
+
}
|