Hyperparameter	Value
LANGUAGES	es
LR	2e-05
EPOCHS	3
MAX_LENGTH	256
USE_BIO	False
USE_LANG_TOKEN	False
GATED_BIO	False
FOCAL_LOSS	True
FOCAL_GAMMA	2.5
USE_SAMPLER	True
R_DROP	True
R_KL_ALPHA	1.0
TEXT_NORMALIZE	True

Dev set results (summary)

Metric	Value
f1_macro_dev_0.5	0.5860987718839823
f1_weighted_dev_0.5	0.6866285008432904
accuracy_dev_0.5	0.6363636363636364
f1_macro_dev_best_global	0.6545794392523364
f1_weighted_dev_best_global	0.8041348060039648
accuracy_dev_best_global	0.7878787878787878
f1_macro_dev_best_by_lang	0.6545794392523364
f1_weighted_dev_best_by_lang	0.8041348060039648
accuracy_dev_best_by_lang	0.7878787878787878
default_threshold	0.5
best_threshold_global	0.55
thresholds_by_lang	{"es": 0.55}

Thresholds

Default: 0.5
Best global: 0.55
Best by language: { "es": 0.55 }

Detailed evaluation

Classification report @ 0.5

text

              precision    recall  f1-score   support

 no-recl (0)     0.9848    0.5804    0.7303       112
    recl (1)     0.2879    0.9500    0.4419        20

    accuracy                         0.6364       132
   macro avg     0.6364    0.7652    0.5861       132
weighted avg     0.8792    0.6364    0.6866       132

Classification report @ best global threshold (t=0.55)

text

              precision    recall  f1-score   support

 no-recl (0)     0.9118    0.8304    0.8692       112
    recl (1)     0.3667    0.5500    0.4400        20

    accuracy                         0.7879       132
   macro avg     0.6392    0.6902    0.6546       132
weighted avg     0.8292    0.7879    0.8041       132

Classification report @ best per-language thresholds

text

              precision    recall  f1-score   support

 no-recl (0)     0.9118    0.8304    0.8692       112
    recl (1)     0.3667    0.5500    0.4400        20

    accuracy                         0.7879       132
   macro avg     0.6392    0.6902    0.6546       132
weighted avg     0.8292    0.7879    0.8041       132

Per-language metrics (at best-by-lang)

lang	n	acc	f1_macro	f1_weighted	prec_macro	rec_macro	prec_weighted	rec_weighted
es	132	0.7879	0.6546	0.8041	0.6392	0.6902	0.8292	0.7879

Data

Train/Dev: private multilingual splits with ~15% stratified Dev (by (lang,label)).
Source: merged EN/IT/ES data with bios retained (ignored if unused by model).

Usage

python

from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoConfig
import torch, numpy as np

repo = "SimoneAstarita/es-no-bio-20251014-t18"
tok = AutoTokenizer.from_pretrained(repo)
cfg = AutoConfig.from_pretrained(repo)
model = AutoModelForSequenceClassification.from_pretrained(repo)

texts = ["example text ..."]
langs = ["en"]

mode = "best_global"  # or "0.5", "by_lang"

enc = tok(texts, truncation=True, padding=True, max_length=256, return_tensors="pt")
with torch.no_grad():
    logits = model(**enc).logits
probs = torch.softmax(logits, dim=-1)[:, 1].cpu().numpy()

if mode == "0.5":
    th = 0.5
    preds = (probs >= th).astype(int)
elif mode == "best_global":
    th = getattr(cfg, "best_threshold_global", 0.5)
    preds = (probs >= th).astype(int)
elif mode == "by_lang":
    th_by_lang = getattr(cfg, "thresholds_by_lang", {})
    preds = np.zeros_like(probs, dtype=int)
    for lg in np.unique(langs):
        t = th_by_lang.get(lg, getattr(cfg, "best_threshold_global", 0.5))
        preds[np.array(langs) == lg] = (probs[np.array(langs) == lg] >= t).astype(int)
print(list(zip(texts, preds, probs)))

Additional files

reports.json: all metrics (macro/weighted/accuracy) for @0.5, @best_global, and @best_by_lang. config.json: stores thresholds: default_threshold, best_threshold_global, thresholds_by_lang. postprocessing.json: duplicate threshold info for external tools.