ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support dev set in web ui

Browse Source 
Former-commit-id: fe1370561a9b027d9ebdef52733344f1e3683081
This commit is contained in:
hiyouga
2023-07-18 20:40:49 +08:00
parent 8e4ae0aaac
commit 35e76879f5
5 changed files with 67 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llmtuner/tuner/sft/metric.py
View File

@@ -23,7 +23,7 @@ class ComputeMetrics:
Uses the model predictions to compute metrics.
"""
preds, labels = eval_preds
score_dict = {"rouge-1": [], "rouge-2": [], "rouge-l": [], "bleu-4": []}
score_dict = {"accuracy": [], "rouge-1": [], "rouge-2": [], "rouge-l": [], "bleu-4": []}
preds = np.where(preds != IGNORE_INDEX, preds, self.tokenizer.pad_token_id)
labels = np.where(labels != IGNORE_INDEX, labels, self.tokenizer.pad_token_id)
@@ -47,5 +47,6 @@ class ComputeMetrics:
bleu_score = sentence_bleu([list(label)], list(pred), smoothing_function=SmoothingFunction().method3)
score_dict["bleu-4"].append(round(bleu_score * 100, 4))
score_dict["accuracy"].append(float(len(label) != 0 and pred[:len(label)] == label))
return {k: float(np.mean(v)) for k, v in score_dict.items()}