Upload 8 files
Browse files- PROJECT_STRUCTURE.txt +53 -0
- README.txt +20 -0
- compare_models.py +2805 -0
- requirements.txt +8 -0
- run_all.bat +3 -0
- run_all.sh +4 -0
- test.py +1353 -0
- train.py +848 -0
PROJECT_STRUCTURE.txt
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
TELECOM QLoRA FOUR-OUTPUT COMPLETE WORKSPACE
|
| 2 |
+
|
| 3 |
+
Project structure
|
| 4 |
+
=================
|
| 5 |
+
train.py
|
| 6 |
+
test.py
|
| 7 |
+
requirements.txt
|
| 8 |
+
run_all.sh
|
| 9 |
+
run_all.bat
|
| 10 |
+
README.txt
|
| 11 |
+
|
| 12 |
+
sample/
|
| 13 |
+
data/
|
| 14 |
+
train_four_output.jsonl
|
| 15 |
+
validation_four_output.jsonl
|
| 16 |
+
test_four_output.jsonl
|
| 17 |
+
.cache/
|
| 18 |
+
huggingface/
|
| 19 |
+
|
| 20 |
+
models/
|
| 21 |
+
(training output will be written here)
|
| 22 |
+
|
| 23 |
+
Training
|
| 24 |
+
========
|
| 25 |
+
1. Install dependencies:
|
| 26 |
+
pip install -r requirements.txt
|
| 27 |
+
|
| 28 |
+
2. Make sure CUDA + a compatible NVIDIA GPU/bitsandbytes setup is available.
|
| 29 |
+
|
| 30 |
+
3. Train:
|
| 31 |
+
python train.py
|
| 32 |
+
|
| 33 |
+
4. Evaluate:
|
| 34 |
+
python test.py --adapter "models/telecom-qwen-four-output" --test "sample/data/test_four_output.jsonl" --samples 0
|
| 35 |
+
|
| 36 |
+
Debug:
|
| 37 |
+
======
|
| 38 |
+
python test.py --adapter "models/telecom-qwen-four-output" --test "sample/data/test_four_output.jsonl" --samples 10 --debug
|
| 39 |
+
|
| 40 |
+
Expected response sections
|
| 41 |
+
===========================
|
| 42 |
+
Probable Root Cause:
|
| 43 |
+
Explanation:
|
| 44 |
+
Recommendation:
|
| 45 |
+
Fault Severity:
|
| 46 |
+
fault_severity=0|1|2
|
| 47 |
+
|
| 48 |
+
Important
|
| 49 |
+
=========
|
| 50 |
+
Root Cause, Explanation, and Recommendation targets are structured,
|
| 51 |
+
data-constrained synthetic targets because the source dataset contains
|
| 52 |
+
fault_severity labels but not engineer-validated root-cause/remediation
|
| 53 |
+
annotations. See README.txt.
|
README.txt
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
TELECOM FOUR-OUTPUT DATASET
|
| 2 |
+
|
| 3 |
+
Files:
|
| 4 |
+
- train_four_output.jsonl
|
| 5 |
+
- validation_four_output.jsonl
|
| 6 |
+
- test_four_output.jsonl
|
| 7 |
+
|
| 8 |
+
IMPORTANT:
|
| 9 |
+
The original cleaned data provides fault_severity labels and telecom
|
| 10 |
+
event/log features, but it does not provide independently verified root-cause
|
| 11 |
+
or remediation ground truth. Therefore, the Root Cause, Explanation, and
|
| 12 |
+
Recommendation fields in these files are STRUCTURED, DATA-CONSTRAINED
|
| 13 |
+
SYNTHETIC TARGETS derived from the supplied features and the existing label.
|
| 14 |
+
They must not be presented as ground-truth engineering diagnoses.
|
| 15 |
+
|
| 16 |
+
The targets intentionally avoid inventing RSRP/RSRQ/SINR/CQI/PRB/PCI,
|
| 17 |
+
throughput, alarms, hardware failures, or other absent telemetry.
|
| 18 |
+
|
| 19 |
+
For a production root-cause model, replace these synthetic targets with
|
| 20 |
+
engineer-validated annotations.
|
compare_models.py
ADDED
|
@@ -0,0 +1,2805 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ============================================================
|
| 2 |
+
# TELECOM FAST MODEL COMPARISON
|
| 3 |
+
# ============================================================
|
| 4 |
+
#
|
| 5 |
+
# Compare:
|
| 6 |
+
#
|
| 7 |
+
# 1. Original Qwen/Qwen2.5-1.5B-Instruct
|
| 8 |
+
# 2. Fine-tuned QLoRA adapter
|
| 9 |
+
#
|
| 10 |
+
# Evaluation:
|
| 11 |
+
#
|
| 12 |
+
# - Fault Severity Accuracy
|
| 13 |
+
# - Fault Severity Macro F1
|
| 14 |
+
# - Fault Severity Weighted F1
|
| 15 |
+
# - Root Cause Token-F1
|
| 16 |
+
# - Explanation Token-F1
|
| 17 |
+
# - Recommendation Token-F1
|
| 18 |
+
# - Four-output Format Compliance
|
| 19 |
+
# - Input Tokens
|
| 20 |
+
# - Output Tokens
|
| 21 |
+
# - Total Tokens
|
| 22 |
+
# - Generation Time
|
| 23 |
+
# - Tokens / Second
|
| 24 |
+
#
|
| 25 |
+
# IMPORTANT:
|
| 26 |
+
#
|
| 27 |
+
# This version does NOT use an LLM judge.
|
| 28 |
+
# It is therefore faster and reproducible.
|
| 29 |
+
#
|
| 30 |
+
# ============================================================
|
| 31 |
+
|
| 32 |
+
import os
|
| 33 |
+
import re
|
| 34 |
+
import json
|
| 35 |
+
import csv
|
| 36 |
+
import argparse
|
| 37 |
+
import time
|
| 38 |
+
import gc
|
| 39 |
+
from collections import Counter
|
| 40 |
+
|
| 41 |
+
import torch
|
| 42 |
+
|
| 43 |
+
from datasets import load_dataset
|
| 44 |
+
|
| 45 |
+
from transformers import (
|
| 46 |
+
AutoTokenizer,
|
| 47 |
+
AutoModelForCausalLM,
|
| 48 |
+
BitsAndBytesConfig,
|
| 49 |
+
)
|
| 50 |
+
|
| 51 |
+
from peft import PeftModel
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
# ============================================================
|
| 55 |
+
# CONFIGURATION
|
| 56 |
+
# ============================================================
|
| 57 |
+
|
| 58 |
+
MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"
|
| 59 |
+
|
| 60 |
+
DEFAULT_ADAPTER = (
|
| 61 |
+
"models/telecom-qwen-four-output"
|
| 62 |
+
)
|
| 63 |
+
|
| 64 |
+
DEFAULT_TEST_FILE = (
|
| 65 |
+
"sample/data/test_four_output.jsonl"
|
| 66 |
+
)
|
| 67 |
+
|
| 68 |
+
DEFAULT_OUTPUT_DIR = (
|
| 69 |
+
"evaluation_results"
|
| 70 |
+
)
|
| 71 |
+
|
| 72 |
+
CACHE_DIR = (
|
| 73 |
+
"sample/.cache/huggingface"
|
| 74 |
+
)
|
| 75 |
+
|
| 76 |
+
# Number of examples:
|
| 77 |
+
#
|
| 78 |
+
# 10 = very quick test
|
| 79 |
+
# 50 = quick evaluation
|
| 80 |
+
# 100 = better evaluation
|
| 81 |
+
# 0 = entire test set
|
| 82 |
+
#
|
| 83 |
+
DEFAULT_SAMPLES = 50
|
| 84 |
+
|
| 85 |
+
MAX_INPUT_LENGTH = 1024
|
| 86 |
+
|
| 87 |
+
MAX_NEW_TOKENS = 220
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
# ============================================================
|
| 91 |
+
# COMMAND LINE
|
| 92 |
+
# ============================================================
|
| 93 |
+
|
| 94 |
+
parser = argparse.ArgumentParser(
|
| 95 |
+
description="Fast comparison of original and fine-tuned Qwen models"
|
| 96 |
+
)
|
| 97 |
+
|
| 98 |
+
parser.add_argument(
|
| 99 |
+
"--adapter",
|
| 100 |
+
default=DEFAULT_ADAPTER,
|
| 101 |
+
help="Path to LoRA adapter",
|
| 102 |
+
)
|
| 103 |
+
|
| 104 |
+
parser.add_argument(
|
| 105 |
+
"--test",
|
| 106 |
+
default=DEFAULT_TEST_FILE,
|
| 107 |
+
help="Path to test JSONL",
|
| 108 |
+
)
|
| 109 |
+
|
| 110 |
+
parser.add_argument(
|
| 111 |
+
"--samples",
|
| 112 |
+
type=int,
|
| 113 |
+
default=DEFAULT_SAMPLES,
|
| 114 |
+
help="Number of examples. 0 = all examples.",
|
| 115 |
+
)
|
| 116 |
+
|
| 117 |
+
parser.add_argument(
|
| 118 |
+
"--output",
|
| 119 |
+
default=DEFAULT_OUTPUT_DIR,
|
| 120 |
+
help="Output directory",
|
| 121 |
+
)
|
| 122 |
+
|
| 123 |
+
parser.add_argument(
|
| 124 |
+
"--debug",
|
| 125 |
+
action="store_true",
|
| 126 |
+
help="Print detailed prediction for every example",
|
| 127 |
+
)
|
| 128 |
+
|
| 129 |
+
args = parser.parse_args()
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
# ============================================================
|
| 133 |
+
# HEADER
|
| 134 |
+
# ============================================================
|
| 135 |
+
|
| 136 |
+
print("=" * 80)
|
| 137 |
+
print("TELECOM FAST MODEL COMPARISON")
|
| 138 |
+
print("=" * 80)
|
| 139 |
+
|
| 140 |
+
print()
|
| 141 |
+
print("Base model:")
|
| 142 |
+
print(MODEL_NAME)
|
| 143 |
+
|
| 144 |
+
print()
|
| 145 |
+
print("Adapter:")
|
| 146 |
+
print(args.adapter)
|
| 147 |
+
|
| 148 |
+
print()
|
| 149 |
+
print("Test file:")
|
| 150 |
+
print(args.test)
|
| 151 |
+
|
| 152 |
+
|
| 153 |
+
# ============================================================
|
| 154 |
+
# GPU CHECK
|
| 155 |
+
# ============================================================
|
| 156 |
+
|
| 157 |
+
print()
|
| 158 |
+
print("=" * 80)
|
| 159 |
+
print("GPU")
|
| 160 |
+
print("=" * 80)
|
| 161 |
+
|
| 162 |
+
print()
|
| 163 |
+
|
| 164 |
+
if not torch.cuda.is_available():
|
| 165 |
+
|
| 166 |
+
raise RuntimeError(
|
| 167 |
+
"CUDA GPU is required for this evaluation."
|
| 168 |
+
)
|
| 169 |
+
|
| 170 |
+
print(
|
| 171 |
+
"CUDA available:",
|
| 172 |
+
torch.cuda.is_available(),
|
| 173 |
+
)
|
| 174 |
+
|
| 175 |
+
print(
|
| 176 |
+
"GPU:",
|
| 177 |
+
torch.cuda.get_device_name(0),
|
| 178 |
+
)
|
| 179 |
+
|
| 180 |
+
gpu_memory = (
|
| 181 |
+
torch.cuda.get_device_properties(0)
|
| 182 |
+
.total_memory
|
| 183 |
+
/ (1024 ** 3)
|
| 184 |
+
)
|
| 185 |
+
|
| 186 |
+
print(
|
| 187 |
+
"VRAM:",
|
| 188 |
+
round(gpu_memory, 2),
|
| 189 |
+
"GB",
|
| 190 |
+
)
|
| 191 |
+
|
| 192 |
+
|
| 193 |
+
# ============================================================
|
| 194 |
+
# DIRECTORY / FILE CHECK
|
| 195 |
+
# ============================================================
|
| 196 |
+
|
| 197 |
+
if not os.path.exists(args.test):
|
| 198 |
+
|
| 199 |
+
raise FileNotFoundError(
|
| 200 |
+
"\nTest file not found:\n"
|
| 201 |
+
+ os.path.abspath(args.test)
|
| 202 |
+
)
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
if not os.path.exists(args.adapter):
|
| 206 |
+
|
| 207 |
+
raise FileNotFoundError(
|
| 208 |
+
"\nAdapter not found:\n"
|
| 209 |
+
+ os.path.abspath(args.adapter)
|
| 210 |
+
)
|
| 211 |
+
|
| 212 |
+
|
| 213 |
+
os.makedirs(
|
| 214 |
+
args.output,
|
| 215 |
+
exist_ok=True,
|
| 216 |
+
)
|
| 217 |
+
|
| 218 |
+
|
| 219 |
+
# ============================================================
|
| 220 |
+
# LOAD DATASET
|
| 221 |
+
# ============================================================
|
| 222 |
+
|
| 223 |
+
print()
|
| 224 |
+
print("=" * 80)
|
| 225 |
+
print("LOADING TEST DATA")
|
| 226 |
+
print("=" * 80)
|
| 227 |
+
|
| 228 |
+
dataset = load_dataset(
|
| 229 |
+
"json",
|
| 230 |
+
data_files=args.test,
|
| 231 |
+
split="train",
|
| 232 |
+
cache_dir=CACHE_DIR,
|
| 233 |
+
)
|
| 234 |
+
|
| 235 |
+
print(
|
| 236 |
+
"Total examples:",
|
| 237 |
+
len(dataset),
|
| 238 |
+
)
|
| 239 |
+
|
| 240 |
+
if args.samples > 0:
|
| 241 |
+
|
| 242 |
+
number_to_test = min(
|
| 243 |
+
args.samples,
|
| 244 |
+
len(dataset),
|
| 245 |
+
)
|
| 246 |
+
|
| 247 |
+
dataset = dataset.select(
|
| 248 |
+
range(number_to_test)
|
| 249 |
+
)
|
| 250 |
+
|
| 251 |
+
print(
|
| 252 |
+
"Testing examples:",
|
| 253 |
+
len(dataset),
|
| 254 |
+
)
|
| 255 |
+
|
| 256 |
+
|
| 257 |
+
# ============================================================
|
| 258 |
+
# DATA VALIDATION
|
| 259 |
+
# ============================================================
|
| 260 |
+
|
| 261 |
+
print()
|
| 262 |
+
print("=" * 80)
|
| 263 |
+
print("VALIDATING TEST DATA")
|
| 264 |
+
print("=" * 80)
|
| 265 |
+
|
| 266 |
+
for i, example in enumerate(dataset):
|
| 267 |
+
|
| 268 |
+
if "messages" not in example:
|
| 269 |
+
|
| 270 |
+
raise ValueError(
|
| 271 |
+
f"Example {i} does not contain 'messages'."
|
| 272 |
+
)
|
| 273 |
+
|
| 274 |
+
if not isinstance(
|
| 275 |
+
example["messages"],
|
| 276 |
+
list,
|
| 277 |
+
):
|
| 278 |
+
|
| 279 |
+
raise ValueError(
|
| 280 |
+
f"Example {i}: messages is not a list."
|
| 281 |
+
)
|
| 282 |
+
|
| 283 |
+
roles = [
|
| 284 |
+
message.get("role")
|
| 285 |
+
for message in example["messages"]
|
| 286 |
+
]
|
| 287 |
+
|
| 288 |
+
if "user" not in roles:
|
| 289 |
+
|
| 290 |
+
raise ValueError(
|
| 291 |
+
f"Example {i} does not contain a user message."
|
| 292 |
+
)
|
| 293 |
+
|
| 294 |
+
if "assistant" not in roles:
|
| 295 |
+
|
| 296 |
+
raise ValueError(
|
| 297 |
+
f"Example {i} does not contain an assistant reference."
|
| 298 |
+
)
|
| 299 |
+
|
| 300 |
+
print(
|
| 301 |
+
"Test data validation completed."
|
| 302 |
+
)
|
| 303 |
+
|
| 304 |
+
|
| 305 |
+
# ============================================================
|
| 306 |
+
# TOKENIZER
|
| 307 |
+
# ============================================================
|
| 308 |
+
|
| 309 |
+
print()
|
| 310 |
+
print("=" * 80)
|
| 311 |
+
print("LOADING TOKENIZER")
|
| 312 |
+
print("=" * 80)
|
| 313 |
+
|
| 314 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 315 |
+
MODEL_NAME,
|
| 316 |
+
trust_remote_code=True,
|
| 317 |
+
cache_dir=CACHE_DIR,
|
| 318 |
+
)
|
| 319 |
+
|
| 320 |
+
if tokenizer.pad_token is None:
|
| 321 |
+
|
| 322 |
+
tokenizer.pad_token = tokenizer.eos_token
|
| 323 |
+
|
| 324 |
+
tokenizer.padding_side = "left"
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
# ============================================================
|
| 328 |
+
# 4-BIT QUANTIZATION
|
| 329 |
+
# ============================================================
|
| 330 |
+
|
| 331 |
+
bnb_config = BitsAndBytesConfig(
|
| 332 |
+
|
| 333 |
+
load_in_4bit=True,
|
| 334 |
+
|
| 335 |
+
bnb_4bit_quant_type="nf4",
|
| 336 |
+
|
| 337 |
+
bnb_4bit_compute_dtype=torch.float16,
|
| 338 |
+
|
| 339 |
+
bnb_4bit_use_double_quant=True,
|
| 340 |
+
)
|
| 341 |
+
|
| 342 |
+
|
| 343 |
+
# ============================================================
|
| 344 |
+
# LOAD ORIGINAL MODEL
|
| 345 |
+
# ============================================================
|
| 346 |
+
|
| 347 |
+
print()
|
| 348 |
+
print("=" * 80)
|
| 349 |
+
print("LOADING ORIGINAL MODEL")
|
| 350 |
+
print("=" * 80)
|
| 351 |
+
|
| 352 |
+
base_model = AutoModelForCausalLM.from_pretrained(
|
| 353 |
+
|
| 354 |
+
MODEL_NAME,
|
| 355 |
+
|
| 356 |
+
quantization_config=bnb_config,
|
| 357 |
+
|
| 358 |
+
device_map="auto",
|
| 359 |
+
|
| 360 |
+
dtype=torch.float16,
|
| 361 |
+
|
| 362 |
+
trust_remote_code=True,
|
| 363 |
+
|
| 364 |
+
cache_dir=CACHE_DIR,
|
| 365 |
+
)
|
| 366 |
+
|
| 367 |
+
base_model.eval()
|
| 368 |
+
|
| 369 |
+
base_model.config.use_cache = True
|
| 370 |
+
|
| 371 |
+
print(
|
| 372 |
+
"Original model loaded."
|
| 373 |
+
)
|
| 374 |
+
|
| 375 |
+
|
| 376 |
+
# ============================================================
|
| 377 |
+
# LOAD FINE-TUNED MODEL
|
| 378 |
+
# ============================================================
|
| 379 |
+
|
| 380 |
+
print()
|
| 381 |
+
print("=" * 80)
|
| 382 |
+
print("LOADING FINE-TUNED MODEL")
|
| 383 |
+
print("=" * 80)
|
| 384 |
+
|
| 385 |
+
fine_tuned_model = PeftModel.from_pretrained(
|
| 386 |
+
|
| 387 |
+
base_model,
|
| 388 |
+
|
| 389 |
+
args.adapter,
|
| 390 |
+
)
|
| 391 |
+
|
| 392 |
+
fine_tuned_model.eval()
|
| 393 |
+
|
| 394 |
+
print(
|
| 395 |
+
"Fine-tuned adapter loaded."
|
| 396 |
+
)
|
| 397 |
+
|
| 398 |
+
|
| 399 |
+
# ============================================================
|
| 400 |
+
# PROMPT CREATION
|
| 401 |
+
# ============================================================
|
| 402 |
+
|
| 403 |
+
def get_prompt(example):
|
| 404 |
+
|
| 405 |
+
messages = []
|
| 406 |
+
|
| 407 |
+
for message in example["messages"]:
|
| 408 |
+
|
| 409 |
+
if message["role"] != "assistant":
|
| 410 |
+
|
| 411 |
+
messages.append(message)
|
| 412 |
+
|
| 413 |
+
return tokenizer.apply_chat_template(
|
| 414 |
+
|
| 415 |
+
messages,
|
| 416 |
+
|
| 417 |
+
tokenize=False,
|
| 418 |
+
|
| 419 |
+
add_generation_prompt=True,
|
| 420 |
+
)
|
| 421 |
+
|
| 422 |
+
|
| 423 |
+
# ============================================================
|
| 424 |
+
# REFERENCE RESPONSE
|
| 425 |
+
# ============================================================
|
| 426 |
+
|
| 427 |
+
def get_reference(example):
|
| 428 |
+
|
| 429 |
+
for message in example["messages"]:
|
| 430 |
+
|
| 431 |
+
if message["role"] == "assistant":
|
| 432 |
+
|
| 433 |
+
content = message.get(
|
| 434 |
+
"content",
|
| 435 |
+
"",
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
return str(content)
|
| 439 |
+
|
| 440 |
+
return ""
|
| 441 |
+
|
| 442 |
+
|
| 443 |
+
# ============================================================
|
| 444 |
+
# SAFE SECTION EXTRACTION
|
| 445 |
+
# ============================================================
|
| 446 |
+
|
| 447 |
+
def extract_section(
|
| 448 |
+
text,
|
| 449 |
+
section_name,
|
| 450 |
+
next_sections,
|
| 451 |
+
):
|
| 452 |
+
"""
|
| 453 |
+
Safely extracts text between section headings.
|
| 454 |
+
|
| 455 |
+
Example:
|
| 456 |
+
|
| 457 |
+
Probable Root Cause:
|
| 458 |
+
Something happened.
|
| 459 |
+
|
| 460 |
+
Explanation:
|
| 461 |
+
Explanation text.
|
| 462 |
+
|
| 463 |
+
Recommendation:
|
| 464 |
+
Restart equipment.
|
| 465 |
+
|
| 466 |
+
Fault Severity:
|
| 467 |
+
1
|
| 468 |
+
|
| 469 |
+
This implementation deliberately avoids complicated
|
| 470 |
+
dynamically-generated lookahead regexes.
|
| 471 |
+
"""
|
| 472 |
+
|
| 473 |
+
if text is None:
|
| 474 |
+
|
| 475 |
+
return ""
|
| 476 |
+
|
| 477 |
+
text = str(text).strip()
|
| 478 |
+
|
| 479 |
+
if not text:
|
| 480 |
+
|
| 481 |
+
return ""
|
| 482 |
+
|
| 483 |
+
# --------------------------------------------------------
|
| 484 |
+
# Find requested heading
|
| 485 |
+
# --------------------------------------------------------
|
| 486 |
+
|
| 487 |
+
start_pattern = (
|
| 488 |
+
r"(?im)^\s*"
|
| 489 |
+
+ re.escape(section_name)
|
| 490 |
+
+ r"\s*:?\s*"
|
| 491 |
+
)
|
| 492 |
+
|
| 493 |
+
start_match = re.search(
|
| 494 |
+
start_pattern,
|
| 495 |
+
text,
|
| 496 |
+
)
|
| 497 |
+
|
| 498 |
+
if start_match is None:
|
| 499 |
+
|
| 500 |
+
return ""
|
| 501 |
+
|
| 502 |
+
content_start = start_match.end()
|
| 503 |
+
|
| 504 |
+
remaining = text[
|
| 505 |
+
content_start:
|
| 506 |
+
]
|
| 507 |
+
|
| 508 |
+
# --------------------------------------------------------
|
| 509 |
+
# Find all possible following section headings
|
| 510 |
+
# --------------------------------------------------------
|
| 511 |
+
|
| 512 |
+
next_positions = []
|
| 513 |
+
|
| 514 |
+
for section in next_sections:
|
| 515 |
+
|
| 516 |
+
pattern = (
|
| 517 |
+
r"(?im)^\s*"
|
| 518 |
+
+ re.escape(section)
|
| 519 |
+
+ r"\s*:?\s*"
|
| 520 |
+
)
|
| 521 |
+
|
| 522 |
+
match = re.search(
|
| 523 |
+
pattern,
|
| 524 |
+
remaining,
|
| 525 |
+
)
|
| 526 |
+
|
| 527 |
+
if match is not None:
|
| 528 |
+
|
| 529 |
+
next_positions.append(
|
| 530 |
+
match.start()
|
| 531 |
+
)
|
| 532 |
+
|
| 533 |
+
# --------------------------------------------------------
|
| 534 |
+
# Stop at earliest next heading
|
| 535 |
+
# --------------------------------------------------------
|
| 536 |
+
|
| 537 |
+
if next_positions:
|
| 538 |
+
|
| 539 |
+
content_end = min(
|
| 540 |
+
next_positions
|
| 541 |
+
)
|
| 542 |
+
|
| 543 |
+
content = remaining[
|
| 544 |
+
:content_end
|
| 545 |
+
]
|
| 546 |
+
|
| 547 |
+
else:
|
| 548 |
+
|
| 549 |
+
content = remaining
|
| 550 |
+
|
| 551 |
+
return content.strip()
|
| 552 |
+
|
| 553 |
+
|
| 554 |
+
# ============================================================
|
| 555 |
+
# ROOT CAUSE
|
| 556 |
+
# ============================================================
|
| 557 |
+
|
| 558 |
+
def extract_root_cause(text):
|
| 559 |
+
|
| 560 |
+
return extract_section(
|
| 561 |
+
|
| 562 |
+
text,
|
| 563 |
+
|
| 564 |
+
"Probable Root Cause",
|
| 565 |
+
|
| 566 |
+
[
|
| 567 |
+
"Explanation",
|
| 568 |
+
"Recommendation",
|
| 569 |
+
"Fault Severity",
|
| 570 |
+
],
|
| 571 |
+
)
|
| 572 |
+
|
| 573 |
+
|
| 574 |
+
# ============================================================
|
| 575 |
+
# EXPLANATION
|
| 576 |
+
# ============================================================
|
| 577 |
+
|
| 578 |
+
def extract_explanation(text):
|
| 579 |
+
|
| 580 |
+
return extract_section(
|
| 581 |
+
|
| 582 |
+
text,
|
| 583 |
+
|
| 584 |
+
"Explanation",
|
| 585 |
+
|
| 586 |
+
[
|
| 587 |
+
"Recommendation",
|
| 588 |
+
"Fault Severity",
|
| 589 |
+
],
|
| 590 |
+
)
|
| 591 |
+
|
| 592 |
+
|
| 593 |
+
# ============================================================
|
| 594 |
+
# RECOMMENDATION
|
| 595 |
+
# ============================================================
|
| 596 |
+
|
| 597 |
+
def extract_recommendation(text):
|
| 598 |
+
|
| 599 |
+
return extract_section(
|
| 600 |
+
|
| 601 |
+
text,
|
| 602 |
+
|
| 603 |
+
"Recommendation",
|
| 604 |
+
|
| 605 |
+
[
|
| 606 |
+
"Fault Severity",
|
| 607 |
+
],
|
| 608 |
+
)
|
| 609 |
+
|
| 610 |
+
|
| 611 |
+
# ============================================================
|
| 612 |
+
# SEVERITY
|
| 613 |
+
# ============================================================
|
| 614 |
+
|
| 615 |
+
def extract_severity(text):
|
| 616 |
+
|
| 617 |
+
if not text:
|
| 618 |
+
|
| 619 |
+
return None
|
| 620 |
+
|
| 621 |
+
patterns = [
|
| 622 |
+
|
| 623 |
+
r"(?im)^\s*Fault\s+Severity\s*[:\-]?\s*([012])\b",
|
| 624 |
+
|
| 625 |
+
r"(?im)^\s*fault_severity\s*[:=]\s*([012])\b",
|
| 626 |
+
|
| 627 |
+
r"(?im)^\s*Severity\s*[:\-]?\s*([012])\b",
|
| 628 |
+
|
| 629 |
+
]
|
| 630 |
+
|
| 631 |
+
for pattern in patterns:
|
| 632 |
+
|
| 633 |
+
match = re.search(
|
| 634 |
+
pattern,
|
| 635 |
+
str(text),
|
| 636 |
+
)
|
| 637 |
+
|
| 638 |
+
if match:
|
| 639 |
+
|
| 640 |
+
return int(
|
| 641 |
+
match.group(1)
|
| 642 |
+
)
|
| 643 |
+
|
| 644 |
+
return None
|
| 645 |
+
|
| 646 |
+
|
| 647 |
+
# ============================================================
|
| 648 |
+
# FOUR-OUTPUT FORMAT
|
| 649 |
+
# ============================================================
|
| 650 |
+
|
| 651 |
+
def format_compliant(text):
|
| 652 |
+
|
| 653 |
+
if not text:
|
| 654 |
+
|
| 655 |
+
return False
|
| 656 |
+
|
| 657 |
+
required_sections = [
|
| 658 |
+
|
| 659 |
+
"Probable Root Cause",
|
| 660 |
+
|
| 661 |
+
"Explanation",
|
| 662 |
+
|
| 663 |
+
"Recommendation",
|
| 664 |
+
|
| 665 |
+
"Fault Severity",
|
| 666 |
+
|
| 667 |
+
]
|
| 668 |
+
|
| 669 |
+
lower_text = text.lower()
|
| 670 |
+
|
| 671 |
+
for section in required_sections:
|
| 672 |
+
|
| 673 |
+
if section.lower() not in lower_text:
|
| 674 |
+
|
| 675 |
+
return False
|
| 676 |
+
|
| 677 |
+
return True
|
| 678 |
+
|
| 679 |
+
|
| 680 |
+
# ============================================================
|
| 681 |
+
# TOKEN NORMALIZATION
|
| 682 |
+
# ============================================================
|
| 683 |
+
|
| 684 |
+
def normalize_tokens(text):
|
| 685 |
+
|
| 686 |
+
if not text:
|
| 687 |
+
|
| 688 |
+
return []
|
| 689 |
+
|
| 690 |
+
text = str(text).lower()
|
| 691 |
+
|
| 692 |
+
text = re.sub(
|
| 693 |
+
r"[^\w\s]",
|
| 694 |
+
" ",
|
| 695 |
+
text,
|
| 696 |
+
)
|
| 697 |
+
|
| 698 |
+
return text.split()
|
| 699 |
+
|
| 700 |
+
|
| 701 |
+
# ============================================================
|
| 702 |
+
# TOKEN F1
|
| 703 |
+
# ============================================================
|
| 704 |
+
|
| 705 |
+
def token_f1(
|
| 706 |
+
prediction,
|
| 707 |
+
reference,
|
| 708 |
+
):
|
| 709 |
+
|
| 710 |
+
pred_tokens = normalize_tokens(
|
| 711 |
+
prediction
|
| 712 |
+
)
|
| 713 |
+
|
| 714 |
+
ref_tokens = normalize_tokens(
|
| 715 |
+
reference
|
| 716 |
+
)
|
| 717 |
+
|
| 718 |
+
if (
|
| 719 |
+
not pred_tokens
|
| 720 |
+
and
|
| 721 |
+
not ref_tokens
|
| 722 |
+
):
|
| 723 |
+
|
| 724 |
+
return 1.0
|
| 725 |
+
|
| 726 |
+
if (
|
| 727 |
+
not pred_tokens
|
| 728 |
+
or
|
| 729 |
+
not ref_tokens
|
| 730 |
+
):
|
| 731 |
+
|
| 732 |
+
return 0.0
|
| 733 |
+
|
| 734 |
+
pred_counts = Counter(
|
| 735 |
+
pred_tokens
|
| 736 |
+
)
|
| 737 |
+
|
| 738 |
+
ref_counts = Counter(
|
| 739 |
+
ref_tokens
|
| 740 |
+
)
|
| 741 |
+
|
| 742 |
+
common = sum(
|
| 743 |
+
(
|
| 744 |
+
pred_counts
|
| 745 |
+
&
|
| 746 |
+
ref_counts
|
| 747 |
+
).values()
|
| 748 |
+
)
|
| 749 |
+
|
| 750 |
+
if common == 0:
|
| 751 |
+
|
| 752 |
+
return 0.0
|
| 753 |
+
|
| 754 |
+
precision = (
|
| 755 |
+
common
|
| 756 |
+
/
|
| 757 |
+
len(pred_tokens)
|
| 758 |
+
)
|
| 759 |
+
|
| 760 |
+
recall = (
|
| 761 |
+
common
|
| 762 |
+
/
|
| 763 |
+
len(ref_tokens)
|
| 764 |
+
)
|
| 765 |
+
|
| 766 |
+
if precision + recall == 0:
|
| 767 |
+
|
| 768 |
+
return 0.0
|
| 769 |
+
|
| 770 |
+
return (
|
| 771 |
+
|
| 772 |
+
2
|
| 773 |
+
*
|
| 774 |
+
precision
|
| 775 |
+
*
|
| 776 |
+
recall
|
| 777 |
+
/
|
| 778 |
+
(
|
| 779 |
+
precision
|
| 780 |
+
+
|
| 781 |
+
recall
|
| 782 |
+
)
|
| 783 |
+
|
| 784 |
+
)
|
| 785 |
+
|
| 786 |
+
|
| 787 |
+
# ============================================================
|
| 788 |
+
# GENERATION
|
| 789 |
+
# ============================================================
|
| 790 |
+
|
| 791 |
+
def generate_response(
|
| 792 |
+
model,
|
| 793 |
+
prompt,
|
| 794 |
+
):
|
| 795 |
+
|
| 796 |
+
encoded = tokenizer(
|
| 797 |
+
|
| 798 |
+
prompt,
|
| 799 |
+
|
| 800 |
+
return_tensors="pt",
|
| 801 |
+
|
| 802 |
+
truncation=True,
|
| 803 |
+
|
| 804 |
+
max_length=MAX_INPUT_LENGTH,
|
| 805 |
+
)
|
| 806 |
+
|
| 807 |
+
input_tokens = int(
|
| 808 |
+
encoded["input_ids"].shape[1]
|
| 809 |
+
)
|
| 810 |
+
|
| 811 |
+
# --------------------------------------------------------
|
| 812 |
+
# Move tensors to model device
|
| 813 |
+
# --------------------------------------------------------
|
| 814 |
+
|
| 815 |
+
encoded = {
|
| 816 |
+
key: value.to(model.device)
|
| 817 |
+
for key, value in encoded.items()
|
| 818 |
+
}
|
| 819 |
+
|
| 820 |
+
if torch.cuda.is_available():
|
| 821 |
+
|
| 822 |
+
torch.cuda.synchronize()
|
| 823 |
+
|
| 824 |
+
start_time = time.perf_counter()
|
| 825 |
+
|
| 826 |
+
with torch.inference_mode():
|
| 827 |
+
|
| 828 |
+
output = model.generate(
|
| 829 |
+
|
| 830 |
+
**encoded,
|
| 831 |
+
|
| 832 |
+
max_new_tokens=MAX_NEW_TOKENS,
|
| 833 |
+
|
| 834 |
+
do_sample=False,
|
| 835 |
+
|
| 836 |
+
num_beams=1,
|
| 837 |
+
|
| 838 |
+
use_cache=True,
|
| 839 |
+
|
| 840 |
+
pad_token_id=(
|
| 841 |
+
tokenizer.pad_token_id
|
| 842 |
+
),
|
| 843 |
+
|
| 844 |
+
eos_token_id=(
|
| 845 |
+
tokenizer.eos_token_id
|
| 846 |
+
),
|
| 847 |
+
)
|
| 848 |
+
|
| 849 |
+
if torch.cuda.is_available():
|
| 850 |
+
|
| 851 |
+
torch.cuda.synchronize()
|
| 852 |
+
|
| 853 |
+
elapsed = (
|
| 854 |
+
time.perf_counter()
|
| 855 |
+
-
|
| 856 |
+
start_time
|
| 857 |
+
)
|
| 858 |
+
|
| 859 |
+
generated_tokens = output[
|
| 860 |
+
0
|
| 861 |
+
][
|
| 862 |
+
input_tokens:
|
| 863 |
+
]
|
| 864 |
+
|
| 865 |
+
output_token_count = int(
|
| 866 |
+
len(generated_tokens)
|
| 867 |
+
)
|
| 868 |
+
|
| 869 |
+
total_tokens = (
|
| 870 |
+
input_tokens
|
| 871 |
+
+
|
| 872 |
+
output_token_count
|
| 873 |
+
)
|
| 874 |
+
|
| 875 |
+
response = tokenizer.decode(
|
| 876 |
+
|
| 877 |
+
generated_tokens,
|
| 878 |
+
|
| 879 |
+
skip_special_tokens=True,
|
| 880 |
+
).strip()
|
| 881 |
+
|
| 882 |
+
tokens_per_second = (
|
| 883 |
+
|
| 884 |
+
output_token_count
|
| 885 |
+
/
|
| 886 |
+
elapsed
|
| 887 |
+
|
| 888 |
+
if elapsed > 0
|
| 889 |
+
|
| 890 |
+
else 0.0
|
| 891 |
+
)
|
| 892 |
+
|
| 893 |
+
return {
|
| 894 |
+
|
| 895 |
+
"response": response,
|
| 896 |
+
|
| 897 |
+
"input_tokens": input_tokens,
|
| 898 |
+
|
| 899 |
+
"output_tokens": output_token_count,
|
| 900 |
+
|
| 901 |
+
"total_tokens": total_tokens,
|
| 902 |
+
|
| 903 |
+
"generation_time_seconds": elapsed,
|
| 904 |
+
|
| 905 |
+
"tokens_per_second": tokens_per_second,
|
| 906 |
+
}
|
| 907 |
+
|
| 908 |
+
|
| 909 |
+
# ============================================================
|
| 910 |
+
# EVALUATE MODEL
|
| 911 |
+
# ============================================================
|
| 912 |
+
|
| 913 |
+
def evaluate_model(
|
| 914 |
+
model,
|
| 915 |
+
model_name,
|
| 916 |
+
):
|
| 917 |
+
|
| 918 |
+
print()
|
| 919 |
+
print("=" * 80)
|
| 920 |
+
print(
|
| 921 |
+
"TESTING:",
|
| 922 |
+
model_name,
|
| 923 |
+
)
|
| 924 |
+
print("=" * 80)
|
| 925 |
+
|
| 926 |
+
results = []
|
| 927 |
+
|
| 928 |
+
total_examples = len(
|
| 929 |
+
dataset
|
| 930 |
+
)
|
| 931 |
+
|
| 932 |
+
for index, example in enumerate(
|
| 933 |
+
dataset
|
| 934 |
+
):
|
| 935 |
+
|
| 936 |
+
prompt = get_prompt(
|
| 937 |
+
example
|
| 938 |
+
)
|
| 939 |
+
|
| 940 |
+
reference = get_reference(
|
| 941 |
+
example
|
| 942 |
+
)
|
| 943 |
+
|
| 944 |
+
generated = generate_response(
|
| 945 |
+
|
| 946 |
+
model,
|
| 947 |
+
|
| 948 |
+
prompt,
|
| 949 |
+
)
|
| 950 |
+
|
| 951 |
+
prediction = generated[
|
| 952 |
+
"response"
|
| 953 |
+
]
|
| 954 |
+
|
| 955 |
+
# ----------------------------------------------------
|
| 956 |
+
# Reference sections
|
| 957 |
+
# ----------------------------------------------------
|
| 958 |
+
|
| 959 |
+
reference_root = (
|
| 960 |
+
extract_root_cause(
|
| 961 |
+
reference
|
| 962 |
+
)
|
| 963 |
+
)
|
| 964 |
+
|
| 965 |
+
reference_explanation = (
|
| 966 |
+
extract_explanation(
|
| 967 |
+
reference
|
| 968 |
+
)
|
| 969 |
+
)
|
| 970 |
+
|
| 971 |
+
reference_recommendation = (
|
| 972 |
+
extract_recommendation(
|
| 973 |
+
reference
|
| 974 |
+
)
|
| 975 |
+
)
|
| 976 |
+
|
| 977 |
+
reference_severity = (
|
| 978 |
+
extract_severity(
|
| 979 |
+
reference
|
| 980 |
+
)
|
| 981 |
+
)
|
| 982 |
+
|
| 983 |
+
# ----------------------------------------------------
|
| 984 |
+
# Prediction sections
|
| 985 |
+
# ----------------------------------------------------
|
| 986 |
+
|
| 987 |
+
predicted_root = (
|
| 988 |
+
extract_root_cause(
|
| 989 |
+
prediction
|
| 990 |
+
)
|
| 991 |
+
)
|
| 992 |
+
|
| 993 |
+
predicted_explanation = (
|
| 994 |
+
extract_explanation(
|
| 995 |
+
prediction
|
| 996 |
+
)
|
| 997 |
+
)
|
| 998 |
+
|
| 999 |
+
predicted_recommendation = (
|
| 1000 |
+
extract_recommendation(
|
| 1001 |
+
prediction
|
| 1002 |
+
)
|
| 1003 |
+
)
|
| 1004 |
+
|
| 1005 |
+
predicted_severity = (
|
| 1006 |
+
extract_severity(
|
| 1007 |
+
prediction
|
| 1008 |
+
)
|
| 1009 |
+
)
|
| 1010 |
+
|
| 1011 |
+
# ----------------------------------------------------
|
| 1012 |
+
# Similarity
|
| 1013 |
+
# ----------------------------------------------------
|
| 1014 |
+
|
| 1015 |
+
root_score = token_f1(
|
| 1016 |
+
|
| 1017 |
+
predicted_root,
|
| 1018 |
+
|
| 1019 |
+
reference_root,
|
| 1020 |
+
)
|
| 1021 |
+
|
| 1022 |
+
explanation_score = token_f1(
|
| 1023 |
+
|
| 1024 |
+
predicted_explanation,
|
| 1025 |
+
|
| 1026 |
+
reference_explanation,
|
| 1027 |
+
)
|
| 1028 |
+
|
| 1029 |
+
recommendation_score = token_f1(
|
| 1030 |
+
|
| 1031 |
+
predicted_recommendation,
|
| 1032 |
+
|
| 1033 |
+
reference_recommendation,
|
| 1034 |
+
)
|
| 1035 |
+
|
| 1036 |
+
# ----------------------------------------------------
|
| 1037 |
+
# Severity
|
| 1038 |
+
# ----------------------------------------------------
|
| 1039 |
+
|
| 1040 |
+
severity_correct = (
|
| 1041 |
+
|
| 1042 |
+
predicted_severity is not None
|
| 1043 |
+
|
| 1044 |
+
and
|
| 1045 |
+
|
| 1046 |
+
reference_severity is not None
|
| 1047 |
+
|
| 1048 |
+
and
|
| 1049 |
+
|
| 1050 |
+
predicted_severity
|
| 1051 |
+
==
|
| 1052 |
+
reference_severity
|
| 1053 |
+
)
|
| 1054 |
+
|
| 1055 |
+
# ----------------------------------------------------
|
| 1056 |
+
# Format
|
| 1057 |
+
# ----------------------------------------------------
|
| 1058 |
+
|
| 1059 |
+
format_ok = format_compliant(
|
| 1060 |
+
prediction
|
| 1061 |
+
)
|
| 1062 |
+
|
| 1063 |
+
# ----------------------------------------------------
|
| 1064 |
+
# Result
|
| 1065 |
+
# ----------------------------------------------------
|
| 1066 |
+
|
| 1067 |
+
row = {
|
| 1068 |
+
|
| 1069 |
+
"index": index + 1,
|
| 1070 |
+
|
| 1071 |
+
"model": model_name,
|
| 1072 |
+
|
| 1073 |
+
"reference_severity": (
|
| 1074 |
+
reference_severity
|
| 1075 |
+
),
|
| 1076 |
+
|
| 1077 |
+
"predicted_severity": (
|
| 1078 |
+
predicted_severity
|
| 1079 |
+
),
|
| 1080 |
+
|
| 1081 |
+
"severity_correct": (
|
| 1082 |
+
severity_correct
|
| 1083 |
+
),
|
| 1084 |
+
|
| 1085 |
+
"format_compliant": (
|
| 1086 |
+
format_ok
|
| 1087 |
+
),
|
| 1088 |
+
|
| 1089 |
+
"root_cause_f1": (
|
| 1090 |
+
root_score
|
| 1091 |
+
),
|
| 1092 |
+
|
| 1093 |
+
"explanation_f1": (
|
| 1094 |
+
explanation_score
|
| 1095 |
+
),
|
| 1096 |
+
|
| 1097 |
+
"recommendation_f1": (
|
| 1098 |
+
recommendation_score
|
| 1099 |
+
),
|
| 1100 |
+
|
| 1101 |
+
"input_tokens": (
|
| 1102 |
+
generated[
|
| 1103 |
+
"input_tokens"
|
| 1104 |
+
]
|
| 1105 |
+
),
|
| 1106 |
+
|
| 1107 |
+
"output_tokens": (
|
| 1108 |
+
generated[
|
| 1109 |
+
"output_tokens"
|
| 1110 |
+
]
|
| 1111 |
+
),
|
| 1112 |
+
|
| 1113 |
+
"total_tokens": (
|
| 1114 |
+
generated[
|
| 1115 |
+
"total_tokens"
|
| 1116 |
+
]
|
| 1117 |
+
),
|
| 1118 |
+
|
| 1119 |
+
"generation_time_seconds": (
|
| 1120 |
+
generated[
|
| 1121 |
+
"generation_time_seconds"
|
| 1122 |
+
]
|
| 1123 |
+
),
|
| 1124 |
+
|
| 1125 |
+
"tokens_per_second": (
|
| 1126 |
+
generated[
|
| 1127 |
+
"tokens_per_second"
|
| 1128 |
+
]
|
| 1129 |
+
),
|
| 1130 |
+
|
| 1131 |
+
"reference": reference,
|
| 1132 |
+
|
| 1133 |
+
"prediction": prediction,
|
| 1134 |
+
|
| 1135 |
+
"reference_root_cause": (
|
| 1136 |
+
reference_root
|
| 1137 |
+
),
|
| 1138 |
+
|
| 1139 |
+
"predicted_root_cause": (
|
| 1140 |
+
predicted_root
|
| 1141 |
+
),
|
| 1142 |
+
|
| 1143 |
+
"reference_explanation": (
|
| 1144 |
+
reference_explanation
|
| 1145 |
+
),
|
| 1146 |
+
|
| 1147 |
+
"predicted_explanation": (
|
| 1148 |
+
predicted_explanation
|
| 1149 |
+
),
|
| 1150 |
+
|
| 1151 |
+
"reference_recommendation": (
|
| 1152 |
+
reference_recommendation
|
| 1153 |
+
),
|
| 1154 |
+
|
| 1155 |
+
"predicted_recommendation": (
|
| 1156 |
+
predicted_recommendation
|
| 1157 |
+
),
|
| 1158 |
+
}
|
| 1159 |
+
|
| 1160 |
+
results.append(row)
|
| 1161 |
+
|
| 1162 |
+
# ----------------------------------------------------
|
| 1163 |
+
# Debug
|
| 1164 |
+
# ----------------------------------------------------
|
| 1165 |
+
|
| 1166 |
+
if args.debug:
|
| 1167 |
+
|
| 1168 |
+
print()
|
| 1169 |
+
print("-" * 80)
|
| 1170 |
+
|
| 1171 |
+
print(
|
| 1172 |
+
"Example:",
|
| 1173 |
+
index + 1,
|
| 1174 |
+
)
|
| 1175 |
+
|
| 1176 |
+
print()
|
| 1177 |
+
print(
|
| 1178 |
+
"REFERENCE:"
|
| 1179 |
+
)
|
| 1180 |
+
|
| 1181 |
+
print(reference)
|
| 1182 |
+
|
| 1183 |
+
print()
|
| 1184 |
+
print(
|
| 1185 |
+
"PREDICTION:"
|
| 1186 |
+
)
|
| 1187 |
+
|
| 1188 |
+
print(prediction)
|
| 1189 |
+
|
| 1190 |
+
print()
|
| 1191 |
+
print(
|
| 1192 |
+
"Severity:",
|
| 1193 |
+
reference_severity,
|
| 1194 |
+
"->",
|
| 1195 |
+
predicted_severity,
|
| 1196 |
+
)
|
| 1197 |
+
|
| 1198 |
+
print(
|
| 1199 |
+
"Root Cause F1:",
|
| 1200 |
+
f"{root_score:.4f}",
|
| 1201 |
+
)
|
| 1202 |
+
|
| 1203 |
+
print(
|
| 1204 |
+
"Explanation F1:",
|
| 1205 |
+
f"{explanation_score:.4f}",
|
| 1206 |
+
)
|
| 1207 |
+
|
| 1208 |
+
print(
|
| 1209 |
+
"Recommendation F1:",
|
| 1210 |
+
f"{recommendation_score:.4f}",
|
| 1211 |
+
)
|
| 1212 |
+
|
| 1213 |
+
print(
|
| 1214 |
+
"Format:",
|
| 1215 |
+
format_ok,
|
| 1216 |
+
)
|
| 1217 |
+
|
| 1218 |
+
print(
|
| 1219 |
+
"Tokens:",
|
| 1220 |
+
generated[
|
| 1221 |
+
"input_tokens"
|
| 1222 |
+
],
|
| 1223 |
+
"/",
|
| 1224 |
+
generated[
|
| 1225 |
+
"output_tokens"
|
| 1226 |
+
],
|
| 1227 |
+
"/",
|
| 1228 |
+
generated[
|
| 1229 |
+
"total_tokens"
|
| 1230 |
+
],
|
| 1231 |
+
)
|
| 1232 |
+
|
| 1233 |
+
print(
|
| 1234 |
+
"Time:",
|
| 1235 |
+
f"{generated['generation_time_seconds']:.3f}s",
|
| 1236 |
+
)
|
| 1237 |
+
|
| 1238 |
+
else:
|
| 1239 |
+
|
| 1240 |
+
if (
|
| 1241 |
+
|
| 1242 |
+
(index + 1) % 10 == 0
|
| 1243 |
+
|
| 1244 |
+
or
|
| 1245 |
+
|
| 1246 |
+
(index + 1)
|
| 1247 |
+
==
|
| 1248 |
+
total_examples
|
| 1249 |
+
|
| 1250 |
+
):
|
| 1251 |
+
|
| 1252 |
+
print(
|
| 1253 |
+
|
| 1254 |
+
f"{model_name}: "
|
| 1255 |
+
f"{index + 1}/"
|
| 1256 |
+
f"{total_examples}"
|
| 1257 |
+
|
| 1258 |
+
)
|
| 1259 |
+
|
| 1260 |
+
return results
|
| 1261 |
+
|
| 1262 |
+
|
| 1263 |
+
# ============================================================
|
| 1264 |
+
# RUN ORIGINAL
|
| 1265 |
+
# ============================================================
|
| 1266 |
+
|
| 1267 |
+
original_results = evaluate_model(
|
| 1268 |
+
|
| 1269 |
+
base_model,
|
| 1270 |
+
|
| 1271 |
+
"Original",
|
| 1272 |
+
)
|
| 1273 |
+
|
| 1274 |
+
|
| 1275 |
+
# ============================================================
|
| 1276 |
+
# RUN FINE-TUNED
|
| 1277 |
+
# ============================================================
|
| 1278 |
+
|
| 1279 |
+
fine_tuned_results = evaluate_model(
|
| 1280 |
+
|
| 1281 |
+
fine_tuned_model,
|
| 1282 |
+
|
| 1283 |
+
"Fine-tuned",
|
| 1284 |
+
)
|
| 1285 |
+
|
| 1286 |
+
|
| 1287 |
+
# ============================================================
|
| 1288 |
+
# AVERAGE
|
| 1289 |
+
# ============================================================
|
| 1290 |
+
|
| 1291 |
+
def average(
|
| 1292 |
+
rows,
|
| 1293 |
+
key,
|
| 1294 |
+
):
|
| 1295 |
+
|
| 1296 |
+
if not rows:
|
| 1297 |
+
|
| 1298 |
+
return 0.0
|
| 1299 |
+
|
| 1300 |
+
values = [
|
| 1301 |
+
|
| 1302 |
+
float(row[key])
|
| 1303 |
+
|
| 1304 |
+
for row in rows
|
| 1305 |
+
|
| 1306 |
+
if isinstance(
|
| 1307 |
+
row[key],
|
| 1308 |
+
(int, float),
|
| 1309 |
+
)
|
| 1310 |
+
|
| 1311 |
+
]
|
| 1312 |
+
|
| 1313 |
+
if not values:
|
| 1314 |
+
|
| 1315 |
+
return 0.0
|
| 1316 |
+
|
| 1317 |
+
return (
|
| 1318 |
+
sum(values)
|
| 1319 |
+
/
|
| 1320 |
+
len(values)
|
| 1321 |
+
)
|
| 1322 |
+
|
| 1323 |
+
|
| 1324 |
+
# ============================================================
|
| 1325 |
+
# ACCURACY
|
| 1326 |
+
# ============================================================
|
| 1327 |
+
|
| 1328 |
+
def severity_accuracy(
|
| 1329 |
+
rows,
|
| 1330 |
+
):
|
| 1331 |
+
|
| 1332 |
+
if not rows:
|
| 1333 |
+
|
| 1334 |
+
return 0.0
|
| 1335 |
+
|
| 1336 |
+
correct = sum(
|
| 1337 |
+
|
| 1338 |
+
1
|
| 1339 |
+
|
| 1340 |
+
for row in rows
|
| 1341 |
+
|
| 1342 |
+
if row[
|
| 1343 |
+
"severity_correct"
|
| 1344 |
+
]
|
| 1345 |
+
|
| 1346 |
+
)
|
| 1347 |
+
|
| 1348 |
+
return (
|
| 1349 |
+
correct
|
| 1350 |
+
/
|
| 1351 |
+
len(rows)
|
| 1352 |
+
)
|
| 1353 |
+
|
| 1354 |
+
|
| 1355 |
+
# ============================================================
|
| 1356 |
+
# FORMAT ACCURACY
|
| 1357 |
+
# ============================================================
|
| 1358 |
+
|
| 1359 |
+
def format_accuracy(
|
| 1360 |
+
rows,
|
| 1361 |
+
):
|
| 1362 |
+
|
| 1363 |
+
if not rows:
|
| 1364 |
+
|
| 1365 |
+
return 0.0
|
| 1366 |
+
|
| 1367 |
+
correct = sum(
|
| 1368 |
+
|
| 1369 |
+
1
|
| 1370 |
+
|
| 1371 |
+
for row in rows
|
| 1372 |
+
|
| 1373 |
+
if row[
|
| 1374 |
+
"format_compliant"
|
| 1375 |
+
]
|
| 1376 |
+
|
| 1377 |
+
)
|
| 1378 |
+
|
| 1379 |
+
return (
|
| 1380 |
+
correct
|
| 1381 |
+
/
|
| 1382 |
+
len(rows)
|
| 1383 |
+
)
|
| 1384 |
+
|
| 1385 |
+
|
| 1386 |
+
# ============================================================
|
| 1387 |
+
# CLASSIFICATION METRICS
|
| 1388 |
+
# ============================================================
|
| 1389 |
+
|
| 1390 |
+
def classification_metrics(
|
| 1391 |
+
rows,
|
| 1392 |
+
):
|
| 1393 |
+
|
| 1394 |
+
labels = [0, 1, 2]
|
| 1395 |
+
|
| 1396 |
+
matrix = {
|
| 1397 |
+
|
| 1398 |
+
actual: {
|
| 1399 |
+
|
| 1400 |
+
predicted: 0
|
| 1401 |
+
|
| 1402 |
+
for predicted in labels
|
| 1403 |
+
|
| 1404 |
+
}
|
| 1405 |
+
|
| 1406 |
+
for actual in labels
|
| 1407 |
+
}
|
| 1408 |
+
|
| 1409 |
+
for row in rows:
|
| 1410 |
+
|
| 1411 |
+
actual = row[
|
| 1412 |
+
"reference_severity"
|
| 1413 |
+
]
|
| 1414 |
+
|
| 1415 |
+
predicted = row[
|
| 1416 |
+
"predicted_severity"
|
| 1417 |
+
]
|
| 1418 |
+
|
| 1419 |
+
if (
|
| 1420 |
+
|
| 1421 |
+
actual in labels
|
| 1422 |
+
|
| 1423 |
+
and
|
| 1424 |
+
|
| 1425 |
+
predicted in labels
|
| 1426 |
+
|
| 1427 |
+
):
|
| 1428 |
+
|
| 1429 |
+
matrix[
|
| 1430 |
+
actual
|
| 1431 |
+
][
|
| 1432 |
+
predicted
|
| 1433 |
+
] += 1
|
| 1434 |
+
|
| 1435 |
+
metrics = {}
|
| 1436 |
+
|
| 1437 |
+
for label in labels:
|
| 1438 |
+
|
| 1439 |
+
true_positive = matrix[
|
| 1440 |
+
label
|
| 1441 |
+
][
|
| 1442 |
+
label
|
| 1443 |
+
]
|
| 1444 |
+
|
| 1445 |
+
false_positive = sum(
|
| 1446 |
+
|
| 1447 |
+
matrix[
|
| 1448 |
+
actual
|
| 1449 |
+
][
|
| 1450 |
+
label
|
| 1451 |
+
]
|
| 1452 |
+
|
| 1453 |
+
for actual in labels
|
| 1454 |
+
|
| 1455 |
+
if actual != label
|
| 1456 |
+
)
|
| 1457 |
+
|
| 1458 |
+
false_negative = sum(
|
| 1459 |
+
|
| 1460 |
+
matrix[
|
| 1461 |
+
label
|
| 1462 |
+
][
|
| 1463 |
+
predicted
|
| 1464 |
+
]
|
| 1465 |
+
|
| 1466 |
+
for predicted in labels
|
| 1467 |
+
|
| 1468 |
+
if predicted != label
|
| 1469 |
+
)
|
| 1470 |
+
|
| 1471 |
+
support = sum(
|
| 1472 |
+
matrix[
|
| 1473 |
+
label
|
| 1474 |
+
].values()
|
| 1475 |
+
)
|
| 1476 |
+
|
| 1477 |
+
precision = (
|
| 1478 |
+
|
| 1479 |
+
true_positive
|
| 1480 |
+
/
|
| 1481 |
+
(
|
| 1482 |
+
true_positive
|
| 1483 |
+
+
|
| 1484 |
+
false_positive
|
| 1485 |
+
)
|
| 1486 |
+
|
| 1487 |
+
if (
|
| 1488 |
+
true_positive
|
| 1489 |
+
+
|
| 1490 |
+
false_positive
|
| 1491 |
+
) > 0
|
| 1492 |
+
|
| 1493 |
+
else 0.0
|
| 1494 |
+
)
|
| 1495 |
+
|
| 1496 |
+
recall = (
|
| 1497 |
+
|
| 1498 |
+
true_positive
|
| 1499 |
+
/
|
| 1500 |
+
(
|
| 1501 |
+
true_positive
|
| 1502 |
+
+
|
| 1503 |
+
false_negative
|
| 1504 |
+
)
|
| 1505 |
+
|
| 1506 |
+
if (
|
| 1507 |
+
true_positive
|
| 1508 |
+
+
|
| 1509 |
+
false_negative
|
| 1510 |
+
) > 0
|
| 1511 |
+
|
| 1512 |
+
else 0.0
|
| 1513 |
+
)
|
| 1514 |
+
|
| 1515 |
+
f1 = (
|
| 1516 |
+
|
| 1517 |
+
2
|
| 1518 |
+
*
|
| 1519 |
+
precision
|
| 1520 |
+
*
|
| 1521 |
+
recall
|
| 1522 |
+
/
|
| 1523 |
+
(
|
| 1524 |
+
precision
|
| 1525 |
+
+
|
| 1526 |
+
recall
|
| 1527 |
+
)
|
| 1528 |
+
|
| 1529 |
+
if (
|
| 1530 |
+
precision
|
| 1531 |
+
+
|
| 1532 |
+
recall
|
| 1533 |
+
) > 0
|
| 1534 |
+
|
| 1535 |
+
else 0.0
|
| 1536 |
+
)
|
| 1537 |
+
|
| 1538 |
+
metrics[label] = {
|
| 1539 |
+
|
| 1540 |
+
"precision": precision,
|
| 1541 |
+
|
| 1542 |
+
"recall": recall,
|
| 1543 |
+
|
| 1544 |
+
"f1": f1,
|
| 1545 |
+
|
| 1546 |
+
"support": support,
|
| 1547 |
+
}
|
| 1548 |
+
|
| 1549 |
+
valid_f1 = [
|
| 1550 |
+
|
| 1551 |
+
metrics[label]["f1"]
|
| 1552 |
+
|
| 1553 |
+
for label in labels
|
| 1554 |
+
|
| 1555 |
+
if metrics[label]["support"] > 0
|
| 1556 |
+
]
|
| 1557 |
+
|
| 1558 |
+
macro_f1 = (
|
| 1559 |
+
|
| 1560 |
+
sum(valid_f1)
|
| 1561 |
+
/
|
| 1562 |
+
len(valid_f1)
|
| 1563 |
+
|
| 1564 |
+
if valid_f1
|
| 1565 |
+
|
| 1566 |
+
else 0.0
|
| 1567 |
+
)
|
| 1568 |
+
|
| 1569 |
+
total_support = sum(
|
| 1570 |
+
|
| 1571 |
+
metrics[label]["support"]
|
| 1572 |
+
|
| 1573 |
+
for label in labels
|
| 1574 |
+
)
|
| 1575 |
+
|
| 1576 |
+
weighted_f1 = (
|
| 1577 |
+
|
| 1578 |
+
sum(
|
| 1579 |
+
|
| 1580 |
+
metrics[label]["f1"]
|
| 1581 |
+
*
|
| 1582 |
+
metrics[label]["support"]
|
| 1583 |
+
|
| 1584 |
+
for label in labels
|
| 1585 |
+
)
|
| 1586 |
+
|
| 1587 |
+
/
|
| 1588 |
+
total_support
|
| 1589 |
+
|
| 1590 |
+
if total_support > 0
|
| 1591 |
+
|
| 1592 |
+
else 0.0
|
| 1593 |
+
)
|
| 1594 |
+
|
| 1595 |
+
return (
|
| 1596 |
+
|
| 1597 |
+
metrics,
|
| 1598 |
+
|
| 1599 |
+
matrix,
|
| 1600 |
+
|
| 1601 |
+
macro_f1,
|
| 1602 |
+
|
| 1603 |
+
weighted_f1,
|
| 1604 |
+
)
|
| 1605 |
+
|
| 1606 |
+
|
| 1607 |
+
# ============================================================
|
| 1608 |
+
# SUMMARY VALUES
|
| 1609 |
+
# ============================================================
|
| 1610 |
+
|
| 1611 |
+
original_accuracy = severity_accuracy(
|
| 1612 |
+
original_results
|
| 1613 |
+
)
|
| 1614 |
+
|
| 1615 |
+
fine_tuned_accuracy = severity_accuracy(
|
| 1616 |
+
fine_tuned_results
|
| 1617 |
+
)
|
| 1618 |
+
|
| 1619 |
+
original_format = format_accuracy(
|
| 1620 |
+
original_results
|
| 1621 |
+
)
|
| 1622 |
+
|
| 1623 |
+
fine_tuned_format = format_accuracy(
|
| 1624 |
+
fine_tuned_results
|
| 1625 |
+
)
|
| 1626 |
+
|
| 1627 |
+
original_root = average(
|
| 1628 |
+
original_results,
|
| 1629 |
+
"root_cause_f1",
|
| 1630 |
+
)
|
| 1631 |
+
|
| 1632 |
+
fine_tuned_root = average(
|
| 1633 |
+
fine_tuned_results,
|
| 1634 |
+
"root_cause_f1",
|
| 1635 |
+
)
|
| 1636 |
+
|
| 1637 |
+
original_explanation = average(
|
| 1638 |
+
original_results,
|
| 1639 |
+
"explanation_f1",
|
| 1640 |
+
)
|
| 1641 |
+
|
| 1642 |
+
fine_tuned_explanation = average(
|
| 1643 |
+
fine_tuned_results,
|
| 1644 |
+
"explanation_f1",
|
| 1645 |
+
)
|
| 1646 |
+
|
| 1647 |
+
original_recommendation = average(
|
| 1648 |
+
original_results,
|
| 1649 |
+
"recommendation_f1",
|
| 1650 |
+
)
|
| 1651 |
+
|
| 1652 |
+
fine_tuned_recommendation = average(
|
| 1653 |
+
fine_tuned_results,
|
| 1654 |
+
"recommendation_f1",
|
| 1655 |
+
)
|
| 1656 |
+
|
| 1657 |
+
original_input = average(
|
| 1658 |
+
original_results,
|
| 1659 |
+
"input_tokens",
|
| 1660 |
+
)
|
| 1661 |
+
|
| 1662 |
+
fine_tuned_input = average(
|
| 1663 |
+
fine_tuned_results,
|
| 1664 |
+
"input_tokens",
|
| 1665 |
+
)
|
| 1666 |
+
|
| 1667 |
+
original_output = average(
|
| 1668 |
+
original_results,
|
| 1669 |
+
"output_tokens",
|
| 1670 |
+
)
|
| 1671 |
+
|
| 1672 |
+
fine_tuned_output = average(
|
| 1673 |
+
fine_tuned_results,
|
| 1674 |
+
"output_tokens",
|
| 1675 |
+
)
|
| 1676 |
+
|
| 1677 |
+
original_total = average(
|
| 1678 |
+
original_results,
|
| 1679 |
+
"total_tokens",
|
| 1680 |
+
)
|
| 1681 |
+
|
| 1682 |
+
fine_tuned_total = average(
|
| 1683 |
+
fine_tuned_results,
|
| 1684 |
+
"total_tokens",
|
| 1685 |
+
)
|
| 1686 |
+
|
| 1687 |
+
original_time = average(
|
| 1688 |
+
original_results,
|
| 1689 |
+
"generation_time_seconds",
|
| 1690 |
+
)
|
| 1691 |
+
|
| 1692 |
+
fine_tuned_time = average(
|
| 1693 |
+
fine_tuned_results,
|
| 1694 |
+
"generation_time_seconds",
|
| 1695 |
+
)
|
| 1696 |
+
|
| 1697 |
+
original_speed = average(
|
| 1698 |
+
original_results,
|
| 1699 |
+
"tokens_per_second",
|
| 1700 |
+
)
|
| 1701 |
+
|
| 1702 |
+
fine_tuned_speed = average(
|
| 1703 |
+
fine_tuned_results,
|
| 1704 |
+
"tokens_per_second",
|
| 1705 |
+
)
|
| 1706 |
+
|
| 1707 |
+
|
| 1708 |
+
(
|
| 1709 |
+
original_classes,
|
| 1710 |
+
original_matrix,
|
| 1711 |
+
original_macro_f1,
|
| 1712 |
+
original_weighted_f1,
|
| 1713 |
+
) = classification_metrics(
|
| 1714 |
+
original_results
|
| 1715 |
+
)
|
| 1716 |
+
|
| 1717 |
+
|
| 1718 |
+
(
|
| 1719 |
+
fine_tuned_classes,
|
| 1720 |
+
fine_tuned_matrix,
|
| 1721 |
+
fine_tuned_macro_f1,
|
| 1722 |
+
fine_tuned_weighted_f1,
|
| 1723 |
+
) = classification_metrics(
|
| 1724 |
+
fine_tuned_results
|
| 1725 |
+
)
|
| 1726 |
+
|
| 1727 |
+
|
| 1728 |
+
# ============================================================
|
| 1729 |
+
# PRINT QUALITY COMPARISON
|
| 1730 |
+
# ============================================================
|
| 1731 |
+
|
| 1732 |
+
print()
|
| 1733 |
+
print("=" * 80)
|
| 1734 |
+
print("FAST QUALITY COMPARISON")
|
| 1735 |
+
print("=" * 80)
|
| 1736 |
+
|
| 1737 |
+
print()
|
| 1738 |
+
|
| 1739 |
+
print(
|
| 1740 |
+
|
| 1741 |
+
f"{'Metric':<32}"
|
| 1742 |
+
f"{'Original':>15}"
|
| 1743 |
+
f"{'Fine-tuned':>15}"
|
| 1744 |
+
f"{'Change':>15}"
|
| 1745 |
+
|
| 1746 |
+
)
|
| 1747 |
+
|
| 1748 |
+
print("-" * 80)
|
| 1749 |
+
|
| 1750 |
+
|
| 1751 |
+
def print_metric(
|
| 1752 |
+
name,
|
| 1753 |
+
original,
|
| 1754 |
+
fine_tuned,
|
| 1755 |
+
percent=False,
|
| 1756 |
+
):
|
| 1757 |
+
|
| 1758 |
+
change = (
|
| 1759 |
+
fine_tuned
|
| 1760 |
+
-
|
| 1761 |
+
original
|
| 1762 |
+
)
|
| 1763 |
+
|
| 1764 |
+
if percent:
|
| 1765 |
+
|
| 1766 |
+
print(
|
| 1767 |
+
|
| 1768 |
+
f"{name:<32}"
|
| 1769 |
+
f"{original * 100:>14.2f}%"
|
| 1770 |
+
f"{fine_tuned * 100:>14.2f}%"
|
| 1771 |
+
f"{change * 100:>+14.2f}%"
|
| 1772 |
+
|
| 1773 |
+
)
|
| 1774 |
+
|
| 1775 |
+
else:
|
| 1776 |
+
|
| 1777 |
+
print(
|
| 1778 |
+
|
| 1779 |
+
f"{name:<32}"
|
| 1780 |
+
f"{original:>15.4f}"
|
| 1781 |
+
f"{fine_tuned:>15.4f}"
|
| 1782 |
+
f"{change:>+15.4f}"
|
| 1783 |
+
|
| 1784 |
+
)
|
| 1785 |
+
|
| 1786 |
+
|
| 1787 |
+
print_metric(
|
| 1788 |
+
|
| 1789 |
+
"Severity Accuracy",
|
| 1790 |
+
|
| 1791 |
+
original_accuracy,
|
| 1792 |
+
|
| 1793 |
+
fine_tuned_accuracy,
|
| 1794 |
+
|
| 1795 |
+
percent=True,
|
| 1796 |
+
)
|
| 1797 |
+
|
| 1798 |
+
print_metric(
|
| 1799 |
+
|
| 1800 |
+
"Severity Macro F1",
|
| 1801 |
+
|
| 1802 |
+
original_macro_f1,
|
| 1803 |
+
|
| 1804 |
+
fine_tuned_macro_f1,
|
| 1805 |
+
)
|
| 1806 |
+
|
| 1807 |
+
print_metric(
|
| 1808 |
+
|
| 1809 |
+
"Severity Weighted F1",
|
| 1810 |
+
|
| 1811 |
+
original_weighted_f1,
|
| 1812 |
+
|
| 1813 |
+
fine_tuned_weighted_f1,
|
| 1814 |
+
)
|
| 1815 |
+
|
| 1816 |
+
print_metric(
|
| 1817 |
+
|
| 1818 |
+
"Root Cause Token-F1",
|
| 1819 |
+
|
| 1820 |
+
original_root,
|
| 1821 |
+
|
| 1822 |
+
fine_tuned_root,
|
| 1823 |
+
)
|
| 1824 |
+
|
| 1825 |
+
print_metric(
|
| 1826 |
+
|
| 1827 |
+
"Explanation Token-F1",
|
| 1828 |
+
|
| 1829 |
+
original_explanation,
|
| 1830 |
+
|
| 1831 |
+
fine_tuned_explanation,
|
| 1832 |
+
)
|
| 1833 |
+
|
| 1834 |
+
print_metric(
|
| 1835 |
+
|
| 1836 |
+
"Recommendation Token-F1",
|
| 1837 |
+
|
| 1838 |
+
original_recommendation,
|
| 1839 |
+
|
| 1840 |
+
fine_tuned_recommendation,
|
| 1841 |
+
)
|
| 1842 |
+
|
| 1843 |
+
print_metric(
|
| 1844 |
+
|
| 1845 |
+
"Four-output Format",
|
| 1846 |
+
|
| 1847 |
+
original_format,
|
| 1848 |
+
|
| 1849 |
+
fine_tuned_format,
|
| 1850 |
+
|
| 1851 |
+
percent=True,
|
| 1852 |
+
)
|
| 1853 |
+
|
| 1854 |
+
|
| 1855 |
+
# ============================================================
|
| 1856 |
+
# TOKEN USAGE
|
| 1857 |
+
# ============================================================
|
| 1858 |
+
|
| 1859 |
+
print()
|
| 1860 |
+
print("=" * 80)
|
| 1861 |
+
print("TOKEN USAGE AND SPEED")
|
| 1862 |
+
print("=" * 80)
|
| 1863 |
+
|
| 1864 |
+
print()
|
| 1865 |
+
|
| 1866 |
+
print_metric(
|
| 1867 |
+
|
| 1868 |
+
"Average Input Tokens",
|
| 1869 |
+
|
| 1870 |
+
original_input,
|
| 1871 |
+
|
| 1872 |
+
fine_tuned_input,
|
| 1873 |
+
)
|
| 1874 |
+
|
| 1875 |
+
print_metric(
|
| 1876 |
+
|
| 1877 |
+
"Average Output Tokens",
|
| 1878 |
+
|
| 1879 |
+
original_output,
|
| 1880 |
+
|
| 1881 |
+
fine_tuned_output,
|
| 1882 |
+
)
|
| 1883 |
+
|
| 1884 |
+
print_metric(
|
| 1885 |
+
|
| 1886 |
+
"Average Total Tokens",
|
| 1887 |
+
|
| 1888 |
+
original_total,
|
| 1889 |
+
|
| 1890 |
+
fine_tuned_total,
|
| 1891 |
+
)
|
| 1892 |
+
|
| 1893 |
+
print_metric(
|
| 1894 |
+
|
| 1895 |
+
"Average Generation Time",
|
| 1896 |
+
|
| 1897 |
+
original_time,
|
| 1898 |
+
|
| 1899 |
+
fine_tuned_time,
|
| 1900 |
+
)
|
| 1901 |
+
|
| 1902 |
+
print_metric(
|
| 1903 |
+
|
| 1904 |
+
"Average Tokens / Second",
|
| 1905 |
+
|
| 1906 |
+
original_speed,
|
| 1907 |
+
|
| 1908 |
+
fine_tuned_speed,
|
| 1909 |
+
)
|
| 1910 |
+
|
| 1911 |
+
|
| 1912 |
+
# ============================================================
|
| 1913 |
+
# CLASS METRICS
|
| 1914 |
+
# ============================================================
|
| 1915 |
+
|
| 1916 |
+
print()
|
| 1917 |
+
print("=" * 80)
|
| 1918 |
+
print("FAULT SEVERITY CLASS METRICS")
|
| 1919 |
+
print("=" * 80)
|
| 1920 |
+
|
| 1921 |
+
for label in [0, 1, 2]:
|
| 1922 |
+
|
| 1923 |
+
print()
|
| 1924 |
+
print(
|
| 1925 |
+
f"CLASS {label}"
|
| 1926 |
+
)
|
| 1927 |
+
|
| 1928 |
+
print()
|
| 1929 |
+
|
| 1930 |
+
print(
|
| 1931 |
+
"Original:"
|
| 1932 |
+
)
|
| 1933 |
+
|
| 1934 |
+
print(
|
| 1935 |
+
|
| 1936 |
+
f" Precision = "
|
| 1937 |
+
f"{original_classes[label]['precision']:.4f}"
|
| 1938 |
+
|
| 1939 |
+
)
|
| 1940 |
+
|
| 1941 |
+
print(
|
| 1942 |
+
|
| 1943 |
+
f" Recall = "
|
| 1944 |
+
f"{original_classes[label]['recall']:.4f}"
|
| 1945 |
+
|
| 1946 |
+
)
|
| 1947 |
+
|
| 1948 |
+
print(
|
| 1949 |
+
|
| 1950 |
+
f" F1 = "
|
| 1951 |
+
f"{original_classes[label]['f1']:.4f}"
|
| 1952 |
+
|
| 1953 |
+
)
|
| 1954 |
+
|
| 1955 |
+
print(
|
| 1956 |
+
|
| 1957 |
+
f" Support = "
|
| 1958 |
+
f"{original_classes[label]['support']}"
|
| 1959 |
+
|
| 1960 |
+
)
|
| 1961 |
+
|
| 1962 |
+
print()
|
| 1963 |
+
|
| 1964 |
+
print(
|
| 1965 |
+
"Fine-tuned:"
|
| 1966 |
+
)
|
| 1967 |
+
|
| 1968 |
+
print(
|
| 1969 |
+
|
| 1970 |
+
f" Precision = "
|
| 1971 |
+
f"{fine_tuned_classes[label]['precision']:.4f}"
|
| 1972 |
+
|
| 1973 |
+
)
|
| 1974 |
+
|
| 1975 |
+
print(
|
| 1976 |
+
|
| 1977 |
+
f" Recall = "
|
| 1978 |
+
f"{fine_tuned_classes[label]['recall']:.4f}"
|
| 1979 |
+
|
| 1980 |
+
)
|
| 1981 |
+
|
| 1982 |
+
print(
|
| 1983 |
+
|
| 1984 |
+
f" F1 = "
|
| 1985 |
+
f"{fine_tuned_classes[label]['f1']:.4f}"
|
| 1986 |
+
|
| 1987 |
+
)
|
| 1988 |
+
|
| 1989 |
+
print(
|
| 1990 |
+
|
| 1991 |
+
f" Support = "
|
| 1992 |
+
f"{fine_tuned_classes[label]['support']}"
|
| 1993 |
+
|
| 1994 |
+
)
|
| 1995 |
+
|
| 1996 |
+
|
| 1997 |
+
# ============================================================
|
| 1998 |
+
# CONFUSION MATRIX
|
| 1999 |
+
# ============================================================
|
| 2000 |
+
|
| 2001 |
+
def print_confusion_matrix(
|
| 2002 |
+
matrix,
|
| 2003 |
+
title,
|
| 2004 |
+
):
|
| 2005 |
+
|
| 2006 |
+
print()
|
| 2007 |
+
print(title)
|
| 2008 |
+
|
| 2009 |
+
print()
|
| 2010 |
+
|
| 2011 |
+
print(
|
| 2012 |
+
" Pred 0 Pred 1 Pred 2"
|
| 2013 |
+
)
|
| 2014 |
+
|
| 2015 |
+
for actual in [0, 1, 2]:
|
| 2016 |
+
|
| 2017 |
+
print(
|
| 2018 |
+
|
| 2019 |
+
f"Actual {actual}"
|
| 2020 |
+
f"{matrix[actual][0]:>12}"
|
| 2021 |
+
f"{matrix[actual][1]:>10}"
|
| 2022 |
+
f"{matrix[actual][2]:>10}"
|
| 2023 |
+
|
| 2024 |
+
)
|
| 2025 |
+
|
| 2026 |
+
|
| 2027 |
+
print_confusion_matrix(
|
| 2028 |
+
|
| 2029 |
+
original_matrix,
|
| 2030 |
+
|
| 2031 |
+
"Original confusion matrix:",
|
| 2032 |
+
)
|
| 2033 |
+
|
| 2034 |
+
print_confusion_matrix(
|
| 2035 |
+
|
| 2036 |
+
fine_tuned_matrix,
|
| 2037 |
+
|
| 2038 |
+
"Fine-tuned confusion matrix:",
|
| 2039 |
+
)
|
| 2040 |
+
|
| 2041 |
+
|
| 2042 |
+
# ============================================================
|
| 2043 |
+
# TOKEN RANGES
|
| 2044 |
+
# ============================================================
|
| 2045 |
+
|
| 2046 |
+
def token_range(
|
| 2047 |
+
rows,
|
| 2048 |
+
key,
|
| 2049 |
+
):
|
| 2050 |
+
|
| 2051 |
+
values = [
|
| 2052 |
+
|
| 2053 |
+
row[key]
|
| 2054 |
+
|
| 2055 |
+
for row in rows
|
| 2056 |
+
|
| 2057 |
+
]
|
| 2058 |
+
|
| 2059 |
+
if not values:
|
| 2060 |
+
|
| 2061 |
+
return 0, 0
|
| 2062 |
+
|
| 2063 |
+
return (
|
| 2064 |
+
min(values),
|
| 2065 |
+
max(values),
|
| 2066 |
+
)
|
| 2067 |
+
|
| 2068 |
+
|
| 2069 |
+
print()
|
| 2070 |
+
print("=" * 80)
|
| 2071 |
+
print("TOKEN RANGE")
|
| 2072 |
+
print("=" * 80)
|
| 2073 |
+
|
| 2074 |
+
for key in [
|
| 2075 |
+
|
| 2076 |
+
"input_tokens",
|
| 2077 |
+
|
| 2078 |
+
"output_tokens",
|
| 2079 |
+
|
| 2080 |
+
"total_tokens",
|
| 2081 |
+
|
| 2082 |
+
]:
|
| 2083 |
+
|
| 2084 |
+
original_min, original_max = (
|
| 2085 |
+
token_range(
|
| 2086 |
+
original_results,
|
| 2087 |
+
key,
|
| 2088 |
+
)
|
| 2089 |
+
)
|
| 2090 |
+
|
| 2091 |
+
fine_tuned_min, fine_tuned_max = (
|
| 2092 |
+
token_range(
|
| 2093 |
+
fine_tuned_results,
|
| 2094 |
+
key,
|
| 2095 |
+
)
|
| 2096 |
+
)
|
| 2097 |
+
|
| 2098 |
+
print()
|
| 2099 |
+
print(key)
|
| 2100 |
+
|
| 2101 |
+
print(
|
| 2102 |
+
|
| 2103 |
+
" Original: "
|
| 2104 |
+
f"{original_min} - "
|
| 2105 |
+
f"{original_max}"
|
| 2106 |
+
|
| 2107 |
+
)
|
| 2108 |
+
|
| 2109 |
+
print(
|
| 2110 |
+
|
| 2111 |
+
" Fine-tuned: "
|
| 2112 |
+
f"{fine_tuned_min} - "
|
| 2113 |
+
f"{fine_tuned_max}"
|
| 2114 |
+
|
| 2115 |
+
)
|
| 2116 |
+
|
| 2117 |
+
|
| 2118 |
+
# ============================================================
|
| 2119 |
+
# SAVE PATHS
|
| 2120 |
+
# ============================================================
|
| 2121 |
+
|
| 2122 |
+
json_path = os.path.join(
|
| 2123 |
+
|
| 2124 |
+
args.output,
|
| 2125 |
+
|
| 2126 |
+
"fast_comparison_results.json",
|
| 2127 |
+
)
|
| 2128 |
+
|
| 2129 |
+
csv_path = os.path.join(
|
| 2130 |
+
|
| 2131 |
+
args.output,
|
| 2132 |
+
|
| 2133 |
+
"fast_comparison_predictions.csv",
|
| 2134 |
+
)
|
| 2135 |
+
|
| 2136 |
+
summary_path = os.path.join(
|
| 2137 |
+
|
| 2138 |
+
args.output,
|
| 2139 |
+
|
| 2140 |
+
"fast_comparison_summary.csv",
|
| 2141 |
+
)
|
| 2142 |
+
|
| 2143 |
+
|
| 2144 |
+
# ============================================================
|
| 2145 |
+
# SAVE JSON
|
| 2146 |
+
# ============================================================
|
| 2147 |
+
|
| 2148 |
+
json_output = {
|
| 2149 |
+
|
| 2150 |
+
"base_model": MODEL_NAME,
|
| 2151 |
+
|
| 2152 |
+
"adapter": os.path.abspath(
|
| 2153 |
+
args.adapter
|
| 2154 |
+
),
|
| 2155 |
+
|
| 2156 |
+
"test_file": os.path.abspath(
|
| 2157 |
+
args.test
|
| 2158 |
+
),
|
| 2159 |
+
|
| 2160 |
+
"number_of_examples": len(
|
| 2161 |
+
dataset
|
| 2162 |
+
),
|
| 2163 |
+
|
| 2164 |
+
"metrics": {
|
| 2165 |
+
|
| 2166 |
+
"severity_accuracy": {
|
| 2167 |
+
|
| 2168 |
+
"original":
|
| 2169 |
+
original_accuracy,
|
| 2170 |
+
|
| 2171 |
+
"fine_tuned":
|
| 2172 |
+
fine_tuned_accuracy,
|
| 2173 |
+
|
| 2174 |
+
"change":
|
| 2175 |
+
fine_tuned_accuracy
|
| 2176 |
+
-
|
| 2177 |
+
original_accuracy,
|
| 2178 |
+
},
|
| 2179 |
+
|
| 2180 |
+
"severity_macro_f1": {
|
| 2181 |
+
|
| 2182 |
+
"original":
|
| 2183 |
+
original_macro_f1,
|
| 2184 |
+
|
| 2185 |
+
"fine_tuned":
|
| 2186 |
+
fine_tuned_macro_f1,
|
| 2187 |
+
|
| 2188 |
+
"change":
|
| 2189 |
+
fine_tuned_macro_f1
|
| 2190 |
+
-
|
| 2191 |
+
original_macro_f1,
|
| 2192 |
+
},
|
| 2193 |
+
|
| 2194 |
+
"severity_weighted_f1": {
|
| 2195 |
+
|
| 2196 |
+
"original":
|
| 2197 |
+
original_weighted_f1,
|
| 2198 |
+
|
| 2199 |
+
"fine_tuned":
|
| 2200 |
+
fine_tuned_weighted_f1,
|
| 2201 |
+
|
| 2202 |
+
"change":
|
| 2203 |
+
fine_tuned_weighted_f1
|
| 2204 |
+
-
|
| 2205 |
+
original_weighted_f1,
|
| 2206 |
+
},
|
| 2207 |
+
|
| 2208 |
+
"root_cause_token_f1": {
|
| 2209 |
+
|
| 2210 |
+
"original":
|
| 2211 |
+
original_root,
|
| 2212 |
+
|
| 2213 |
+
"fine_tuned":
|
| 2214 |
+
fine_tuned_root,
|
| 2215 |
+
|
| 2216 |
+
"change":
|
| 2217 |
+
fine_tuned_root
|
| 2218 |
+
-
|
| 2219 |
+
original_root,
|
| 2220 |
+
},
|
| 2221 |
+
|
| 2222 |
+
"explanation_token_f1": {
|
| 2223 |
+
|
| 2224 |
+
"original":
|
| 2225 |
+
original_explanation,
|
| 2226 |
+
|
| 2227 |
+
"fine_tuned":
|
| 2228 |
+
fine_tuned_explanation,
|
| 2229 |
+
|
| 2230 |
+
"change":
|
| 2231 |
+
fine_tuned_explanation
|
| 2232 |
+
-
|
| 2233 |
+
original_explanation,
|
| 2234 |
+
},
|
| 2235 |
+
|
| 2236 |
+
"recommendation_token_f1": {
|
| 2237 |
+
|
| 2238 |
+
"original":
|
| 2239 |
+
original_recommendation,
|
| 2240 |
+
|
| 2241 |
+
"fine_tuned":
|
| 2242 |
+
fine_tuned_recommendation,
|
| 2243 |
+
|
| 2244 |
+
"change":
|
| 2245 |
+
fine_tuned_recommendation
|
| 2246 |
+
-
|
| 2247 |
+
original_recommendation,
|
| 2248 |
+
},
|
| 2249 |
+
|
| 2250 |
+
"format_compliance": {
|
| 2251 |
+
|
| 2252 |
+
"original":
|
| 2253 |
+
original_format,
|
| 2254 |
+
|
| 2255 |
+
"fine_tuned":
|
| 2256 |
+
fine_tuned_format,
|
| 2257 |
+
|
| 2258 |
+
"change":
|
| 2259 |
+
fine_tuned_format
|
| 2260 |
+
-
|
| 2261 |
+
original_format,
|
| 2262 |
+
},
|
| 2263 |
+
},
|
| 2264 |
+
|
| 2265 |
+
"token_usage": {
|
| 2266 |
+
|
| 2267 |
+
"input_tokens": {
|
| 2268 |
+
|
| 2269 |
+
"original":
|
| 2270 |
+
original_input,
|
| 2271 |
+
|
| 2272 |
+
"fine_tuned":
|
| 2273 |
+
fine_tuned_input,
|
| 2274 |
+
},
|
| 2275 |
+
|
| 2276 |
+
"output_tokens": {
|
| 2277 |
+
|
| 2278 |
+
"original":
|
| 2279 |
+
original_output,
|
| 2280 |
+
|
| 2281 |
+
"fine_tuned":
|
| 2282 |
+
fine_tuned_output,
|
| 2283 |
+
},
|
| 2284 |
+
|
| 2285 |
+
"total_tokens": {
|
| 2286 |
+
|
| 2287 |
+
"original":
|
| 2288 |
+
original_total,
|
| 2289 |
+
|
| 2290 |
+
"fine_tuned":
|
| 2291 |
+
fine_tuned_total,
|
| 2292 |
+
},
|
| 2293 |
+
|
| 2294 |
+
"generation_time_seconds": {
|
| 2295 |
+
|
| 2296 |
+
"original":
|
| 2297 |
+
original_time,
|
| 2298 |
+
|
| 2299 |
+
"fine_tuned":
|
| 2300 |
+
fine_tuned_time,
|
| 2301 |
+
},
|
| 2302 |
+
|
| 2303 |
+
"tokens_per_second": {
|
| 2304 |
+
|
| 2305 |
+
"original":
|
| 2306 |
+
original_speed,
|
| 2307 |
+
|
| 2308 |
+
"fine_tuned":
|
| 2309 |
+
fine_tuned_speed,
|
| 2310 |
+
},
|
| 2311 |
+
},
|
| 2312 |
+
|
| 2313 |
+
"class_metrics": {
|
| 2314 |
+
|
| 2315 |
+
"original":
|
| 2316 |
+
original_classes,
|
| 2317 |
+
|
| 2318 |
+
"fine_tuned":
|
| 2319 |
+
fine_tuned_classes,
|
| 2320 |
+
},
|
| 2321 |
+
|
| 2322 |
+
"confusion_matrix": {
|
| 2323 |
+
|
| 2324 |
+
"original":
|
| 2325 |
+
original_matrix,
|
| 2326 |
+
|
| 2327 |
+
"fine_tuned":
|
| 2328 |
+
fine_tuned_matrix,
|
| 2329 |
+
},
|
| 2330 |
+
|
| 2331 |
+
"predictions": {
|
| 2332 |
+
|
| 2333 |
+
"original":
|
| 2334 |
+
original_results,
|
| 2335 |
+
|
| 2336 |
+
"fine_tuned":
|
| 2337 |
+
fine_tuned_results,
|
| 2338 |
+
},
|
| 2339 |
+
}
|
| 2340 |
+
|
| 2341 |
+
|
| 2342 |
+
with open(
|
| 2343 |
+
|
| 2344 |
+
json_path,
|
| 2345 |
+
|
| 2346 |
+
"w",
|
| 2347 |
+
|
| 2348 |
+
encoding="utf-8",
|
| 2349 |
+
|
| 2350 |
+
) as file:
|
| 2351 |
+
|
| 2352 |
+
json.dump(
|
| 2353 |
+
|
| 2354 |
+
json_output,
|
| 2355 |
+
|
| 2356 |
+
file,
|
| 2357 |
+
|
| 2358 |
+
indent=2,
|
| 2359 |
+
|
| 2360 |
+
ensure_ascii=False,
|
| 2361 |
+
)
|
| 2362 |
+
|
| 2363 |
+
|
| 2364 |
+
# ============================================================
|
| 2365 |
+
# SAVE PREDICTIONS CSV
|
| 2366 |
+
# ============================================================
|
| 2367 |
+
|
| 2368 |
+
combined_rows = []
|
| 2369 |
+
|
| 2370 |
+
for original, fine_tuned in zip(
|
| 2371 |
+
|
| 2372 |
+
original_results,
|
| 2373 |
+
|
| 2374 |
+
fine_tuned_results,
|
| 2375 |
+
|
| 2376 |
+
):
|
| 2377 |
+
|
| 2378 |
+
combined_rows.append({
|
| 2379 |
+
|
| 2380 |
+
"index":
|
| 2381 |
+
original["index"],
|
| 2382 |
+
|
| 2383 |
+
"reference_severity":
|
| 2384 |
+
original[
|
| 2385 |
+
"reference_severity"
|
| 2386 |
+
],
|
| 2387 |
+
|
| 2388 |
+
"original_severity":
|
| 2389 |
+
original[
|
| 2390 |
+
"predicted_severity"
|
| 2391 |
+
],
|
| 2392 |
+
|
| 2393 |
+
"fine_tuned_severity":
|
| 2394 |
+
fine_tuned[
|
| 2395 |
+
"predicted_severity"
|
| 2396 |
+
],
|
| 2397 |
+
|
| 2398 |
+
"original_correct":
|
| 2399 |
+
original[
|
| 2400 |
+
"severity_correct"
|
| 2401 |
+
],
|
| 2402 |
+
|
| 2403 |
+
"fine_tuned_correct":
|
| 2404 |
+
fine_tuned[
|
| 2405 |
+
"severity_correct"
|
| 2406 |
+
],
|
| 2407 |
+
|
| 2408 |
+
"original_format":
|
| 2409 |
+
original[
|
| 2410 |
+
"format_compliant"
|
| 2411 |
+
],
|
| 2412 |
+
|
| 2413 |
+
"fine_tuned_format":
|
| 2414 |
+
fine_tuned[
|
| 2415 |
+
"format_compliant"
|
| 2416 |
+
],
|
| 2417 |
+
|
| 2418 |
+
"original_root_f1":
|
| 2419 |
+
original[
|
| 2420 |
+
"root_cause_f1"
|
| 2421 |
+
],
|
| 2422 |
+
|
| 2423 |
+
"fine_tuned_root_f1":
|
| 2424 |
+
fine_tuned[
|
| 2425 |
+
"root_cause_f1"
|
| 2426 |
+
],
|
| 2427 |
+
|
| 2428 |
+
"original_explanation_f1":
|
| 2429 |
+
original[
|
| 2430 |
+
"explanation_f1"
|
| 2431 |
+
],
|
| 2432 |
+
|
| 2433 |
+
"fine_tuned_explanation_f1":
|
| 2434 |
+
fine_tuned[
|
| 2435 |
+
"explanation_f1"
|
| 2436 |
+
],
|
| 2437 |
+
|
| 2438 |
+
"original_recommendation_f1":
|
| 2439 |
+
original[
|
| 2440 |
+
"recommendation_f1"
|
| 2441 |
+
],
|
| 2442 |
+
|
| 2443 |
+
"fine_tuned_recommendation_f1":
|
| 2444 |
+
fine_tuned[
|
| 2445 |
+
"recommendation_f1"
|
| 2446 |
+
],
|
| 2447 |
+
|
| 2448 |
+
"original_input_tokens":
|
| 2449 |
+
original[
|
| 2450 |
+
"input_tokens"
|
| 2451 |
+
],
|
| 2452 |
+
|
| 2453 |
+
"fine_tuned_input_tokens":
|
| 2454 |
+
fine_tuned[
|
| 2455 |
+
"input_tokens"
|
| 2456 |
+
],
|
| 2457 |
+
|
| 2458 |
+
"original_output_tokens":
|
| 2459 |
+
original[
|
| 2460 |
+
"output_tokens"
|
| 2461 |
+
],
|
| 2462 |
+
|
| 2463 |
+
"fine_tuned_output_tokens":
|
| 2464 |
+
fine_tuned[
|
| 2465 |
+
"output_tokens"
|
| 2466 |
+
],
|
| 2467 |
+
|
| 2468 |
+
"original_total_tokens":
|
| 2469 |
+
original[
|
| 2470 |
+
"total_tokens"
|
| 2471 |
+
],
|
| 2472 |
+
|
| 2473 |
+
"fine_tuned_total_tokens":
|
| 2474 |
+
fine_tuned[
|
| 2475 |
+
"total_tokens"
|
| 2476 |
+
],
|
| 2477 |
+
|
| 2478 |
+
"original_time_seconds":
|
| 2479 |
+
original[
|
| 2480 |
+
"generation_time_seconds"
|
| 2481 |
+
],
|
| 2482 |
+
|
| 2483 |
+
"fine_tuned_time_seconds":
|
| 2484 |
+
fine_tuned[
|
| 2485 |
+
"generation_time_seconds"
|
| 2486 |
+
],
|
| 2487 |
+
|
| 2488 |
+
"original_tokens_per_second":
|
| 2489 |
+
original[
|
| 2490 |
+
"tokens_per_second"
|
| 2491 |
+
],
|
| 2492 |
+
|
| 2493 |
+
"fine_tuned_tokens_per_second":
|
| 2494 |
+
fine_tuned[
|
| 2495 |
+
"tokens_per_second"
|
| 2496 |
+
],
|
| 2497 |
+
|
| 2498 |
+
"reference":
|
| 2499 |
+
original[
|
| 2500 |
+
"reference"
|
| 2501 |
+
],
|
| 2502 |
+
|
| 2503 |
+
"original_prediction":
|
| 2504 |
+
original[
|
| 2505 |
+
"prediction"
|
| 2506 |
+
],
|
| 2507 |
+
|
| 2508 |
+
"fine_tuned_prediction":
|
| 2509 |
+
fine_tuned[
|
| 2510 |
+
"prediction"
|
| 2511 |
+
],
|
| 2512 |
+
})
|
| 2513 |
+
|
| 2514 |
+
|
| 2515 |
+
if combined_rows:
|
| 2516 |
+
|
| 2517 |
+
with open(
|
| 2518 |
+
|
| 2519 |
+
csv_path,
|
| 2520 |
+
|
| 2521 |
+
"w",
|
| 2522 |
+
|
| 2523 |
+
newline="",
|
| 2524 |
+
|
| 2525 |
+
encoding="utf-8",
|
| 2526 |
+
|
| 2527 |
+
) as file:
|
| 2528 |
+
|
| 2529 |
+
writer = csv.DictWriter(
|
| 2530 |
+
|
| 2531 |
+
file,
|
| 2532 |
+
|
| 2533 |
+
fieldnames=list(
|
| 2534 |
+
combined_rows[0].keys()
|
| 2535 |
+
),
|
| 2536 |
+
)
|
| 2537 |
+
|
| 2538 |
+
writer.writeheader()
|
| 2539 |
+
|
| 2540 |
+
writer.writerows(
|
| 2541 |
+
combined_rows
|
| 2542 |
+
)
|
| 2543 |
+
|
| 2544 |
+
|
| 2545 |
+
# ============================================================
|
| 2546 |
+
# SUMMARY CSV
|
| 2547 |
+
# ============================================================
|
| 2548 |
+
|
| 2549 |
+
summary_rows = [
|
| 2550 |
+
|
| 2551 |
+
[
|
| 2552 |
+
"Severity Accuracy",
|
| 2553 |
+
original_accuracy,
|
| 2554 |
+
fine_tuned_accuracy,
|
| 2555 |
+
fine_tuned_accuracy
|
| 2556 |
+
-
|
| 2557 |
+
original_accuracy,
|
| 2558 |
+
],
|
| 2559 |
+
|
| 2560 |
+
[
|
| 2561 |
+
"Severity Macro F1",
|
| 2562 |
+
original_macro_f1,
|
| 2563 |
+
fine_tuned_macro_f1,
|
| 2564 |
+
fine_tuned_macro_f1
|
| 2565 |
+
-
|
| 2566 |
+
original_macro_f1,
|
| 2567 |
+
],
|
| 2568 |
+
|
| 2569 |
+
[
|
| 2570 |
+
"Severity Weighted F1",
|
| 2571 |
+
original_weighted_f1,
|
| 2572 |
+
fine_tuned_weighted_f1,
|
| 2573 |
+
fine_tuned_weighted_f1
|
| 2574 |
+
-
|
| 2575 |
+
original_weighted_f1,
|
| 2576 |
+
],
|
| 2577 |
+
|
| 2578 |
+
[
|
| 2579 |
+
"Root Cause Token-F1",
|
| 2580 |
+
original_root,
|
| 2581 |
+
fine_tuned_root,
|
| 2582 |
+
fine_tuned_root
|
| 2583 |
+
-
|
| 2584 |
+
original_root,
|
| 2585 |
+
],
|
| 2586 |
+
|
| 2587 |
+
[
|
| 2588 |
+
"Explanation Token-F1",
|
| 2589 |
+
original_explanation,
|
| 2590 |
+
fine_tuned_explanation,
|
| 2591 |
+
fine_tuned_explanation
|
| 2592 |
+
-
|
| 2593 |
+
original_explanation,
|
| 2594 |
+
],
|
| 2595 |
+
|
| 2596 |
+
[
|
| 2597 |
+
"Recommendation Token-F1",
|
| 2598 |
+
original_recommendation,
|
| 2599 |
+
fine_tuned_recommendation,
|
| 2600 |
+
fine_tuned_recommendation
|
| 2601 |
+
-
|
| 2602 |
+
original_recommendation,
|
| 2603 |
+
],
|
| 2604 |
+
|
| 2605 |
+
[
|
| 2606 |
+
"Format Compliance",
|
| 2607 |
+
original_format,
|
| 2608 |
+
fine_tuned_format,
|
| 2609 |
+
fine_tuned_format
|
| 2610 |
+
-
|
| 2611 |
+
original_format,
|
| 2612 |
+
],
|
| 2613 |
+
|
| 2614 |
+
[
|
| 2615 |
+
"Average Input Tokens",
|
| 2616 |
+
original_input,
|
| 2617 |
+
fine_tuned_input,
|
| 2618 |
+
fine_tuned_input
|
| 2619 |
+
-
|
| 2620 |
+
original_input,
|
| 2621 |
+
],
|
| 2622 |
+
|
| 2623 |
+
[
|
| 2624 |
+
"Average Output Tokens",
|
| 2625 |
+
original_output,
|
| 2626 |
+
fine_tuned_output,
|
| 2627 |
+
fine_tuned_output
|
| 2628 |
+
-
|
| 2629 |
+
original_output,
|
| 2630 |
+
],
|
| 2631 |
+
|
| 2632 |
+
[
|
| 2633 |
+
"Average Total Tokens",
|
| 2634 |
+
original_total,
|
| 2635 |
+
fine_tuned_total,
|
| 2636 |
+
fine_tuned_total
|
| 2637 |
+
-
|
| 2638 |
+
original_total,
|
| 2639 |
+
],
|
| 2640 |
+
|
| 2641 |
+
[
|
| 2642 |
+
"Average Generation Time",
|
| 2643 |
+
original_time,
|
| 2644 |
+
fine_tuned_time,
|
| 2645 |
+
fine_tuned_time
|
| 2646 |
+
-
|
| 2647 |
+
original_time,
|
| 2648 |
+
],
|
| 2649 |
+
|
| 2650 |
+
[
|
| 2651 |
+
"Average Tokens / Second",
|
| 2652 |
+
original_speed,
|
| 2653 |
+
fine_tuned_speed,
|
| 2654 |
+
fine_tuned_speed
|
| 2655 |
+
-
|
| 2656 |
+
original_speed,
|
| 2657 |
+
],
|
| 2658 |
+
]
|
| 2659 |
+
|
| 2660 |
+
|
| 2661 |
+
with open(
|
| 2662 |
+
|
| 2663 |
+
summary_path,
|
| 2664 |
+
|
| 2665 |
+
"w",
|
| 2666 |
+
|
| 2667 |
+
newline="",
|
| 2668 |
+
|
| 2669 |
+
encoding="utf-8",
|
| 2670 |
+
|
| 2671 |
+
) as file:
|
| 2672 |
+
|
| 2673 |
+
writer = csv.writer(
|
| 2674 |
+
file
|
| 2675 |
+
)
|
| 2676 |
+
|
| 2677 |
+
writer.writerow([
|
| 2678 |
+
|
| 2679 |
+
"Metric",
|
| 2680 |
+
|
| 2681 |
+
"Original",
|
| 2682 |
+
|
| 2683 |
+
"Fine-tuned",
|
| 2684 |
+
|
| 2685 |
+
"Change",
|
| 2686 |
+
|
| 2687 |
+
])
|
| 2688 |
+
|
| 2689 |
+
writer.writerows(
|
| 2690 |
+
summary_rows
|
| 2691 |
+
)
|
| 2692 |
+
|
| 2693 |
+
|
| 2694 |
+
# ============================================================
|
| 2695 |
+
# FINAL MESSAGE
|
| 2696 |
+
# ============================================================
|
| 2697 |
+
|
| 2698 |
+
print()
|
| 2699 |
+
print("=" * 80)
|
| 2700 |
+
print("COMPARISON COMPLETE")
|
| 2701 |
+
print("=" * 80)
|
| 2702 |
+
|
| 2703 |
+
print()
|
| 2704 |
+
|
| 2705 |
+
print(
|
| 2706 |
+
"Examples tested:",
|
| 2707 |
+
len(dataset),
|
| 2708 |
+
)
|
| 2709 |
+
|
| 2710 |
+
print()
|
| 2711 |
+
|
| 2712 |
+
print(
|
| 2713 |
+
"Detailed predictions:"
|
| 2714 |
+
)
|
| 2715 |
+
|
| 2716 |
+
print(
|
| 2717 |
+
os.path.abspath(
|
| 2718 |
+
csv_path
|
| 2719 |
+
)
|
| 2720 |
+
)
|
| 2721 |
+
|
| 2722 |
+
print()
|
| 2723 |
+
|
| 2724 |
+
print(
|
| 2725 |
+
"Summary:"
|
| 2726 |
+
)
|
| 2727 |
+
|
| 2728 |
+
print(
|
| 2729 |
+
os.path.abspath(
|
| 2730 |
+
summary_path
|
| 2731 |
+
)
|
| 2732 |
+
)
|
| 2733 |
+
|
| 2734 |
+
print()
|
| 2735 |
+
|
| 2736 |
+
print(
|
| 2737 |
+
"JSON:"
|
| 2738 |
+
)
|
| 2739 |
+
|
| 2740 |
+
print(
|
| 2741 |
+
os.path.abspath(
|
| 2742 |
+
json_path
|
| 2743 |
+
)
|
| 2744 |
+
)
|
| 2745 |
+
|
| 2746 |
+
print()
|
| 2747 |
+
print("=" * 80)
|
| 2748 |
+
print("IMPORTANT")
|
| 2749 |
+
print("=" * 80)
|
| 2750 |
+
|
| 2751 |
+
print(
|
| 2752 |
+
"This is an objective reference-based evaluation."
|
| 2753 |
+
)
|
| 2754 |
+
|
| 2755 |
+
print()
|
| 2756 |
+
|
| 2757 |
+
print(
|
| 2758 |
+
"Token-F1 measures similarity to the "
|
| 2759 |
+
"reference response. It does not prove "
|
| 2760 |
+
"real-world telecom engineering correctness."
|
| 2761 |
+
)
|
| 2762 |
+
|
| 2763 |
+
print()
|
| 2764 |
+
|
| 2765 |
+
print(
|
| 2766 |
+
"Relevance, Coherence, Faithfulness and "
|
| 2767 |
+
"Helpfulness are intentionally not estimated "
|
| 2768 |
+
"by the 1.5B model itself."
|
| 2769 |
+
)
|
| 2770 |
+
|
| 2771 |
+
print()
|
| 2772 |
+
|
| 2773 |
+
print(
|
| 2774 |
+
"For those qualities, use engineer validation "
|
| 2775 |
+
"or a separate stronger evaluation model."
|
| 2776 |
+
)
|
| 2777 |
+
|
| 2778 |
+
print("=" * 80)
|
| 2779 |
+
|
| 2780 |
+
|
| 2781 |
+
# ============================================================
|
| 2782 |
+
# CLEANUP
|
| 2783 |
+
# ============================================================
|
| 2784 |
+
|
| 2785 |
+
try:
|
| 2786 |
+
|
| 2787 |
+
del fine_tuned_model
|
| 2788 |
+
|
| 2789 |
+
except Exception:
|
| 2790 |
+
|
| 2791 |
+
pass
|
| 2792 |
+
|
| 2793 |
+
try:
|
| 2794 |
+
|
| 2795 |
+
del base_model
|
| 2796 |
+
|
| 2797 |
+
except Exception:
|
| 2798 |
+
|
| 2799 |
+
pass
|
| 2800 |
+
|
| 2801 |
+
gc.collect()
|
| 2802 |
+
|
| 2803 |
+
if torch.cuda.is_available():
|
| 2804 |
+
|
| 2805 |
+
torch.cuda.empty_cache()
|
requirements.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch
|
| 2 |
+
transformers
|
| 3 |
+
datasets
|
| 4 |
+
peft
|
| 5 |
+
trl
|
| 6 |
+
bitsandbytes
|
| 7 |
+
accelerate
|
| 8 |
+
scikit-learn
|
run_all.bat
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
@echo off
|
| 2 |
+
python train.py
|
| 3 |
+
python test.py --adapter "models/telecom-qwen-four-output" --test "sample/data/test_four_output.jsonl" --samples 0
|
run_all.sh
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
set -e
|
| 3 |
+
python train.py
|
| 4 |
+
python test.py --adapter "models/telecom-qwen-four-output" --test "sample/data/test_four_output.jsonl" --samples 0
|
test.py
ADDED
|
@@ -0,0 +1,1353 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ============================================================
|
| 2 |
+
# TELECOM QLoRA TEST / EVALUATION
|
| 3 |
+
# FOUR-OUTPUT TELECOM DIAGNOSIS
|
| 4 |
+
# ============================================================
|
| 5 |
+
|
| 6 |
+
import os
|
| 7 |
+
import re
|
| 8 |
+
import json
|
| 9 |
+
import argparse
|
| 10 |
+
from collections import Counter
|
| 11 |
+
|
| 12 |
+
import torch
|
| 13 |
+
|
| 14 |
+
from datasets import load_dataset
|
| 15 |
+
|
| 16 |
+
from transformers import (
|
| 17 |
+
AutoTokenizer,
|
| 18 |
+
AutoModelForCausalLM,
|
| 19 |
+
BitsAndBytesConfig,
|
| 20 |
+
)
|
| 21 |
+
|
| 22 |
+
from peft import PeftModel
|
| 23 |
+
|
| 24 |
+
from sklearn.metrics import (
|
| 25 |
+
accuracy_score,
|
| 26 |
+
precision_recall_fscore_support,
|
| 27 |
+
confusion_matrix,
|
| 28 |
+
)
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
# ============================================================
|
| 32 |
+
# CONFIGURATION
|
| 33 |
+
# ============================================================
|
| 34 |
+
|
| 35 |
+
MODEL_NAME = "C:\\Users\\aadhi\\Downloads\\telecom_four_output_complete_workspace\\models\\telecom-qwen-four-output"
|
| 36 |
+
|
| 37 |
+
CACHE_DIR = "sample/.cache/huggingface"
|
| 38 |
+
|
| 39 |
+
DEFAULT_TEST_FILE = (
|
| 40 |
+
"sample/data/test_four_output.jsonl"
|
| 41 |
+
)
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
# ============================================================
|
| 45 |
+
# REQUIRED OUTPUT SECTIONS
|
| 46 |
+
# ============================================================
|
| 47 |
+
|
| 48 |
+
REQUIRED_SECTIONS = [
|
| 49 |
+
|
| 50 |
+
"Probable Root Cause:",
|
| 51 |
+
|
| 52 |
+
"Explanation:",
|
| 53 |
+
|
| 54 |
+
"Recommendation:",
|
| 55 |
+
|
| 56 |
+
"Fault Severity:",
|
| 57 |
+
]
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
# ============================================================
|
| 61 |
+
# COMMAND-LINE ARGUMENTS
|
| 62 |
+
# ============================================================
|
| 63 |
+
|
| 64 |
+
parser = argparse.ArgumentParser(
|
| 65 |
+
|
| 66 |
+
description=(
|
| 67 |
+
"Evaluate telecom QLoRA four-output model."
|
| 68 |
+
)
|
| 69 |
+
)
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
parser.add_argument(
|
| 73 |
+
|
| 74 |
+
"--adapter",
|
| 75 |
+
|
| 76 |
+
required=True,
|
| 77 |
+
|
| 78 |
+
help=(
|
| 79 |
+
"Path to trained LoRA adapter."
|
| 80 |
+
),
|
| 81 |
+
)
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
parser.add_argument(
|
| 85 |
+
|
| 86 |
+
"--test",
|
| 87 |
+
|
| 88 |
+
default=DEFAULT_TEST_FILE,
|
| 89 |
+
|
| 90 |
+
help=(
|
| 91 |
+
"Path to test JSONL dataset."
|
| 92 |
+
),
|
| 93 |
+
)
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
parser.add_argument(
|
| 97 |
+
|
| 98 |
+
"--samples",
|
| 99 |
+
|
| 100 |
+
type=int,
|
| 101 |
+
|
| 102 |
+
default=0,
|
| 103 |
+
|
| 104 |
+
help=(
|
| 105 |
+
"Number of test samples. "
|
| 106 |
+
"0 = all samples."
|
| 107 |
+
),
|
| 108 |
+
)
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
parser.add_argument(
|
| 112 |
+
|
| 113 |
+
"--debug",
|
| 114 |
+
|
| 115 |
+
action="store_true",
|
| 116 |
+
|
| 117 |
+
help=(
|
| 118 |
+
"Print generated responses."
|
| 119 |
+
),
|
| 120 |
+
)
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
args = parser.parse_args()
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
# ============================================================
|
| 127 |
+
# HELPERS
|
| 128 |
+
# ============================================================
|
| 129 |
+
|
| 130 |
+
def extract_fault_severity(text):
|
| 131 |
+
|
| 132 |
+
matches = re.findall(
|
| 133 |
+
|
| 134 |
+
r"fault[_\s-]*severity\s*[:=]\s*([012])",
|
| 135 |
+
|
| 136 |
+
text,
|
| 137 |
+
|
| 138 |
+
re.IGNORECASE,
|
| 139 |
+
)
|
| 140 |
+
|
| 141 |
+
if not matches:
|
| 142 |
+
|
| 143 |
+
return None
|
| 144 |
+
|
| 145 |
+
return int(
|
| 146 |
+
matches[-1]
|
| 147 |
+
)
|
| 148 |
+
|
| 149 |
+
|
| 150 |
+
def get_assistant_message(example):
|
| 151 |
+
|
| 152 |
+
for message in example["messages"]:
|
| 153 |
+
|
| 154 |
+
if message["role"] == "assistant":
|
| 155 |
+
|
| 156 |
+
return message["content"]
|
| 157 |
+
|
| 158 |
+
return ""
|
| 159 |
+
|
| 160 |
+
|
| 161 |
+
def extract_section(
|
| 162 |
+
text,
|
| 163 |
+
section_name,
|
| 164 |
+
next_sections,
|
| 165 |
+
):
|
| 166 |
+
|
| 167 |
+
if section_name not in text:
|
| 168 |
+
|
| 169 |
+
return ""
|
| 170 |
+
|
| 171 |
+
content = text.split(
|
| 172 |
+
section_name,
|
| 173 |
+
1
|
| 174 |
+
)[1]
|
| 175 |
+
|
| 176 |
+
end_positions = []
|
| 177 |
+
|
| 178 |
+
for section in next_sections:
|
| 179 |
+
|
| 180 |
+
position = content.find(
|
| 181 |
+
section
|
| 182 |
+
)
|
| 183 |
+
|
| 184 |
+
if position >= 0:
|
| 185 |
+
|
| 186 |
+
end_positions.append(
|
| 187 |
+
position
|
| 188 |
+
)
|
| 189 |
+
|
| 190 |
+
if end_positions:
|
| 191 |
+
|
| 192 |
+
content = content[
|
| 193 |
+
:min(end_positions)
|
| 194 |
+
]
|
| 195 |
+
|
| 196 |
+
return content.strip()
|
| 197 |
+
|
| 198 |
+
|
| 199 |
+
def tokenize_for_overlap(text):
|
| 200 |
+
|
| 201 |
+
return set(
|
| 202 |
+
re.findall(
|
| 203 |
+
r"[a-z0-9_]+",
|
| 204 |
+
text.lower()
|
| 205 |
+
)
|
| 206 |
+
)
|
| 207 |
+
|
| 208 |
+
|
| 209 |
+
def token_f1(
|
| 210 |
+
reference,
|
| 211 |
+
prediction,
|
| 212 |
+
):
|
| 213 |
+
|
| 214 |
+
reference_tokens = (
|
| 215 |
+
tokenize_for_overlap(
|
| 216 |
+
reference
|
| 217 |
+
)
|
| 218 |
+
)
|
| 219 |
+
|
| 220 |
+
prediction_tokens = (
|
| 221 |
+
tokenize_for_overlap(
|
| 222 |
+
prediction
|
| 223 |
+
)
|
| 224 |
+
)
|
| 225 |
+
|
| 226 |
+
if not reference_tokens:
|
| 227 |
+
|
| 228 |
+
return 0.0
|
| 229 |
+
|
| 230 |
+
if not prediction_tokens:
|
| 231 |
+
|
| 232 |
+
return 0.0
|
| 233 |
+
|
| 234 |
+
intersection = (
|
| 235 |
+
reference_tokens
|
| 236 |
+
&
|
| 237 |
+
prediction_tokens
|
| 238 |
+
)
|
| 239 |
+
|
| 240 |
+
precision = (
|
| 241 |
+
len(intersection)
|
| 242 |
+
/
|
| 243 |
+
len(prediction_tokens)
|
| 244 |
+
)
|
| 245 |
+
|
| 246 |
+
recall = (
|
| 247 |
+
len(intersection)
|
| 248 |
+
/
|
| 249 |
+
len(reference_tokens)
|
| 250 |
+
)
|
| 251 |
+
|
| 252 |
+
if precision + recall == 0:
|
| 253 |
+
|
| 254 |
+
return 0.0
|
| 255 |
+
|
| 256 |
+
return (
|
| 257 |
+
2
|
| 258 |
+
* precision
|
| 259 |
+
* recall
|
| 260 |
+
/
|
| 261 |
+
(precision + recall)
|
| 262 |
+
)
|
| 263 |
+
|
| 264 |
+
|
| 265 |
+
# ============================================================
|
| 266 |
+
# GPU CHECK
|
| 267 |
+
# ============================================================
|
| 268 |
+
|
| 269 |
+
print("=" * 80)
|
| 270 |
+
|
| 271 |
+
print(
|
| 272 |
+
"TELECOM FOUR-OUTPUT MODEL EVALUATION"
|
| 273 |
+
)
|
| 274 |
+
|
| 275 |
+
print("=" * 80)
|
| 276 |
+
|
| 277 |
+
|
| 278 |
+
print()
|
| 279 |
+
|
| 280 |
+
print(
|
| 281 |
+
"CUDA available:",
|
| 282 |
+
torch.cuda.is_available()
|
| 283 |
+
)
|
| 284 |
+
|
| 285 |
+
|
| 286 |
+
if not torch.cuda.is_available():
|
| 287 |
+
|
| 288 |
+
raise RuntimeError(
|
| 289 |
+
"CUDA GPU is required."
|
| 290 |
+
)
|
| 291 |
+
|
| 292 |
+
|
| 293 |
+
print(
|
| 294 |
+
"GPU:",
|
| 295 |
+
torch.cuda.get_device_name(0)
|
| 296 |
+
)
|
| 297 |
+
|
| 298 |
+
|
| 299 |
+
print(
|
| 300 |
+
"VRAM:",
|
| 301 |
+
round(
|
| 302 |
+
torch.cuda.get_device_properties(
|
| 303 |
+
0
|
| 304 |
+
).total_memory
|
| 305 |
+
/ (1024 ** 3),
|
| 306 |
+
2,
|
| 307 |
+
),
|
| 308 |
+
"GB",
|
| 309 |
+
)
|
| 310 |
+
|
| 311 |
+
|
| 312 |
+
# ============================================================
|
| 313 |
+
# CHECK FILES
|
| 314 |
+
# ============================================================
|
| 315 |
+
|
| 316 |
+
if not os.path.exists(
|
| 317 |
+
args.adapter
|
| 318 |
+
):
|
| 319 |
+
|
| 320 |
+
raise FileNotFoundError(
|
| 321 |
+
|
| 322 |
+
"Adapter directory not found:\n"
|
| 323 |
+
f"{args.adapter}"
|
| 324 |
+
)
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
if not os.path.exists(
|
| 328 |
+
args.test
|
| 329 |
+
):
|
| 330 |
+
|
| 331 |
+
raise FileNotFoundError(
|
| 332 |
+
|
| 333 |
+
"Test dataset not found:\n"
|
| 334 |
+
f"{args.test}"
|
| 335 |
+
)
|
| 336 |
+
|
| 337 |
+
|
| 338 |
+
# ============================================================
|
| 339 |
+
# LOAD TEST DATA
|
| 340 |
+
# ============================================================
|
| 341 |
+
|
| 342 |
+
print()
|
| 343 |
+
|
| 344 |
+
print(
|
| 345 |
+
"Loading test dataset..."
|
| 346 |
+
)
|
| 347 |
+
|
| 348 |
+
|
| 349 |
+
test_dataset = load_dataset(
|
| 350 |
+
|
| 351 |
+
"json",
|
| 352 |
+
|
| 353 |
+
data_files=args.test,
|
| 354 |
+
|
| 355 |
+
split="train",
|
| 356 |
+
|
| 357 |
+
cache_dir=CACHE_DIR,
|
| 358 |
+
)
|
| 359 |
+
|
| 360 |
+
|
| 361 |
+
print(
|
| 362 |
+
"Total test examples:",
|
| 363 |
+
len(test_dataset)
|
| 364 |
+
)
|
| 365 |
+
|
| 366 |
+
|
| 367 |
+
if args.samples > 0:
|
| 368 |
+
|
| 369 |
+
number = min(
|
| 370 |
+
args.samples,
|
| 371 |
+
len(test_dataset)
|
| 372 |
+
)
|
| 373 |
+
|
| 374 |
+
test_dataset = (
|
| 375 |
+
test_dataset.select(
|
| 376 |
+
range(number)
|
| 377 |
+
)
|
| 378 |
+
)
|
| 379 |
+
|
| 380 |
+
|
| 381 |
+
print(
|
| 382 |
+
"Examples to evaluate:",
|
| 383 |
+
len(test_dataset)
|
| 384 |
+
)
|
| 385 |
+
|
| 386 |
+
|
| 387 |
+
# ============================================================
|
| 388 |
+
# LOAD TOKENIZER
|
| 389 |
+
# ============================================================
|
| 390 |
+
|
| 391 |
+
print()
|
| 392 |
+
|
| 393 |
+
print(
|
| 394 |
+
"Loading tokenizer..."
|
| 395 |
+
)
|
| 396 |
+
|
| 397 |
+
|
| 398 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 399 |
+
|
| 400 |
+
args.adapter,
|
| 401 |
+
|
| 402 |
+
trust_remote_code=True,
|
| 403 |
+
|
| 404 |
+
cache_dir=CACHE_DIR,
|
| 405 |
+
)
|
| 406 |
+
|
| 407 |
+
|
| 408 |
+
if tokenizer.pad_token is None:
|
| 409 |
+
|
| 410 |
+
tokenizer.pad_token = (
|
| 411 |
+
tokenizer.eos_token
|
| 412 |
+
)
|
| 413 |
+
|
| 414 |
+
|
| 415 |
+
# ============================================================
|
| 416 |
+
# QUANTIZATION
|
| 417 |
+
# ============================================================
|
| 418 |
+
|
| 419 |
+
bnb_config = BitsAndBytesConfig(
|
| 420 |
+
|
| 421 |
+
load_in_4bit=True,
|
| 422 |
+
|
| 423 |
+
bnb_4bit_quant_type="nf4",
|
| 424 |
+
|
| 425 |
+
bnb_4bit_compute_dtype=torch.float16,
|
| 426 |
+
|
| 427 |
+
bnb_4bit_use_double_quant=True,
|
| 428 |
+
)
|
| 429 |
+
|
| 430 |
+
|
| 431 |
+
# ============================================================
|
| 432 |
+
# LOAD BASE MODEL
|
| 433 |
+
# ============================================================
|
| 434 |
+
|
| 435 |
+
print()
|
| 436 |
+
|
| 437 |
+
print(
|
| 438 |
+
"Loading base Qwen model..."
|
| 439 |
+
)
|
| 440 |
+
|
| 441 |
+
|
| 442 |
+
base_model = (
|
| 443 |
+
AutoModelForCausalLM.from_pretrained(
|
| 444 |
+
|
| 445 |
+
MODEL_NAME,
|
| 446 |
+
|
| 447 |
+
quantization_config=bnb_config,
|
| 448 |
+
|
| 449 |
+
device_map="auto",
|
| 450 |
+
|
| 451 |
+
dtype=torch.float16,
|
| 452 |
+
|
| 453 |
+
trust_remote_code=True,
|
| 454 |
+
|
| 455 |
+
cache_dir=CACHE_DIR,
|
| 456 |
+
)
|
| 457 |
+
)
|
| 458 |
+
|
| 459 |
+
|
| 460 |
+
# ============================================================
|
| 461 |
+
# LOAD LORA ADAPTER
|
| 462 |
+
# ============================================================
|
| 463 |
+
|
| 464 |
+
print()
|
| 465 |
+
|
| 466 |
+
print(
|
| 467 |
+
"Loading LoRA adapter..."
|
| 468 |
+
)
|
| 469 |
+
|
| 470 |
+
|
| 471 |
+
model = PeftModel.from_pretrained(
|
| 472 |
+
|
| 473 |
+
base_model,
|
| 474 |
+
|
| 475 |
+
args.adapter,
|
| 476 |
+
)
|
| 477 |
+
|
| 478 |
+
|
| 479 |
+
model.eval()
|
| 480 |
+
|
| 481 |
+
|
| 482 |
+
print(
|
| 483 |
+
"Model ready."
|
| 484 |
+
)
|
| 485 |
+
|
| 486 |
+
|
| 487 |
+
# ============================================================
|
| 488 |
+
# EVALUATION STORAGE
|
| 489 |
+
# ============================================================
|
| 490 |
+
|
| 491 |
+
predictions = []
|
| 492 |
+
|
| 493 |
+
y_true = []
|
| 494 |
+
|
| 495 |
+
y_pred = []
|
| 496 |
+
|
| 497 |
+
root_scores = []
|
| 498 |
+
|
| 499 |
+
explanation_scores = []
|
| 500 |
+
|
| 501 |
+
recommendation_scores = []
|
| 502 |
+
|
| 503 |
+
|
| 504 |
+
# ============================================================
|
| 505 |
+
# GENERATE RESPONSES
|
| 506 |
+
# ============================================================
|
| 507 |
+
|
| 508 |
+
print()
|
| 509 |
+
|
| 510 |
+
print("=" * 80)
|
| 511 |
+
|
| 512 |
+
print(
|
| 513 |
+
"GENERATING TEST RESPONSES"
|
| 514 |
+
)
|
| 515 |
+
|
| 516 |
+
print("=" * 80)
|
| 517 |
+
|
| 518 |
+
|
| 519 |
+
for index, example in enumerate(
|
| 520 |
+
test_dataset
|
| 521 |
+
):
|
| 522 |
+
|
| 523 |
+
# --------------------------------------------------------
|
| 524 |
+
# Get messages
|
| 525 |
+
# --------------------------------------------------------
|
| 526 |
+
|
| 527 |
+
messages = example[
|
| 528 |
+
"messages"
|
| 529 |
+
]
|
| 530 |
+
|
| 531 |
+
|
| 532 |
+
# --------------------------------------------------------
|
| 533 |
+
# Remove assistant answer
|
| 534 |
+
# --------------------------------------------------------
|
| 535 |
+
|
| 536 |
+
prompt_messages = [
|
| 537 |
+
|
| 538 |
+
message
|
| 539 |
+
|
| 540 |
+
for message in messages
|
| 541 |
+
|
| 542 |
+
if message["role"]
|
| 543 |
+
!= "assistant"
|
| 544 |
+
|
| 545 |
+
]
|
| 546 |
+
|
| 547 |
+
|
| 548 |
+
# --------------------------------------------------------
|
| 549 |
+
# Reference answer
|
| 550 |
+
# --------------------------------------------------------
|
| 551 |
+
|
| 552 |
+
reference = (
|
| 553 |
+
get_assistant_message(
|
| 554 |
+
example
|
| 555 |
+
)
|
| 556 |
+
)
|
| 557 |
+
|
| 558 |
+
|
| 559 |
+
# --------------------------------------------------------
|
| 560 |
+
# Build prompt
|
| 561 |
+
# --------------------------------------------------------
|
| 562 |
+
|
| 563 |
+
prompt = (
|
| 564 |
+
tokenizer.apply_chat_template(
|
| 565 |
+
|
| 566 |
+
prompt_messages,
|
| 567 |
+
|
| 568 |
+
tokenize=False,
|
| 569 |
+
|
| 570 |
+
add_generation_prompt=True,
|
| 571 |
+
)
|
| 572 |
+
)
|
| 573 |
+
|
| 574 |
+
|
| 575 |
+
# --------------------------------------------------------
|
| 576 |
+
# Tokenize
|
| 577 |
+
# --------------------------------------------------------
|
| 578 |
+
|
| 579 |
+
inputs = tokenizer(
|
| 580 |
+
|
| 581 |
+
prompt,
|
| 582 |
+
|
| 583 |
+
return_tensors="pt",
|
| 584 |
+
|
| 585 |
+
)
|
| 586 |
+
|
| 587 |
+
|
| 588 |
+
inputs = {
|
| 589 |
+
|
| 590 |
+
key: value.to(
|
| 591 |
+
model.device
|
| 592 |
+
)
|
| 593 |
+
|
| 594 |
+
for key, value
|
| 595 |
+
in inputs.items()
|
| 596 |
+
|
| 597 |
+
}
|
| 598 |
+
|
| 599 |
+
|
| 600 |
+
# --------------------------------------------------------
|
| 601 |
+
# Generate
|
| 602 |
+
# --------------------------------------------------------
|
| 603 |
+
|
| 604 |
+
with torch.no_grad():
|
| 605 |
+
|
| 606 |
+
output = model.generate(
|
| 607 |
+
|
| 608 |
+
**inputs,
|
| 609 |
+
|
| 610 |
+
max_new_tokens=350,
|
| 611 |
+
|
| 612 |
+
do_sample=False,
|
| 613 |
+
|
| 614 |
+
pad_token_id=(
|
| 615 |
+
tokenizer.pad_token_id
|
| 616 |
+
),
|
| 617 |
+
|
| 618 |
+
eos_token_id=(
|
| 619 |
+
tokenizer.eos_token_id
|
| 620 |
+
),
|
| 621 |
+
)
|
| 622 |
+
|
| 623 |
+
|
| 624 |
+
# --------------------------------------------------------
|
| 625 |
+
# Decode ONLY generated tokens
|
| 626 |
+
# --------------------------------------------------------
|
| 627 |
+
|
| 628 |
+
generated_tokens = output[
|
| 629 |
+
|
| 630 |
+
0
|
| 631 |
+
|
| 632 |
+
][
|
| 633 |
+
|
| 634 |
+
inputs["input_ids"].shape[1]:
|
| 635 |
+
|
| 636 |
+
]
|
| 637 |
+
|
| 638 |
+
|
| 639 |
+
generated = tokenizer.decode(
|
| 640 |
+
|
| 641 |
+
generated_tokens,
|
| 642 |
+
|
| 643 |
+
skip_special_tokens=True,
|
| 644 |
+
).strip()
|
| 645 |
+
|
| 646 |
+
|
| 647 |
+
# --------------------------------------------------------
|
| 648 |
+
# Severity
|
| 649 |
+
# --------------------------------------------------------
|
| 650 |
+
|
| 651 |
+
true_label = (
|
| 652 |
+
extract_fault_severity(
|
| 653 |
+
reference
|
| 654 |
+
)
|
| 655 |
+
)
|
| 656 |
+
|
| 657 |
+
|
| 658 |
+
predicted_label = (
|
| 659 |
+
extract_fault_severity(
|
| 660 |
+
generated
|
| 661 |
+
)
|
| 662 |
+
)
|
| 663 |
+
|
| 664 |
+
|
| 665 |
+
y_true.append(
|
| 666 |
+
true_label
|
| 667 |
+
)
|
| 668 |
+
|
| 669 |
+
y_pred.append(
|
| 670 |
+
predicted_label
|
| 671 |
+
)
|
| 672 |
+
|
| 673 |
+
|
| 674 |
+
# --------------------------------------------------------
|
| 675 |
+
# Root Cause
|
| 676 |
+
# --------------------------------------------------------
|
| 677 |
+
|
| 678 |
+
root_reference = extract_section(
|
| 679 |
+
|
| 680 |
+
reference,
|
| 681 |
+
|
| 682 |
+
"Probable Root Cause:",
|
| 683 |
+
|
| 684 |
+
[
|
| 685 |
+
"Explanation:",
|
| 686 |
+
"Recommendation:",
|
| 687 |
+
"Fault Severity:",
|
| 688 |
+
],
|
| 689 |
+
)
|
| 690 |
+
|
| 691 |
+
|
| 692 |
+
root_prediction = extract_section(
|
| 693 |
+
|
| 694 |
+
generated,
|
| 695 |
+
|
| 696 |
+
"Probable Root Cause:",
|
| 697 |
+
|
| 698 |
+
[
|
| 699 |
+
"Explanation:",
|
| 700 |
+
"Recommendation:",
|
| 701 |
+
"Fault Severity:",
|
| 702 |
+
],
|
| 703 |
+
)
|
| 704 |
+
|
| 705 |
+
|
| 706 |
+
root_f1 = token_f1(
|
| 707 |
+
|
| 708 |
+
root_reference,
|
| 709 |
+
|
| 710 |
+
root_prediction,
|
| 711 |
+
)
|
| 712 |
+
|
| 713 |
+
|
| 714 |
+
root_scores.append(
|
| 715 |
+
root_f1
|
| 716 |
+
)
|
| 717 |
+
|
| 718 |
+
|
| 719 |
+
# --------------------------------------------------------
|
| 720 |
+
# Explanation
|
| 721 |
+
# --------------------------------------------------------
|
| 722 |
+
|
| 723 |
+
explanation_reference = extract_section(
|
| 724 |
+
|
| 725 |
+
reference,
|
| 726 |
+
|
| 727 |
+
"Explanation:",
|
| 728 |
+
|
| 729 |
+
[
|
| 730 |
+
"Recommendation:",
|
| 731 |
+
"Fault Severity:",
|
| 732 |
+
],
|
| 733 |
+
)
|
| 734 |
+
|
| 735 |
+
|
| 736 |
+
explanation_prediction = extract_section(
|
| 737 |
+
|
| 738 |
+
generated,
|
| 739 |
+
|
| 740 |
+
"Explanation:",
|
| 741 |
+
|
| 742 |
+
[
|
| 743 |
+
"Recommendation:",
|
| 744 |
+
"Fault Severity:",
|
| 745 |
+
],
|
| 746 |
+
)
|
| 747 |
+
|
| 748 |
+
|
| 749 |
+
explanation_f1 = token_f1(
|
| 750 |
+
|
| 751 |
+
explanation_reference,
|
| 752 |
+
|
| 753 |
+
explanation_prediction,
|
| 754 |
+
)
|
| 755 |
+
|
| 756 |
+
|
| 757 |
+
explanation_scores.append(
|
| 758 |
+
explanation_f1
|
| 759 |
+
)
|
| 760 |
+
|
| 761 |
+
|
| 762 |
+
# --------------------------------------------------------
|
| 763 |
+
# Recommendation
|
| 764 |
+
# --------------------------------------------------------
|
| 765 |
+
|
| 766 |
+
recommendation_reference = extract_section(
|
| 767 |
+
|
| 768 |
+
reference,
|
| 769 |
+
|
| 770 |
+
"Recommendation:",
|
| 771 |
+
|
| 772 |
+
[
|
| 773 |
+
"Fault Severity:",
|
| 774 |
+
],
|
| 775 |
+
)
|
| 776 |
+
|
| 777 |
+
|
| 778 |
+
recommendation_prediction = extract_section(
|
| 779 |
+
|
| 780 |
+
generated,
|
| 781 |
+
|
| 782 |
+
"Recommendation:",
|
| 783 |
+
|
| 784 |
+
[
|
| 785 |
+
"Fault Severity:",
|
| 786 |
+
],
|
| 787 |
+
)
|
| 788 |
+
|
| 789 |
+
|
| 790 |
+
recommendation_f1 = token_f1(
|
| 791 |
+
|
| 792 |
+
recommendation_reference,
|
| 793 |
+
|
| 794 |
+
recommendation_prediction,
|
| 795 |
+
)
|
| 796 |
+
|
| 797 |
+
|
| 798 |
+
recommendation_scores.append(
|
| 799 |
+
recommendation_f1
|
| 800 |
+
)
|
| 801 |
+
|
| 802 |
+
|
| 803 |
+
# --------------------------------------------------------
|
| 804 |
+
# Format check
|
| 805 |
+
# --------------------------------------------------------
|
| 806 |
+
|
| 807 |
+
all_sections_present = all(
|
| 808 |
+
|
| 809 |
+
section in generated
|
| 810 |
+
|
| 811 |
+
for section
|
| 812 |
+
in REQUIRED_SECTIONS
|
| 813 |
+
|
| 814 |
+
)
|
| 815 |
+
|
| 816 |
+
|
| 817 |
+
# --------------------------------------------------------
|
| 818 |
+
# Save result
|
| 819 |
+
# --------------------------------------------------------
|
| 820 |
+
|
| 821 |
+
predictions.append({
|
| 822 |
+
|
| 823 |
+
"index": index,
|
| 824 |
+
|
| 825 |
+
"true_fault_severity": (
|
| 826 |
+
true_label
|
| 827 |
+
),
|
| 828 |
+
|
| 829 |
+
"predicted_fault_severity": (
|
| 830 |
+
predicted_label
|
| 831 |
+
),
|
| 832 |
+
|
| 833 |
+
"severity_correct": (
|
| 834 |
+
|
| 835 |
+
true_label
|
| 836 |
+
==
|
| 837 |
+
predicted_label
|
| 838 |
+
|
| 839 |
+
),
|
| 840 |
+
|
| 841 |
+
"all_sections_present": (
|
| 842 |
+
all_sections_present
|
| 843 |
+
),
|
| 844 |
+
|
| 845 |
+
"root_cause_token_f1": (
|
| 846 |
+
root_f1
|
| 847 |
+
),
|
| 848 |
+
|
| 849 |
+
"explanation_token_f1": (
|
| 850 |
+
explanation_f1
|
| 851 |
+
),
|
| 852 |
+
|
| 853 |
+
"recommendation_token_f1": (
|
| 854 |
+
recommendation_f1
|
| 855 |
+
),
|
| 856 |
+
|
| 857 |
+
"model_response": (
|
| 858 |
+
generated
|
| 859 |
+
),
|
| 860 |
+
|
| 861 |
+
"reference_response": (
|
| 862 |
+
reference
|
| 863 |
+
),
|
| 864 |
+
|
| 865 |
+
})
|
| 866 |
+
|
| 867 |
+
|
| 868 |
+
# --------------------------------------------------------
|
| 869 |
+
# Debug output
|
| 870 |
+
# --------------------------------------------------------
|
| 871 |
+
|
| 872 |
+
if args.debug:
|
| 873 |
+
|
| 874 |
+
print()
|
| 875 |
+
|
| 876 |
+
print("-" * 80)
|
| 877 |
+
|
| 878 |
+
print(
|
| 879 |
+
"Example:",
|
| 880 |
+
index + 1
|
| 881 |
+
)
|
| 882 |
+
|
| 883 |
+
print(
|
| 884 |
+
"Expected severity:",
|
| 885 |
+
true_label
|
| 886 |
+
)
|
| 887 |
+
|
| 888 |
+
print(
|
| 889 |
+
"Predicted severity:",
|
| 890 |
+
predicted_label
|
| 891 |
+
)
|
| 892 |
+
|
| 893 |
+
print()
|
| 894 |
+
|
| 895 |
+
print(
|
| 896 |
+
"MODEL RESPONSE:"
|
| 897 |
+
)
|
| 898 |
+
|
| 899 |
+
print()
|
| 900 |
+
|
| 901 |
+
print(
|
| 902 |
+
generated
|
| 903 |
+
)
|
| 904 |
+
|
| 905 |
+
|
| 906 |
+
# --------------------------------------------------------
|
| 907 |
+
# Progress
|
| 908 |
+
# --------------------------------------------------------
|
| 909 |
+
|
| 910 |
+
if not args.debug:
|
| 911 |
+
|
| 912 |
+
if (
|
| 913 |
+
(index + 1) % 10 == 0
|
| 914 |
+
or
|
| 915 |
+
(index + 1)
|
| 916 |
+
== len(test_dataset)
|
| 917 |
+
):
|
| 918 |
+
|
| 919 |
+
print(
|
| 920 |
+
|
| 921 |
+
f"Processed "
|
| 922 |
+
f"{index + 1}/"
|
| 923 |
+
f"{len(test_dataset)}"
|
| 924 |
+
|
| 925 |
+
)
|
| 926 |
+
|
| 927 |
+
|
| 928 |
+
# ============================================================
|
| 929 |
+
# SAVE PREDICTIONS
|
| 930 |
+
# ============================================================
|
| 931 |
+
|
| 932 |
+
prediction_file = os.path.join(
|
| 933 |
+
|
| 934 |
+
args.adapter,
|
| 935 |
+
|
| 936 |
+
"test_four_output_predictions.jsonl",
|
| 937 |
+
)
|
| 938 |
+
|
| 939 |
+
|
| 940 |
+
with open(
|
| 941 |
+
|
| 942 |
+
prediction_file,
|
| 943 |
+
|
| 944 |
+
"w",
|
| 945 |
+
|
| 946 |
+
encoding="utf-8",
|
| 947 |
+
|
| 948 |
+
) as file:
|
| 949 |
+
|
| 950 |
+
for row in predictions:
|
| 951 |
+
|
| 952 |
+
file.write(
|
| 953 |
+
|
| 954 |
+
json.dumps(
|
| 955 |
+
|
| 956 |
+
row,
|
| 957 |
+
|
| 958 |
+
ensure_ascii=False,
|
| 959 |
+
|
| 960 |
+
)
|
| 961 |
+
|
| 962 |
+
+ "\n"
|
| 963 |
+
|
| 964 |
+
)
|
| 965 |
+
|
| 966 |
+
|
| 967 |
+
# ============================================================
|
| 968 |
+
# VALID SEVERITY PREDICTIONS
|
| 969 |
+
# ============================================================
|
| 970 |
+
|
| 971 |
+
valid_pairs = [
|
| 972 |
+
|
| 973 |
+
(
|
| 974 |
+
true,
|
| 975 |
+
pred
|
| 976 |
+
)
|
| 977 |
+
|
| 978 |
+
for true, pred
|
| 979 |
+
|
| 980 |
+
in zip(
|
| 981 |
+
y_true,
|
| 982 |
+
y_pred
|
| 983 |
+
)
|
| 984 |
+
|
| 985 |
+
if true in [0, 1, 2]
|
| 986 |
+
and pred in [0, 1, 2]
|
| 987 |
+
|
| 988 |
+
]
|
| 989 |
+
|
| 990 |
+
|
| 991 |
+
if not valid_pairs:
|
| 992 |
+
|
| 993 |
+
print()
|
| 994 |
+
|
| 995 |
+
print(
|
| 996 |
+
"ERROR: Model did not produce"
|
| 997 |
+
" valid fault_severity values."
|
| 998 |
+
)
|
| 999 |
+
|
| 1000 |
+
print(
|
| 1001 |
+
"Check the generated responses."
|
| 1002 |
+
)
|
| 1003 |
+
|
| 1004 |
+
raise RuntimeError(
|
| 1005 |
+
"No valid severity predictions."
|
| 1006 |
+
)
|
| 1007 |
+
|
| 1008 |
+
|
| 1009 |
+
valid_true = [
|
| 1010 |
+
|
| 1011 |
+
pair[0]
|
| 1012 |
+
|
| 1013 |
+
for pair in valid_pairs
|
| 1014 |
+
|
| 1015 |
+
]
|
| 1016 |
+
|
| 1017 |
+
|
| 1018 |
+
valid_pred = [
|
| 1019 |
+
|
| 1020 |
+
pair[1]
|
| 1021 |
+
|
| 1022 |
+
for pair in valid_pairs
|
| 1023 |
+
|
| 1024 |
+
]
|
| 1025 |
+
|
| 1026 |
+
|
| 1027 |
+
# ============================================================
|
| 1028 |
+
# SEVERITY METRICS
|
| 1029 |
+
# ============================================================
|
| 1030 |
+
|
| 1031 |
+
accuracy = accuracy_score(
|
| 1032 |
+
|
| 1033 |
+
valid_true,
|
| 1034 |
+
|
| 1035 |
+
valid_pred,
|
| 1036 |
+
)
|
| 1037 |
+
|
| 1038 |
+
|
| 1039 |
+
precision, recall, f1, support = (
|
| 1040 |
+
precision_recall_fscore_support(
|
| 1041 |
+
|
| 1042 |
+
valid_true,
|
| 1043 |
+
|
| 1044 |
+
valid_pred,
|
| 1045 |
+
|
| 1046 |
+
labels=[
|
| 1047 |
+
0,
|
| 1048 |
+
1,
|
| 1049 |
+
2
|
| 1050 |
+
],
|
| 1051 |
+
|
| 1052 |
+
zero_division=0,
|
| 1053 |
+
|
| 1054 |
+
)
|
| 1055 |
+
)
|
| 1056 |
+
|
| 1057 |
+
|
| 1058 |
+
matrix = confusion_matrix(
|
| 1059 |
+
|
| 1060 |
+
valid_true,
|
| 1061 |
+
|
| 1062 |
+
valid_pred,
|
| 1063 |
+
|
| 1064 |
+
labels=[
|
| 1065 |
+
0,
|
| 1066 |
+
1,
|
| 1067 |
+
2
|
| 1068 |
+
],
|
| 1069 |
+
|
| 1070 |
+
)
|
| 1071 |
+
|
| 1072 |
+
|
| 1073 |
+
# ============================================================
|
| 1074 |
+
# FORMAT COMPLIANCE
|
| 1075 |
+
# ============================================================
|
| 1076 |
+
|
| 1077 |
+
format_compliance = (
|
| 1078 |
+
|
| 1079 |
+
sum(
|
| 1080 |
+
|
| 1081 |
+
row[
|
| 1082 |
+
"all_sections_present"
|
| 1083 |
+
]
|
| 1084 |
+
|
| 1085 |
+
for row
|
| 1086 |
+
in predictions
|
| 1087 |
+
|
| 1088 |
+
)
|
| 1089 |
+
|
| 1090 |
+
/
|
| 1091 |
+
|
| 1092 |
+
len(predictions)
|
| 1093 |
+
|
| 1094 |
+
)
|
| 1095 |
+
|
| 1096 |
+
|
| 1097 |
+
# ============================================================
|
| 1098 |
+
# AVERAGE TEXT SCORES
|
| 1099 |
+
# ============================================================
|
| 1100 |
+
|
| 1101 |
+
average_root_f1 = (
|
| 1102 |
+
|
| 1103 |
+
sum(root_scores)
|
| 1104 |
+
/
|
| 1105 |
+
len(root_scores)
|
| 1106 |
+
|
| 1107 |
+
)
|
| 1108 |
+
|
| 1109 |
+
|
| 1110 |
+
average_explanation_f1 = (
|
| 1111 |
+
|
| 1112 |
+
sum(explanation_scores)
|
| 1113 |
+
/
|
| 1114 |
+
len(explanation_scores)
|
| 1115 |
+
|
| 1116 |
+
)
|
| 1117 |
+
|
| 1118 |
+
|
| 1119 |
+
average_recommendation_f1 = (
|
| 1120 |
+
|
| 1121 |
+
sum(recommendation_scores)
|
| 1122 |
+
/
|
| 1123 |
+
len(recommendation_scores)
|
| 1124 |
+
|
| 1125 |
+
)
|
| 1126 |
+
|
| 1127 |
+
|
| 1128 |
+
# ============================================================
|
| 1129 |
+
# RESULTS
|
| 1130 |
+
# ============================================================
|
| 1131 |
+
|
| 1132 |
+
print()
|
| 1133 |
+
|
| 1134 |
+
print("=" * 80)
|
| 1135 |
+
|
| 1136 |
+
print(
|
| 1137 |
+
"FOUR-OUTPUT EVALUATION RESULTS"
|
| 1138 |
+
)
|
| 1139 |
+
|
| 1140 |
+
print("=" * 80)
|
| 1141 |
+
|
| 1142 |
+
|
| 1143 |
+
print()
|
| 1144 |
+
|
| 1145 |
+
print(
|
| 1146 |
+
f"Fault Severity Accuracy: "
|
| 1147 |
+
f"{accuracy:.4f}"
|
| 1148 |
+
)
|
| 1149 |
+
|
| 1150 |
+
|
| 1151 |
+
print(
|
| 1152 |
+
f"Fault Severity Accuracy: "
|
| 1153 |
+
f"{accuracy * 100:.2f}%"
|
| 1154 |
+
)
|
| 1155 |
+
|
| 1156 |
+
|
| 1157 |
+
print()
|
| 1158 |
+
|
| 1159 |
+
print(
|
| 1160 |
+
f"Four-section format compliance: "
|
| 1161 |
+
f"{format_compliance * 100:.2f}%"
|
| 1162 |
+
)
|
| 1163 |
+
|
| 1164 |
+
|
| 1165 |
+
print()
|
| 1166 |
+
|
| 1167 |
+
print(
|
| 1168 |
+
f"Average Root Cause token-F1: "
|
| 1169 |
+
f"{average_root_f1:.4f}"
|
| 1170 |
+
)
|
| 1171 |
+
|
| 1172 |
+
|
| 1173 |
+
print(
|
| 1174 |
+
f"Average Explanation token-F1: "
|
| 1175 |
+
f"{average_explanation_f1:.4f}"
|
| 1176 |
+
)
|
| 1177 |
+
|
| 1178 |
+
|
| 1179 |
+
print(
|
| 1180 |
+
f"Average Recommendation token-F1: "
|
| 1181 |
+
f"{average_recommendation_f1:.4f}"
|
| 1182 |
+
)
|
| 1183 |
+
|
| 1184 |
+
|
| 1185 |
+
# ============================================================
|
| 1186 |
+
# PER-CLASS METRICS
|
| 1187 |
+
# ============================================================
|
| 1188 |
+
|
| 1189 |
+
print()
|
| 1190 |
+
|
| 1191 |
+
print(
|
| 1192 |
+
"Per-class fault severity metrics:"
|
| 1193 |
+
)
|
| 1194 |
+
|
| 1195 |
+
|
| 1196 |
+
for index, severity in enumerate(
|
| 1197 |
+
[0, 1, 2]
|
| 1198 |
+
):
|
| 1199 |
+
|
| 1200 |
+
print(
|
| 1201 |
+
|
| 1202 |
+
f"Class {severity}: "
|
| 1203 |
+
|
| 1204 |
+
f"precision={precision[index]:.4f}, "
|
| 1205 |
+
|
| 1206 |
+
f"recall={recall[index]:.4f}, "
|
| 1207 |
+
|
| 1208 |
+
f"f1={f1[index]:.4f}, "
|
| 1209 |
+
|
| 1210 |
+
f"support={support[index]}"
|
| 1211 |
+
|
| 1212 |
+
)
|
| 1213 |
+
|
| 1214 |
+
|
| 1215 |
+
# ============================================================
|
| 1216 |
+
# CONFUSION MATRIX
|
| 1217 |
+
# ============================================================
|
| 1218 |
+
|
| 1219 |
+
print()
|
| 1220 |
+
|
| 1221 |
+
print(
|
| 1222 |
+
"Confusion matrix:"
|
| 1223 |
+
)
|
| 1224 |
+
|
| 1225 |
+
print()
|
| 1226 |
+
|
| 1227 |
+
print(
|
| 1228 |
+
" Predicted"
|
| 1229 |
+
)
|
| 1230 |
+
|
| 1231 |
+
print(
|
| 1232 |
+
" 0 1 2"
|
| 1233 |
+
)
|
| 1234 |
+
|
| 1235 |
+
|
| 1236 |
+
for index, row in enumerate(
|
| 1237 |
+
matrix
|
| 1238 |
+
):
|
| 1239 |
+
|
| 1240 |
+
print(
|
| 1241 |
+
|
| 1242 |
+
f"Actual {index} "
|
| 1243 |
+
|
| 1244 |
+
f"{row[0]:6d} "
|
| 1245 |
+
|
| 1246 |
+
f"{row[1]:6d} "
|
| 1247 |
+
|
| 1248 |
+
f"{row[2]:6d}"
|
| 1249 |
+
|
| 1250 |
+
)
|
| 1251 |
+
|
| 1252 |
+
|
| 1253 |
+
# ============================================================
|
| 1254 |
+
# MAJORITY BASELINE
|
| 1255 |
+
# ============================================================
|
| 1256 |
+
|
| 1257 |
+
counter = Counter(
|
| 1258 |
+
valid_true
|
| 1259 |
+
)
|
| 1260 |
+
|
| 1261 |
+
|
| 1262 |
+
majority_class = (
|
| 1263 |
+
counter.most_common(1)[0][0]
|
| 1264 |
+
)
|
| 1265 |
+
|
| 1266 |
+
|
| 1267 |
+
majority_accuracy = (
|
| 1268 |
+
|
| 1269 |
+
sum(
|
| 1270 |
+
|
| 1271 |
+
value
|
| 1272 |
+
== majority_class
|
| 1273 |
+
|
| 1274 |
+
for value
|
| 1275 |
+
in valid_true
|
| 1276 |
+
|
| 1277 |
+
)
|
| 1278 |
+
|
| 1279 |
+
/
|
| 1280 |
+
|
| 1281 |
+
len(valid_true)
|
| 1282 |
+
|
| 1283 |
+
)
|
| 1284 |
+
|
| 1285 |
+
|
| 1286 |
+
print()
|
| 1287 |
+
|
| 1288 |
+
print(
|
| 1289 |
+
"Majority-class baseline:"
|
| 1290 |
+
)
|
| 1291 |
+
|
| 1292 |
+
print(
|
| 1293 |
+
"Majority class:",
|
| 1294 |
+
majority_class
|
| 1295 |
+
)
|
| 1296 |
+
|
| 1297 |
+
print(
|
| 1298 |
+
f"Baseline accuracy: "
|
| 1299 |
+
f"{majority_accuracy:.4f}"
|
| 1300 |
+
)
|
| 1301 |
+
|
| 1302 |
+
|
| 1303 |
+
# ============================================================
|
| 1304 |
+
# OUTPUT FILE
|
| 1305 |
+
# ============================================================
|
| 1306 |
+
|
| 1307 |
+
print()
|
| 1308 |
+
|
| 1309 |
+
print(
|
| 1310 |
+
"Detailed predictions saved to:"
|
| 1311 |
+
)
|
| 1312 |
+
|
| 1313 |
+
print(
|
| 1314 |
+
os.path.abspath(
|
| 1315 |
+
prediction_file
|
| 1316 |
+
)
|
| 1317 |
+
)
|
| 1318 |
+
|
| 1319 |
+
|
| 1320 |
+
# ============================================================
|
| 1321 |
+
# WARNING
|
| 1322 |
+
# ============================================================
|
| 1323 |
+
|
| 1324 |
+
print()
|
| 1325 |
+
|
| 1326 |
+
print("=" * 80)
|
| 1327 |
+
|
| 1328 |
+
print(
|
| 1329 |
+
"IMPORTANT"
|
| 1330 |
+
)
|
| 1331 |
+
|
| 1332 |
+
print("=" * 80)
|
| 1333 |
+
|
| 1334 |
+
print(
|
| 1335 |
+
|
| 1336 |
+
"Root Cause, Explanation and Recommendation "
|
| 1337 |
+
"token-F1 are similarity metrics against the "
|
| 1338 |
+
"structured reference responses. They are NOT "
|
| 1339 |
+
"proof of real-world telecom engineering correctness."
|
| 1340 |
+
|
| 1341 |
+
)
|
| 1342 |
+
|
| 1343 |
+
print()
|
| 1344 |
+
|
| 1345 |
+
print(
|
| 1346 |
+
|
| 1347 |
+
"For production deployment, replace synthetic "
|
| 1348 |
+
"root-cause/recommendation targets with "
|
| 1349 |
+
"engineer-validated annotations."
|
| 1350 |
+
|
| 1351 |
+
)
|
| 1352 |
+
|
| 1353 |
+
print("=" * 80)
|
train.py
ADDED
|
@@ -0,0 +1,848 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ============================================================
|
| 2 |
+
# TELECOM QLoRA FINE-TUNING
|
| 3 |
+
# FOUR-OUTPUT TELECOM DIAGNOSIS
|
| 4 |
+
#
|
| 5 |
+
# Model:
|
| 6 |
+
# Qwen/Qwen2.5-1.5B-Instruct
|
| 7 |
+
#
|
| 8 |
+
# Output:
|
| 9 |
+
# Probable Root Cause
|
| 10 |
+
# Explanation
|
| 11 |
+
# Recommendation
|
| 12 |
+
# Fault Severity
|
| 13 |
+
# ============================================================
|
| 14 |
+
|
| 15 |
+
import os
|
| 16 |
+
import re
|
| 17 |
+
import torch
|
| 18 |
+
|
| 19 |
+
from datasets import load_dataset
|
| 20 |
+
|
| 21 |
+
from transformers import (
|
| 22 |
+
AutoTokenizer,
|
| 23 |
+
AutoModelForCausalLM,
|
| 24 |
+
BitsAndBytesConfig,
|
| 25 |
+
)
|
| 26 |
+
|
| 27 |
+
from peft import (
|
| 28 |
+
LoraConfig,
|
| 29 |
+
prepare_model_for_kbit_training,
|
| 30 |
+
)
|
| 31 |
+
|
| 32 |
+
from trl import (
|
| 33 |
+
SFTTrainer,
|
| 34 |
+
SFTConfig,
|
| 35 |
+
)
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
# ============================================================
|
| 39 |
+
# CONFIGURATION
|
| 40 |
+
# ============================================================
|
| 41 |
+
|
| 42 |
+
MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"
|
| 43 |
+
|
| 44 |
+
TRAIN_FILE = "sample/data/train_four_output.jsonl"
|
| 45 |
+
VALIDATION_FILE = "sample/data/validation_four_output.jsonl"
|
| 46 |
+
|
| 47 |
+
OUTPUT_DIR = "models/telecom-qwen-four-output"
|
| 48 |
+
|
| 49 |
+
CACHE_DIR = "sample/.cache/huggingface"
|
| 50 |
+
|
| 51 |
+
EPOCHS = 3
|
| 52 |
+
|
| 53 |
+
MAX_LENGTH = 1024
|
| 54 |
+
|
| 55 |
+
TRAIN_BATCH_SIZE = 1
|
| 56 |
+
|
| 57 |
+
EVAL_BATCH_SIZE = 1
|
| 58 |
+
|
| 59 |
+
GRADIENT_ACCUMULATION = 8
|
| 60 |
+
|
| 61 |
+
LEARNING_RATE = 2e-4
|
| 62 |
+
|
| 63 |
+
SEED = 42
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
# ============================================================
|
| 67 |
+
# REQUIRED OUTPUT FORMAT
|
| 68 |
+
# ============================================================
|
| 69 |
+
|
| 70 |
+
REQUIRED_SECTIONS = [
|
| 71 |
+
"Probable Root Cause:",
|
| 72 |
+
"Explanation:",
|
| 73 |
+
"Recommendation:",
|
| 74 |
+
"Fault Severity:",
|
| 75 |
+
]
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
# ============================================================
|
| 79 |
+
# HELPER FUNCTIONS
|
| 80 |
+
# ============================================================
|
| 81 |
+
|
| 82 |
+
def get_assistant_message(example):
|
| 83 |
+
|
| 84 |
+
for message in example["messages"]:
|
| 85 |
+
|
| 86 |
+
if message["role"] == "assistant":
|
| 87 |
+
|
| 88 |
+
return message["content"]
|
| 89 |
+
|
| 90 |
+
raise ValueError(
|
| 91 |
+
"Assistant message not found."
|
| 92 |
+
)
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def extract_fault_severity(text):
|
| 96 |
+
|
| 97 |
+
matches = re.findall(
|
| 98 |
+
r"fault[_\s-]*severity\s*[:=]\s*([012])",
|
| 99 |
+
text,
|
| 100 |
+
re.IGNORECASE,
|
| 101 |
+
)
|
| 102 |
+
|
| 103 |
+
if not matches:
|
| 104 |
+
|
| 105 |
+
return None
|
| 106 |
+
|
| 107 |
+
return int(matches[-1])
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
def verify_example(example):
|
| 111 |
+
|
| 112 |
+
# --------------------------------------------------------
|
| 113 |
+
# Check messages
|
| 114 |
+
# --------------------------------------------------------
|
| 115 |
+
|
| 116 |
+
if "messages" not in example:
|
| 117 |
+
|
| 118 |
+
raise ValueError(
|
| 119 |
+
"Dataset example does not contain 'messages'."
|
| 120 |
+
)
|
| 121 |
+
|
| 122 |
+
roles = [
|
| 123 |
+
message["role"]
|
| 124 |
+
for message in example["messages"]
|
| 125 |
+
]
|
| 126 |
+
|
| 127 |
+
required_roles = {
|
| 128 |
+
"system",
|
| 129 |
+
"user",
|
| 130 |
+
"assistant",
|
| 131 |
+
}
|
| 132 |
+
|
| 133 |
+
if not required_roles.issubset(set(roles)):
|
| 134 |
+
|
| 135 |
+
raise ValueError(
|
| 136 |
+
"Example must contain system, user and assistant messages."
|
| 137 |
+
)
|
| 138 |
+
|
| 139 |
+
# --------------------------------------------------------
|
| 140 |
+
# Check assistant response
|
| 141 |
+
# --------------------------------------------------------
|
| 142 |
+
|
| 143 |
+
assistant = get_assistant_message(example)
|
| 144 |
+
|
| 145 |
+
for section in REQUIRED_SECTIONS:
|
| 146 |
+
|
| 147 |
+
if section not in assistant:
|
| 148 |
+
|
| 149 |
+
raise ValueError(
|
| 150 |
+
f"Missing required section: {section}"
|
| 151 |
+
)
|
| 152 |
+
|
| 153 |
+
# --------------------------------------------------------
|
| 154 |
+
# Check severity
|
| 155 |
+
# --------------------------------------------------------
|
| 156 |
+
|
| 157 |
+
severity = extract_fault_severity(
|
| 158 |
+
assistant
|
| 159 |
+
)
|
| 160 |
+
|
| 161 |
+
if severity not in [0, 1, 2]:
|
| 162 |
+
|
| 163 |
+
raise ValueError(
|
| 164 |
+
f"Invalid fault severity: {severity}"
|
| 165 |
+
)
|
| 166 |
+
|
| 167 |
+
return example
|
| 168 |
+
|
| 169 |
+
|
| 170 |
+
def print_distribution(
|
| 171 |
+
dataset,
|
| 172 |
+
name,
|
| 173 |
+
):
|
| 174 |
+
|
| 175 |
+
counts = {
|
| 176 |
+
0: 0,
|
| 177 |
+
1: 0,
|
| 178 |
+
2: 0,
|
| 179 |
+
}
|
| 180 |
+
|
| 181 |
+
for example in dataset:
|
| 182 |
+
|
| 183 |
+
assistant = get_assistant_message(
|
| 184 |
+
example
|
| 185 |
+
)
|
| 186 |
+
|
| 187 |
+
severity = extract_fault_severity(
|
| 188 |
+
assistant
|
| 189 |
+
)
|
| 190 |
+
|
| 191 |
+
if severity in counts:
|
| 192 |
+
|
| 193 |
+
counts[severity] += 1
|
| 194 |
+
|
| 195 |
+
total = len(dataset)
|
| 196 |
+
|
| 197 |
+
print()
|
| 198 |
+
print(
|
| 199 |
+
f"{name} fault_severity distribution:"
|
| 200 |
+
)
|
| 201 |
+
|
| 202 |
+
for severity in [0, 1, 2]:
|
| 203 |
+
|
| 204 |
+
percentage = (
|
| 205 |
+
counts[severity] / total * 100
|
| 206 |
+
)
|
| 207 |
+
|
| 208 |
+
print(
|
| 209 |
+
f" {severity}: "
|
| 210 |
+
f"{counts[severity]} "
|
| 211 |
+
f"({percentage:.2f}%)"
|
| 212 |
+
)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
# ============================================================
|
| 216 |
+
# START
|
| 217 |
+
# ============================================================
|
| 218 |
+
|
| 219 |
+
print("=" * 80)
|
| 220 |
+
|
| 221 |
+
print(
|
| 222 |
+
"TELECOM QLoRA FINE-TUNING"
|
| 223 |
+
)
|
| 224 |
+
|
| 225 |
+
print(
|
| 226 |
+
"FOUR-OUTPUT TELECOM DIAGNOSIS"
|
| 227 |
+
)
|
| 228 |
+
|
| 229 |
+
print("=" * 80)
|
| 230 |
+
|
| 231 |
+
|
| 232 |
+
# ============================================================
|
| 233 |
+
# GPU CHECK
|
| 234 |
+
# ============================================================
|
| 235 |
+
|
| 236 |
+
print()
|
| 237 |
+
|
| 238 |
+
print(
|
| 239 |
+
"CUDA available:",
|
| 240 |
+
torch.cuda.is_available()
|
| 241 |
+
)
|
| 242 |
+
|
| 243 |
+
if not torch.cuda.is_available():
|
| 244 |
+
|
| 245 |
+
raise RuntimeError(
|
| 246 |
+
"CUDA GPU is required for this training configuration."
|
| 247 |
+
)
|
| 248 |
+
|
| 249 |
+
|
| 250 |
+
gpu_name = torch.cuda.get_device_name(0)
|
| 251 |
+
|
| 252 |
+
gpu_memory = (
|
| 253 |
+
torch.cuda.get_device_properties(0)
|
| 254 |
+
.total_memory
|
| 255 |
+
/ (1024 ** 3)
|
| 256 |
+
)
|
| 257 |
+
|
| 258 |
+
|
| 259 |
+
print(
|
| 260 |
+
"GPU:",
|
| 261 |
+
gpu_name
|
| 262 |
+
)
|
| 263 |
+
|
| 264 |
+
print(
|
| 265 |
+
"VRAM:",
|
| 266 |
+
round(gpu_memory, 2),
|
| 267 |
+
"GB"
|
| 268 |
+
)
|
| 269 |
+
|
| 270 |
+
|
| 271 |
+
# ============================================================
|
| 272 |
+
# DIRECTORIES
|
| 273 |
+
# ============================================================
|
| 274 |
+
|
| 275 |
+
os.makedirs(
|
| 276 |
+
CACHE_DIR,
|
| 277 |
+
exist_ok=True
|
| 278 |
+
)
|
| 279 |
+
|
| 280 |
+
os.makedirs(
|
| 281 |
+
OUTPUT_DIR,
|
| 282 |
+
exist_ok=True
|
| 283 |
+
)
|
| 284 |
+
|
| 285 |
+
|
| 286 |
+
# ============================================================
|
| 287 |
+
# CHECK DATA FILES
|
| 288 |
+
# ============================================================
|
| 289 |
+
|
| 290 |
+
if not os.path.exists(TRAIN_FILE):
|
| 291 |
+
|
| 292 |
+
raise FileNotFoundError(
|
| 293 |
+
f"Training dataset not found:\n{TRAIN_FILE}"
|
| 294 |
+
)
|
| 295 |
+
|
| 296 |
+
|
| 297 |
+
if not os.path.exists(
|
| 298 |
+
VALIDATION_FILE
|
| 299 |
+
):
|
| 300 |
+
|
| 301 |
+
raise FileNotFoundError(
|
| 302 |
+
f"Validation dataset not found:\n"
|
| 303 |
+
f"{VALIDATION_FILE}"
|
| 304 |
+
)
|
| 305 |
+
|
| 306 |
+
|
| 307 |
+
# ============================================================
|
| 308 |
+
# LOAD DATA
|
| 309 |
+
# ============================================================
|
| 310 |
+
|
| 311 |
+
print()
|
| 312 |
+
|
| 313 |
+
print("=" * 80)
|
| 314 |
+
|
| 315 |
+
print(
|
| 316 |
+
"LOADING DATASETS"
|
| 317 |
+
)
|
| 318 |
+
|
| 319 |
+
print("=" * 80)
|
| 320 |
+
|
| 321 |
+
|
| 322 |
+
train_dataset = load_dataset(
|
| 323 |
+
"json",
|
| 324 |
+
data_files=TRAIN_FILE,
|
| 325 |
+
split="train",
|
| 326 |
+
cache_dir=CACHE_DIR,
|
| 327 |
+
)
|
| 328 |
+
|
| 329 |
+
|
| 330 |
+
validation_dataset = load_dataset(
|
| 331 |
+
"json",
|
| 332 |
+
data_files=VALIDATION_FILE,
|
| 333 |
+
split="train",
|
| 334 |
+
cache_dir=CACHE_DIR,
|
| 335 |
+
)
|
| 336 |
+
|
| 337 |
+
|
| 338 |
+
print(
|
| 339 |
+
"Training examples:",
|
| 340 |
+
len(train_dataset)
|
| 341 |
+
)
|
| 342 |
+
|
| 343 |
+
print(
|
| 344 |
+
"Validation examples:",
|
| 345 |
+
len(validation_dataset)
|
| 346 |
+
)
|
| 347 |
+
|
| 348 |
+
|
| 349 |
+
# ============================================================
|
| 350 |
+
# VERIFY DATA
|
| 351 |
+
# ============================================================
|
| 352 |
+
|
| 353 |
+
print()
|
| 354 |
+
|
| 355 |
+
print(
|
| 356 |
+
"Verifying four-output format..."
|
| 357 |
+
)
|
| 358 |
+
|
| 359 |
+
|
| 360 |
+
train_dataset = train_dataset.map(
|
| 361 |
+
verify_example
|
| 362 |
+
)
|
| 363 |
+
|
| 364 |
+
|
| 365 |
+
validation_dataset = validation_dataset.map(
|
| 366 |
+
verify_example
|
| 367 |
+
)
|
| 368 |
+
|
| 369 |
+
|
| 370 |
+
print(
|
| 371 |
+
"Dataset verification completed."
|
| 372 |
+
)
|
| 373 |
+
|
| 374 |
+
|
| 375 |
+
# ============================================================
|
| 376 |
+
# PRINT LABEL DISTRIBUTION
|
| 377 |
+
# ============================================================
|
| 378 |
+
|
| 379 |
+
print_distribution(
|
| 380 |
+
train_dataset,
|
| 381 |
+
"Training"
|
| 382 |
+
)
|
| 383 |
+
|
| 384 |
+
|
| 385 |
+
print_distribution(
|
| 386 |
+
validation_dataset,
|
| 387 |
+
"Validation"
|
| 388 |
+
)
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
# ============================================================
|
| 392 |
+
# TOKENIZER
|
| 393 |
+
# ============================================================
|
| 394 |
+
|
| 395 |
+
print()
|
| 396 |
+
|
| 397 |
+
print("=" * 80)
|
| 398 |
+
|
| 399 |
+
print(
|
| 400 |
+
"LOADING TOKENIZER"
|
| 401 |
+
)
|
| 402 |
+
|
| 403 |
+
print("=" * 80)
|
| 404 |
+
|
| 405 |
+
|
| 406 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 407 |
+
MODEL_NAME,
|
| 408 |
+
trust_remote_code=True,
|
| 409 |
+
cache_dir=CACHE_DIR,
|
| 410 |
+
)
|
| 411 |
+
|
| 412 |
+
|
| 413 |
+
if tokenizer.pad_token is None:
|
| 414 |
+
|
| 415 |
+
tokenizer.pad_token = tokenizer.eos_token
|
| 416 |
+
|
| 417 |
+
|
| 418 |
+
tokenizer.padding_side = "right"
|
| 419 |
+
|
| 420 |
+
|
| 421 |
+
# ============================================================
|
| 422 |
+
# 4-BIT QUANTIZATION
|
| 423 |
+
# ============================================================
|
| 424 |
+
|
| 425 |
+
print()
|
| 426 |
+
|
| 427 |
+
print("=" * 80)
|
| 428 |
+
|
| 429 |
+
print(
|
| 430 |
+
"CONFIGURING 4-BIT QUANTIZATION"
|
| 431 |
+
)
|
| 432 |
+
|
| 433 |
+
print("=" * 80)
|
| 434 |
+
|
| 435 |
+
|
| 436 |
+
bnb_config = BitsAndBytesConfig(
|
| 437 |
+
|
| 438 |
+
load_in_4bit=True,
|
| 439 |
+
|
| 440 |
+
bnb_4bit_quant_type="nf4",
|
| 441 |
+
|
| 442 |
+
bnb_4bit_compute_dtype=torch.float16,
|
| 443 |
+
|
| 444 |
+
bnb_4bit_use_double_quant=True,
|
| 445 |
+
)
|
| 446 |
+
|
| 447 |
+
|
| 448 |
+
# ============================================================
|
| 449 |
+
# LOAD BASE MODEL
|
| 450 |
+
# ============================================================
|
| 451 |
+
|
| 452 |
+
print()
|
| 453 |
+
|
| 454 |
+
print("=" * 80)
|
| 455 |
+
|
| 456 |
+
print(
|
| 457 |
+
"LOADING BASE MODEL"
|
| 458 |
+
)
|
| 459 |
+
|
| 460 |
+
print("=" * 80)
|
| 461 |
+
|
| 462 |
+
|
| 463 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 464 |
+
|
| 465 |
+
MODEL_NAME,
|
| 466 |
+
|
| 467 |
+
quantization_config=bnb_config,
|
| 468 |
+
|
| 469 |
+
device_map="auto",
|
| 470 |
+
|
| 471 |
+
dtype=torch.float16,
|
| 472 |
+
|
| 473 |
+
trust_remote_code=True,
|
| 474 |
+
|
| 475 |
+
cache_dir=CACHE_DIR,
|
| 476 |
+
)
|
| 477 |
+
|
| 478 |
+
|
| 479 |
+
print(
|
| 480 |
+
"Base model loaded."
|
| 481 |
+
)
|
| 482 |
+
|
| 483 |
+
|
| 484 |
+
# ============================================================
|
| 485 |
+
# PREPARE QLORA
|
| 486 |
+
# ============================================================
|
| 487 |
+
|
| 488 |
+
print()
|
| 489 |
+
|
| 490 |
+
print(
|
| 491 |
+
"Preparing model for QLoRA..."
|
| 492 |
+
)
|
| 493 |
+
|
| 494 |
+
|
| 495 |
+
model = prepare_model_for_kbit_training(
|
| 496 |
+
model
|
| 497 |
+
)
|
| 498 |
+
|
| 499 |
+
|
| 500 |
+
model.config.use_cache = False
|
| 501 |
+
|
| 502 |
+
|
| 503 |
+
# ============================================================
|
| 504 |
+
# LORA CONFIGURATION
|
| 505 |
+
# ============================================================
|
| 506 |
+
|
| 507 |
+
print()
|
| 508 |
+
|
| 509 |
+
print("=" * 80)
|
| 510 |
+
|
| 511 |
+
print(
|
| 512 |
+
"CONFIGURING LoRA"
|
| 513 |
+
)
|
| 514 |
+
|
| 515 |
+
print("=" * 80)
|
| 516 |
+
|
| 517 |
+
|
| 518 |
+
lora_config = LoraConfig(
|
| 519 |
+
|
| 520 |
+
r=8,
|
| 521 |
+
|
| 522 |
+
lora_alpha=16,
|
| 523 |
+
|
| 524 |
+
lora_dropout=0.05,
|
| 525 |
+
|
| 526 |
+
target_modules=[
|
| 527 |
+
"q_proj",
|
| 528 |
+
"k_proj",
|
| 529 |
+
"v_proj",
|
| 530 |
+
"o_proj",
|
| 531 |
+
],
|
| 532 |
+
|
| 533 |
+
bias="none",
|
| 534 |
+
|
| 535 |
+
task_type="CAUSAL_LM",
|
| 536 |
+
)
|
| 537 |
+
|
| 538 |
+
|
| 539 |
+
# ============================================================
|
| 540 |
+
# CHAT FORMAT
|
| 541 |
+
# ============================================================
|
| 542 |
+
|
| 543 |
+
def formatting_func(example):
|
| 544 |
+
|
| 545 |
+
return tokenizer.apply_chat_template(
|
| 546 |
+
|
| 547 |
+
example["messages"],
|
| 548 |
+
|
| 549 |
+
tokenize=False,
|
| 550 |
+
|
| 551 |
+
add_generation_prompt=False,
|
| 552 |
+
)
|
| 553 |
+
|
| 554 |
+
|
| 555 |
+
# ============================================================
|
| 556 |
+
# TRAINING CONFIGURATION
|
| 557 |
+
# ============================================================
|
| 558 |
+
|
| 559 |
+
print()
|
| 560 |
+
|
| 561 |
+
print("=" * 80)
|
| 562 |
+
|
| 563 |
+
print(
|
| 564 |
+
"CONFIGURING TRAINING"
|
| 565 |
+
)
|
| 566 |
+
|
| 567 |
+
print("=" * 80)
|
| 568 |
+
|
| 569 |
+
|
| 570 |
+
# IMPORTANT:
|
| 571 |
+
# max_length belongs to SFTConfig, not SFTTrainer.
|
| 572 |
+
|
| 573 |
+
training_args = SFTConfig(
|
| 574 |
+
|
| 575 |
+
output_dir=OUTPUT_DIR,
|
| 576 |
+
|
| 577 |
+
seed=SEED,
|
| 578 |
+
|
| 579 |
+
data_seed=SEED,
|
| 580 |
+
|
| 581 |
+
per_device_train_batch_size=TRAIN_BATCH_SIZE,
|
| 582 |
+
|
| 583 |
+
per_device_eval_batch_size=EVAL_BATCH_SIZE,
|
| 584 |
+
|
| 585 |
+
gradient_accumulation_steps=GRADIENT_ACCUMULATION,
|
| 586 |
+
|
| 587 |
+
num_train_epochs=EPOCHS,
|
| 588 |
+
|
| 589 |
+
learning_rate=LEARNING_RATE,
|
| 590 |
+
|
| 591 |
+
fp16=False,
|
| 592 |
+
|
| 593 |
+
bf16=False,
|
| 594 |
+
|
| 595 |
+
gradient_checkpointing=True,
|
| 596 |
+
|
| 597 |
+
gradient_checkpointing_kwargs={
|
| 598 |
+
"use_reentrant": False
|
| 599 |
+
},
|
| 600 |
+
|
| 601 |
+
optim="paged_adamw_8bit",
|
| 602 |
+
|
| 603 |
+
logging_steps=10,
|
| 604 |
+
|
| 605 |
+
eval_strategy="epoch",
|
| 606 |
+
|
| 607 |
+
save_strategy="epoch",
|
| 608 |
+
|
| 609 |
+
save_total_limit=2,
|
| 610 |
+
|
| 611 |
+
load_best_model_at_end=True,
|
| 612 |
+
|
| 613 |
+
metric_for_best_model="eval_loss",
|
| 614 |
+
|
| 615 |
+
greater_is_better=False,
|
| 616 |
+
|
| 617 |
+
report_to="none",
|
| 618 |
+
|
| 619 |
+
remove_unused_columns=False,
|
| 620 |
+
|
| 621 |
+
max_length=MAX_LENGTH,
|
| 622 |
+
|
| 623 |
+
packing=False,
|
| 624 |
+
)
|
| 625 |
+
|
| 626 |
+
|
| 627 |
+
# ============================================================
|
| 628 |
+
# CREATE SFT TRAINER
|
| 629 |
+
# ============================================================
|
| 630 |
+
|
| 631 |
+
print()
|
| 632 |
+
|
| 633 |
+
print("=" * 80)
|
| 634 |
+
|
| 635 |
+
print(
|
| 636 |
+
"CREATING SFT TRAINER"
|
| 637 |
+
)
|
| 638 |
+
|
| 639 |
+
print("=" * 80)
|
| 640 |
+
|
| 641 |
+
|
| 642 |
+
trainer = SFTTrainer(
|
| 643 |
+
|
| 644 |
+
model=model,
|
| 645 |
+
|
| 646 |
+
train_dataset=train_dataset,
|
| 647 |
+
|
| 648 |
+
eval_dataset=validation_dataset,
|
| 649 |
+
|
| 650 |
+
peft_config=lora_config,
|
| 651 |
+
|
| 652 |
+
formatting_func=formatting_func,
|
| 653 |
+
|
| 654 |
+
processing_class=tokenizer,
|
| 655 |
+
|
| 656 |
+
args=training_args,
|
| 657 |
+
)
|
| 658 |
+
|
| 659 |
+
|
| 660 |
+
# ============================================================
|
| 661 |
+
# TRAIN
|
| 662 |
+
# ============================================================
|
| 663 |
+
|
| 664 |
+
print()
|
| 665 |
+
|
| 666 |
+
print("=" * 80)
|
| 667 |
+
|
| 668 |
+
print(
|
| 669 |
+
"STARTING TRAINING"
|
| 670 |
+
)
|
| 671 |
+
|
| 672 |
+
print("=" * 80)
|
| 673 |
+
|
| 674 |
+
|
| 675 |
+
print(
|
| 676 |
+
"Training examples:",
|
| 677 |
+
len(train_dataset)
|
| 678 |
+
)
|
| 679 |
+
|
| 680 |
+
print(
|
| 681 |
+
"Validation examples:",
|
| 682 |
+
len(validation_dataset)
|
| 683 |
+
)
|
| 684 |
+
|
| 685 |
+
print(
|
| 686 |
+
"Epochs:",
|
| 687 |
+
EPOCHS
|
| 688 |
+
)
|
| 689 |
+
|
| 690 |
+
print(
|
| 691 |
+
"Batch size:",
|
| 692 |
+
TRAIN_BATCH_SIZE
|
| 693 |
+
)
|
| 694 |
+
|
| 695 |
+
print(
|
| 696 |
+
"Gradient accumulation:",
|
| 697 |
+
GRADIENT_ACCUMULATION
|
| 698 |
+
)
|
| 699 |
+
|
| 700 |
+
print(
|
| 701 |
+
"Effective batch size:",
|
| 702 |
+
TRAIN_BATCH_SIZE
|
| 703 |
+
* GRADIENT_ACCUMULATION
|
| 704 |
+
)
|
| 705 |
+
|
| 706 |
+
print(
|
| 707 |
+
"Learning rate:",
|
| 708 |
+
LEARNING_RATE
|
| 709 |
+
)
|
| 710 |
+
|
| 711 |
+
print(
|
| 712 |
+
"Maximum sequence length:",
|
| 713 |
+
MAX_LENGTH
|
| 714 |
+
)
|
| 715 |
+
|
| 716 |
+
print("=" * 80)
|
| 717 |
+
|
| 718 |
+
|
| 719 |
+
try:
|
| 720 |
+
|
| 721 |
+
result = trainer.train()
|
| 722 |
+
|
| 723 |
+
except KeyboardInterrupt:
|
| 724 |
+
|
| 725 |
+
print()
|
| 726 |
+
|
| 727 |
+
print(
|
| 728 |
+
"Training interrupted."
|
| 729 |
+
)
|
| 730 |
+
|
| 731 |
+
print(
|
| 732 |
+
"Saving current adapter..."
|
| 733 |
+
)
|
| 734 |
+
|
| 735 |
+
trainer.save_model(
|
| 736 |
+
OUTPUT_DIR
|
| 737 |
+
)
|
| 738 |
+
|
| 739 |
+
tokenizer.save_pretrained(
|
| 740 |
+
OUTPUT_DIR
|
| 741 |
+
)
|
| 742 |
+
|
| 743 |
+
trainer.save_state()
|
| 744 |
+
|
| 745 |
+
raise
|
| 746 |
+
|
| 747 |
+
|
| 748 |
+
# ============================================================
|
| 749 |
+
# SAVE MODEL
|
| 750 |
+
# ============================================================
|
| 751 |
+
|
| 752 |
+
print()
|
| 753 |
+
|
| 754 |
+
print("=" * 80)
|
| 755 |
+
|
| 756 |
+
print(
|
| 757 |
+
"SAVING MODEL"
|
| 758 |
+
)
|
| 759 |
+
|
| 760 |
+
print("=" * 80)
|
| 761 |
+
|
| 762 |
+
|
| 763 |
+
trainer.save_model(
|
| 764 |
+
OUTPUT_DIR
|
| 765 |
+
)
|
| 766 |
+
|
| 767 |
+
|
| 768 |
+
tokenizer.save_pretrained(
|
| 769 |
+
OUTPUT_DIR
|
| 770 |
+
)
|
| 771 |
+
|
| 772 |
+
|
| 773 |
+
trainer.save_state()
|
| 774 |
+
|
| 775 |
+
|
| 776 |
+
# ============================================================
|
| 777 |
+
# RESULTS
|
| 778 |
+
# ============================================================
|
| 779 |
+
|
| 780 |
+
print()
|
| 781 |
+
|
| 782 |
+
print("=" * 80)
|
| 783 |
+
|
| 784 |
+
print(
|
| 785 |
+
"TRAINING COMPLETE"
|
| 786 |
+
)
|
| 787 |
+
|
| 788 |
+
print("=" * 80)
|
| 789 |
+
|
| 790 |
+
|
| 791 |
+
print(
|
| 792 |
+
"Adapter saved to:"
|
| 793 |
+
)
|
| 794 |
+
|
| 795 |
+
print(
|
| 796 |
+
os.path.abspath(
|
| 797 |
+
OUTPUT_DIR
|
| 798 |
+
)
|
| 799 |
+
)
|
| 800 |
+
|
| 801 |
+
|
| 802 |
+
if result is not None:
|
| 803 |
+
|
| 804 |
+
print()
|
| 805 |
+
|
| 806 |
+
print(
|
| 807 |
+
"Training metrics:"
|
| 808 |
+
)
|
| 809 |
+
|
| 810 |
+
for key, value in result.metrics.items():
|
| 811 |
+
|
| 812 |
+
print(
|
| 813 |
+
f"{key}: {value}"
|
| 814 |
+
)
|
| 815 |
+
|
| 816 |
+
|
| 817 |
+
# ============================================================
|
| 818 |
+
# EXPECTED OUTPUT
|
| 819 |
+
# ============================================================
|
| 820 |
+
|
| 821 |
+
print()
|
| 822 |
+
|
| 823 |
+
print("=" * 80)
|
| 824 |
+
|
| 825 |
+
print(
|
| 826 |
+
"EXPECTED MODEL RESPONSE FORMAT"
|
| 827 |
+
)
|
| 828 |
+
|
| 829 |
+
print("=" * 80)
|
| 830 |
+
|
| 831 |
+
print(
|
| 832 |
+
"""Probable Root Cause:
|
| 833 |
+
<probable root cause based only on supplied evidence>
|
| 834 |
+
|
| 835 |
+
Explanation:
|
| 836 |
+
<technical explanation>
|
| 837 |
+
|
| 838 |
+
Recommendation:
|
| 839 |
+
1. <recommended action>
|
| 840 |
+
2. <recommended action>
|
| 841 |
+
3. <recommended action>
|
| 842 |
+
|
| 843 |
+
Fault Severity:
|
| 844 |
+
fault_severity=0|1|2
|
| 845 |
+
"""
|
| 846 |
+
)
|
| 847 |
+
|
| 848 |
+
print("=" * 80)
|