Spaces:
Sleeping
Sleeping
Jit Bahadur Khamcha
commited on
Commit
•
0bf21b8
1
Parent(s):
1068021
add code and streamlit code
Browse files- app.py +26 -2
- finetune.ipynb +2720 -0
- finetuning_squad/checkpoint-16000/config.json +24 -0
- finetuning_squad/checkpoint-16000/model.safetensors +3 -0
- finetuning_squad/checkpoint-16000/optimizer.pt +3 -0
- finetuning_squad/checkpoint-16000/rng_state.pth +3 -0
- finetuning_squad/checkpoint-16000/scheduler.pt +3 -0
- finetuning_squad/checkpoint-16000/special_tokens_map.json +7 -0
- finetuning_squad/checkpoint-16000/tokenizer.json +0 -0
- finetuning_squad/checkpoint-16000/tokenizer_config.json +55 -0
- finetuning_squad/checkpoint-16000/trainer_state.json +229 -0
- finetuning_squad/checkpoint-16000/training_args.bin +3 -0
- finetuning_squad/checkpoint-16000/vocab.txt +0 -0
- finetuning_squad/runs/Feb04_15-16-16_gpu-MS-7C06/events.out.tfevents.1707039077.gpu-MS-7C06.1949275.0 +3 -0
- finetuning_squad/runs/Feb04_15-16-59_gpu-MS-7C06/events.out.tfevents.1707039122.gpu-MS-7C06.1949275.1 +3 -0
- finetuning_squad/runs/Feb04_15-17-09_gpu-MS-7C06/events.out.tfevents.1707039130.gpu-MS-7C06.1949275.2 +3 -0
- requirements.txt +88 -0
app.py
CHANGED
@@ -1,4 +1,28 @@
|
|
1 |
import streamlit as st
|
|
|
|
|
2 |
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
import streamlit as st
|
2 |
+
import torch
|
3 |
+
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
|
4 |
|
5 |
+
|
6 |
+
# Load the question answering pipeline
|
7 |
+
question_answerer = pipeline("question-answering", model="finetuning_squad/checkpoint-16000")
|
8 |
+
|
9 |
+
# Streamlit app
|
10 |
+
st.title("Question Answering App")
|
11 |
+
|
12 |
+
# Text box for context
|
13 |
+
context = st.text_area("Enter Context", "")
|
14 |
+
|
15 |
+
# Text box for question
|
16 |
+
question = st.text_input("Enter Question", "")
|
17 |
+
|
18 |
+
# Button to find the answer
|
19 |
+
if st.button("Find Answer"):
|
20 |
+
if context and question:
|
21 |
+
# Perform question answering
|
22 |
+
answer = question_answerer(context=context, question=question)
|
23 |
+
|
24 |
+
# Display the answer
|
25 |
+
st.subheader("Answer:")
|
26 |
+
st.write(answer)
|
27 |
+
else:
|
28 |
+
st.warning("Please enter both context and question.")
|
finetune.ipynb
ADDED
@@ -0,0 +1,2720 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 2,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [],
|
8 |
+
"source": [
|
9 |
+
"# importing libraries\n",
|
10 |
+
"\n",
|
11 |
+
"import pandas as pd\n",
|
12 |
+
"from datasets import load_dataset\n",
|
13 |
+
"\n",
|
14 |
+
"import torch\n",
|
15 |
+
"from transformers import AutoTokenizer, Trainer, TrainingArguments, DefaultDataCollator, AutoModelForQuestionAnswering\n"
|
16 |
+
]
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"cell_type": "code",
|
20 |
+
"execution_count": 2,
|
21 |
+
"metadata": {},
|
22 |
+
"outputs": [],
|
23 |
+
"source": [
|
24 |
+
"# download and load the dataset splitting intor train and test set. Here only number of dataset is limited to 5000 \n",
|
25 |
+
"squad = load_dataset(\"squad\")"
|
26 |
+
]
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"cell_type": "code",
|
30 |
+
"execution_count": 3,
|
31 |
+
"metadata": {},
|
32 |
+
"outputs": [
|
33 |
+
{
|
34 |
+
"data": {
|
35 |
+
"text/plain": [
|
36 |
+
"DatasetDict({\n",
|
37 |
+
" train: Dataset({\n",
|
38 |
+
" features: ['id', 'title', 'context', 'question', 'answers'],\n",
|
39 |
+
" num_rows: 87599\n",
|
40 |
+
" })\n",
|
41 |
+
" validation: Dataset({\n",
|
42 |
+
" features: ['id', 'title', 'context', 'question', 'answers'],\n",
|
43 |
+
" num_rows: 10570\n",
|
44 |
+
" })\n",
|
45 |
+
"})"
|
46 |
+
]
|
47 |
+
},
|
48 |
+
"execution_count": 3,
|
49 |
+
"metadata": {},
|
50 |
+
"output_type": "execute_result"
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"source": [
|
54 |
+
"squad"
|
55 |
+
]
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"cell_type": "code",
|
59 |
+
"execution_count": 4,
|
60 |
+
"metadata": {},
|
61 |
+
"outputs": [
|
62 |
+
{
|
63 |
+
"data": {
|
64 |
+
"text/plain": [
|
65 |
+
"DatasetDict({\n",
|
66 |
+
" train: Dataset({\n",
|
67 |
+
" features: ['id', 'title', 'context', 'question', 'answers'],\n",
|
68 |
+
" num_rows: 87599\n",
|
69 |
+
" })\n",
|
70 |
+
" validation: Dataset({\n",
|
71 |
+
" features: ['id', 'title', 'context', 'question', 'answers'],\n",
|
72 |
+
" num_rows: 10570\n",
|
73 |
+
" })\n",
|
74 |
+
"})"
|
75 |
+
]
|
76 |
+
},
|
77 |
+
"execution_count": 4,
|
78 |
+
"metadata": {},
|
79 |
+
"output_type": "execute_result"
|
80 |
+
}
|
81 |
+
],
|
82 |
+
"source": [
|
83 |
+
"squad"
|
84 |
+
]
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"cell_type": "code",
|
88 |
+
"execution_count": 5,
|
89 |
+
"metadata": {},
|
90 |
+
"outputs": [
|
91 |
+
{
|
92 |
+
"name": "stdout",
|
93 |
+
"output_type": "stream",
|
94 |
+
"text": [
|
95 |
+
"{'id': '5733be284776f41900661182', 'title': 'University_of_Notre_Dame', 'context': 'Architecturally, the school has a Catholic character. Atop the Main Building\\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend \"Venite Ad Me Omnes\". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.', 'question': 'To whom did the Virgin Mary allegedly appear in 1858 in Lourdes France?', 'answers': {'text': ['Saint Bernadette Soubirous'], 'answer_start': [515]}}\n",
|
96 |
+
"{'id': '5733be284776f4190066117f', 'title': 'University_of_Notre_Dame', 'context': 'Architecturally, the school has a Catholic character. Atop the Main Building\\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend \"Venite Ad Me Omnes\". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.', 'question': 'What is in front of the Notre Dame Main Building?', 'answers': {'text': ['a copper statue of Christ'], 'answer_start': [188]}}\n",
|
97 |
+
"{'id': '5733be284776f41900661180', 'title': 'University_of_Notre_Dame', 'context': 'Architecturally, the school has a Catholic character. Atop the Main Building\\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend \"Venite Ad Me Omnes\". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.', 'question': 'The Basilica of the Sacred heart at Notre Dame is beside to which structure?', 'answers': {'text': ['the Main Building'], 'answer_start': [279]}}\n",
|
98 |
+
"{'id': '5733be284776f41900661181', 'title': 'University_of_Notre_Dame', 'context': 'Architecturally, the school has a Catholic character. Atop the Main Building\\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend \"Venite Ad Me Omnes\". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.', 'question': 'What is the Grotto at Notre Dame?', 'answers': {'text': ['a Marian place of prayer and reflection'], 'answer_start': [381]}}\n",
|
99 |
+
"{'id': '5733be284776f4190066117e', 'title': 'University_of_Notre_Dame', 'context': 'Architecturally, the school has a Catholic character. Atop the Main Building\\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend \"Venite Ad Me Omnes\". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.', 'question': 'What sits on top of the Main Building at Notre Dame?', 'answers': {'text': ['a golden statue of the Virgin Mary'], 'answer_start': [92]}}\n"
|
100 |
+
]
|
101 |
+
}
|
102 |
+
],
|
103 |
+
"source": [
|
104 |
+
"# Print the top 5 rows\n",
|
105 |
+
"for i in range(5):\n",
|
106 |
+
" print(squad[\"train\"][i])"
|
107 |
+
]
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"cell_type": "markdown",
|
111 |
+
"metadata": {},
|
112 |
+
"source": [
|
113 |
+
"### several important fields \n",
|
114 |
+
"<li>answers: the starting location of the answer token and the answer text. </li>\n",
|
115 |
+
"<li>context: background information from which the model needs to extract the answer. </li>\n",
|
116 |
+
"<li>question: the question a model should answer. </li>"
|
117 |
+
]
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"cell_type": "code",
|
121 |
+
"execution_count": 6,
|
122 |
+
"metadata": {},
|
123 |
+
"outputs": [],
|
124 |
+
"source": [
|
125 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"distilbert-base-uncased\")"
|
126 |
+
]
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"cell_type": "markdown",
|
130 |
+
"metadata": {},
|
131 |
+
"source": [
|
132 |
+
"## Preprocessing Steps for Question Answering Tasks\n",
|
133 |
+
"\n",
|
134 |
+
"### Dealing with Long Contexts\n",
|
135 |
+
"\n",
|
136 |
+
"Some examples in a dataset may have a very long context that exceeds the maximum input length of the model. To address this:\n",
|
137 |
+
"\n",
|
138 |
+
"- Truncate only the context by setting `truncation=\"only_second\"`.\n",
|
139 |
+
"\n",
|
140 |
+
"### Mapping Answer Positions to Original Context\n",
|
141 |
+
"\n",
|
142 |
+
"To map the start and end positions of the answer to the original context:\n",
|
143 |
+
"\n",
|
144 |
+
"- Set `return_offset_mapping=True` during tokenization.\n",
|
145 |
+
"\n",
|
146 |
+
"### Finding Start and End Tokens of the Answer\n",
|
147 |
+
"\n",
|
148 |
+
"With the offset mapping, use the following steps to find the start and end tokens of the answer:\n",
|
149 |
+
"\n",
|
150 |
+
"- Utilize the `sequence_ids` method to determine which part of the offset corresponds to the question and which corresponds to the context."
|
151 |
+
]
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"cell_type": "code",
|
155 |
+
"execution_count": 7,
|
156 |
+
"metadata": {},
|
157 |
+
"outputs": [],
|
158 |
+
"source": [
|
159 |
+
"def preprocess_function(examples):\n",
|
160 |
+
" questions = [q.strip() for q in examples[\"question\"]]\n",
|
161 |
+
" inputs = tokenizer(\n",
|
162 |
+
" questions,\n",
|
163 |
+
" examples[\"context\"],\n",
|
164 |
+
" max_length=384,\n",
|
165 |
+
" truncation=\"only_second\",\n",
|
166 |
+
" return_offsets_mapping=True,\n",
|
167 |
+
" padding=\"max_length\",\n",
|
168 |
+
" )\n",
|
169 |
+
"\n",
|
170 |
+
" offset_mapping = inputs.pop(\"offset_mapping\")\n",
|
171 |
+
" answers = examples[\"answers\"]\n",
|
172 |
+
" start_positions = []\n",
|
173 |
+
" end_positions = []\n",
|
174 |
+
"\n",
|
175 |
+
" for i, offset in enumerate(offset_mapping):\n",
|
176 |
+
" answer = answers[i]\n",
|
177 |
+
" start_char = answer[\"answer_start\"][0]\n",
|
178 |
+
" end_char = answer[\"answer_start\"][0] + len(answer[\"text\"][0])\n",
|
179 |
+
" sequence_ids = inputs.sequence_ids(i)\n",
|
180 |
+
"\n",
|
181 |
+
" # Find the start and end of the context\n",
|
182 |
+
" idx = 0\n",
|
183 |
+
" while sequence_ids[idx] != 1:\n",
|
184 |
+
" idx += 1\n",
|
185 |
+
" context_start = idx\n",
|
186 |
+
" while sequence_ids[idx] == 1:\n",
|
187 |
+
" idx += 1\n",
|
188 |
+
" context_end = idx - 1\n",
|
189 |
+
"\n",
|
190 |
+
" # If the answer is not fully inside the context, label it (0, 0)\n",
|
191 |
+
" if offset[context_start][0] > end_char or offset[context_end][1] < start_char:\n",
|
192 |
+
" start_positions.append(0)\n",
|
193 |
+
" end_positions.append(0)\n",
|
194 |
+
" else:\n",
|
195 |
+
" # Otherwise it's the start and end token positions\n",
|
196 |
+
" idx = context_start\n",
|
197 |
+
" while idx <= context_end and offset[idx][0] <= start_char:\n",
|
198 |
+
" idx += 1\n",
|
199 |
+
" start_positions.append(idx - 1)\n",
|
200 |
+
"\n",
|
201 |
+
" idx = context_end\n",
|
202 |
+
" while idx >= context_start and offset[idx][1] >= end_char:\n",
|
203 |
+
" idx -= 1\n",
|
204 |
+
" end_positions.append(idx + 1)\n",
|
205 |
+
"\n",
|
206 |
+
" inputs[\"start_positions\"] = start_positions\n",
|
207 |
+
" inputs[\"end_positions\"] = end_positions\n",
|
208 |
+
" return inputs"
|
209 |
+
]
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"cell_type": "code",
|
213 |
+
"execution_count": 8,
|
214 |
+
"metadata": {},
|
215 |
+
"outputs": [
|
216 |
+
{
|
217 |
+
"name": "stderr",
|
218 |
+
"output_type": "stream",
|
219 |
+
"text": [
|
220 |
+
"Map: 0%| | 0/87599 [00:00<?, ? examples/s]"
|
221 |
+
]
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"name": "stderr",
|
225 |
+
"output_type": "stream",
|
226 |
+
"text": [
|
227 |
+
"Map: 100%|██████████| 87599/87599 [00:18<00:00, 4649.42 examples/s]\n",
|
228 |
+
"Map: 100%|██████████| 10570/10570 [00:02<00:00, 4331.36 examples/s]\n"
|
229 |
+
]
|
230 |
+
}
|
231 |
+
],
|
232 |
+
"source": [
|
233 |
+
"# applying preprocessing function to entire dataset\n",
|
234 |
+
"tokenized_datasets = squad.map(preprocess_function, batched=True)"
|
235 |
+
]
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"cell_type": "code",
|
239 |
+
"execution_count": 9,
|
240 |
+
"metadata": {},
|
241 |
+
"outputs": [
|
242 |
+
{
|
243 |
+
"data": {
|
244 |
+
"text/plain": [
|
245 |
+
"{'id': '5733be284776f41900661182',\n",
|
246 |
+
" 'title': 'University_of_Notre_Dame',\n",
|
247 |
+
" 'context': 'Architecturally, the school has a Catholic character. Atop the Main Building\\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend \"Venite Ad Me Omnes\". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.',\n",
|
248 |
+
" 'question': 'To whom did the Virgin Mary allegedly appear in 1858 in Lourdes France?',\n",
|
249 |
+
" 'answers': {'text': ['Saint Bernadette Soubirous'], 'answer_start': [515]},\n",
|
250 |
+
" 'input_ids': [101,\n",
|
251 |
+
" 2000,\n",
|
252 |
+
" 3183,\n",
|
253 |
+
" 2106,\n",
|
254 |
+
" 1996,\n",
|
255 |
+
" 6261,\n",
|
256 |
+
" 2984,\n",
|
257 |
+
" 9382,\n",
|
258 |
+
" 3711,\n",
|
259 |
+
" 1999,\n",
|
260 |
+
" 8517,\n",
|
261 |
+
" 1999,\n",
|
262 |
+
" 10223,\n",
|
263 |
+
" 26371,\n",
|
264 |
+
" 2605,\n",
|
265 |
+
" 1029,\n",
|
266 |
+
" 102,\n",
|
267 |
+
" 6549,\n",
|
268 |
+
" 2135,\n",
|
269 |
+
" 1010,\n",
|
270 |
+
" 1996,\n",
|
271 |
+
" 2082,\n",
|
272 |
+
" 2038,\n",
|
273 |
+
" 1037,\n",
|
274 |
+
" 3234,\n",
|
275 |
+
" 2839,\n",
|
276 |
+
" 1012,\n",
|
277 |
+
" 10234,\n",
|
278 |
+
" 1996,\n",
|
279 |
+
" 2364,\n",
|
280 |
+
" 2311,\n",
|
281 |
+
" 1005,\n",
|
282 |
+
" 1055,\n",
|
283 |
+
" 2751,\n",
|
284 |
+
" 8514,\n",
|
285 |
+
" 2003,\n",
|
286 |
+
" 1037,\n",
|
287 |
+
" 3585,\n",
|
288 |
+
" 6231,\n",
|
289 |
+
" 1997,\n",
|
290 |
+
" 1996,\n",
|
291 |
+
" 6261,\n",
|
292 |
+
" 2984,\n",
|
293 |
+
" 1012,\n",
|
294 |
+
" 3202,\n",
|
295 |
+
" 1999,\n",
|
296 |
+
" 2392,\n",
|
297 |
+
" 1997,\n",
|
298 |
+
" 1996,\n",
|
299 |
+
" 2364,\n",
|
300 |
+
" 2311,\n",
|
301 |
+
" 1998,\n",
|
302 |
+
" 5307,\n",
|
303 |
+
" 2009,\n",
|
304 |
+
" 1010,\n",
|
305 |
+
" 2003,\n",
|
306 |
+
" 1037,\n",
|
307 |
+
" 6967,\n",
|
308 |
+
" 6231,\n",
|
309 |
+
" 1997,\n",
|
310 |
+
" 4828,\n",
|
311 |
+
" 2007,\n",
|
312 |
+
" 2608,\n",
|
313 |
+
" 2039,\n",
|
314 |
+
" 14995,\n",
|
315 |
+
" 6924,\n",
|
316 |
+
" 2007,\n",
|
317 |
+
" 1996,\n",
|
318 |
+
" 5722,\n",
|
319 |
+
" 1000,\n",
|
320 |
+
" 2310,\n",
|
321 |
+
" 3490,\n",
|
322 |
+
" 2618,\n",
|
323 |
+
" 4748,\n",
|
324 |
+
" 2033,\n",
|
325 |
+
" 18168,\n",
|
326 |
+
" 5267,\n",
|
327 |
+
" 1000,\n",
|
328 |
+
" 1012,\n",
|
329 |
+
" 2279,\n",
|
330 |
+
" 2000,\n",
|
331 |
+
" 1996,\n",
|
332 |
+
" 2364,\n",
|
333 |
+
" 2311,\n",
|
334 |
+
" 2003,\n",
|
335 |
+
" 1996,\n",
|
336 |
+
" 13546,\n",
|
337 |
+
" 1997,\n",
|
338 |
+
" 1996,\n",
|
339 |
+
" 6730,\n",
|
340 |
+
" 2540,\n",
|
341 |
+
" 1012,\n",
|
342 |
+
" 3202,\n",
|
343 |
+
" 2369,\n",
|
344 |
+
" 1996,\n",
|
345 |
+
" 13546,\n",
|
346 |
+
" 2003,\n",
|
347 |
+
" 1996,\n",
|
348 |
+
" 24665,\n",
|
349 |
+
" 23052,\n",
|
350 |
+
" 1010,\n",
|
351 |
+
" 1037,\n",
|
352 |
+
" 14042,\n",
|
353 |
+
" 2173,\n",
|
354 |
+
" 1997,\n",
|
355 |
+
" 7083,\n",
|
356 |
+
" 1998,\n",
|
357 |
+
" 9185,\n",
|
358 |
+
" 1012,\n",
|
359 |
+
" 2009,\n",
|
360 |
+
" 2003,\n",
|
361 |
+
" 1037,\n",
|
362 |
+
" 15059,\n",
|
363 |
+
" 1997,\n",
|
364 |
+
" 1996,\n",
|
365 |
+
" 24665,\n",
|
366 |
+
" 23052,\n",
|
367 |
+
" 2012,\n",
|
368 |
+
" 10223,\n",
|
369 |
+
" 26371,\n",
|
370 |
+
" 1010,\n",
|
371 |
+
" 2605,\n",
|
372 |
+
" 2073,\n",
|
373 |
+
" 1996,\n",
|
374 |
+
" 6261,\n",
|
375 |
+
" 2984,\n",
|
376 |
+
" 22353,\n",
|
377 |
+
" 2135,\n",
|
378 |
+
" 2596,\n",
|
379 |
+
" 2000,\n",
|
380 |
+
" 3002,\n",
|
381 |
+
" 16595,\n",
|
382 |
+
" 9648,\n",
|
383 |
+
" 4674,\n",
|
384 |
+
" 2061,\n",
|
385 |
+
" 12083,\n",
|
386 |
+
" 9711,\n",
|
387 |
+
" 2271,\n",
|
388 |
+
" 1999,\n",
|
389 |
+
" 8517,\n",
|
390 |
+
" 1012,\n",
|
391 |
+
" 2012,\n",
|
392 |
+
" 1996,\n",
|
393 |
+
" 2203,\n",
|
394 |
+
" 1997,\n",
|
395 |
+
" 1996,\n",
|
396 |
+
" 2364,\n",
|
397 |
+
" 3298,\n",
|
398 |
+
" 1006,\n",
|
399 |
+
" 1998,\n",
|
400 |
+
" 1999,\n",
|
401 |
+
" 1037,\n",
|
402 |
+
" 3622,\n",
|
403 |
+
" 2240,\n",
|
404 |
+
" 2008,\n",
|
405 |
+
" 8539,\n",
|
406 |
+
" 2083,\n",
|
407 |
+
" 1017,\n",
|
408 |
+
" 11342,\n",
|
409 |
+
" 1998,\n",
|
410 |
+
" 1996,\n",
|
411 |
+
" 2751,\n",
|
412 |
+
" 8514,\n",
|
413 |
+
" 1007,\n",
|
414 |
+
" 1010,\n",
|
415 |
+
" 2003,\n",
|
416 |
+
" 1037,\n",
|
417 |
+
" 3722,\n",
|
418 |
+
" 1010,\n",
|
419 |
+
" 2715,\n",
|
420 |
+
" 2962,\n",
|
421 |
+
" 6231,\n",
|
422 |
+
" 1997,\n",
|
423 |
+
" 2984,\n",
|
424 |
+
" 1012,\n",
|
425 |
+
" 102,\n",
|
426 |
+
" 0,\n",
|
427 |
+
" 0,\n",
|
428 |
+
" 0,\n",
|
429 |
+
" 0,\n",
|
430 |
+
" 0,\n",
|
431 |
+
" 0,\n",
|
432 |
+
" 0,\n",
|
433 |
+
" 0,\n",
|
434 |
+
" 0,\n",
|
435 |
+
" 0,\n",
|
436 |
+
" 0,\n",
|
437 |
+
" 0,\n",
|
438 |
+
" 0,\n",
|
439 |
+
" 0,\n",
|
440 |
+
" 0,\n",
|
441 |
+
" 0,\n",
|
442 |
+
" 0,\n",
|
443 |
+
" 0,\n",
|
444 |
+
" 0,\n",
|
445 |
+
" 0,\n",
|
446 |
+
" 0,\n",
|
447 |
+
" 0,\n",
|
448 |
+
" 0,\n",
|
449 |
+
" 0,\n",
|
450 |
+
" 0,\n",
|
451 |
+
" 0,\n",
|
452 |
+
" 0,\n",
|
453 |
+
" 0,\n",
|
454 |
+
" 0,\n",
|
455 |
+
" 0,\n",
|
456 |
+
" 0,\n",
|
457 |
+
" 0,\n",
|
458 |
+
" 0,\n",
|
459 |
+
" 0,\n",
|
460 |
+
" 0,\n",
|
461 |
+
" 0,\n",
|
462 |
+
" 0,\n",
|
463 |
+
" 0,\n",
|
464 |
+
" 0,\n",
|
465 |
+
" 0,\n",
|
466 |
+
" 0,\n",
|
467 |
+
" 0,\n",
|
468 |
+
" 0,\n",
|
469 |
+
" 0,\n",
|
470 |
+
" 0,\n",
|
471 |
+
" 0,\n",
|
472 |
+
" 0,\n",
|
473 |
+
" 0,\n",
|
474 |
+
" 0,\n",
|
475 |
+
" 0,\n",
|
476 |
+
" 0,\n",
|
477 |
+
" 0,\n",
|
478 |
+
" 0,\n",
|
479 |
+
" 0,\n",
|
480 |
+
" 0,\n",
|
481 |
+
" 0,\n",
|
482 |
+
" 0,\n",
|
483 |
+
" 0,\n",
|
484 |
+
" 0,\n",
|
485 |
+
" 0,\n",
|
486 |
+
" 0,\n",
|
487 |
+
" 0,\n",
|
488 |
+
" 0,\n",
|
489 |
+
" 0,\n",
|
490 |
+
" 0,\n",
|
491 |
+
" 0,\n",
|
492 |
+
" 0,\n",
|
493 |
+
" 0,\n",
|
494 |
+
" 0,\n",
|
495 |
+
" 0,\n",
|
496 |
+
" 0,\n",
|
497 |
+
" 0,\n",
|
498 |
+
" 0,\n",
|
499 |
+
" 0,\n",
|
500 |
+
" 0,\n",
|
501 |
+
" 0,\n",
|
502 |
+
" 0,\n",
|
503 |
+
" 0,\n",
|
504 |
+
" 0,\n",
|
505 |
+
" 0,\n",
|
506 |
+
" 0,\n",
|
507 |
+
" 0,\n",
|
508 |
+
" 0,\n",
|
509 |
+
" 0,\n",
|
510 |
+
" 0,\n",
|
511 |
+
" 0,\n",
|
512 |
+
" 0,\n",
|
513 |
+
" 0,\n",
|
514 |
+
" 0,\n",
|
515 |
+
" 0,\n",
|
516 |
+
" 0,\n",
|
517 |
+
" 0,\n",
|
518 |
+
" 0,\n",
|
519 |
+
" 0,\n",
|
520 |
+
" 0,\n",
|
521 |
+
" 0,\n",
|
522 |
+
" 0,\n",
|
523 |
+
" 0,\n",
|
524 |
+
" 0,\n",
|
525 |
+
" 0,\n",
|
526 |
+
" 0,\n",
|
527 |
+
" 0,\n",
|
528 |
+
" 0,\n",
|
529 |
+
" 0,\n",
|
530 |
+
" 0,\n",
|
531 |
+
" 0,\n",
|
532 |
+
" 0,\n",
|
533 |
+
" 0,\n",
|
534 |
+
" 0,\n",
|
535 |
+
" 0,\n",
|
536 |
+
" 0,\n",
|
537 |
+
" 0,\n",
|
538 |
+
" 0,\n",
|
539 |
+
" 0,\n",
|
540 |
+
" 0,\n",
|
541 |
+
" 0,\n",
|
542 |
+
" 0,\n",
|
543 |
+
" 0,\n",
|
544 |
+
" 0,\n",
|
545 |
+
" 0,\n",
|
546 |
+
" 0,\n",
|
547 |
+
" 0,\n",
|
548 |
+
" 0,\n",
|
549 |
+
" 0,\n",
|
550 |
+
" 0,\n",
|
551 |
+
" 0,\n",
|
552 |
+
" 0,\n",
|
553 |
+
" 0,\n",
|
554 |
+
" 0,\n",
|
555 |
+
" 0,\n",
|
556 |
+
" 0,\n",
|
557 |
+
" 0,\n",
|
558 |
+
" 0,\n",
|
559 |
+
" 0,\n",
|
560 |
+
" 0,\n",
|
561 |
+
" 0,\n",
|
562 |
+
" 0,\n",
|
563 |
+
" 0,\n",
|
564 |
+
" 0,\n",
|
565 |
+
" 0,\n",
|
566 |
+
" 0,\n",
|
567 |
+
" 0,\n",
|
568 |
+
" 0,\n",
|
569 |
+
" 0,\n",
|
570 |
+
" 0,\n",
|
571 |
+
" 0,\n",
|
572 |
+
" 0,\n",
|
573 |
+
" 0,\n",
|
574 |
+
" 0,\n",
|
575 |
+
" 0,\n",
|
576 |
+
" 0,\n",
|
577 |
+
" 0,\n",
|
578 |
+
" 0,\n",
|
579 |
+
" 0,\n",
|
580 |
+
" 0,\n",
|
581 |
+
" 0,\n",
|
582 |
+
" 0,\n",
|
583 |
+
" 0,\n",
|
584 |
+
" 0,\n",
|
585 |
+
" 0,\n",
|
586 |
+
" 0,\n",
|
587 |
+
" 0,\n",
|
588 |
+
" 0,\n",
|
589 |
+
" 0,\n",
|
590 |
+
" 0,\n",
|
591 |
+
" 0,\n",
|
592 |
+
" 0,\n",
|
593 |
+
" 0,\n",
|
594 |
+
" 0,\n",
|
595 |
+
" 0,\n",
|
596 |
+
" 0,\n",
|
597 |
+
" 0,\n",
|
598 |
+
" 0,\n",
|
599 |
+
" 0,\n",
|
600 |
+
" 0,\n",
|
601 |
+
" 0,\n",
|
602 |
+
" 0,\n",
|
603 |
+
" 0,\n",
|
604 |
+
" 0,\n",
|
605 |
+
" 0,\n",
|
606 |
+
" 0,\n",
|
607 |
+
" 0,\n",
|
608 |
+
" 0,\n",
|
609 |
+
" 0,\n",
|
610 |
+
" 0,\n",
|
611 |
+
" 0,\n",
|
612 |
+
" 0,\n",
|
613 |
+
" 0,\n",
|
614 |
+
" 0,\n",
|
615 |
+
" 0,\n",
|
616 |
+
" 0,\n",
|
617 |
+
" 0,\n",
|
618 |
+
" 0,\n",
|
619 |
+
" 0,\n",
|
620 |
+
" 0,\n",
|
621 |
+
" 0,\n",
|
622 |
+
" 0,\n",
|
623 |
+
" 0,\n",
|
624 |
+
" 0,\n",
|
625 |
+
" 0,\n",
|
626 |
+
" 0,\n",
|
627 |
+
" 0,\n",
|
628 |
+
" 0,\n",
|
629 |
+
" 0,\n",
|
630 |
+
" 0,\n",
|
631 |
+
" 0,\n",
|
632 |
+
" 0,\n",
|
633 |
+
" 0],\n",
|
634 |
+
" 'attention_mask': [1,\n",
|
635 |
+
" 1,\n",
|
636 |
+
" 1,\n",
|
637 |
+
" 1,\n",
|
638 |
+
" 1,\n",
|
639 |
+
" 1,\n",
|
640 |
+
" 1,\n",
|
641 |
+
" 1,\n",
|
642 |
+
" 1,\n",
|
643 |
+
" 1,\n",
|
644 |
+
" 1,\n",
|
645 |
+
" 1,\n",
|
646 |
+
" 1,\n",
|
647 |
+
" 1,\n",
|
648 |
+
" 1,\n",
|
649 |
+
" 1,\n",
|
650 |
+
" 1,\n",
|
651 |
+
" 1,\n",
|
652 |
+
" 1,\n",
|
653 |
+
" 1,\n",
|
654 |
+
" 1,\n",
|
655 |
+
" 1,\n",
|
656 |
+
" 1,\n",
|
657 |
+
" 1,\n",
|
658 |
+
" 1,\n",
|
659 |
+
" 1,\n",
|
660 |
+
" 1,\n",
|
661 |
+
" 1,\n",
|
662 |
+
" 1,\n",
|
663 |
+
" 1,\n",
|
664 |
+
" 1,\n",
|
665 |
+
" 1,\n",
|
666 |
+
" 1,\n",
|
667 |
+
" 1,\n",
|
668 |
+
" 1,\n",
|
669 |
+
" 1,\n",
|
670 |
+
" 1,\n",
|
671 |
+
" 1,\n",
|
672 |
+
" 1,\n",
|
673 |
+
" 1,\n",
|
674 |
+
" 1,\n",
|
675 |
+
" 1,\n",
|
676 |
+
" 1,\n",
|
677 |
+
" 1,\n",
|
678 |
+
" 1,\n",
|
679 |
+
" 1,\n",
|
680 |
+
" 1,\n",
|
681 |
+
" 1,\n",
|
682 |
+
" 1,\n",
|
683 |
+
" 1,\n",
|
684 |
+
" 1,\n",
|
685 |
+
" 1,\n",
|
686 |
+
" 1,\n",
|
687 |
+
" 1,\n",
|
688 |
+
" 1,\n",
|
689 |
+
" 1,\n",
|
690 |
+
" 1,\n",
|
691 |
+
" 1,\n",
|
692 |
+
" 1,\n",
|
693 |
+
" 1,\n",
|
694 |
+
" 1,\n",
|
695 |
+
" 1,\n",
|
696 |
+
" 1,\n",
|
697 |
+
" 1,\n",
|
698 |
+
" 1,\n",
|
699 |
+
" 1,\n",
|
700 |
+
" 1,\n",
|
701 |
+
" 1,\n",
|
702 |
+
" 1,\n",
|
703 |
+
" 1,\n",
|
704 |
+
" 1,\n",
|
705 |
+
" 1,\n",
|
706 |
+
" 1,\n",
|
707 |
+
" 1,\n",
|
708 |
+
" 1,\n",
|
709 |
+
" 1,\n",
|
710 |
+
" 1,\n",
|
711 |
+
" 1,\n",
|
712 |
+
" 1,\n",
|
713 |
+
" 1,\n",
|
714 |
+
" 1,\n",
|
715 |
+
" 1,\n",
|
716 |
+
" 1,\n",
|
717 |
+
" 1,\n",
|
718 |
+
" 1,\n",
|
719 |
+
" 1,\n",
|
720 |
+
" 1,\n",
|
721 |
+
" 1,\n",
|
722 |
+
" 1,\n",
|
723 |
+
" 1,\n",
|
724 |
+
" 1,\n",
|
725 |
+
" 1,\n",
|
726 |
+
" 1,\n",
|
727 |
+
" 1,\n",
|
728 |
+
" 1,\n",
|
729 |
+
" 1,\n",
|
730 |
+
" 1,\n",
|
731 |
+
" 1,\n",
|
732 |
+
" 1,\n",
|
733 |
+
" 1,\n",
|
734 |
+
" 1,\n",
|
735 |
+
" 1,\n",
|
736 |
+
" 1,\n",
|
737 |
+
" 1,\n",
|
738 |
+
" 1,\n",
|
739 |
+
" 1,\n",
|
740 |
+
" 1,\n",
|
741 |
+
" 1,\n",
|
742 |
+
" 1,\n",
|
743 |
+
" 1,\n",
|
744 |
+
" 1,\n",
|
745 |
+
" 1,\n",
|
746 |
+
" 1,\n",
|
747 |
+
" 1,\n",
|
748 |
+
" 1,\n",
|
749 |
+
" 1,\n",
|
750 |
+
" 1,\n",
|
751 |
+
" 1,\n",
|
752 |
+
" 1,\n",
|
753 |
+
" 1,\n",
|
754 |
+
" 1,\n",
|
755 |
+
" 1,\n",
|
756 |
+
" 1,\n",
|
757 |
+
" 1,\n",
|
758 |
+
" 1,\n",
|
759 |
+
" 1,\n",
|
760 |
+
" 1,\n",
|
761 |
+
" 1,\n",
|
762 |
+
" 1,\n",
|
763 |
+
" 1,\n",
|
764 |
+
" 1,\n",
|
765 |
+
" 1,\n",
|
766 |
+
" 1,\n",
|
767 |
+
" 1,\n",
|
768 |
+
" 1,\n",
|
769 |
+
" 1,\n",
|
770 |
+
" 1,\n",
|
771 |
+
" 1,\n",
|
772 |
+
" 1,\n",
|
773 |
+
" 1,\n",
|
774 |
+
" 1,\n",
|
775 |
+
" 1,\n",
|
776 |
+
" 1,\n",
|
777 |
+
" 1,\n",
|
778 |
+
" 1,\n",
|
779 |
+
" 1,\n",
|
780 |
+
" 1,\n",
|
781 |
+
" 1,\n",
|
782 |
+
" 1,\n",
|
783 |
+
" 1,\n",
|
784 |
+
" 1,\n",
|
785 |
+
" 1,\n",
|
786 |
+
" 1,\n",
|
787 |
+
" 1,\n",
|
788 |
+
" 1,\n",
|
789 |
+
" 1,\n",
|
790 |
+
" 1,\n",
|
791 |
+
" 1,\n",
|
792 |
+
" 1,\n",
|
793 |
+
" 1,\n",
|
794 |
+
" 1,\n",
|
795 |
+
" 1,\n",
|
796 |
+
" 1,\n",
|
797 |
+
" 1,\n",
|
798 |
+
" 1,\n",
|
799 |
+
" 1,\n",
|
800 |
+
" 1,\n",
|
801 |
+
" 1,\n",
|
802 |
+
" 1,\n",
|
803 |
+
" 1,\n",
|
804 |
+
" 1,\n",
|
805 |
+
" 1,\n",
|
806 |
+
" 1,\n",
|
807 |
+
" 1,\n",
|
808 |
+
" 1,\n",
|
809 |
+
" 1,\n",
|
810 |
+
" 0,\n",
|
811 |
+
" 0,\n",
|
812 |
+
" 0,\n",
|
813 |
+
" 0,\n",
|
814 |
+
" 0,\n",
|
815 |
+
" 0,\n",
|
816 |
+
" 0,\n",
|
817 |
+
" 0,\n",
|
818 |
+
" 0,\n",
|
819 |
+
" 0,\n",
|
820 |
+
" 0,\n",
|
821 |
+
" 0,\n",
|
822 |
+
" 0,\n",
|
823 |
+
" 0,\n",
|
824 |
+
" 0,\n",
|
825 |
+
" 0,\n",
|
826 |
+
" 0,\n",
|
827 |
+
" 0,\n",
|
828 |
+
" 0,\n",
|
829 |
+
" 0,\n",
|
830 |
+
" 0,\n",
|
831 |
+
" 0,\n",
|
832 |
+
" 0,\n",
|
833 |
+
" 0,\n",
|
834 |
+
" 0,\n",
|
835 |
+
" 0,\n",
|
836 |
+
" 0,\n",
|
837 |
+
" 0,\n",
|
838 |
+
" 0,\n",
|
839 |
+
" 0,\n",
|
840 |
+
" 0,\n",
|
841 |
+
" 0,\n",
|
842 |
+
" 0,\n",
|
843 |
+
" 0,\n",
|
844 |
+
" 0,\n",
|
845 |
+
" 0,\n",
|
846 |
+
" 0,\n",
|
847 |
+
" 0,\n",
|
848 |
+
" 0,\n",
|
849 |
+
" 0,\n",
|
850 |
+
" 0,\n",
|
851 |
+
" 0,\n",
|
852 |
+
" 0,\n",
|
853 |
+
" 0,\n",
|
854 |
+
" 0,\n",
|
855 |
+
" 0,\n",
|
856 |
+
" 0,\n",
|
857 |
+
" 0,\n",
|
858 |
+
" 0,\n",
|
859 |
+
" 0,\n",
|
860 |
+
" 0,\n",
|
861 |
+
" 0,\n",
|
862 |
+
" 0,\n",
|
863 |
+
" 0,\n",
|
864 |
+
" 0,\n",
|
865 |
+
" 0,\n",
|
866 |
+
" 0,\n",
|
867 |
+
" 0,\n",
|
868 |
+
" 0,\n",
|
869 |
+
" 0,\n",
|
870 |
+
" 0,\n",
|
871 |
+
" 0,\n",
|
872 |
+
" 0,\n",
|
873 |
+
" 0,\n",
|
874 |
+
" 0,\n",
|
875 |
+
" 0,\n",
|
876 |
+
" 0,\n",
|
877 |
+
" 0,\n",
|
878 |
+
" 0,\n",
|
879 |
+
" 0,\n",
|
880 |
+
" 0,\n",
|
881 |
+
" 0,\n",
|
882 |
+
" 0,\n",
|
883 |
+
" 0,\n",
|
884 |
+
" 0,\n",
|
885 |
+
" 0,\n",
|
886 |
+
" 0,\n",
|
887 |
+
" 0,\n",
|
888 |
+
" 0,\n",
|
889 |
+
" 0,\n",
|
890 |
+
" 0,\n",
|
891 |
+
" 0,\n",
|
892 |
+
" 0,\n",
|
893 |
+
" 0,\n",
|
894 |
+
" 0,\n",
|
895 |
+
" 0,\n",
|
896 |
+
" 0,\n",
|
897 |
+
" 0,\n",
|
898 |
+
" 0,\n",
|
899 |
+
" 0,\n",
|
900 |
+
" 0,\n",
|
901 |
+
" 0,\n",
|
902 |
+
" 0,\n",
|
903 |
+
" 0,\n",
|
904 |
+
" 0,\n",
|
905 |
+
" 0,\n",
|
906 |
+
" 0,\n",
|
907 |
+
" 0,\n",
|
908 |
+
" 0,\n",
|
909 |
+
" 0,\n",
|
910 |
+
" 0,\n",
|
911 |
+
" 0,\n",
|
912 |
+
" 0,\n",
|
913 |
+
" 0,\n",
|
914 |
+
" 0,\n",
|
915 |
+
" 0,\n",
|
916 |
+
" 0,\n",
|
917 |
+
" 0,\n",
|
918 |
+
" 0,\n",
|
919 |
+
" 0,\n",
|
920 |
+
" 0,\n",
|
921 |
+
" 0,\n",
|
922 |
+
" 0,\n",
|
923 |
+
" 0,\n",
|
924 |
+
" 0,\n",
|
925 |
+
" 0,\n",
|
926 |
+
" 0,\n",
|
927 |
+
" 0,\n",
|
928 |
+
" 0,\n",
|
929 |
+
" 0,\n",
|
930 |
+
" 0,\n",
|
931 |
+
" 0,\n",
|
932 |
+
" 0,\n",
|
933 |
+
" 0,\n",
|
934 |
+
" 0,\n",
|
935 |
+
" 0,\n",
|
936 |
+
" 0,\n",
|
937 |
+
" 0,\n",
|
938 |
+
" 0,\n",
|
939 |
+
" 0,\n",
|
940 |
+
" 0,\n",
|
941 |
+
" 0,\n",
|
942 |
+
" 0,\n",
|
943 |
+
" 0,\n",
|
944 |
+
" 0,\n",
|
945 |
+
" 0,\n",
|
946 |
+
" 0,\n",
|
947 |
+
" 0,\n",
|
948 |
+
" 0,\n",
|
949 |
+
" 0,\n",
|
950 |
+
" 0,\n",
|
951 |
+
" 0,\n",
|
952 |
+
" 0,\n",
|
953 |
+
" 0,\n",
|
954 |
+
" 0,\n",
|
955 |
+
" 0,\n",
|
956 |
+
" 0,\n",
|
957 |
+
" 0,\n",
|
958 |
+
" 0,\n",
|
959 |
+
" 0,\n",
|
960 |
+
" 0,\n",
|
961 |
+
" 0,\n",
|
962 |
+
" 0,\n",
|
963 |
+
" 0,\n",
|
964 |
+
" 0,\n",
|
965 |
+
" 0,\n",
|
966 |
+
" 0,\n",
|
967 |
+
" 0,\n",
|
968 |
+
" 0,\n",
|
969 |
+
" 0,\n",
|
970 |
+
" 0,\n",
|
971 |
+
" 0,\n",
|
972 |
+
" 0,\n",
|
973 |
+
" 0,\n",
|
974 |
+
" 0,\n",
|
975 |
+
" 0,\n",
|
976 |
+
" 0,\n",
|
977 |
+
" 0,\n",
|
978 |
+
" 0,\n",
|
979 |
+
" 0,\n",
|
980 |
+
" 0,\n",
|
981 |
+
" 0,\n",
|
982 |
+
" 0,\n",
|
983 |
+
" 0,\n",
|
984 |
+
" 0,\n",
|
985 |
+
" 0,\n",
|
986 |
+
" 0,\n",
|
987 |
+
" 0,\n",
|
988 |
+
" 0,\n",
|
989 |
+
" 0,\n",
|
990 |
+
" 0,\n",
|
991 |
+
" 0,\n",
|
992 |
+
" 0,\n",
|
993 |
+
" 0,\n",
|
994 |
+
" 0,\n",
|
995 |
+
" 0,\n",
|
996 |
+
" 0,\n",
|
997 |
+
" 0,\n",
|
998 |
+
" 0,\n",
|
999 |
+
" 0,\n",
|
1000 |
+
" 0,\n",
|
1001 |
+
" 0,\n",
|
1002 |
+
" 0,\n",
|
1003 |
+
" 0,\n",
|
1004 |
+
" 0,\n",
|
1005 |
+
" 0,\n",
|
1006 |
+
" 0,\n",
|
1007 |
+
" 0,\n",
|
1008 |
+
" 0,\n",
|
1009 |
+
" 0,\n",
|
1010 |
+
" 0,\n",
|
1011 |
+
" 0,\n",
|
1012 |
+
" 0,\n",
|
1013 |
+
" 0,\n",
|
1014 |
+
" 0,\n",
|
1015 |
+
" 0,\n",
|
1016 |
+
" 0,\n",
|
1017 |
+
" 0],\n",
|
1018 |
+
" 'start_positions': 130,\n",
|
1019 |
+
" 'end_positions': 137}"
|
1020 |
+
]
|
1021 |
+
},
|
1022 |
+
"execution_count": 9,
|
1023 |
+
"metadata": {},
|
1024 |
+
"output_type": "execute_result"
|
1025 |
+
}
|
1026 |
+
],
|
1027 |
+
"source": [
|
1028 |
+
"tokenized_datasets['train'][0]"
|
1029 |
+
]
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"cell_type": "code",
|
1033 |
+
"execution_count": 10,
|
1034 |
+
"metadata": {},
|
1035 |
+
"outputs": [],
|
1036 |
+
"source": [
|
1037 |
+
"# creating a batch of examples using DefaultDataCollator\n",
|
1038 |
+
"data_collator = DefaultDataCollator()"
|
1039 |
+
]
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"cell_type": "code",
|
1043 |
+
"execution_count": 11,
|
1044 |
+
"metadata": {},
|
1045 |
+
"outputs": [
|
1046 |
+
{
|
1047 |
+
"name": "stderr",
|
1048 |
+
"output_type": "stream",
|
1049 |
+
"text": [
|
1050 |
+
"Some weights of DistilBertForQuestionAnswering were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['qa_outputs.weight', 'qa_outputs.bias']\n",
|
1051 |
+
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
|
1052 |
+
]
|
1053 |
+
}
|
1054 |
+
],
|
1055 |
+
"source": [
|
1056 |
+
"# loading pre-trained model\n",
|
1057 |
+
"model = AutoModelForQuestionAnswering.from_pretrained(\"distilbert-base-uncased\")\n"
|
1058 |
+
]
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"cell_type": "code",
|
1062 |
+
"execution_count": 16,
|
1063 |
+
"metadata": {},
|
1064 |
+
"outputs": [],
|
1065 |
+
"source": [
|
1066 |
+
"# fine tuning the distilber-base-uncased model\n",
|
1067 |
+
"\n",
|
1068 |
+
"training_args = TrainingArguments(\n",
|
1069 |
+
" output_dir=\"finetuning_squad\",\n",
|
1070 |
+
" evaluation_strategy=\"epoch\",\n",
|
1071 |
+
" learning_rate=2e-5,\n",
|
1072 |
+
" per_device_train_batch_size=16,\n",
|
1073 |
+
" per_device_eval_batch_size=16,\n",
|
1074 |
+
" num_train_epochs=3,\n",
|
1075 |
+
" weight_decay=0.01,\n",
|
1076 |
+
")\n",
|
1077 |
+
"\n",
|
1078 |
+
"trainer = Trainer(\n",
|
1079 |
+
" model=model,\n",
|
1080 |
+
" args=training_args,\n",
|
1081 |
+
" train_dataset=tokenized_datasets['train'],\n",
|
1082 |
+
" eval_dataset=tokenized_datasets['validation'],\n",
|
1083 |
+
" tokenizer=tokenizer,\n",
|
1084 |
+
" data_collator=data_collator,\n",
|
1085 |
+
")\n"
|
1086 |
+
]
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"cell_type": "code",
|
1090 |
+
"execution_count": 17,
|
1091 |
+
"metadata": {},
|
1092 |
+
"outputs": [
|
1093 |
+
{
|
1094 |
+
"name": "stderr",
|
1095 |
+
"output_type": "stream",
|
1096 |
+
"text": [
|
1097 |
+
" 0%| | 0/4107 [00:53<?, ?it/s]\n",
|
1098 |
+
" \n",
|
1099 |
+
" 3%|▎ | 500/16425 [02:27<1:18:36, 3.38it/s]"
|
1100 |
+
]
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"name": "stdout",
|
1104 |
+
"output_type": "stream",
|
1105 |
+
"text": [
|
1106 |
+
"{'loss': 2.9417, 'learning_rate': 1.9391171993911722e-05, 'epoch': 0.09}\n"
|
1107 |
+
]
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"name": "stderr",
|
1111 |
+
"output_type": "stream",
|
1112 |
+
"text": [
|
1113 |
+
" \n",
|
1114 |
+
" 6%|▌ | 1000/16425 [04:54<1:13:37, 3.49it/s]"
|
1115 |
+
]
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"name": "stdout",
|
1119 |
+
"output_type": "stream",
|
1120 |
+
"text": [
|
1121 |
+
"{'loss': 1.7699, 'learning_rate': 1.8782343987823442e-05, 'epoch': 0.18}\n"
|
1122 |
+
]
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"name": "stderr",
|
1126 |
+
"output_type": "stream",
|
1127 |
+
"text": [
|
1128 |
+
" \n",
|
1129 |
+
" 9%|▉ | 1500/16425 [07:18<1:10:45, 3.52it/s]"
|
1130 |
+
]
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"name": "stdout",
|
1134 |
+
"output_type": "stream",
|
1135 |
+
"text": [
|
1136 |
+
"{'loss': 1.5303, 'learning_rate': 1.8173515981735163e-05, 'epoch': 0.27}\n"
|
1137 |
+
]
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"name": "stderr",
|
1141 |
+
"output_type": "stream",
|
1142 |
+
"text": [
|
1143 |
+
" \n",
|
1144 |
+
" 12%|█▏ | 2000/16425 [09:42<1:08:20, 3.52it/s]"
|
1145 |
+
]
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"name": "stdout",
|
1149 |
+
"output_type": "stream",
|
1150 |
+
"text": [
|
1151 |
+
"{'loss': 1.46, 'learning_rate': 1.756468797564688e-05, 'epoch': 0.37}\n"
|
1152 |
+
]
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"name": "stderr",
|
1156 |
+
"output_type": "stream",
|
1157 |
+
"text": [
|
1158 |
+
" \n",
|
1159 |
+
" 15%|█▌ | 2500/16425 [12:06<1:05:58, 3.52it/s]"
|
1160 |
+
]
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"name": "stdout",
|
1164 |
+
"output_type": "stream",
|
1165 |
+
"text": [
|
1166 |
+
"{'loss': 1.393, 'learning_rate': 1.69558599695586e-05, 'epoch': 0.46}\n"
|
1167 |
+
]
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"name": "stderr",
|
1171 |
+
"output_type": "stream",
|
1172 |
+
"text": [
|
1173 |
+
" \n",
|
1174 |
+
" 18%|█▊ | 3000/16425 [14:27<1:00:22, 3.71it/s]"
|
1175 |
+
]
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"name": "stdout",
|
1179 |
+
"output_type": "stream",
|
1180 |
+
"text": [
|
1181 |
+
"{'loss': 1.3692, 'learning_rate': 1.634703196347032e-05, 'epoch': 0.55}\n"
|
1182 |
+
]
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"name": "stderr",
|
1186 |
+
"output_type": "stream",
|
1187 |
+
"text": [
|
1188 |
+
" \n",
|
1189 |
+
" 21%|██▏ | 3500/16425 [16:43<58:09, 3.70it/s]"
|
1190 |
+
]
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"name": "stdout",
|
1194 |
+
"output_type": "stream",
|
1195 |
+
"text": [
|
1196 |
+
"{'loss': 1.3134, 'learning_rate': 1.573820395738204e-05, 'epoch': 0.64}\n"
|
1197 |
+
]
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"name": "stderr",
|
1201 |
+
"output_type": "stream",
|
1202 |
+
"text": [
|
1203 |
+
" \n",
|
1204 |
+
" 24%|██▍ | 4000/16425 [18:59<55:51, 3.71it/s]"
|
1205 |
+
]
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"name": "stdout",
|
1209 |
+
"output_type": "stream",
|
1210 |
+
"text": [
|
1211 |
+
"{'loss': 1.2416, 'learning_rate': 1.5129375951293761e-05, 'epoch': 0.73}\n"
|
1212 |
+
]
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"name": "stderr",
|
1216 |
+
"output_type": "stream",
|
1217 |
+
"text": [
|
1218 |
+
" \n",
|
1219 |
+
" 27%|██▋ | 4500/16425 [21:15<53:34, 3.71it/s]"
|
1220 |
+
]
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"name": "stdout",
|
1224 |
+
"output_type": "stream",
|
1225 |
+
"text": [
|
1226 |
+
"{'loss': 1.2574, 'learning_rate': 1.4520547945205482e-05, 'epoch': 0.82}\n"
|
1227 |
+
]
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"name": "stderr",
|
1231 |
+
"output_type": "stream",
|
1232 |
+
"text": [
|
1233 |
+
" \n",
|
1234 |
+
" 30%|███ | 5000/16425 [23:31<51:17, 3.71it/s]"
|
1235 |
+
]
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"name": "stdout",
|
1239 |
+
"output_type": "stream",
|
1240 |
+
"text": [
|
1241 |
+
"{'loss': 1.2039, 'learning_rate': 1.39117199391172e-05, 'epoch': 0.91}\n"
|
1242 |
+
]
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"name": "stderr",
|
1246 |
+
"output_type": "stream",
|
1247 |
+
"text": [
|
1248 |
+
" 33%|███▎ | 5475/16425 [25:40<48:05, 3.80it/s] \n",
|
1249 |
+
"\u001b[A\n",
|
1250 |
+
"\u001b[A\n",
|
1251 |
+
"\u001b[A\n",
|
1252 |
+
"\u001b[A\n",
|
1253 |
+
"\u001b[A\n",
|
1254 |
+
"\u001b[A\n",
|
1255 |
+
"\u001b[A\n",
|
1256 |
+
"\u001b[A\n",
|
1257 |
+
"\u001b[A\n",
|
1258 |
+
"\u001b[A\n",
|
1259 |
+
"\u001b[A\n",
|
1260 |
+
"\u001b[A\n",
|
1261 |
+
"\u001b[A\n",
|
1262 |
+
"\u001b[A\n",
|
1263 |
+
"\u001b[A\n",
|
1264 |
+
"\u001b[A\n",
|
1265 |
+
"\u001b[A\n",
|
1266 |
+
"\u001b[A\n",
|
1267 |
+
"\u001b[A\n",
|
1268 |
+
"\u001b[A\n",
|
1269 |
+
"\u001b[A\n",
|
1270 |
+
"\u001b[A\n",
|
1271 |
+
"\u001b[A\n",
|
1272 |
+
"\u001b[A\n",
|
1273 |
+
"\u001b[A\n",
|
1274 |
+
"\u001b[A\n",
|
1275 |
+
"\u001b[A\n",
|
1276 |
+
"\u001b[A\n",
|
1277 |
+
"\u001b[A\n",
|
1278 |
+
"\u001b[A\n",
|
1279 |
+
"\u001b[A\n",
|
1280 |
+
"\u001b[A\n",
|
1281 |
+
"\u001b[A\n",
|
1282 |
+
"\u001b[A\n",
|
1283 |
+
"\u001b[A\n",
|
1284 |
+
"\u001b[A\n",
|
1285 |
+
"\u001b[A\n",
|
1286 |
+
"\u001b[A\n",
|
1287 |
+
"\u001b[A\n",
|
1288 |
+
"\u001b[A\n",
|
1289 |
+
"\u001b[A\n",
|
1290 |
+
"\u001b[A\n",
|
1291 |
+
"\u001b[A\n",
|
1292 |
+
"\u001b[A\n",
|
1293 |
+
"\u001b[A\n",
|
1294 |
+
"\u001b[A\n",
|
1295 |
+
"\u001b[A\n",
|
1296 |
+
"\u001b[A\n",
|
1297 |
+
"\u001b[A\n",
|
1298 |
+
"\u001b[A\n",
|
1299 |
+
"\u001b[A\n",
|
1300 |
+
"\u001b[A\n",
|
1301 |
+
"\u001b[A\n",
|
1302 |
+
"\u001b[A\n",
|
1303 |
+
"\u001b[A\n",
|
1304 |
+
"\u001b[A\n",
|
1305 |
+
"\u001b[A\n",
|
1306 |
+
"\u001b[A\n",
|
1307 |
+
"\u001b[A\n",
|
1308 |
+
"\u001b[A\n",
|
1309 |
+
"\u001b[A\n",
|
1310 |
+
"\u001b[A\n",
|
1311 |
+
"\u001b[A\n",
|
1312 |
+
"\u001b[A\n",
|
1313 |
+
"\u001b[A\n",
|
1314 |
+
"\u001b[A\n",
|
1315 |
+
"\u001b[A\n",
|
1316 |
+
"\u001b[A\n",
|
1317 |
+
"\u001b[A\n",
|
1318 |
+
"\u001b[A\n",
|
1319 |
+
"\u001b[A\n",
|
1320 |
+
"\u001b[A\n",
|
1321 |
+
"\u001b[A\n",
|
1322 |
+
"\u001b[A\n",
|
1323 |
+
"\u001b[A\n",
|
1324 |
+
"\u001b[A\n",
|
1325 |
+
"\u001b[A\n",
|
1326 |
+
"\u001b[A\n",
|
1327 |
+
"\u001b[A\n",
|
1328 |
+
"\u001b[A\n",
|
1329 |
+
"\u001b[A\n",
|
1330 |
+
"\u001b[A\n",
|
1331 |
+
"\u001b[A\n",
|
1332 |
+
"\u001b[A\n",
|
1333 |
+
"\u001b[A\n",
|
1334 |
+
"\u001b[A\n",
|
1335 |
+
"\u001b[A\n",
|
1336 |
+
"\u001b[A\n",
|
1337 |
+
"\u001b[A\n",
|
1338 |
+
"\u001b[A\n",
|
1339 |
+
"\u001b[A\n",
|
1340 |
+
"\u001b[A\n",
|
1341 |
+
"\u001b[A\n",
|
1342 |
+
"\u001b[A\n",
|
1343 |
+
"\u001b[A\n",
|
1344 |
+
"\u001b[A\n",
|
1345 |
+
"\u001b[A\n",
|
1346 |
+
"\u001b[A\n",
|
1347 |
+
"\u001b[A\n",
|
1348 |
+
"\u001b[A\n",
|
1349 |
+
"\u001b[A\n",
|
1350 |
+
"\u001b[A\n",
|
1351 |
+
"\u001b[A\n",
|
1352 |
+
"\u001b[A\n",
|
1353 |
+
"\u001b[A\n",
|
1354 |
+
"\u001b[A\n",
|
1355 |
+
"\u001b[A\n",
|
1356 |
+
"\u001b[A\n",
|
1357 |
+
"\u001b[A\n",
|
1358 |
+
"\u001b[A\n",
|
1359 |
+
"\u001b[A\n",
|
1360 |
+
"\u001b[A\n",
|
1361 |
+
"\u001b[A\n",
|
1362 |
+
"\u001b[A\n",
|
1363 |
+
"\u001b[A\n",
|
1364 |
+
"\u001b[A\n",
|
1365 |
+
"\u001b[A\n",
|
1366 |
+
"\u001b[A\n",
|
1367 |
+
"\u001b[A\n",
|
1368 |
+
"\u001b[A\n",
|
1369 |
+
"\u001b[A\n",
|
1370 |
+
"\u001b[A\n",
|
1371 |
+
"\u001b[A\n",
|
1372 |
+
"\u001b[A\n",
|
1373 |
+
"\u001b[A\n",
|
1374 |
+
"\u001b[A\n",
|
1375 |
+
"\u001b[A\n",
|
1376 |
+
"\u001b[A\n",
|
1377 |
+
"\u001b[A\n",
|
1378 |
+
"\u001b[A\n",
|
1379 |
+
"\u001b[A\n",
|
1380 |
+
"\u001b[A\n",
|
1381 |
+
"\u001b[A\n",
|
1382 |
+
"\u001b[A\n",
|
1383 |
+
"\u001b[A\n",
|
1384 |
+
"\u001b[A\n",
|
1385 |
+
"\u001b[A\n",
|
1386 |
+
"\u001b[A\n",
|
1387 |
+
"\u001b[A\n",
|
1388 |
+
"\u001b[A\n",
|
1389 |
+
"\u001b[A\n",
|
1390 |
+
"\u001b[A\n",
|
1391 |
+
"\u001b[A\n",
|
1392 |
+
"\u001b[A\n",
|
1393 |
+
"\u001b[A\n",
|
1394 |
+
"\u001b[A\n",
|
1395 |
+
"\u001b[A\n",
|
1396 |
+
"\u001b[A\n",
|
1397 |
+
"\u001b[A\n",
|
1398 |
+
"\u001b[A\n",
|
1399 |
+
"\u001b[A\n",
|
1400 |
+
"\u001b[A\n",
|
1401 |
+
"\u001b[A\n",
|
1402 |
+
"\u001b[A\n",
|
1403 |
+
"\u001b[A\n",
|
1404 |
+
"\u001b[A\n",
|
1405 |
+
"\u001b[A\n",
|
1406 |
+
"\u001b[A\n",
|
1407 |
+
"\u001b[A\n",
|
1408 |
+
"\u001b[A\n",
|
1409 |
+
"\u001b[A\n",
|
1410 |
+
"\u001b[A\n",
|
1411 |
+
"\u001b[A\n",
|
1412 |
+
"\u001b[A\n",
|
1413 |
+
"\u001b[A\n",
|
1414 |
+
"\u001b[A\n",
|
1415 |
+
"\u001b[A\n",
|
1416 |
+
"\u001b[A\n",
|
1417 |
+
"\u001b[A\n",
|
1418 |
+
"\u001b[A\n",
|
1419 |
+
"\u001b[A\n",
|
1420 |
+
"\u001b[A\n",
|
1421 |
+
"\u001b[A\n",
|
1422 |
+
"\u001b[A\n",
|
1423 |
+
"\u001b[A\n",
|
1424 |
+
"\u001b[A\n",
|
1425 |
+
"\u001b[A\n",
|
1426 |
+
"\u001b[A\n",
|
1427 |
+
"\u001b[A\n",
|
1428 |
+
"\u001b[A\n",
|
1429 |
+
"\u001b[A\n",
|
1430 |
+
"\u001b[A\n",
|
1431 |
+
"\u001b[A\n",
|
1432 |
+
"\u001b[A\n",
|
1433 |
+
"\u001b[A\n",
|
1434 |
+
"\u001b[A\n",
|
1435 |
+
"\u001b[A\n",
|
1436 |
+
"\u001b[A\n",
|
1437 |
+
"\u001b[A\n",
|
1438 |
+
"\u001b[A\n",
|
1439 |
+
"\u001b[A\n",
|
1440 |
+
"\u001b[A\n",
|
1441 |
+
"\u001b[A\n",
|
1442 |
+
"\u001b[A\n",
|
1443 |
+
"\u001b[A\n",
|
1444 |
+
"\u001b[A\n",
|
1445 |
+
"\u001b[A\n",
|
1446 |
+
"\u001b[A\n",
|
1447 |
+
"\u001b[A\n",
|
1448 |
+
"\u001b[A\n",
|
1449 |
+
"\u001b[A\n",
|
1450 |
+
"\u001b[A\n",
|
1451 |
+
"\u001b[A\n",
|
1452 |
+
"\u001b[A\n",
|
1453 |
+
"\u001b[A\n",
|
1454 |
+
"\u001b[A\n",
|
1455 |
+
"\u001b[A\n",
|
1456 |
+
"\u001b[A\n",
|
1457 |
+
"\u001b[A\n",
|
1458 |
+
"\u001b[A\n",
|
1459 |
+
"\u001b[A\n",
|
1460 |
+
"\u001b[A\n",
|
1461 |
+
"\u001b[A\n",
|
1462 |
+
"\u001b[A\n",
|
1463 |
+
"\u001b[A\n",
|
1464 |
+
"\u001b[A\n",
|
1465 |
+
"\u001b[A\n",
|
1466 |
+
"\u001b[A\n",
|
1467 |
+
"\u001b[A\n",
|
1468 |
+
"\u001b[A\n",
|
1469 |
+
"\u001b[A\n",
|
1470 |
+
"\u001b[A\n",
|
1471 |
+
"\u001b[A\n",
|
1472 |
+
"\u001b[A\n",
|
1473 |
+
"\u001b[A\n",
|
1474 |
+
"\u001b[A\n",
|
1475 |
+
"\u001b[A\n",
|
1476 |
+
"\u001b[A\n",
|
1477 |
+
"\u001b[A\n",
|
1478 |
+
"\u001b[A\n",
|
1479 |
+
"\u001b[A\n",
|
1480 |
+
"\u001b[A\n",
|
1481 |
+
"\u001b[A\n",
|
1482 |
+
"\u001b[A\n",
|
1483 |
+
"\u001b[A\n",
|
1484 |
+
"\u001b[A\n",
|
1485 |
+
"\u001b[A\n",
|
1486 |
+
"\u001b[A\n",
|
1487 |
+
"\u001b[A\n",
|
1488 |
+
"\u001b[A\n",
|
1489 |
+
"\u001b[A\n",
|
1490 |
+
"\u001b[A\n",
|
1491 |
+
"\u001b[A\n",
|
1492 |
+
"\u001b[A\n",
|
1493 |
+
"\u001b[A\n",
|
1494 |
+
"\u001b[A\n",
|
1495 |
+
"\u001b[A\n",
|
1496 |
+
"\u001b[A\n",
|
1497 |
+
"\u001b[A\n",
|
1498 |
+
"\u001b[A\n",
|
1499 |
+
"\u001b[A\n",
|
1500 |
+
"\u001b[A\n",
|
1501 |
+
"\u001b[A\n",
|
1502 |
+
"\u001b[A\n",
|
1503 |
+
"\u001b[A\n",
|
1504 |
+
"\u001b[A\n",
|
1505 |
+
"\u001b[A\n",
|
1506 |
+
"\u001b[A\n",
|
1507 |
+
"\u001b[A\n",
|
1508 |
+
"\u001b[A\n",
|
1509 |
+
"\u001b[A\n",
|
1510 |
+
"\u001b[A\n",
|
1511 |
+
"\u001b[A\n",
|
1512 |
+
"\u001b[A\n",
|
1513 |
+
"\u001b[A\n",
|
1514 |
+
"\u001b[A\n",
|
1515 |
+
"\u001b[A\n",
|
1516 |
+
"\u001b[A\n",
|
1517 |
+
"\u001b[A\n",
|
1518 |
+
"\u001b[A\n",
|
1519 |
+
"\u001b[A\n",
|
1520 |
+
"\u001b[A\n",
|
1521 |
+
"\u001b[A\n",
|
1522 |
+
"\u001b[A\n",
|
1523 |
+
"\u001b[A\n",
|
1524 |
+
"\u001b[A\n",
|
1525 |
+
"\u001b[A\n",
|
1526 |
+
"\u001b[A\n",
|
1527 |
+
"\u001b[A\n",
|
1528 |
+
"\u001b[A\n",
|
1529 |
+
"\u001b[A\n",
|
1530 |
+
"\u001b[A\n",
|
1531 |
+
"\u001b[A\n",
|
1532 |
+
"\u001b[A\n",
|
1533 |
+
"\u001b[A\n",
|
1534 |
+
"\u001b[A\n",
|
1535 |
+
"\u001b[A\n",
|
1536 |
+
"\u001b[A\n",
|
1537 |
+
"\u001b[A\n",
|
1538 |
+
"\u001b[A\n",
|
1539 |
+
"\u001b[A\n",
|
1540 |
+
"\u001b[A\n",
|
1541 |
+
"\u001b[A\n",
|
1542 |
+
"\u001b[A\n",
|
1543 |
+
"\u001b[A\n",
|
1544 |
+
"\u001b[A\n",
|
1545 |
+
"\u001b[A\n",
|
1546 |
+
"\u001b[A\n",
|
1547 |
+
"\u001b[A\n",
|
1548 |
+
"\u001b[A\n",
|
1549 |
+
"\u001b[A\n",
|
1550 |
+
"\u001b[A\n",
|
1551 |
+
"\u001b[A\n",
|
1552 |
+
"\u001b[A\n",
|
1553 |
+
"\u001b[A\n",
|
1554 |
+
"\u001b[A\n",
|
1555 |
+
"\u001b[A\n",
|
1556 |
+
"\u001b[A\n",
|
1557 |
+
"\u001b[A\n",
|
1558 |
+
"\u001b[A\n",
|
1559 |
+
"\u001b[A\n",
|
1560 |
+
"\u001b[A\n",
|
1561 |
+
"\u001b[A\n",
|
1562 |
+
"\u001b[A\n",
|
1563 |
+
"\u001b[A\n",
|
1564 |
+
"\u001b[A\n",
|
1565 |
+
"\u001b[A\n",
|
1566 |
+
"\u001b[A\n",
|
1567 |
+
"\u001b[A\n",
|
1568 |
+
"\u001b[A\n",
|
1569 |
+
"\u001b[A\n",
|
1570 |
+
"\u001b[A\n",
|
1571 |
+
"\u001b[A\n",
|
1572 |
+
"\u001b[A\n",
|
1573 |
+
"\u001b[A\n",
|
1574 |
+
"\u001b[A\n",
|
1575 |
+
"\u001b[A\n",
|
1576 |
+
"\u001b[A\n",
|
1577 |
+
"\u001b[A\n",
|
1578 |
+
"\u001b[A\n",
|
1579 |
+
" \n",
|
1580 |
+
"\u001b[A \n",
|
1581 |
+
"\n",
|
1582 |
+
" 33%|███▎ | 5475/16425 [26:39<48:05, 3.80it/s]\n",
|
1583 |
+
"\u001b[A\n",
|
1584 |
+
"\u001b[A"
|
1585 |
+
]
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"name": "stdout",
|
1589 |
+
"output_type": "stream",
|
1590 |
+
"text": [
|
1591 |
+
"{'eval_loss': 1.1474684476852417, 'eval_runtime': 59.0937, 'eval_samples_per_second': 178.868, 'eval_steps_per_second': 11.186, 'epoch': 1.0}\n"
|
1592 |
+
]
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"name": "stderr",
|
1596 |
+
"output_type": "stream",
|
1597 |
+
"text": [
|
1598 |
+
" \n",
|
1599 |
+
" 33%|███▎ | 5500/16425 [26:46<49:41, 3.66it/s]"
|
1600 |
+
]
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"name": "stdout",
|
1604 |
+
"output_type": "stream",
|
1605 |
+
"text": [
|
1606 |
+
"{'loss': 1.1717, 'learning_rate': 1.330289193302892e-05, 'epoch': 1.0}\n"
|
1607 |
+
]
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"name": "stderr",
|
1611 |
+
"output_type": "stream",
|
1612 |
+
"text": [
|
1613 |
+
" \n",
|
1614 |
+
" 37%|███▋ | 6000/16425 [29:02<46:49, 3.71it/s]"
|
1615 |
+
]
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"name": "stdout",
|
1619 |
+
"output_type": "stream",
|
1620 |
+
"text": [
|
1621 |
+
"{'loss': 0.9552, 'learning_rate': 1.2694063926940641e-05, 'epoch': 1.1}\n"
|
1622 |
+
]
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"name": "stderr",
|
1626 |
+
"output_type": "stream",
|
1627 |
+
"text": [
|
1628 |
+
" \n",
|
1629 |
+
" 40%|███▉ | 6500/16425 [31:18<44:30, 3.72it/s]"
|
1630 |
+
]
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"name": "stdout",
|
1634 |
+
"output_type": "stream",
|
1635 |
+
"text": [
|
1636 |
+
"{'loss': 0.9877, 'learning_rate': 1.2085235920852361e-05, 'epoch': 1.19}\n"
|
1637 |
+
]
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"name": "stderr",
|
1641 |
+
"output_type": "stream",
|
1642 |
+
"text": [
|
1643 |
+
" \n",
|
1644 |
+
" 43%|████▎ | 7000/16425 [33:45<46:40, 3.37it/s]"
|
1645 |
+
]
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"name": "stdout",
|
1649 |
+
"output_type": "stream",
|
1650 |
+
"text": [
|
1651 |
+
"{'loss': 0.9877, 'learning_rate': 1.147640791476408e-05, 'epoch': 1.28}\n"
|
1652 |
+
]
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"name": "stderr",
|
1656 |
+
"output_type": "stream",
|
1657 |
+
"text": [
|
1658 |
+
" \n",
|
1659 |
+
" 46%|████▌ | 7500/16425 [36:13<43:45, 3.40it/s]"
|
1660 |
+
]
|
1661 |
+
},
|
1662 |
+
{
|
1663 |
+
"name": "stdout",
|
1664 |
+
"output_type": "stream",
|
1665 |
+
"text": [
|
1666 |
+
"{'loss': 0.9727, 'learning_rate': 1.08675799086758e-05, 'epoch': 1.37}\n"
|
1667 |
+
]
|
1668 |
+
},
|
1669 |
+
{
|
1670 |
+
"name": "stderr",
|
1671 |
+
"output_type": "stream",
|
1672 |
+
"text": [
|
1673 |
+
" \n",
|
1674 |
+
" 49%|████▊ | 8000/16425 [38:33<37:53, 3.71it/s]"
|
1675 |
+
]
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"name": "stdout",
|
1679 |
+
"output_type": "stream",
|
1680 |
+
"text": [
|
1681 |
+
"{'loss': 0.9713, 'learning_rate': 1.025875190258752e-05, 'epoch': 1.46}\n"
|
1682 |
+
]
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"name": "stderr",
|
1686 |
+
"output_type": "stream",
|
1687 |
+
"text": [
|
1688 |
+
" \n",
|
1689 |
+
" 52%|█████▏ | 8500/16425 [40:49<35:44, 3.70it/s]"
|
1690 |
+
]
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"name": "stdout",
|
1694 |
+
"output_type": "stream",
|
1695 |
+
"text": [
|
1696 |
+
"{'loss': 0.9441, 'learning_rate': 9.64992389649924e-06, 'epoch': 1.55}\n"
|
1697 |
+
]
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"name": "stderr",
|
1701 |
+
"output_type": "stream",
|
1702 |
+
"text": [
|
1703 |
+
" \n",
|
1704 |
+
" 55%|█████▍ | 9000/16425 [43:05<33:23, 3.71it/s]"
|
1705 |
+
]
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"name": "stdout",
|
1709 |
+
"output_type": "stream",
|
1710 |
+
"text": [
|
1711 |
+
"{'loss': 0.9527, 'learning_rate': 9.04109589041096e-06, 'epoch': 1.64}\n"
|
1712 |
+
]
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"name": "stderr",
|
1716 |
+
"output_type": "stream",
|
1717 |
+
"text": [
|
1718 |
+
" \n",
|
1719 |
+
" 58%|█████▊ | 9500/16425 [45:21<31:09, 3.70it/s]"
|
1720 |
+
]
|
1721 |
+
},
|
1722 |
+
{
|
1723 |
+
"name": "stdout",
|
1724 |
+
"output_type": "stream",
|
1725 |
+
"text": [
|
1726 |
+
"{'loss': 0.9311, 'learning_rate': 8.432267884322679e-06, 'epoch': 1.74}\n"
|
1727 |
+
]
|
1728 |
+
},
|
1729 |
+
{
|
1730 |
+
"name": "stderr",
|
1731 |
+
"output_type": "stream",
|
1732 |
+
"text": [
|
1733 |
+
" \n",
|
1734 |
+
" 61%|██████ | 10000/16425 [47:38<28:52, 3.71it/s]"
|
1735 |
+
]
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"name": "stdout",
|
1739 |
+
"output_type": "stream",
|
1740 |
+
"text": [
|
1741 |
+
"{'loss': 0.9318, 'learning_rate': 7.823439878234399e-06, 'epoch': 1.83}\n"
|
1742 |
+
]
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"name": "stderr",
|
1746 |
+
"output_type": "stream",
|
1747 |
+
"text": [
|
1748 |
+
" \n",
|
1749 |
+
" 64%|██████▍ | 10500/16425 [49:54<26:39, 3.70it/s]"
|
1750 |
+
]
|
1751 |
+
},
|
1752 |
+
{
|
1753 |
+
"name": "stdout",
|
1754 |
+
"output_type": "stream",
|
1755 |
+
"text": [
|
1756 |
+
"{'loss': 0.9639, 'learning_rate': 7.214611872146119e-06, 'epoch': 1.92}\n"
|
1757 |
+
]
|
1758 |
+
},
|
1759 |
+
{
|
1760 |
+
"name": "stderr",
|
1761 |
+
"output_type": "stream",
|
1762 |
+
"text": [
|
1763 |
+
" 67%|██████▋ | 10950/16425 [51:56<24:02, 3.80it/s] \n",
|
1764 |
+
"\u001b[A\n",
|
1765 |
+
"\u001b[A\n",
|
1766 |
+
"\u001b[A\n",
|
1767 |
+
"\u001b[A\n",
|
1768 |
+
"\u001b[A\n",
|
1769 |
+
"\u001b[A\n",
|
1770 |
+
"\u001b[A\n",
|
1771 |
+
"\u001b[A\n",
|
1772 |
+
"\u001b[A\n",
|
1773 |
+
"\u001b[A\n",
|
1774 |
+
"\u001b[A\n",
|
1775 |
+
"\u001b[A\n",
|
1776 |
+
"\u001b[A\n",
|
1777 |
+
"\u001b[A\n",
|
1778 |
+
"\u001b[A\n",
|
1779 |
+
"\u001b[A\n",
|
1780 |
+
"\u001b[A\n",
|
1781 |
+
"\u001b[A\n",
|
1782 |
+
"\u001b[A\n",
|
1783 |
+
"\u001b[A\n",
|
1784 |
+
"\u001b[A\n",
|
1785 |
+
"\u001b[A\n",
|
1786 |
+
"\u001b[A\n",
|
1787 |
+
"\u001b[A\n",
|
1788 |
+
"\u001b[A\n",
|
1789 |
+
"\u001b[A\n",
|
1790 |
+
"\u001b[A\n",
|
1791 |
+
"\u001b[A\n",
|
1792 |
+
"\u001b[A\n",
|
1793 |
+
"\u001b[A\n",
|
1794 |
+
"\u001b[A\n",
|
1795 |
+
"\u001b[A\n",
|
1796 |
+
"\u001b[A\n",
|
1797 |
+
"\u001b[A\n",
|
1798 |
+
"\u001b[A\n",
|
1799 |
+
"\u001b[A\n",
|
1800 |
+
"\u001b[A\n",
|
1801 |
+
"\u001b[A\n",
|
1802 |
+
"\u001b[A\n",
|
1803 |
+
"\u001b[A\n",
|
1804 |
+
"\u001b[A\n",
|
1805 |
+
"\u001b[A\n",
|
1806 |
+
"\u001b[A\n",
|
1807 |
+
"\u001b[A\n",
|
1808 |
+
"\u001b[A\n",
|
1809 |
+
"\u001b[A\n",
|
1810 |
+
"\u001b[A\n",
|
1811 |
+
"\u001b[A\n",
|
1812 |
+
"\u001b[A\n",
|
1813 |
+
"\u001b[A\n",
|
1814 |
+
"\u001b[A\n",
|
1815 |
+
"\u001b[A\n",
|
1816 |
+
"\u001b[A\n",
|
1817 |
+
"\u001b[A\n",
|
1818 |
+
"\u001b[A\n",
|
1819 |
+
"\u001b[A\n",
|
1820 |
+
"\u001b[A\n",
|
1821 |
+
"\u001b[A\n",
|
1822 |
+
"\u001b[A\n",
|
1823 |
+
"\u001b[A\n",
|
1824 |
+
"\u001b[A\n",
|
1825 |
+
"\u001b[A\n",
|
1826 |
+
"\u001b[A\n",
|
1827 |
+
"\u001b[A\n",
|
1828 |
+
"\u001b[A\n",
|
1829 |
+
"\u001b[A\n",
|
1830 |
+
"\u001b[A\n",
|
1831 |
+
"\u001b[A\n",
|
1832 |
+
"\u001b[A\n",
|
1833 |
+
"\u001b[A\n",
|
1834 |
+
"\u001b[A\n",
|
1835 |
+
"\u001b[A\n",
|
1836 |
+
"\u001b[A\n",
|
1837 |
+
"\u001b[A\n",
|
1838 |
+
"\u001b[A\n",
|
1839 |
+
"\u001b[A\n",
|
1840 |
+
"\u001b[A\n",
|
1841 |
+
"\u001b[A\n",
|
1842 |
+
"\u001b[A\n",
|
1843 |
+
"\u001b[A\n",
|
1844 |
+
"\u001b[A\n",
|
1845 |
+
"\u001b[A\n",
|
1846 |
+
"\u001b[A\n",
|
1847 |
+
"\u001b[A\n",
|
1848 |
+
"\u001b[A\n",
|
1849 |
+
"\u001b[A\n",
|
1850 |
+
"\u001b[A\n",
|
1851 |
+
"\u001b[A\n",
|
1852 |
+
"\u001b[A\n",
|
1853 |
+
"\u001b[A\n",
|
1854 |
+
"\u001b[A\n",
|
1855 |
+
"\u001b[A\n",
|
1856 |
+
"\u001b[A\n",
|
1857 |
+
"\u001b[A\n",
|
1858 |
+
"\u001b[A\n",
|
1859 |
+
"\u001b[A\n",
|
1860 |
+
"\u001b[A\n",
|
1861 |
+
"\u001b[A\n",
|
1862 |
+
"\u001b[A\n",
|
1863 |
+
"\u001b[A\n",
|
1864 |
+
"\u001b[A\n",
|
1865 |
+
"\u001b[A\n",
|
1866 |
+
"\u001b[A\n",
|
1867 |
+
"\u001b[A\n",
|
1868 |
+
"\u001b[A\n",
|
1869 |
+
"\u001b[A\n",
|
1870 |
+
"\u001b[A\n",
|
1871 |
+
"\u001b[A\n",
|
1872 |
+
"\u001b[A\n",
|
1873 |
+
"\u001b[A\n",
|
1874 |
+
"\u001b[A\n",
|
1875 |
+
"\u001b[A\n",
|
1876 |
+
"\u001b[A\n",
|
1877 |
+
"\u001b[A\n",
|
1878 |
+
"\u001b[A\n",
|
1879 |
+
"\u001b[A\n",
|
1880 |
+
"\u001b[A\n",
|
1881 |
+
"\u001b[A\n",
|
1882 |
+
"\u001b[A\n",
|
1883 |
+
"\u001b[A\n",
|
1884 |
+
"\u001b[A\n",
|
1885 |
+
"\u001b[A\n",
|
1886 |
+
"\u001b[A\n",
|
1887 |
+
"\u001b[A\n",
|
1888 |
+
"\u001b[A\n",
|
1889 |
+
"\u001b[A\n",
|
1890 |
+
"\u001b[A\n",
|
1891 |
+
"\u001b[A\n",
|
1892 |
+
"\u001b[A\n",
|
1893 |
+
"\u001b[A\n",
|
1894 |
+
"\u001b[A\n",
|
1895 |
+
"\u001b[A\n",
|
1896 |
+
"\u001b[A\n",
|
1897 |
+
"\u001b[A\n",
|
1898 |
+
"\u001b[A\n",
|
1899 |
+
"\u001b[A\n",
|
1900 |
+
"\u001b[A\n",
|
1901 |
+
"\u001b[A\n",
|
1902 |
+
"\u001b[A\n",
|
1903 |
+
"\u001b[A\n",
|
1904 |
+
"\u001b[A\n",
|
1905 |
+
"\u001b[A\n",
|
1906 |
+
"\u001b[A\n",
|
1907 |
+
"\u001b[A\n",
|
1908 |
+
"\u001b[A\n",
|
1909 |
+
"\u001b[A\n",
|
1910 |
+
"\u001b[A\n",
|
1911 |
+
"\u001b[A\n",
|
1912 |
+
"\u001b[A\n",
|
1913 |
+
"\u001b[A\n",
|
1914 |
+
"\u001b[A\n",
|
1915 |
+
"\u001b[A\n",
|
1916 |
+
"\u001b[A\n",
|
1917 |
+
"\u001b[A\n",
|
1918 |
+
"\u001b[A\n",
|
1919 |
+
"\u001b[A\n",
|
1920 |
+
"\u001b[A\n",
|
1921 |
+
"\u001b[A\n",
|
1922 |
+
"\u001b[A\n",
|
1923 |
+
"\u001b[A\n",
|
1924 |
+
"\u001b[A\n",
|
1925 |
+
"\u001b[A\n",
|
1926 |
+
"\u001b[A\n",
|
1927 |
+
"\u001b[A\n",
|
1928 |
+
"\u001b[A\n",
|
1929 |
+
"\u001b[A\n",
|
1930 |
+
"\u001b[A\n",
|
1931 |
+
"\u001b[A\n",
|
1932 |
+
"\u001b[A\n",
|
1933 |
+
"\u001b[A\n",
|
1934 |
+
"\u001b[A\n",
|
1935 |
+
"\u001b[A\n",
|
1936 |
+
"\u001b[A\n",
|
1937 |
+
"\u001b[A\n",
|
1938 |
+
"\u001b[A\n",
|
1939 |
+
"\u001b[A\n",
|
1940 |
+
"\u001b[A\n",
|
1941 |
+
"\u001b[A\n",
|
1942 |
+
"\u001b[A\n",
|
1943 |
+
"\u001b[A\n",
|
1944 |
+
"\u001b[A\n",
|
1945 |
+
"\u001b[A\n",
|
1946 |
+
"\u001b[A\n",
|
1947 |
+
"\u001b[A\n",
|
1948 |
+
"\u001b[A\n",
|
1949 |
+
"\u001b[A\n",
|
1950 |
+
"\u001b[A\n",
|
1951 |
+
"\u001b[A\n",
|
1952 |
+
"\u001b[A\n",
|
1953 |
+
"\u001b[A\n",
|
1954 |
+
"\u001b[A\n",
|
1955 |
+
"\u001b[A\n",
|
1956 |
+
"\u001b[A\n",
|
1957 |
+
"\u001b[A\n",
|
1958 |
+
"\u001b[A\n",
|
1959 |
+
"\u001b[A\n",
|
1960 |
+
"\u001b[A\n",
|
1961 |
+
"\u001b[A\n",
|
1962 |
+
"\u001b[A\n",
|
1963 |
+
"\u001b[A\n",
|
1964 |
+
"\u001b[A\n",
|
1965 |
+
"\u001b[A\n",
|
1966 |
+
"\u001b[A\n",
|
1967 |
+
"\u001b[A\n",
|
1968 |
+
"\u001b[A\n",
|
1969 |
+
"\u001b[A\n",
|
1970 |
+
"\u001b[A\n",
|
1971 |
+
"\u001b[A\n",
|
1972 |
+
"\u001b[A\n",
|
1973 |
+
"\u001b[A\n",
|
1974 |
+
"\u001b[A\n",
|
1975 |
+
"\u001b[A\n",
|
1976 |
+
"\u001b[A\n",
|
1977 |
+
"\u001b[A\n",
|
1978 |
+
"\u001b[A\n",
|
1979 |
+
"\u001b[A\n",
|
1980 |
+
"\u001b[A\n",
|
1981 |
+
"\u001b[A\n",
|
1982 |
+
"\u001b[A\n",
|
1983 |
+
"\u001b[A\n",
|
1984 |
+
"\u001b[A\n",
|
1985 |
+
"\u001b[A\n",
|
1986 |
+
"\u001b[A\n",
|
1987 |
+
"\u001b[A\n",
|
1988 |
+
"\u001b[A\n",
|
1989 |
+
"\u001b[A\n",
|
1990 |
+
"\u001b[A\n",
|
1991 |
+
"\u001b[A\n",
|
1992 |
+
"\u001b[A\n",
|
1993 |
+
"\u001b[A\n",
|
1994 |
+
"\u001b[A\n",
|
1995 |
+
"\u001b[A\n",
|
1996 |
+
"\u001b[A\n",
|
1997 |
+
"\u001b[A\n",
|
1998 |
+
"\u001b[A\n",
|
1999 |
+
"\u001b[A\n",
|
2000 |
+
"\u001b[A\n",
|
2001 |
+
"\u001b[A\n",
|
2002 |
+
"\u001b[A\n",
|
2003 |
+
"\u001b[A\n",
|
2004 |
+
"\u001b[A\n",
|
2005 |
+
"\u001b[A\n",
|
2006 |
+
"\u001b[A\n",
|
2007 |
+
"\u001b[A\n",
|
2008 |
+
"\u001b[A\n",
|
2009 |
+
"\u001b[A\n",
|
2010 |
+
"\u001b[A\n",
|
2011 |
+
"\u001b[A\n",
|
2012 |
+
"\u001b[A\n",
|
2013 |
+
"\u001b[A\n",
|
2014 |
+
"\u001b[A\n",
|
2015 |
+
"\u001b[A\n",
|
2016 |
+
"\u001b[A\n",
|
2017 |
+
"\u001b[A\n",
|
2018 |
+
"\u001b[A\n",
|
2019 |
+
"\u001b[A\n",
|
2020 |
+
"\u001b[A\n",
|
2021 |
+
"\u001b[A\n",
|
2022 |
+
"\u001b[A\n",
|
2023 |
+
"\u001b[A\n",
|
2024 |
+
"\u001b[A\n",
|
2025 |
+
"\u001b[A\n",
|
2026 |
+
"\u001b[A\n",
|
2027 |
+
"\u001b[A\n",
|
2028 |
+
"\u001b[A\n",
|
2029 |
+
"\u001b[A\n",
|
2030 |
+
"\u001b[A\n",
|
2031 |
+
"\u001b[A\n",
|
2032 |
+
"\u001b[A\n",
|
2033 |
+
"\u001b[A\n",
|
2034 |
+
"\u001b[A\n",
|
2035 |
+
"\u001b[A\n",
|
2036 |
+
"\u001b[A\n",
|
2037 |
+
"\u001b[A\n",
|
2038 |
+
"\u001b[A\n",
|
2039 |
+
"\u001b[A\n",
|
2040 |
+
"\u001b[A\n",
|
2041 |
+
"\u001b[A\n",
|
2042 |
+
"\u001b[A\n",
|
2043 |
+
"\u001b[A\n",
|
2044 |
+
"\u001b[A\n",
|
2045 |
+
"\u001b[A\n",
|
2046 |
+
"\u001b[A\n",
|
2047 |
+
"\u001b[A\n",
|
2048 |
+
"\u001b[A\n",
|
2049 |
+
"\u001b[A\n",
|
2050 |
+
"\u001b[A\n",
|
2051 |
+
"\u001b[A\n",
|
2052 |
+
"\u001b[A\n",
|
2053 |
+
"\u001b[A\n",
|
2054 |
+
"\u001b[A\n",
|
2055 |
+
"\u001b[A\n",
|
2056 |
+
"\u001b[A\n",
|
2057 |
+
"\u001b[A\n",
|
2058 |
+
"\u001b[A\n",
|
2059 |
+
"\u001b[A\n",
|
2060 |
+
"\u001b[A\n",
|
2061 |
+
"\u001b[A\n",
|
2062 |
+
"\u001b[A\n",
|
2063 |
+
"\u001b[A\n",
|
2064 |
+
"\u001b[A\n",
|
2065 |
+
"\u001b[A\n",
|
2066 |
+
"\u001b[A\n",
|
2067 |
+
"\u001b[A\n",
|
2068 |
+
"\u001b[A\n",
|
2069 |
+
"\u001b[A\n",
|
2070 |
+
"\u001b[A\n",
|
2071 |
+
"\u001b[A\n",
|
2072 |
+
"\u001b[A\n",
|
2073 |
+
"\u001b[A\n",
|
2074 |
+
"\u001b[A\n",
|
2075 |
+
"\u001b[A\n",
|
2076 |
+
"\u001b[A\n",
|
2077 |
+
"\u001b[A\n",
|
2078 |
+
"\u001b[A\n",
|
2079 |
+
"\u001b[A\n",
|
2080 |
+
"\u001b[A\n",
|
2081 |
+
"\u001b[A\n",
|
2082 |
+
"\u001b[A\n",
|
2083 |
+
"\u001b[A\n",
|
2084 |
+
"\u001b[A\n",
|
2085 |
+
"\u001b[A\n",
|
2086 |
+
"\u001b[A\n",
|
2087 |
+
"\u001b[A\n",
|
2088 |
+
"\u001b[A\n",
|
2089 |
+
"\u001b[A\n",
|
2090 |
+
"\u001b[A\n",
|
2091 |
+
"\u001b[A\n",
|
2092 |
+
"\u001b[A\n",
|
2093 |
+
"\u001b[A\n",
|
2094 |
+
" \n",
|
2095 |
+
"\n",
|
2096 |
+
"\u001b[A\u001b[A \n",
|
2097 |
+
" 67%|██████▋ | 10950/16425 [52:56<24:02, 3.80it/s]\n",
|
2098 |
+
"\u001b[A\n",
|
2099 |
+
"\u001b[A"
|
2100 |
+
]
|
2101 |
+
},
|
2102 |
+
{
|
2103 |
+
"name": "stdout",
|
2104 |
+
"output_type": "stream",
|
2105 |
+
"text": [
|
2106 |
+
"{'eval_loss': 1.0952799320220947, 'eval_runtime': 59.2147, 'eval_samples_per_second': 178.503, 'eval_steps_per_second': 11.163, 'epoch': 2.0}\n"
|
2107 |
+
]
|
2108 |
+
},
|
2109 |
+
{
|
2110 |
+
"name": "stderr",
|
2111 |
+
"output_type": "stream",
|
2112 |
+
"text": [
|
2113 |
+
" \n",
|
2114 |
+
" 67%|██████▋ | 11000/16425 [53:09<24:24, 3.71it/s]"
|
2115 |
+
]
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"name": "stdout",
|
2119 |
+
"output_type": "stream",
|
2120 |
+
"text": [
|
2121 |
+
"{'loss': 0.9442, 'learning_rate': 6.605783866057839e-06, 'epoch': 2.01}\n"
|
2122 |
+
]
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"name": "stderr",
|
2126 |
+
"output_type": "stream",
|
2127 |
+
"text": [
|
2128 |
+
" \n",
|
2129 |
+
" 70%|███████ | 11500/16425 [55:29<24:05, 3.41it/s]"
|
2130 |
+
]
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"name": "stdout",
|
2134 |
+
"output_type": "stream",
|
2135 |
+
"text": [
|
2136 |
+
"{'loss': 0.7817, 'learning_rate': 5.996955859969558e-06, 'epoch': 2.1}\n"
|
2137 |
+
]
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"name": "stderr",
|
2141 |
+
"output_type": "stream",
|
2142 |
+
"text": [
|
2143 |
+
" \n",
|
2144 |
+
" 73%|███████▎ | 12000/16425 [57:57<21:38, 3.41it/s]"
|
2145 |
+
]
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"name": "stdout",
|
2149 |
+
"output_type": "stream",
|
2150 |
+
"text": [
|
2151 |
+
"{'loss': 0.7787, 'learning_rate': 5.388127853881279e-06, 'epoch': 2.19}\n"
|
2152 |
+
]
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"name": "stderr",
|
2156 |
+
"output_type": "stream",
|
2157 |
+
"text": [
|
2158 |
+
" \n",
|
2159 |
+
" 76%|███████▌ | 12500/16425 [1:00:25<17:38, 3.71it/s]"
|
2160 |
+
]
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"name": "stdout",
|
2164 |
+
"output_type": "stream",
|
2165 |
+
"text": [
|
2166 |
+
"{'loss': 0.7367, 'learning_rate': 4.779299847792998e-06, 'epoch': 2.28}\n"
|
2167 |
+
]
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"name": "stderr",
|
2171 |
+
"output_type": "stream",
|
2172 |
+
"text": [
|
2173 |
+
" \n",
|
2174 |
+
" 79%|███████▉ | 13000/16425 [1:02:41<15:24, 3.70it/s]"
|
2175 |
+
]
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"name": "stdout",
|
2179 |
+
"output_type": "stream",
|
2180 |
+
"text": [
|
2181 |
+
"{'loss': 0.7513, 'learning_rate': 4.170471841704719e-06, 'epoch': 2.37}\n"
|
2182 |
+
]
|
2183 |
+
},
|
2184 |
+
{
|
2185 |
+
"name": "stderr",
|
2186 |
+
"output_type": "stream",
|
2187 |
+
"text": [
|
2188 |
+
" \n",
|
2189 |
+
" 82%|████████▏ | 13500/16425 [1:04:57<13:10, 3.70it/s]"
|
2190 |
+
]
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"name": "stdout",
|
2194 |
+
"output_type": "stream",
|
2195 |
+
"text": [
|
2196 |
+
"{'loss': 0.7739, 'learning_rate': 3.5616438356164386e-06, 'epoch': 2.47}\n"
|
2197 |
+
]
|
2198 |
+
},
|
2199 |
+
{
|
2200 |
+
"name": "stderr",
|
2201 |
+
"output_type": "stream",
|
2202 |
+
"text": [
|
2203 |
+
" \n",
|
2204 |
+
" 85%|████████▌ | 14000/16425 [1:07:14<11:57, 3.38it/s]"
|
2205 |
+
]
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"name": "stdout",
|
2209 |
+
"output_type": "stream",
|
2210 |
+
"text": [
|
2211 |
+
"{'loss': 0.7591, 'learning_rate': 2.9528158295281586e-06, 'epoch': 2.56}\n"
|
2212 |
+
]
|
2213 |
+
},
|
2214 |
+
{
|
2215 |
+
"name": "stderr",
|
2216 |
+
"output_type": "stream",
|
2217 |
+
"text": [
|
2218 |
+
" \n",
|
2219 |
+
" 88%|████████▊ | 14500/16425 [1:09:43<09:28, 3.39it/s]"
|
2220 |
+
]
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"name": "stdout",
|
2224 |
+
"output_type": "stream",
|
2225 |
+
"text": [
|
2226 |
+
"{'loss': 0.7491, 'learning_rate': 2.343987823439878e-06, 'epoch': 2.65}\n"
|
2227 |
+
]
|
2228 |
+
},
|
2229 |
+
{
|
2230 |
+
"name": "stderr",
|
2231 |
+
"output_type": "stream",
|
2232 |
+
"text": [
|
2233 |
+
" \n",
|
2234 |
+
" 91%|█████████▏| 15000/16425 [1:12:12<07:00, 3.39it/s]"
|
2235 |
+
]
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"name": "stdout",
|
2239 |
+
"output_type": "stream",
|
2240 |
+
"text": [
|
2241 |
+
"{'loss': 0.7394, 'learning_rate': 1.7351598173515982e-06, 'epoch': 2.74}\n"
|
2242 |
+
]
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"name": "stderr",
|
2246 |
+
"output_type": "stream",
|
2247 |
+
"text": [
|
2248 |
+
" \n",
|
2249 |
+
" 94%|█████████▍| 15500/16425 [1:14:29<04:10, 3.70it/s]"
|
2250 |
+
]
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"name": "stdout",
|
2254 |
+
"output_type": "stream",
|
2255 |
+
"text": [
|
2256 |
+
"{'loss': 0.7548, 'learning_rate': 1.1263318112633182e-06, 'epoch': 2.83}\n"
|
2257 |
+
]
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"name": "stderr",
|
2261 |
+
"output_type": "stream",
|
2262 |
+
"text": [
|
2263 |
+
" \n",
|
2264 |
+
" 97%|█████████▋| 16000/16425 [1:16:46<01:54, 3.70it/s]"
|
2265 |
+
]
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"name": "stdout",
|
2269 |
+
"output_type": "stream",
|
2270 |
+
"text": [
|
2271 |
+
"{'loss': 0.7728, 'learning_rate': 5.17503805175038e-07, 'epoch': 2.92}\n"
|
2272 |
+
]
|
2273 |
+
},
|
2274 |
+
{
|
2275 |
+
"name": "stderr",
|
2276 |
+
"output_type": "stream",
|
2277 |
+
"text": [
|
2278 |
+
"100%|██████████| 16425/16425 [1:18:46<00:00, 3.48it/s]\n",
|
2279 |
+
"\u001b[A\n",
|
2280 |
+
"\u001b[A\n",
|
2281 |
+
"\u001b[A\n",
|
2282 |
+
"\u001b[A\n",
|
2283 |
+
"\u001b[A\n",
|
2284 |
+
"\u001b[A\n",
|
2285 |
+
"\u001b[A\n",
|
2286 |
+
"\u001b[A\n",
|
2287 |
+
"\u001b[A\n",
|
2288 |
+
"\u001b[A\n",
|
2289 |
+
"\u001b[A\n",
|
2290 |
+
"\u001b[A\n",
|
2291 |
+
"\u001b[A\n",
|
2292 |
+
"\u001b[A\n",
|
2293 |
+
"\u001b[A\n",
|
2294 |
+
"\u001b[A\n",
|
2295 |
+
"\u001b[A\n",
|
2296 |
+
"\u001b[A\n",
|
2297 |
+
"\u001b[A\n",
|
2298 |
+
"\u001b[A\n",
|
2299 |
+
"\u001b[A\n",
|
2300 |
+
"\u001b[A\n",
|
2301 |
+
"\u001b[A\n",
|
2302 |
+
"\u001b[A\n",
|
2303 |
+
"\u001b[A\n",
|
2304 |
+
"\u001b[A\n",
|
2305 |
+
"\u001b[A\n",
|
2306 |
+
"\u001b[A\n",
|
2307 |
+
"\u001b[A\n",
|
2308 |
+
"\u001b[A\n",
|
2309 |
+
"\u001b[A\n",
|
2310 |
+
"\u001b[A\n",
|
2311 |
+
"\u001b[A\n",
|
2312 |
+
"\u001b[A\n",
|
2313 |
+
"\u001b[A\n",
|
2314 |
+
"\u001b[A\n",
|
2315 |
+
"\u001b[A\n",
|
2316 |
+
"\u001b[A\n",
|
2317 |
+
"\u001b[A\n",
|
2318 |
+
"\u001b[A\n",
|
2319 |
+
"\u001b[A\n",
|
2320 |
+
"\u001b[A\n",
|
2321 |
+
"\u001b[A\n",
|
2322 |
+
"\u001b[A\n",
|
2323 |
+
"\u001b[A\n",
|
2324 |
+
"\u001b[A\n",
|
2325 |
+
"\u001b[A\n",
|
2326 |
+
"\u001b[A\n",
|
2327 |
+
"\u001b[A\n",
|
2328 |
+
"\u001b[A\n",
|
2329 |
+
"\u001b[A\n",
|
2330 |
+
"\u001b[A\n",
|
2331 |
+
"\u001b[A\n",
|
2332 |
+
"\u001b[A\n",
|
2333 |
+
"\u001b[A\n",
|
2334 |
+
"\u001b[A\n",
|
2335 |
+
"\u001b[A\n",
|
2336 |
+
"\u001b[A\n",
|
2337 |
+
"\u001b[A\n",
|
2338 |
+
"\u001b[A\n",
|
2339 |
+
"\u001b[A\n",
|
2340 |
+
"\u001b[A\n",
|
2341 |
+
"\u001b[A\n",
|
2342 |
+
"\u001b[A\n",
|
2343 |
+
"\u001b[A\n",
|
2344 |
+
"\u001b[A\n",
|
2345 |
+
"\u001b[A\n",
|
2346 |
+
"\u001b[A\n",
|
2347 |
+
"\u001b[A\n",
|
2348 |
+
"\u001b[A\n",
|
2349 |
+
"\u001b[A\n",
|
2350 |
+
"\u001b[A\n",
|
2351 |
+
"\u001b[A\n",
|
2352 |
+
"\u001b[A\n",
|
2353 |
+
"\u001b[A\n",
|
2354 |
+
"\u001b[A\n",
|
2355 |
+
"\u001b[A\n",
|
2356 |
+
"\u001b[A\n",
|
2357 |
+
"\u001b[A\n",
|
2358 |
+
"\u001b[A\n",
|
2359 |
+
"\u001b[A\n",
|
2360 |
+
"\u001b[A\n",
|
2361 |
+
"\u001b[A\n",
|
2362 |
+
"\u001b[A\n",
|
2363 |
+
"\u001b[A\n",
|
2364 |
+
"\u001b[A\n",
|
2365 |
+
"\u001b[A\n",
|
2366 |
+
"\u001b[A\n",
|
2367 |
+
"\u001b[A\n",
|
2368 |
+
"\u001b[A\n",
|
2369 |
+
"\u001b[A\n",
|
2370 |
+
"\u001b[A\n",
|
2371 |
+
"\u001b[A\n",
|
2372 |
+
"\u001b[A\n",
|
2373 |
+
"\u001b[A\n",
|
2374 |
+
"\u001b[A\n",
|
2375 |
+
"\u001b[A\n",
|
2376 |
+
"\u001b[A\n",
|
2377 |
+
"\u001b[A\n",
|
2378 |
+
"\u001b[A\n",
|
2379 |
+
"\u001b[A\n",
|
2380 |
+
"\u001b[A\n",
|
2381 |
+
"\u001b[A\n",
|
2382 |
+
"\u001b[A\n",
|
2383 |
+
"\u001b[A\n",
|
2384 |
+
"\u001b[A\n",
|
2385 |
+
"\u001b[A\n",
|
2386 |
+
"\u001b[A\n",
|
2387 |
+
"\u001b[A\n",
|
2388 |
+
"\u001b[A\n",
|
2389 |
+
"\u001b[A\n",
|
2390 |
+
"\u001b[A\n",
|
2391 |
+
"\u001b[A\n",
|
2392 |
+
"\u001b[A\n",
|
2393 |
+
"\u001b[A\n",
|
2394 |
+
"\u001b[A\n",
|
2395 |
+
"\u001b[A\n",
|
2396 |
+
"\u001b[A\n",
|
2397 |
+
"\u001b[A\n",
|
2398 |
+
"\u001b[A\n",
|
2399 |
+
"\u001b[A\n",
|
2400 |
+
"\u001b[A\n",
|
2401 |
+
"\u001b[A\n",
|
2402 |
+
"\u001b[A\n",
|
2403 |
+
"\u001b[A\n",
|
2404 |
+
"\u001b[A\n",
|
2405 |
+
"\u001b[A\n",
|
2406 |
+
"\u001b[A\n",
|
2407 |
+
"\u001b[A\n",
|
2408 |
+
"\u001b[A\n",
|
2409 |
+
"\u001b[A\n",
|
2410 |
+
"\u001b[A\n",
|
2411 |
+
"\u001b[A\n",
|
2412 |
+
"\u001b[A\n",
|
2413 |
+
"\u001b[A\n",
|
2414 |
+
"\u001b[A\n",
|
2415 |
+
"\u001b[A\n",
|
2416 |
+
"\u001b[A\n",
|
2417 |
+
"\u001b[A\n",
|
2418 |
+
"\u001b[A\n",
|
2419 |
+
"\u001b[A\n",
|
2420 |
+
"\u001b[A\n",
|
2421 |
+
"\u001b[A\n",
|
2422 |
+
"\u001b[A\n",
|
2423 |
+
"\u001b[A\n",
|
2424 |
+
"\u001b[A\n",
|
2425 |
+
"\u001b[A\n",
|
2426 |
+
"\u001b[A\n",
|
2427 |
+
"\u001b[A\n",
|
2428 |
+
"\u001b[A\n",
|
2429 |
+
"\u001b[A\n",
|
2430 |
+
"\u001b[A\n",
|
2431 |
+
"\u001b[A\n",
|
2432 |
+
"\u001b[A\n",
|
2433 |
+
"\u001b[A\n",
|
2434 |
+
"\u001b[A\n",
|
2435 |
+
"\u001b[A\n",
|
2436 |
+
"\u001b[A\n",
|
2437 |
+
"\u001b[A\n",
|
2438 |
+
"\u001b[A\n",
|
2439 |
+
"\u001b[A\n",
|
2440 |
+
"\u001b[A\n",
|
2441 |
+
"\u001b[A\n",
|
2442 |
+
"\u001b[A\n",
|
2443 |
+
"\u001b[A\n",
|
2444 |
+
"\u001b[A\n",
|
2445 |
+
"\u001b[A\n",
|
2446 |
+
"\u001b[A\n",
|
2447 |
+
"\u001b[A\n",
|
2448 |
+
"\u001b[A\n",
|
2449 |
+
"\u001b[A\n",
|
2450 |
+
"\u001b[A\n",
|
2451 |
+
"\u001b[A\n",
|
2452 |
+
"\u001b[A\n",
|
2453 |
+
"\u001b[A\n",
|
2454 |
+
"\u001b[A\n",
|
2455 |
+
"\u001b[A\n",
|
2456 |
+
"\u001b[A\n",
|
2457 |
+
"\u001b[A\n",
|
2458 |
+
"\u001b[A\n",
|
2459 |
+
"\u001b[A\n",
|
2460 |
+
"\u001b[A\n",
|
2461 |
+
"\u001b[A\n",
|
2462 |
+
"\u001b[A\n",
|
2463 |
+
"\u001b[A\n",
|
2464 |
+
"\u001b[A\n",
|
2465 |
+
"\u001b[A\n",
|
2466 |
+
"\u001b[A\n",
|
2467 |
+
"\u001b[A\n",
|
2468 |
+
"\u001b[A\n",
|
2469 |
+
"\u001b[A\n",
|
2470 |
+
"\u001b[A\n",
|
2471 |
+
"\u001b[A\n",
|
2472 |
+
"\u001b[A\n",
|
2473 |
+
"\u001b[A\n",
|
2474 |
+
"\u001b[A\n",
|
2475 |
+
"\u001b[A\n",
|
2476 |
+
"\u001b[A\n",
|
2477 |
+
"\u001b[A\n",
|
2478 |
+
"\u001b[A\n",
|
2479 |
+
"\u001b[A\n",
|
2480 |
+
"\u001b[A\n",
|
2481 |
+
"\u001b[A\n",
|
2482 |
+
"\u001b[A\n",
|
2483 |
+
"\u001b[A\n",
|
2484 |
+
"\u001b[A\n",
|
2485 |
+
"\u001b[A\n",
|
2486 |
+
"\u001b[A\n",
|
2487 |
+
"\u001b[A\n",
|
2488 |
+
"\u001b[A\n",
|
2489 |
+
"\u001b[A\n",
|
2490 |
+
"\u001b[A\n",
|
2491 |
+
"\u001b[A\n",
|
2492 |
+
"\u001b[A\n",
|
2493 |
+
"\u001b[A\n",
|
2494 |
+
"\u001b[A\n",
|
2495 |
+
"\u001b[A\n",
|
2496 |
+
"\u001b[A\n",
|
2497 |
+
"\u001b[A\n",
|
2498 |
+
"\u001b[A\n",
|
2499 |
+
"\u001b[A\n",
|
2500 |
+
"\u001b[A\n",
|
2501 |
+
"\u001b[A\n",
|
2502 |
+
"\u001b[A\n",
|
2503 |
+
"\u001b[A\n",
|
2504 |
+
"\u001b[A\n",
|
2505 |
+
"\u001b[A\n",
|
2506 |
+
"\u001b[A\n",
|
2507 |
+
"\u001b[A\n",
|
2508 |
+
"\u001b[A\n",
|
2509 |
+
"\u001b[A\n",
|
2510 |
+
"\u001b[A\n",
|
2511 |
+
"\u001b[A\n",
|
2512 |
+
"\u001b[A\n",
|
2513 |
+
"\u001b[A\n",
|
2514 |
+
"\u001b[A\n",
|
2515 |
+
"\u001b[A\n",
|
2516 |
+
"\u001b[A\n",
|
2517 |
+
"\u001b[A\n",
|
2518 |
+
"\u001b[A\n",
|
2519 |
+
"\u001b[A\n",
|
2520 |
+
"\u001b[A\n",
|
2521 |
+
"\u001b[A\n",
|
2522 |
+
"\u001b[A\n",
|
2523 |
+
"\u001b[A\n",
|
2524 |
+
"\u001b[A\n",
|
2525 |
+
"\u001b[A\n",
|
2526 |
+
"\u001b[A\n",
|
2527 |
+
"\u001b[A\n",
|
2528 |
+
"\u001b[A\n",
|
2529 |
+
"\u001b[A\n",
|
2530 |
+
"\u001b[A\n",
|
2531 |
+
"\u001b[A\n",
|
2532 |
+
"\u001b[A\n",
|
2533 |
+
"\u001b[A\n",
|
2534 |
+
"\u001b[A\n",
|
2535 |
+
"\u001b[A\n",
|
2536 |
+
"\u001b[A\n",
|
2537 |
+
"\u001b[A\n",
|
2538 |
+
"\u001b[A\n",
|
2539 |
+
"\u001b[A\n",
|
2540 |
+
"\u001b[A\n",
|
2541 |
+
"\u001b[A\n",
|
2542 |
+
"\u001b[A\n",
|
2543 |
+
"\u001b[A\n",
|
2544 |
+
"\u001b[A\n",
|
2545 |
+
"\u001b[A\n",
|
2546 |
+
"\u001b[A\n",
|
2547 |
+
"\u001b[A\n",
|
2548 |
+
"\u001b[A\n",
|
2549 |
+
"\u001b[A\n",
|
2550 |
+
"\u001b[A\n",
|
2551 |
+
"\u001b[A\n",
|
2552 |
+
"\u001b[A\n",
|
2553 |
+
"\u001b[A\n",
|
2554 |
+
"\u001b[A\n",
|
2555 |
+
"\u001b[A\n",
|
2556 |
+
"\u001b[A\n",
|
2557 |
+
"\u001b[A\n",
|
2558 |
+
"\u001b[A\n",
|
2559 |
+
"\u001b[A\n",
|
2560 |
+
"\u001b[A\n",
|
2561 |
+
"\u001b[A\n",
|
2562 |
+
"\u001b[A\n",
|
2563 |
+
"\u001b[A\n",
|
2564 |
+
"\u001b[A\n",
|
2565 |
+
"\u001b[A\n",
|
2566 |
+
"\u001b[A\n",
|
2567 |
+
"\u001b[A\n",
|
2568 |
+
"\u001b[A\n",
|
2569 |
+
"\u001b[A\n",
|
2570 |
+
"\u001b[A\n",
|
2571 |
+
"\u001b[A\n",
|
2572 |
+
"\u001b[A\n",
|
2573 |
+
"\u001b[A\n",
|
2574 |
+
"\u001b[A\n",
|
2575 |
+
"\u001b[A\n",
|
2576 |
+
"\u001b[A\n",
|
2577 |
+
"\u001b[A\n",
|
2578 |
+
"\u001b[A\n",
|
2579 |
+
"\u001b[A\n",
|
2580 |
+
"\u001b[A\n",
|
2581 |
+
"\u001b[A\n",
|
2582 |
+
"\u001b[A\n",
|
2583 |
+
"\u001b[A\n",
|
2584 |
+
"\u001b[A\n",
|
2585 |
+
"\u001b[A\n",
|
2586 |
+
"\u001b[A\n",
|
2587 |
+
"\u001b[A\n",
|
2588 |
+
"\u001b[A\n",
|
2589 |
+
"\u001b[A\n",
|
2590 |
+
"\u001b[A\n",
|
2591 |
+
"\u001b[A\n",
|
2592 |
+
"\u001b[A\n",
|
2593 |
+
"\u001b[A\n",
|
2594 |
+
"\u001b[A\n",
|
2595 |
+
"\u001b[A\n",
|
2596 |
+
"\u001b[A\n",
|
2597 |
+
"\u001b[A\n",
|
2598 |
+
"\u001b[A\n",
|
2599 |
+
"\u001b[A\n",
|
2600 |
+
"\u001b[A\n",
|
2601 |
+
"\u001b[A\n",
|
2602 |
+
"\u001b[A\n",
|
2603 |
+
"\u001b[A\n",
|
2604 |
+
"\u001b[A\n",
|
2605 |
+
"\u001b[A\n",
|
2606 |
+
"\u001b[A\n",
|
2607 |
+
"\u001b[A\n",
|
2608 |
+
"\u001b[A\n",
|
2609 |
+
"\u001b[A\n",
|
2610 |
+
"\u001b[A\n",
|
2611 |
+
"\u001b[A\n",
|
2612 |
+
"\u001b[A\n",
|
2613 |
+
"\u001b[A\n",
|
2614 |
+
"\u001b[A\n",
|
2615 |
+
"\u001b[A\n",
|
2616 |
+
"\u001b[A\n",
|
2617 |
+
"\u001b[A\n",
|
2618 |
+
"\u001b[A\n",
|
2619 |
+
"\u001b[A\n",
|
2620 |
+
" \n",
|
2621 |
+
"\u001b[A \n",
|
2622 |
+
"\n",
|
2623 |
+
"100%|██████████| 16425/16425 [1:19:51<00:00, 3.48it/s]\n",
|
2624 |
+
"\u001b[A\n",
|
2625 |
+
" \n",
|
2626 |
+
"100%|██████████| 16425/16425 [1:19:51<00:00, 3.43it/s]"
|
2627 |
+
]
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"name": "stdout",
|
2631 |
+
"output_type": "stream",
|
2632 |
+
"text": [
|
2633 |
+
"{'eval_loss': 1.1455239057540894, 'eval_runtime': 64.9253, 'eval_samples_per_second': 162.802, 'eval_steps_per_second': 10.181, 'epoch': 3.0}\n",
|
2634 |
+
"{'train_runtime': 4791.8158, 'train_samples_per_second': 54.843, 'train_steps_per_second': 3.428, 'train_loss': 1.0782835241866437, 'epoch': 3.0}\n"
|
2635 |
+
]
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"name": "stderr",
|
2639 |
+
"output_type": "stream",
|
2640 |
+
"text": [
|
2641 |
+
"\n"
|
2642 |
+
]
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"data": {
|
2646 |
+
"text/plain": [
|
2647 |
+
"TrainOutput(global_step=16425, training_loss=1.0782835241866437, metrics={'train_runtime': 4791.8158, 'train_samples_per_second': 54.843, 'train_steps_per_second': 3.428, 'train_loss': 1.0782835241866437, 'epoch': 3.0})"
|
2648 |
+
]
|
2649 |
+
},
|
2650 |
+
"execution_count": 17,
|
2651 |
+
"metadata": {},
|
2652 |
+
"output_type": "execute_result"
|
2653 |
+
}
|
2654 |
+
],
|
2655 |
+
"source": [
|
2656 |
+
"trainer.train()"
|
2657 |
+
]
|
2658 |
+
},
|
2659 |
+
{
|
2660 |
+
"cell_type": "code",
|
2661 |
+
"execution_count": 6,
|
2662 |
+
"metadata": {},
|
2663 |
+
"outputs": [],
|
2664 |
+
"source": [
|
2665 |
+
"question = \"how many parameters in bloom?\"\n",
|
2666 |
+
"context = \"BLOOM has 176 billion parameters and can generate text in 46 languages natural languages and 13 programming languages.\""
|
2667 |
+
]
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"cell_type": "code",
|
2671 |
+
"execution_count": 7,
|
2672 |
+
"metadata": {},
|
2673 |
+
"outputs": [
|
2674 |
+
{
|
2675 |
+
"data": {
|
2676 |
+
"text/plain": [
|
2677 |
+
"{'score': 0.8450772762298584, 'start': 10, 'end': 21, 'answer': '176 billion'}"
|
2678 |
+
]
|
2679 |
+
},
|
2680 |
+
"execution_count": 7,
|
2681 |
+
"metadata": {},
|
2682 |
+
"output_type": "execute_result"
|
2683 |
+
}
|
2684 |
+
],
|
2685 |
+
"source": [
|
2686 |
+
"from transformers import pipeline\n",
|
2687 |
+
"question_answerer = pipeline(\"question-answering\", model=\"finetuning_squad/checkpoint-16000\")\n",
|
2688 |
+
"question_answerer(question=question, context=context)"
|
2689 |
+
]
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"cell_type": "code",
|
2693 |
+
"execution_count": null,
|
2694 |
+
"metadata": {},
|
2695 |
+
"outputs": [],
|
2696 |
+
"source": []
|
2697 |
+
}
|
2698 |
+
],
|
2699 |
+
"metadata": {
|
2700 |
+
"kernelspec": {
|
2701 |
+
"display_name": "transformer",
|
2702 |
+
"language": "python",
|
2703 |
+
"name": "python3"
|
2704 |
+
},
|
2705 |
+
"language_info": {
|
2706 |
+
"codemirror_mode": {
|
2707 |
+
"name": "ipython",
|
2708 |
+
"version": 3
|
2709 |
+
},
|
2710 |
+
"file_extension": ".py",
|
2711 |
+
"mimetype": "text/x-python",
|
2712 |
+
"name": "python",
|
2713 |
+
"nbconvert_exporter": "python",
|
2714 |
+
"pygments_lexer": "ipython3",
|
2715 |
+
"version": "3.12.1"
|
2716 |
+
}
|
2717 |
+
},
|
2718 |
+
"nbformat": 4,
|
2719 |
+
"nbformat_minor": 2
|
2720 |
+
}
|
finetuning_squad/checkpoint-16000/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForQuestionAnswering"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.36.2",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
finetuning_squad/checkpoint-16000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31d5b145696822a4d87bbbbfb78718c21d0e3af6d3223481ed6583cad3634933
|
3 |
+
size 265470032
|
finetuning_squad/checkpoint-16000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ed327d5a672048f2766660157675fc6060d6a8fea4b668d5b57a8cd257717c1
|
3 |
+
size 531000890
|
finetuning_squad/checkpoint-16000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7694ad61c6f3fdf06c3886f3b2051ac78ad82b8d781c31b56980e3472c1e84b
|
3 |
+
size 14244
|
finetuning_squad/checkpoint-16000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9606f0ea2f5eb5f76ad015d4a642c5e3726e2eb5a07b004c0b731a70b88768fb
|
3 |
+
size 1064
|
finetuning_squad/checkpoint-16000/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
finetuning_squad/checkpoint-16000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
finetuning_squad/checkpoint-16000/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
finetuning_squad/checkpoint-16000/trainer_state.json
ADDED
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.922374429223744,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 16000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.09,
|
13 |
+
"learning_rate": 1.9391171993911722e-05,
|
14 |
+
"loss": 2.9417,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.18,
|
19 |
+
"learning_rate": 1.8782343987823442e-05,
|
20 |
+
"loss": 1.7699,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.27,
|
25 |
+
"learning_rate": 1.8173515981735163e-05,
|
26 |
+
"loss": 1.5303,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.37,
|
31 |
+
"learning_rate": 1.756468797564688e-05,
|
32 |
+
"loss": 1.46,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.46,
|
37 |
+
"learning_rate": 1.69558599695586e-05,
|
38 |
+
"loss": 1.393,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.55,
|
43 |
+
"learning_rate": 1.634703196347032e-05,
|
44 |
+
"loss": 1.3692,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.64,
|
49 |
+
"learning_rate": 1.573820395738204e-05,
|
50 |
+
"loss": 1.3134,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.73,
|
55 |
+
"learning_rate": 1.5129375951293761e-05,
|
56 |
+
"loss": 1.2416,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.82,
|
61 |
+
"learning_rate": 1.4520547945205482e-05,
|
62 |
+
"loss": 1.2574,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.91,
|
67 |
+
"learning_rate": 1.39117199391172e-05,
|
68 |
+
"loss": 1.2039,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.0,
|
73 |
+
"eval_loss": 1.1474684476852417,
|
74 |
+
"eval_runtime": 59.0937,
|
75 |
+
"eval_samples_per_second": 178.868,
|
76 |
+
"eval_steps_per_second": 11.186,
|
77 |
+
"step": 5475
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.0,
|
81 |
+
"learning_rate": 1.330289193302892e-05,
|
82 |
+
"loss": 1.1717,
|
83 |
+
"step": 5500
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.1,
|
87 |
+
"learning_rate": 1.2694063926940641e-05,
|
88 |
+
"loss": 0.9552,
|
89 |
+
"step": 6000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.19,
|
93 |
+
"learning_rate": 1.2085235920852361e-05,
|
94 |
+
"loss": 0.9877,
|
95 |
+
"step": 6500
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.28,
|
99 |
+
"learning_rate": 1.147640791476408e-05,
|
100 |
+
"loss": 0.9877,
|
101 |
+
"step": 7000
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.37,
|
105 |
+
"learning_rate": 1.08675799086758e-05,
|
106 |
+
"loss": 0.9727,
|
107 |
+
"step": 7500
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.46,
|
111 |
+
"learning_rate": 1.025875190258752e-05,
|
112 |
+
"loss": 0.9713,
|
113 |
+
"step": 8000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.55,
|
117 |
+
"learning_rate": 9.64992389649924e-06,
|
118 |
+
"loss": 0.9441,
|
119 |
+
"step": 8500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.64,
|
123 |
+
"learning_rate": 9.04109589041096e-06,
|
124 |
+
"loss": 0.9527,
|
125 |
+
"step": 9000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.74,
|
129 |
+
"learning_rate": 8.432267884322679e-06,
|
130 |
+
"loss": 0.9311,
|
131 |
+
"step": 9500
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.83,
|
135 |
+
"learning_rate": 7.823439878234399e-06,
|
136 |
+
"loss": 0.9318,
|
137 |
+
"step": 10000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.92,
|
141 |
+
"learning_rate": 7.214611872146119e-06,
|
142 |
+
"loss": 0.9639,
|
143 |
+
"step": 10500
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 2.0,
|
147 |
+
"eval_loss": 1.0952799320220947,
|
148 |
+
"eval_runtime": 59.2147,
|
149 |
+
"eval_samples_per_second": 178.503,
|
150 |
+
"eval_steps_per_second": 11.163,
|
151 |
+
"step": 10950
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 2.01,
|
155 |
+
"learning_rate": 6.605783866057839e-06,
|
156 |
+
"loss": 0.9442,
|
157 |
+
"step": 11000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 2.1,
|
161 |
+
"learning_rate": 5.996955859969558e-06,
|
162 |
+
"loss": 0.7817,
|
163 |
+
"step": 11500
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.19,
|
167 |
+
"learning_rate": 5.388127853881279e-06,
|
168 |
+
"loss": 0.7787,
|
169 |
+
"step": 12000
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 2.28,
|
173 |
+
"learning_rate": 4.779299847792998e-06,
|
174 |
+
"loss": 0.7367,
|
175 |
+
"step": 12500
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 2.37,
|
179 |
+
"learning_rate": 4.170471841704719e-06,
|
180 |
+
"loss": 0.7513,
|
181 |
+
"step": 13000
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 2.47,
|
185 |
+
"learning_rate": 3.5616438356164386e-06,
|
186 |
+
"loss": 0.7739,
|
187 |
+
"step": 13500
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 2.56,
|
191 |
+
"learning_rate": 2.9528158295281586e-06,
|
192 |
+
"loss": 0.7591,
|
193 |
+
"step": 14000
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 2.65,
|
197 |
+
"learning_rate": 2.343987823439878e-06,
|
198 |
+
"loss": 0.7491,
|
199 |
+
"step": 14500
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 2.74,
|
203 |
+
"learning_rate": 1.7351598173515982e-06,
|
204 |
+
"loss": 0.7394,
|
205 |
+
"step": 15000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.83,
|
209 |
+
"learning_rate": 1.1263318112633182e-06,
|
210 |
+
"loss": 0.7548,
|
211 |
+
"step": 15500
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 2.92,
|
215 |
+
"learning_rate": 5.17503805175038e-07,
|
216 |
+
"loss": 0.7728,
|
217 |
+
"step": 16000
|
218 |
+
}
|
219 |
+
],
|
220 |
+
"logging_steps": 500,
|
221 |
+
"max_steps": 16425,
|
222 |
+
"num_input_tokens_seen": 0,
|
223 |
+
"num_train_epochs": 3,
|
224 |
+
"save_steps": 500,
|
225 |
+
"total_flos": 2.508519922649395e+16,
|
226 |
+
"train_batch_size": 16,
|
227 |
+
"trial_name": null,
|
228 |
+
"trial_params": null
|
229 |
+
}
|
finetuning_squad/checkpoint-16000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef75c14140ee1a816e11644c80a4f2ddc72be729b079d3bd065d7c138a8789ae
|
3 |
+
size 4664
|
finetuning_squad/checkpoint-16000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
finetuning_squad/runs/Feb04_15-16-16_gpu-MS-7C06/events.out.tfevents.1707039077.gpu-MS-7C06.1949275.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e4e3b23a4abd33f5d2d3c2395f9e5369b147d6ad87af4f04663d0713cfb45f3
|
3 |
+
size 4184
|
finetuning_squad/runs/Feb04_15-16-59_gpu-MS-7C06/events.out.tfevents.1707039122.gpu-MS-7C06.1949275.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faa2173fe2fef60ae9786509ae0c0ef1babf79e919b2d708c3f13486475f88dd
|
3 |
+
size 4184
|
finetuning_squad/runs/Feb04_15-17-09_gpu-MS-7C06/events.out.tfevents.1707039130.gpu-MS-7C06.1949275.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04b6ae48515fca49b081f9198716de0654024dd6c98e7b6ea633d9359004f3f8
|
3 |
+
size 10386
|
requirements.txt
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
accelerate==0.26.1
|
2 |
+
aiohttp==3.9.3
|
3 |
+
aiosignal==1.3.1
|
4 |
+
asttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1698341106958/work
|
5 |
+
attrs==23.2.0
|
6 |
+
certifi==2024.2.2
|
7 |
+
charset-normalizer==3.3.2
|
8 |
+
comm @ file:///home/conda/feedstock_root/build_artifacts/comm_1704278392174/work
|
9 |
+
datasets==2.16.1
|
10 |
+
debugpy @ file:///work/perseverance-python-buildout/croot/debugpy_1698884710808/work
|
11 |
+
decorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1641555617451/work
|
12 |
+
dill==0.3.7
|
13 |
+
exceptiongroup @ file:///home/conda/feedstock_root/build_artifacts/exceptiongroup_1704921103267/work
|
14 |
+
executing @ file:///home/conda/feedstock_root/build_artifacts/executing_1698579936712/work
|
15 |
+
filelock==3.13.1
|
16 |
+
frozenlist==1.4.1
|
17 |
+
fsspec==2023.10.0
|
18 |
+
huggingface-hub==0.20.3
|
19 |
+
idna==3.6
|
20 |
+
importlib-metadata @ file:///home/conda/feedstock_root/build_artifacts/importlib-metadata_1703269254275/work
|
21 |
+
ipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1705417941265/work
|
22 |
+
ipython @ file:///home/conda/feedstock_root/build_artifacts/ipython_1706795662110/work
|
23 |
+
jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1696326070614/work
|
24 |
+
Jinja2==3.1.3
|
25 |
+
jupyter_client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1699283905679/work
|
26 |
+
jupyter_core @ file:///work/perseverance-python-buildout/croot/jupyter_core_1701731747496/work
|
27 |
+
MarkupSafe==2.1.5
|
28 |
+
matplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1660814786464/work
|
29 |
+
mpmath==1.3.0
|
30 |
+
multidict==6.0.5
|
31 |
+
multiprocess==0.70.15
|
32 |
+
nest_asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1705850609492/work
|
33 |
+
networkx==3.2.1
|
34 |
+
numpy==1.26.3
|
35 |
+
nvidia-cublas-cu12==12.1.3.1
|
36 |
+
nvidia-cuda-cupti-cu12==12.1.105
|
37 |
+
nvidia-cuda-nvrtc-cu12==12.1.105
|
38 |
+
nvidia-cuda-runtime-cu12==12.1.105
|
39 |
+
nvidia-cudnn-cu12==8.9.2.26
|
40 |
+
nvidia-cufft-cu12==11.0.2.54
|
41 |
+
nvidia-curand-cu12==10.3.2.106
|
42 |
+
nvidia-cusolver-cu12==11.4.5.107
|
43 |
+
nvidia-cusparse-cu12==12.1.0.106
|
44 |
+
nvidia-nccl-cu12==2.19.3
|
45 |
+
nvidia-nvjitlink-cu12==12.3.101
|
46 |
+
nvidia-nvtx-cu12==12.1.105
|
47 |
+
packaging @ file:///home/conda/feedstock_root/build_artifacts/packaging_1696202382185/work
|
48 |
+
pandas==2.2.0
|
49 |
+
parso @ file:///home/conda/feedstock_root/build_artifacts/parso_1638334955874/work
|
50 |
+
pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1706113125309/work
|
51 |
+
pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602536217715/work
|
52 |
+
pillow==10.2.0
|
53 |
+
platformdirs @ file:///home/conda/feedstock_root/build_artifacts/platformdirs_1706713388748/work
|
54 |
+
prompt-toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1702399386289/work
|
55 |
+
psutil @ file:///work/perseverance-python-buildout/croot/psutil_1698863411559/work
|
56 |
+
ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
|
57 |
+
pure-eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1642875951954/work
|
58 |
+
pyarrow==15.0.0
|
59 |
+
pyarrow-hotfix==0.6
|
60 |
+
Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1700607939962/work
|
61 |
+
python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1626286286081/work
|
62 |
+
pytz==2024.1
|
63 |
+
PyYAML==6.0.1
|
64 |
+
pyzmq @ file:///croot/pyzmq_1705605076900/work
|
65 |
+
regex==2023.12.25
|
66 |
+
requests==2.31.0
|
67 |
+
safetensors==0.4.2
|
68 |
+
setuptools==68.2.2
|
69 |
+
six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
|
70 |
+
stack-data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1669632077133/work
|
71 |
+
sympy==1.12
|
72 |
+
tokenizers==0.15.1
|
73 |
+
torch==2.2.0
|
74 |
+
torchaudio==2.2.0+cu118
|
75 |
+
torchvision==0.17.0+cu118
|
76 |
+
tornado @ file:///work/perseverance-python-buildout/croot/tornado_1698866362018/work
|
77 |
+
tqdm==4.66.1
|
78 |
+
traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1704212992681/work
|
79 |
+
transformers==4.37.2
|
80 |
+
triton==2.2.0
|
81 |
+
typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1702176139754/work
|
82 |
+
tzdata==2023.4
|
83 |
+
urllib3==2.2.0
|
84 |
+
wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1704731205417/work
|
85 |
+
wheel==0.41.2
|
86 |
+
xxhash==3.4.1
|
87 |
+
yarl==1.9.4
|
88 |
+
zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1695255097490/work
|