some stuff
Browse files
batch_finetune_eu_jav_base_exp_fulltext.sh
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
PROJECT_DIR=${HOME}"/models/eu-jav-categorisation"
|
2 |
export PYTHONPATH=${PROJECT_DIR}
|
3 |
INITIAL_CHECKPOINT_PATH=\"gs://t5-data/pretrained_models/t5x/mt5_base/checkpoint_1000000\"
|
4 |
-
TRAIN_STEPS=
|
5 |
|
6 |
-
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/
|
7 |
-
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/
|
8 |
-
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/
|
9 |
-
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/
|
10 |
-
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/
|
11 |
|
|
|
1 |
PROJECT_DIR=${HOME}"/models/eu-jav-categorisation"
|
2 |
export PYTHONPATH=${PROJECT_DIR}
|
3 |
INITIAL_CHECKPOINT_PATH=\"gs://t5-data/pretrained_models/t5x/mt5_base/checkpoint_1000000\"
|
4 |
+
TRAIN_STEPS=1010000
|
5 |
|
6 |
+
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/fulltext_corrected_classify_tweets_fulltext_base_v1\" &&
|
7 |
+
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/fulltext_corrected_classify_tweets_fulltext_base_v2\" &&
|
8 |
+
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/fulltext_corrected_classify_tweets_fulltext_base_v3\" &&
|
9 |
+
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/fulltext_corrected_classify_tweets_fulltext_base_v4\" &&
|
10 |
+
python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_classification_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"classify_tweets_fulltext\" --gin.MODEL_DIR=\"gs://eu-jav-t5x/finetuned/italian_tweets/fulltext_corrected_classify_tweets_fulltext_base_v5\"
|
11 |
|
finetune_classification_base.gin
CHANGED
@@ -11,7 +11,7 @@ include "t5x/examples/t5/mt5/base.gin"
|
|
11 |
include "t5x/configs/runs/finetune.gin"
|
12 |
|
13 |
MIXTURE_OR_TASK_NAME = %gin.REQUIRED
|
14 |
-
TASK_FEATURE_LENGTHS = {"inputs": 256, "targets":
|
15 |
INITIAL_CHECKPOINT_PATH = %gin.REQUIRED
|
16 |
TRAIN_STEPS = %gin.REQUIRED # 1000000 pre-trained steps + 10000 fine-tuning steps.
|
17 |
USE_CACHED_TASKS = False
|
@@ -24,7 +24,7 @@ infer_eval/utils.DatasetConfig:
|
|
24 |
|
25 |
#Saving every 1000 steps
|
26 |
utils.SaveCheckpointConfig:
|
27 |
-
period =
|
28 |
|
29 |
|
30 |
# Pere: Only necessary if we load a t5 model. We can start with an t5x model here
|
|
|
11 |
include "t5x/configs/runs/finetune.gin"
|
12 |
|
13 |
MIXTURE_OR_TASK_NAME = %gin.REQUIRED
|
14 |
+
TASK_FEATURE_LENGTHS = {"inputs": 256, "targets": 64}
|
15 |
INITIAL_CHECKPOINT_PATH = %gin.REQUIRED
|
16 |
TRAIN_STEPS = %gin.REQUIRED # 1000000 pre-trained steps + 10000 fine-tuning steps.
|
17 |
USE_CACHED_TASKS = False
|
|
|
24 |
|
25 |
#Saving every 1000 steps
|
26 |
utils.SaveCheckpointConfig:
|
27 |
+
period = 1000
|
28 |
|
29 |
|
30 |
# Pere: Only necessary if we load a t5 model. We can start with an t5x model here
|
tasks.py
CHANGED
@@ -59,7 +59,7 @@ def categorise_fulltext_preprocessor(ds):
|
|
59 |
t="il testo è favorevole alla vaccinazione"
|
60 |
elif t=="1":
|
61 |
t="il testo è neutro rispetto alla vaccinazione"
|
62 |
-
elif t=="
|
63 |
t="is testo è sfavorevole alla vaccinazione"
|
64 |
return t
|
65 |
|
|
|
59 |
t="il testo è favorevole alla vaccinazione"
|
60 |
elif t=="1":
|
61 |
t="il testo è neutro rispetto alla vaccinazione"
|
62 |
+
elif t=="2":
|
63 |
t="is testo è sfavorevole alla vaccinazione"
|
64 |
return t
|
65 |
|