forked from AI4Finance-Foundation/FinGPT
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
5 changed files
with
78 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
33 changes: 33 additions & 0 deletions
33
...struct-FinGPT/training/supervised_finetuning/training_scripts/multi_node/run_sent-1.3b.sh
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,33 @@ | ||
#!/bin/bash | ||
# Copyright (c) Microsoft Corporation. | ||
# SPDX-License-Identifier: Apache-2.0 | ||
|
||
# DeepSpeed Team | ||
OUTPUT=$1 | ||
ZERO_STAGE=$2 | ||
if [ "$OUTPUT" == "" ]; then | ||
OUTPUT=./output | ||
fi | ||
if [ "$ZERO_STAGE" == "" ]; then | ||
ZERO_STAGE=2 | ||
fi | ||
mkdir -p $OUTPUT | ||
|
||
deepspeed main.py \ | ||
--data_path zeroshot/twitter-financial-news-sentiment chiapudding/kaggle-financial-sentiment \ | ||
--data_split 10,0,0 \ | ||
--model_name_or_path facebook/opt-1.3b \ | ||
--per_device_train_batch_size 8 \ | ||
--per_device_eval_batch_size 8 \ | ||
--max_seq_len 512 \ | ||
--learning_rate 9.65e-6 \ | ||
--weight_decay 0.1 \ | ||
--num_train_epochs 2 \ | ||
--gradient_accumulation_steps 1 \ | ||
--lr_scheduler_type cosine \ | ||
--num_warmup_steps 0 \ | ||
--seed 1234 \ | ||
--zero_stage $ZERO_STAGE \ | ||
--deepspeed \ | ||
--output_dir $OUTPUT \ | ||
&> $OUTPUT/training.log |
38 changes: 38 additions & 0 deletions
38
...ct-FinGPT/training/supervised_finetuning/training_scripts/multi_node/run_sent-llama-7b.sh
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,38 @@ | ||
#!/bin/bash | ||
# Copyright (c) Microsoft Corporation. | ||
# SPDX-License-Identifier: Apache-2.0 | ||
|
||
# DeepSpeed Team | ||
OUTPUT=$1 | ||
ZERO_STAGE=$2 | ||
if [ "$OUTPUT" == "" ]; then | ||
OUTPUT=./output | ||
fi | ||
if [ "$ZERO_STAGE" == "" ]; then | ||
ZERO_STAGE=3 | ||
fi | ||
mkdir -p $OUTPUT | ||
|
||
deepspeed main.py \ | ||
--data_path zeroshot/twitter-financial-news-sentiment chiapudding/kaggle-financial-sentiment \ | ||
--data_split 10,0,0 \ | ||
--model_name_or_path decapoda-research/llama-7b-hf \ | ||
--per_device_train_batch_size 4 \ | ||
--per_device_eval_batch_size 4 \ | ||
--max_seq_len 512 \ | ||
--learning_rate 1e-5 \ | ||
--weight_decay 0.1 \ | ||
--num_train_epochs 2 \ | ||
--gradient_accumulation_steps 1 \ | ||
--lr_scheduler_type cosine \ | ||
--num_warmup_steps 0 \ | ||
--seed 1234 \ | ||
--gradient_checkpointing \ | ||
--zero_stage $ZERO_STAGE \ | ||
--deepspeed \ | ||
--output_dir $OUTPUT \ | ||
&> $OUTPUT/training.log | ||
|
||
|
||
# --lora_dim 128 \ | ||
# --lora_module_name model.layers. \ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters