Skip to content

GitLab

"...subjective/alignbench/alignbench_judgeby_critiquellm.py" did not exist on "bfe4aa2af51040d0050ed57c81b98cf030ce071e"
Switch branch/tag
Find file Normal viewHistoryPermalink
eval-allenai-wmt19.sh 2.95 KB
Newer Older
Stas Bekman's avatar
[fsmt] build/test scripts (#7257)  
Stas Bekman committed
1 
#!/usr/bin/env bash
Sylvain Gugger's avatar
Copyright (#8970)  
Sylvain Gugger committed
2
3
4
5
6
7
8
9
10
11
12
13
14 
# Copyright 2020 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
Stas Bekman's avatar
build/eval/gen-card scripts for fsmt (#7155)  
Stas Bekman committed
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67 

# this script evals the following fsmt models
# it covers:
# - allenai/wmt19-de-en-6-6-base
# - allenai/wmt19-de-en-6-6-big

# this script needs to be run from the top level of the transformers repo
if [ ! -d "src/transformers" ]; then
    echo "Error: This script needs to be run from the top of the transformers repo"
    exit 1
fi

# In these scripts you may have to lower BS if you get CUDA OOM (or increase it if you have a large GPU)

### Normal eval ###

export PAIR=de-en
export DATA_DIR=data/$PAIR
export SAVE_DIR=data/$PAIR
export BS=64
export NUM_BEAMS=5
mkdir -p $DATA_DIR
sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target

MODEL_PATH=allenai/wmt19-de-en-6-6-base
echo $PAIR $MODEL_PATH
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py $MODEL_PATH $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS

MODEL_PATH=allenai/wmt19-de-en-6-6-big
echo $PAIR $MODEL_PATH
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py $MODEL_PATH $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS



### Searching hparams eval ###

export PAIR=de-en
export DATA_DIR=data/$PAIR
export SAVE_DIR=data/$PAIR
export BS=16
export NUM_BEAMS=5
mkdir -p $DATA_DIR
sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target

MODEL_PATH=allenai/wmt19-de-en-6-6-base
echo $PAIR $MODEL_PATH
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval_search.py $MODEL_PATH $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --search="num_beams=5:10:15 length_penalty=0.6:0.7:0.8:0.9:1.0:1.1"

MODEL_PATH=allenai/wmt19-de-en-6-6-big
echo $PAIR $MODEL_PATH
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval_search.py $MODEL_PATH $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --search="num_beams=5:10:15 length_penalty=0.6:0.7:0.8:0.9:1.0:1.1"