htlou commited on
Commit
ebacaea
·
verified ·
1 Parent(s): 43efed0

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ wandb/run-20241028_201718-oidiwtgb/run-oidiwtgb.wandb filter=lfs diff=lfs merge=lfs -text
arguments.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name_or_path": "/mnt/data/hantao/models/Llama-3.1-8B-Instruct",
3
+ "max_length": 4096,
4
+ "trust_remote_code": true,
5
+ "train_datasets": [
6
+ [
7
+ "correction-plus",
8
+ {
9
+ "proportion": 1.0,
10
+ "path": "/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027.json"
11
+ }
12
+ ]
13
+ ],
14
+ "eval_datasets": null,
15
+ "epochs": 3,
16
+ "per_device_train_batch_size": 4,
17
+ "per_device_eval_batch_size": 4,
18
+ "gradient_accumulation_steps": 2,
19
+ "gradient_checkpointing": true,
20
+ "lr": 2e-05,
21
+ "lr_scheduler_type": "cosine",
22
+ "lr_warmup_ratio": 0.03,
23
+ "weight_decay": 0.0,
24
+ "seed": 42,
25
+ "fp16": false,
26
+ "bf16": true,
27
+ "tf32": true,
28
+ "eval_strategy": "epoch",
29
+ "eval_interval": 1000000,
30
+ "need_eval": false,
31
+ "eval_split_ratio": null,
32
+ "output_dir": "/mnt/data/hantao/stream_output/1029_general_alpaca_8b",
33
+ "log_type": "wandb",
34
+ "log_dir": "/mnt/data/hantao/stream_output/1029_general_alpaca_8b",
35
+ "log_project": "stream_aligner",
36
+ "log_run_name": "sft-2024-10-28-20-17-17",
37
+ "save_16bit": true,
38
+ "save_interval": 500,
39
+ "local_rank": 0,
40
+ "zero_stage": 3,
41
+ "offload": "none",
42
+ "deepspeed": false,
43
+ "deepspeed_config": null,
44
+ "deepscale": false,
45
+ "deepscale_config": null,
46
+ "global_rank": 0,
47
+ "device": {
48
+ "type": "torch.device",
49
+ "repr": "device(type='cuda', index=0)"
50
+ },
51
+ "num_update_steps_per_epoch": 1466,
52
+ "total_training_steps": 4398
53
+ }
arguments.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215f92a0fecc95b7e0ce2d40609bf2c7be2690d1d896999568fa12572eeaea0d
3
+ size 1144
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/data/hantao/models/Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128256,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.45.2",
35
+ "use_cache": true,
36
+ "vocab_size": 128258
37
+ }
environ.txt ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ CONDA_DEFAULT_ENV=hantao_stream
2
+ CONDA_EXE=/home/saev/miniconda3/bin/conda
3
+ CONDA_PREFIX=/home/saev/miniconda3/envs/hantao_stream
4
+ CONDA_PREFIX_1=/home/saev/miniconda3
5
+ CONDA_PREFIX_2=/home/saev/miniconda3/envs/hantao_interp
6
+ CONDA_PREFIX_3=/home/saev/miniconda3
7
+ CONDA_PROMPT_MODIFIER=(hantao_stream)
8
+ CONDA_PYTHON_EXE=/home/saev/miniconda3/bin/python
9
+ CONDA_SHLVL=4
10
+ CROSS_RANK=0
11
+ CROSS_SIZE=1
12
+ CUDA_MODULE_LOADING=LAZY
13
+ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
14
+ DBUS_SESSION_BUS_ADDRESS=unix:path=/run/user/1003/bus
15
+ HOME=/home/saev
16
+ LANG=en_US.UTF-8
17
+ LESSCLOSE=/usr/bin/lesspipe %s %s
18
+ LESSOPEN=| /usr/bin/lesspipe %s
19
+ LOCAL_RANK=0
20
+ LOCAL_SIZE=8
21
+ LOGLEVEL=INFO
22
+ LOGNAME=saev
23
+ LS_COLORS=rs=0:di=01;34:ln=01;36:mh=00:pi=40;33:so=01;35:do=01;35:bd=40;33;01:cd=40;33;01:or=40;31;01:mi=00:su=37;41:sg=30;43:ca=30;41:tw=30;42:ow=34;42:st=37;44:ex=01;32:*.tar=01;31:*.tgz=01;31:*.arc=01;31:*.arj=01;31:*.taz=01;31:*.lha=01;31:*.lz4=01;31:*.lzh=01;31:*.lzma=01;31:*.tlz=01;31:*.txz=01;31:*.tzo=01;31:*.t7z=01;31:*.zip=01;31:*.z=01;31:*.dz=01;31:*.gz=01;31:*.lrz=01;31:*.lz=01;31:*.lzo=01;31:*.xz=01;31:*.zst=01;31:*.tzst=01;31:*.bz2=01;31:*.bz=01;31:*.tbz=01;31:*.tbz2=01;31:*.tz=01;31:*.deb=01;31:*.rpm=01;31:*.jar=01;31:*.war=01;31:*.ear=01;31:*.sar=01;31:*.rar=01;31:*.alz=01;31:*.ace=01;31:*.zoo=01;31:*.cpio=01;31:*.7z=01;31:*.rz=01;31:*.cab=01;31:*.wim=01;31:*.swm=01;31:*.dwm=01;31:*.esd=01;31:*.jpg=01;35:*.jpeg=01;35:*.mjpg=01;35:*.mjpeg=01;35:*.gif=01;35:*.bmp=01;35:*.pbm=01;35:*.pgm=01;35:*.ppm=01;35:*.tga=01;35:*.xbm=01;35:*.xpm=01;35:*.tif=01;35:*.tiff=01;35:*.png=01;35:*.svg=01;35:*.svgz=01;35:*.mng=01;35:*.pcx=01;35:*.mov=01;35:*.mpg=01;35:*.mpeg=01;35:*.m2v=01;35:*.mkv=01;35:*.webm=01;35:*.webp=01;35:*.ogm=01;35:*.mp4=01;35:*.m4v=01;35:*.mp4v=01;35:*.vob=01;35:*.qt=01;35:*.nuv=01;35:*.wmv=01;35:*.asf=01;35:*.rm=01;35:*.rmvb=01;35:*.flc=01;35:*.avi=01;35:*.fli=01;35:*.flv=01;35:*.gl=01;35:*.dl=01;35:*.xcf=01;35:*.xwd=01;35:*.yuv=01;35:*.cgm=01;35:*.emf=01;35:*.ogv=01;35:*.ogx=01;35:*.aac=00;36:*.au=00;36:*.flac=00;36:*.m4a=00;36:*.mid=00;36:*.midi=00;36:*.mka=00;36:*.mp3=00;36:*.mpc=00;36:*.ogg=00;36:*.ra=00;36:*.wav=00;36:*.oga=00;36:*.opus=00;36:*.spx=00;36:*.xspf=00;36:
24
+ MASTER_ADDR=127.0.0.1
25
+ MASTER_PORT=27874
26
+ MOTD_SHOWN=pam
27
+ OLDPWD=/home/saev/hantao/stream_aligner/safe-rlhf-lht/safe_rlhf/configs
28
+ PATH=/home/saev/miniconda3/envs/hantao_stream/bin:/home/saev/miniconda3/bin:/home/saev/miniconda3/condabin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin
29
+ PWD=/home/saev/hantao/stream_aligner/safe-rlhf-lht/scripts
30
+ PYTHONHASHSEED=42
31
+ PYTHONPATH=/home/saev/hantao/stream_aligner/safe-rlhf-lht
32
+ RANK=0
33
+ SHELL=/bin/bash
34
+ SHLVL=3
35
+ SSH_CLIENT=111.205.233.209 40803 31100
36
+ SSH_CONNECTION=111.205.230.212 33832 10.10.212.201 31100
37
+ SSH_TTY=/dev/pts/2
38
+ TERM=screen
39
+ TERM_PROGRAM=tmux
40
+ TERM_PROGRAM_VERSION=3.2a
41
+ TMUX=/tmp/tmux-1003/default,119466,18
42
+ TMUX_PANE=%19
43
+ USER=saev
44
+ WANDB_API_KEY=7e2dcc0c310ebcb7cdcafd5e9320d6be55cf1a33
45
+ WANDB_SERVICE=2-745177-tcp-localhost-37087
46
+ WORLD_SIZE=8
47
+ XDG_DATA_DIRS=/usr/local/share:/usr/share:/var/lib/snapd/desktop
48
+ XDG_RUNTIME_DIR=/run/user/1003
49
+ XDG_SESSION_CLASS=user
50
+ XDG_SESSION_ID=60
51
+ XDG_SESSION_TYPE=tty
52
+ _=/home/saev/miniconda3/envs/hantao_stream/bin/deepspeed
53
+ _CE_CONDA=
54
+ _CE_M=
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d89a3bfb6204a32c5e42f74b638779f658bdf4c47bf027d98a192872f1fecf
3
+ size 16060652330
script.sh ADDED
@@ -0,0 +1,311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ #
3
+ # Copyright 2023 PKU-Alignment Team. All Rights Reserved.
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+ # ==============================================================================
17
+
18
+ if [ -z "${BASH_VERSION}" ]; then
19
+ echo "Please use bash to run this script." >&2
20
+ exit 1
21
+ fi
22
+
23
+ set -x
24
+
25
+ SCRIPT_DIR="$(cd "$(dirname "$0")" &>/dev/null && pwd)"
26
+ ROOT_DIR="$(dirname "${SCRIPT_DIR}")"
27
+ export PYTHONPATH="${ROOT_DIR}${PYTHONPATH:+:${PYTHONPATH}}"
28
+ export LOGLEVEL="${LOGLEVEL:-WARNING}"
29
+
30
+ # -------------------need to change-------------
31
+ export LOGLEVEL="INFO"
32
+ export WANDB_API_KEY="7e2dcc0c310ebcb7cdcafd5e9320d6be55cf1a33"
33
+ MODEL_NAME_OR_PATH="/mnt/data/hantao/models/Llama-3.1-8B-Instruct"
34
+ OUTPUT_DIR="/mnt/data/hantao/stream_output/1029_general_alpaca_8b_copy_5k"
35
+ DATASET="/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027_copy_5k.json"
36
+ # -------------------need to change------------
37
+
38
+ unset HOSTFILE
39
+ ZERO_STAGE=3
40
+ OFFLOAD="none"
41
+
42
+ mkdir -p "${OUTPUT_DIR}"
43
+ OUTPUT_DIR="$(cd "${OUTPUT_DIR}" &>/dev/null && pwd)"
44
+ if [[ ! -f "${OUTPUT_DIR}/.gitignore" ]]; then
45
+ echo '*' >"${OUTPUT_DIR}/.gitignore"
46
+ fi
47
+
48
+ cp -f "$0" "${OUTPUT_DIR}/script.sh"
49
+
50
+ # if [[ -z "${WANDB_API_KEY}" ]]; then
51
+ # export WANDB_MODE="offline"
52
+ # fi
53
+
54
+ MASTER_PORT_START=10000
55
+ MASTER_PORT_END=65535
56
+ MASTER_PORT="$(
57
+ comm -23 \
58
+ <(seq "${MASTER_PORT_START}" "${MASTER_PORT_END}" | sort) \
59
+ <(ss -Htan | awk '{ print $4 }' | awk -F ':' '{ print $NF }' | sort -u) |
60
+ shuf | head -n 1
61
+ )"
62
+
63
+ DEEPSPEED_ARGS=()
64
+ if [[ -n "${HOSTFILE+x}" ]]; then
65
+ DEEPSPEED_ARGS+=("--hostfile" "${HOSTFILE}")
66
+ fi
67
+ DEEPSPEED_ARGS+=("--master_port" "${MASTER_PORT}")
68
+
69
+ exec 1> >(tee "${OUTPUT_DIR}/stdout.log" >&1) 2> >(tee "${OUTPUT_DIR}/stderr.log" >&2)
70
+
71
+ deepspeed "${DEEPSPEED_ARGS[@]}" \
72
+ --module safe_rlhf.finetune \
73
+ --train_datasets correction-plus::${DATASET} \
74
+ --model_name_or_path "${MODEL_NAME_OR_PATH}" \
75
+ --max_length 4096 \
76
+ --trust_remote_code True \
77
+ --epochs 3 \
78
+ --per_device_train_batch_size 4 \
79
+ --per_device_eval_batch_size 4 \
80
+ --gradient_accumulation_steps 2 \
81
+ --gradient_checkpointing \
82
+ --learning_rate 2e-5 \
83
+ --lr_scheduler_type cosine \
84
+ --lr_warmup_ratio 0.03 \
85
+ --weight_decay 0.0 \
86
+ --seed 42 \
87
+ --output_dir "${OUTPUT_DIR}" \
88
+ --log_type wandb \
89
+ --log_project stream_aligner \
90
+ --zero_stage "${ZERO_STAGE}" \
91
+ --offload "${OFFLOAD}" \
92
+ --bf16 True \
93
+ --tf32 True \
94
+ --save_interval 500 \
95
+ --save_16bit
96
+
97
+
98
+ # -------------------need to change-------------
99
+ export LOGLEVEL="INFO"
100
+ export WANDB_API_KEY="7e2dcc0c310ebcb7cdcafd5e9320d6be55cf1a33"
101
+ MODEL_NAME_OR_PATH="/mnt/data/hantao/models/Llama-3.1-8B-Instruct"
102
+ OUTPUT_DIR="/mnt/data/hantao/stream_output/1029_general_alpaca_8b"
103
+ DATASET="/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027.json"
104
+ # -------------------need to change------------
105
+
106
+ unset HOSTFILE
107
+ ZERO_STAGE=3
108
+ OFFLOAD="none"
109
+
110
+ mkdir -p "${OUTPUT_DIR}"
111
+ OUTPUT_DIR="$(cd "${OUTPUT_DIR}" &>/dev/null && pwd)"
112
+ if [[ ! -f "${OUTPUT_DIR}/.gitignore" ]]; then
113
+ echo '*' >"${OUTPUT_DIR}/.gitignore"
114
+ fi
115
+
116
+ cp -f "$0" "${OUTPUT_DIR}/script.sh"
117
+
118
+ # if [[ -z "${WANDB_API_KEY}" ]]; then
119
+ # export WANDB_MODE="offline"
120
+ # fi
121
+
122
+ MASTER_PORT_START=10000
123
+ MASTER_PORT_END=65535
124
+ MASTER_PORT="$(
125
+ comm -23 \
126
+ <(seq "${MASTER_PORT_START}" "${MASTER_PORT_END}" | sort) \
127
+ <(ss -Htan | awk '{ print $4 }' | awk -F ':' '{ print $NF }' | sort -u) |
128
+ shuf | head -n 1
129
+ )"
130
+
131
+ DEEPSPEED_ARGS=()
132
+ if [[ -n "${HOSTFILE+x}" ]]; then
133
+ DEEPSPEED_ARGS+=("--hostfile" "${HOSTFILE}")
134
+ fi
135
+ DEEPSPEED_ARGS+=("--master_port" "${MASTER_PORT}")
136
+
137
+ exec 1> >(tee "${OUTPUT_DIR}/stdout.log" >&1) 2> >(tee "${OUTPUT_DIR}/stderr.log" >&2)
138
+
139
+ deepspeed "${DEEPSPEED_ARGS[@]}" \
140
+ --module safe_rlhf.finetune \
141
+ --train_datasets correction-plus::${DATASET} \
142
+ --model_name_or_path "${MODEL_NAME_OR_PATH}" \
143
+ --max_length 4096 \
144
+ --trust_remote_code True \
145
+ --epochs 3 \
146
+ --per_device_train_batch_size 4 \
147
+ --per_device_eval_batch_size 4 \
148
+ --gradient_accumulation_steps 2 \
149
+ --gradient_checkpointing \
150
+ --learning_rate 2e-5 \
151
+ --lr_scheduler_type cosine \
152
+ --lr_warmup_ratio 0.03 \
153
+ --weight_decay 0.0 \
154
+ --seed 42 \
155
+ --output_dir "${OUTPUT_DIR}" \
156
+ --log_type wandb \
157
+ --log_project stream_aligner \
158
+ --zero_stage "${ZERO_STAGE}" \
159
+ --offload "${OFFLOAD}" \
160
+ --bf16 True \
161
+ --tf32 True \
162
+ --save_interval 500 \
163
+ --save_16bit
164
+
165
+
166
+ if [ -z "${BASH_VERSION}" ]; then
167
+ echo "Please use bash to run this script." >&2
168
+ exit 1
169
+ fi
170
+
171
+ set -x
172
+
173
+ SCRIPT_DIR="$(cd "$(dirname "$0")" &>/dev/null && pwd)"
174
+ ROOT_DIR="$(dirname "${SCRIPT_DIR}")"
175
+ export PYTHONPATH="${ROOT_DIR}${PYTHONPATH:+:${PYTHONPATH}}"
176
+ export LOGLEVEL="${LOGLEVEL:-WARNING}"
177
+
178
+ # -------------------need to change-------------
179
+ export LOGLEVEL="INFO"
180
+ export WANDB_API_KEY="7e2dcc0c310ebcb7cdcafd5e9320d6be55cf1a33"
181
+ MODEL_NAME_OR_PATH="/mnt/data/hantao/models/Llama-3.2-3B-Instruct"
182
+ OUTPUT_DIR="/mnt/data/hantao/stream_output/1029_general_alpaca_3b_copy_5k"
183
+ DATASET="/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027_copy_5k.json"
184
+ # -------------------need to change------------
185
+
186
+ unset HOSTFILE
187
+ ZERO_STAGE=3
188
+ OFFLOAD="none"
189
+
190
+ mkdir -p "${OUTPUT_DIR}"
191
+ OUTPUT_DIR="$(cd "${OUTPUT_DIR}" &>/dev/null && pwd)"
192
+ if [[ ! -f "${OUTPUT_DIR}/.gitignore" ]]; then
193
+ echo '*' >"${OUTPUT_DIR}/.gitignore"
194
+ fi
195
+
196
+ cp -f "$0" "${OUTPUT_DIR}/script.sh"
197
+
198
+ # if [[ -z "${WANDB_API_KEY}" ]]; then
199
+ # export WANDB_MODE="offline"
200
+ # fi
201
+
202
+ MASTER_PORT_START=10000
203
+ MASTER_PORT_END=65535
204
+ MASTER_PORT="$(
205
+ comm -23 \
206
+ <(seq "${MASTER_PORT_START}" "${MASTER_PORT_END}" | sort) \
207
+ <(ss -Htan | awk '{ print $4 }' | awk -F ':' '{ print $NF }' | sort -u) |
208
+ shuf | head -n 1
209
+ )"
210
+
211
+ DEEPSPEED_ARGS=()
212
+ if [[ -n "${HOSTFILE+x}" ]]; then
213
+ DEEPSPEED_ARGS+=("--hostfile" "${HOSTFILE}")
214
+ fi
215
+ DEEPSPEED_ARGS+=("--master_port" "${MASTER_PORT}")
216
+
217
+ exec 1> >(tee "${OUTPUT_DIR}/stdout.log" >&1) 2> >(tee "${OUTPUT_DIR}/stderr.log" >&2)
218
+
219
+ deepspeed "${DEEPSPEED_ARGS[@]}" \
220
+ --module safe_rlhf.finetune \
221
+ --train_datasets correction-plus::${DATASET} \
222
+ --model_name_or_path "${MODEL_NAME_OR_PATH}" \
223
+ --max_length 4096 \
224
+ --trust_remote_code True \
225
+ --epochs 3 \
226
+ --per_device_train_batch_size 4 \
227
+ --per_device_eval_batch_size 4 \
228
+ --gradient_accumulation_steps 2 \
229
+ --gradient_checkpointing \
230
+ --learning_rate 2e-5 \
231
+ --lr_scheduler_type cosine \
232
+ --lr_warmup_ratio 0.03 \
233
+ --weight_decay 0.0 \
234
+ --seed 42 \
235
+ --output_dir "${OUTPUT_DIR}" \
236
+ --log_type wandb \
237
+ --log_project stream_aligner \
238
+ --zero_stage "${ZERO_STAGE}" \
239
+ --offload "${OFFLOAD}" \
240
+ --bf16 True \
241
+ --tf32 True \
242
+ --save_interval 500 \
243
+ --save_16bit
244
+
245
+
246
+ # -------------------need to change-------------
247
+ export LOGLEVEL="INFO"
248
+ export WANDB_API_KEY="7e2dcc0c310ebcb7cdcafd5e9320d6be55cf1a33"
249
+ MODEL_NAME_OR_PATH="/mnt/data/hantao/models/Llama-3.2-3B-Instruct"
250
+ OUTPUT_DIR="/mnt/data/hantao/stream_output/1029_general_alpaca_3b"
251
+ DATASET="/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027.json"
252
+ # -------------------need to change------------
253
+
254
+ unset HOSTFILE
255
+ ZERO_STAGE=3
256
+ OFFLOAD="none"
257
+
258
+ mkdir -p "${OUTPUT_DIR}"
259
+ OUTPUT_DIR="$(cd "${OUTPUT_DIR}" &>/dev/null && pwd)"
260
+ if [[ ! -f "${OUTPUT_DIR}/.gitignore" ]]; then
261
+ echo '*' >"${OUTPUT_DIR}/.gitignore"
262
+ fi
263
+
264
+ cp -f "$0" "${OUTPUT_DIR}/script.sh"
265
+
266
+ # if [[ -z "${WANDB_API_KEY}" ]]; then
267
+ # export WANDB_MODE="offline"
268
+ # fi
269
+
270
+ MASTER_PORT_START=10000
271
+ MASTER_PORT_END=65535
272
+ MASTER_PORT="$(
273
+ comm -23 \
274
+ <(seq "${MASTER_PORT_START}" "${MASTER_PORT_END}" | sort) \
275
+ <(ss -Htan | awk '{ print $4 }' | awk -F ':' '{ print $NF }' | sort -u) |
276
+ shuf | head -n 1
277
+ )"
278
+
279
+ DEEPSPEED_ARGS=()
280
+ if [[ -n "${HOSTFILE+x}" ]]; then
281
+ DEEPSPEED_ARGS+=("--hostfile" "${HOSTFILE}")
282
+ fi
283
+ DEEPSPEED_ARGS+=("--master_port" "${MASTER_PORT}")
284
+
285
+ exec 1> >(tee "${OUTPUT_DIR}/stdout.log" >&1) 2> >(tee "${OUTPUT_DIR}/stderr.log" >&2)
286
+
287
+ deepspeed "${DEEPSPEED_ARGS[@]}" \
288
+ --module safe_rlhf.finetune \
289
+ --train_datasets correction-plus::${DATASET} \
290
+ --model_name_or_path "${MODEL_NAME_OR_PATH}" \
291
+ --max_length 4096 \
292
+ --trust_remote_code True \
293
+ --epochs 3 \
294
+ --per_device_train_batch_size 4 \
295
+ --per_device_eval_batch_size 4 \
296
+ --gradient_accumulation_steps 2 \
297
+ --gradient_checkpointing \
298
+ --learning_rate 2e-5 \
299
+ --lr_scheduler_type cosine \
300
+ --lr_warmup_ratio 0.03 \
301
+ --weight_decay 0.0 \
302
+ --seed 42 \
303
+ --output_dir "${OUTPUT_DIR}" \
304
+ --log_type wandb \
305
+ --log_project stream_aligner \
306
+ --zero_stage "${ZERO_STAGE}" \
307
+ --offload "${OFFLOAD}" \
308
+ --bf16 True \
309
+ --tf32 True \
310
+ --save_interval 500 \
311
+ --save_16bit
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
stderr.log ADDED
The diff for this file is too large to render. See raw diff
 
stdout.log ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089fcc22ecea628694d8dcd8b57815f68d90d070e4012c9964a622d4473b14db
3
+ size 17210383
tokenizer_config.json ADDED
@@ -0,0 +1,2081 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<pad>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<unk>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ }
2067
+ },
2068
+ "bos_token": "<|begin_of_text|>",
2069
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2070
+ "clean_up_tokenization_spaces": true,
2071
+ "eos_token": "<|eot_id|>",
2072
+ "model_input_names": [
2073
+ "input_ids",
2074
+ "attention_mask"
2075
+ ],
2076
+ "model_max_length": 4096,
2077
+ "pad_token": "<pad>",
2078
+ "padding_side": "right",
2079
+ "tokenizer_class": "PreTrainedTokenizerFast",
2080
+ "unk_token": "<unk>"
2081
+ }
wandb/debug-internal.log ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2024-10-28T20:17:18.03178695Z","level":"INFO","msg":"using version","core version":"0.18.5"}
2
+ {"time":"2024-10-28T20:17:18.03182537Z","level":"INFO","msg":"created symlink","path":"/mnt/data/hantao/stream_output/1029_general_alpaca_8b/wandb/run-20241028_201718-oidiwtgb/logs/debug-core.log"}
3
+ {"time":"2024-10-28T20:17:18.145947312Z","level":"INFO","msg":"created new stream","id":"oidiwtgb"}
4
+ {"time":"2024-10-28T20:17:18.145984312Z","level":"INFO","msg":"stream: started","id":"oidiwtgb"}
5
+ {"time":"2024-10-28T20:17:18.146095623Z","level":"INFO","msg":"sender: started","stream_id":"oidiwtgb"}
6
+ {"time":"2024-10-28T20:17:18.146160223Z","level":"INFO","msg":"handler: started","stream_id":{"value":"oidiwtgb"}}
7
+ {"time":"2024-10-28T20:17:18.146047192Z","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"oidiwtgb"}}
8
+ {"time":"2024-10-28T20:17:18.690659896Z","level":"INFO","msg":"Starting system monitor"}
9
+ {"time":"2024-10-28T22:20:26.682175893Z","level":"INFO","msg":"Stopping system monitor"}
10
+ {"time":"2024-10-28T22:20:26.684155623Z","level":"INFO","msg":"Stopped system monitor"}
11
+ {"time":"2024-10-28T22:20:27.222985066Z","level":"WARN","msg":"No job ingredients found, not creating job artifact"}
12
+ {"time":"2024-10-28T22:20:27.223025096Z","level":"WARN","msg":"No source type found, not creating job artifact"}
13
+ {"time":"2024-10-28T22:20:27.223036736Z","level":"INFO","msg":"sender: sendDefer: no job artifact to save"}
14
+ {"time":"2024-10-28T22:20:27.683053302Z","level":"INFO","msg":"handler: operation stats","stats":{"operations":[{"desc":"uploading wandb-summary.json","runtime_seconds":0.419228961,"progress":"183B/183B"},{"desc":"uploading output.log","runtime_seconds":0.148623508,"progress":"64.0KB/184.2KB"},{"desc":"uploading config.yaml","runtime_seconds":0.148599098,"progress":"2.2KB/2.2KB"}],"total_operations":3}}
15
+ {"time":"2024-10-28T22:20:28.277908208Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
16
+ {"time":"2024-10-28T22:20:29.889792431Z","level":"INFO","msg":"stream: closing","id":"oidiwtgb"}
17
+ {"time":"2024-10-28T22:20:29.889831071Z","level":"INFO","msg":"handler: closed","stream_id":{"value":"oidiwtgb"}}
18
+ {"time":"2024-10-28T22:20:29.889874332Z","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"oidiwtgb"}}
19
+ {"time":"2024-10-28T22:20:29.889895492Z","level":"INFO","msg":"sender: closed","stream_id":"oidiwtgb"}
20
+ {"time":"2024-10-28T22:20:29.889991772Z","level":"INFO","msg":"stream: closed","id":"oidiwtgb"}
wandb/debug.log ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
2
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Configure stats pid to 745177
3
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Loading settings from /home/saev/.config/wandb/settings
4
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Loading settings from /home/saev/hantao/stream_aligner/safe-rlhf-lht/scripts/wandb/settings
5
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Loading settings from environment variables: {'api_key': '***REDACTED***'}
6
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
7
+ 2024-10-28 20:17:18,026 WARNING MainThread:745177 [wandb_setup.py:_flush():79] Could not find program at -m safe_rlhf.finetune.__main__
8
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m safe_rlhf.finetune.__main__'}
9
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Applying login settings: {}
10
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/data/hantao/stream_output/1029_general_alpaca_8b/wandb/run-20241028_201718-oidiwtgb/logs/debug.log
11
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/data/hantao/stream_output/1029_general_alpaca_8b/wandb/run-20241028_201718-oidiwtgb/logs/debug-internal.log
12
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():621] calling init triggers
13
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
14
+ config: {'model_name_or_path': '/mnt/data/hantao/models/Llama-3.1-8B-Instruct', 'max_length': 4096, 'trust_remote_code': True, 'train_datasets': [('correction-plus', {'proportion': 1.0, 'path': '/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027.json'})], 'eval_datasets': None, 'epochs': 3, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'gradient_accumulation_steps': 2, 'gradient_checkpointing': True, 'lr': 2e-05, 'lr_scheduler_type': <SchedulerType.COSINE: 'cosine'>, 'lr_warmup_ratio': 0.03, 'weight_decay': 0.0, 'seed': 42, 'fp16': False, 'bf16': True, 'tf32': True, 'eval_strategy': 'epoch', 'eval_interval': 1000000, 'need_eval': False, 'eval_split_ratio': None, 'output_dir': '/mnt/data/hantao/stream_output/1029_general_alpaca_8b', 'log_type': 'wandb', 'log_dir': '/mnt/data/hantao/stream_output/1029_general_alpaca_8b', 'log_project': 'stream_aligner', 'log_run_name': 'sft-2024-10-28-20-17-17', 'save_16bit': True, 'save_interval': 500, 'local_rank': 0, 'zero_stage': 3, 'offload': 'none', 'deepspeed': False, 'deepspeed_config': None, 'deepscale': False, 'deepscale_config': None, 'global_rank': 0, 'device': device(type='cuda', index=0), 'num_update_steps_per_epoch': 1466, 'total_training_steps': 4398}
15
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():671] starting backend
16
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():675] sending inform_init request
17
+ 2024-10-28 20:17:18,027 INFO MainThread:745177 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-10-28 20:17:18,027 INFO MainThread:745177 [wandb_init.py:init():688] backend started and connected
19
+ 2024-10-28 20:17:18,030 INFO MainThread:745177 [wandb_init.py:init():783] updated telemetry
20
+ 2024-10-28 20:17:18,030 INFO MainThread:745177 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
21
+ 2024-10-28 20:17:18,686 INFO MainThread:745177 [wandb_init.py:init():867] starting run threads in backend
22
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_console_start():2463] atexit reg
23
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_redirect():2311] redirect: wrap_raw
24
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_redirect():2376] Wrapping output streams.
25
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_redirect():2401] Redirects installed.
26
+ 2024-10-28 20:17:18,785 INFO MainThread:745177 [wandb_init.py:init():911] run started, returning control to user process
27
+ 2024-10-28 22:20:26,678 INFO MainThread:745177 [wandb_run.py:_finish():2158] finishing run htlou/stream_aligner/oidiwtgb
28
+ 2024-10-28 22:20:26,679 INFO MainThread:745177 [wandb_run.py:_atexit_cleanup():2426] got exitcode: 0
29
+ 2024-10-28 22:20:26,679 INFO MainThread:745177 [wandb_run.py:_restore():2408] restore
30
+ 2024-10-28 22:20:26,679 INFO MainThread:745177 [wandb_run.py:_restore():2414] restore done
31
+ 2024-10-28 22:20:29,876 INFO MainThread:745177 [wandb_run.py:_footer_history_summary_info():3975] rendering history
32
+ 2024-10-28 22:20:29,879 INFO MainThread:745177 [wandb_run.py:_footer_history_summary_info():4007] rendering summary
33
+ 2024-10-28 22:20:29,888 INFO MainThread:745177 [wandb_run.py:_footer_sync_info():3934] logging synced files
wandb/run-20241028_201718-oidiwtgb/files/config.yaml ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _wandb:
2
+ value:
3
+ cli_version: 0.18.5
4
+ m: []
5
+ python_version: 3.11.10
6
+ t:
7
+ "1":
8
+ - 1
9
+ - 11
10
+ - 49
11
+ - 51
12
+ - 55
13
+ - 71
14
+ "2":
15
+ - 1
16
+ - 11
17
+ - 49
18
+ - 51
19
+ - 55
20
+ - 71
21
+ "3":
22
+ - 2
23
+ - 13
24
+ - 16
25
+ - 23
26
+ - 55
27
+ - 61
28
+ "4": 3.11.10
29
+ "5": 0.18.5
30
+ "6": 4.45.2
31
+ "8":
32
+ - 5
33
+ "12": 0.18.5
34
+ "13": linux-x86_64
35
+ bf16:
36
+ value: true
37
+ deepscale:
38
+ value: false
39
+ deepscale_config:
40
+ value: null
41
+ deepspeed:
42
+ value: false
43
+ deepspeed_config:
44
+ value: null
45
+ device:
46
+ value: cuda:0
47
+ epochs:
48
+ value: 3
49
+ eval_datasets:
50
+ value: null
51
+ eval_interval:
52
+ value: 1000000
53
+ eval_split_ratio:
54
+ value: null
55
+ eval_strategy:
56
+ value: epoch
57
+ fp16:
58
+ value: false
59
+ global_rank:
60
+ value: 0
61
+ gradient_accumulation_steps:
62
+ value: 2
63
+ gradient_checkpointing:
64
+ value: true
65
+ local_rank:
66
+ value: 0
67
+ log_dir:
68
+ value: /mnt/data/hantao/stream_output/1029_general_alpaca_8b
69
+ log_project:
70
+ value: stream_aligner
71
+ log_run_name:
72
+ value: sft-2024-10-28-20-17-17
73
+ log_type:
74
+ value: wandb
75
+ lr:
76
+ value: 2e-05
77
+ lr_scheduler_type:
78
+ value: COSINE
79
+ lr_warmup_ratio:
80
+ value: 0.03
81
+ max_length:
82
+ value: 4096
83
+ model_name_or_path:
84
+ value: /mnt/data/hantao/models/Llama-3.1-8B-Instruct
85
+ need_eval:
86
+ value: false
87
+ num_update_steps_per_epoch:
88
+ value: 1466
89
+ offload:
90
+ value: none
91
+ output_dir:
92
+ value: /mnt/data/hantao/stream_output/1029_general_alpaca_8b
93
+ per_device_eval_batch_size:
94
+ value: 4
95
+ per_device_train_batch_size:
96
+ value: 4
97
+ save_16bit:
98
+ value: true
99
+ save_interval:
100
+ value: 500
101
+ seed:
102
+ value: 42
103
+ tf32:
104
+ value: true
105
+ total_training_steps:
106
+ value: 4398
107
+ train_datasets:
108
+ value:
109
+ - - correction-plus
110
+ - path: /home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027.json
111
+ proportion: 1
112
+ trust_remote_code:
113
+ value: true
114
+ weight_decay:
115
+ value: 0
116
+ zero_stage:
117
+ value: 3
wandb/run-20241028_201718-oidiwtgb/files/output.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20241028_201718-oidiwtgb/files/requirements.txt ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ safe-rlhf==0.0.1.dev0
2
+ accelerate==1.0.1
3
+ docker-pycreds==0.4.0
4
+ outlines==0.0.46
5
+ nvidia-nvjitlink-cu12==12.4.127
6
+ nest-asyncio==1.6.0
7
+ tzdata==2024.2
8
+ matplotlib==3.9.2
9
+ ray==2.38.0
10
+ mdurl==0.1.2
11
+ pytz==2024.2
12
+ msgspec==0.18.6
13
+ nvidia-cusolver-cu12==11.4.5.107
14
+ fsspec==2024.9.0
15
+ nvidia-cufft-cu12==11.0.2.54
16
+ regex==2024.9.11
17
+ diskcache==5.6.3
18
+ partial-json-parser==0.2.1.1.post4
19
+ propcache==0.2.0
20
+ pyparsing==3.2.0
21
+ typing_extensions==4.12.2
22
+ rich==13.9.3
23
+ nvidia-cuda-runtime-cu12==12.1.105
24
+ urllib3==2.2.3
25
+ pydantic==2.9.2
26
+ aiosignal==1.3.1
27
+ h11==0.14.0
28
+ mpmath==1.3.0
29
+ markdown-it-py==3.0.0
30
+ scipy==1.14.1
31
+ einops==0.8.0
32
+ nvidia-cublas-cu12==12.1.3.1
33
+ prometheus_client==0.21.0
34
+ mistral_common==1.4.4
35
+ GitPython==3.1.43
36
+ py-cpuinfo==9.0.0
37
+ anyio==4.6.2.post1
38
+ optree==0.13.0
39
+ openai==1.52.1
40
+ absl-py==2.1.0
41
+ jsonschema-specifications==2024.10.1
42
+ watchfiles==0.24.0
43
+ uvloop==0.21.0
44
+ cycler==0.12.1
45
+ charset-normalizer==3.4.0
46
+ tensorboard==2.18.0
47
+ pyarrow==17.0.0
48
+ gguf==0.10.0
49
+ hjson==3.1.0
50
+ pandas==2.2.3
51
+ yarl==1.16.0
52
+ grpcio==1.67.0
53
+ pillow==10.4.0
54
+ safetensors==0.4.5
55
+ httpcore==1.0.6
56
+ requests==2.32.3
57
+ click==8.1.7
58
+ Jinja2==3.1.4
59
+ setproctitle==1.3.3
60
+ zipp==3.20.2
61
+ attrs==24.2.0
62
+ referencing==0.35.1
63
+ numpy==1.26.4
64
+ filelock==3.16.1
65
+ nvidia-cuda-cupti-cu12==12.1.105
66
+ smmap==5.0.1
67
+ protobuf==5.28.3
68
+ pyzmq==26.2.0
69
+ nvidia-curand-cu12==10.3.2.106
70
+ sentencepiece==0.2.0
71
+ tokenizers==0.20.1
72
+ xxhash==3.5.0
73
+ jsonschema==4.23.0
74
+ nvidia-nvtx-cu12==12.1.105
75
+ six==1.16.0
76
+ nvidia-cusparse-cu12==12.1.0.106
77
+ websockets==13.1
78
+ idna==3.10
79
+ xformers==0.0.27.post2
80
+ distro==1.9.0
81
+ numba==0.60.0
82
+ triton==3.0.0
83
+ llvmlite==0.43.0
84
+ setuptools==75.1.0
85
+ importlib_metadata==8.5.0
86
+ prometheus-fastapi-instrumentator==7.0.0
87
+ Werkzeug==3.0.4
88
+ sniffio==1.3.1
89
+ sympy==1.13.1
90
+ kiwisolver==1.4.7
91
+ torch==2.4.0
92
+ fastapi==0.115.3
93
+ interegular==0.3.3
94
+ msgpack==1.1.0
95
+ tqdm==4.66.5
96
+ lark==1.2.2
97
+ lm-format-enforcer==0.10.6
98
+ PyYAML==6.0.2
99
+ pyairports==2.1.1
100
+ MarkupSafe==3.0.2
101
+ compressed-tensors==0.6.0
102
+ uvicorn==0.32.0
103
+ pydantic_core==2.23.4
104
+ frozenlist==1.5.0
105
+ contourpy==1.3.0
106
+ httptools==0.6.4
107
+ packaging==24.1
108
+ cloudpickle==3.1.0
109
+ Pygments==2.18.0
110
+ pip==24.2
111
+ multidict==6.1.0
112
+ rpds-py==0.20.0
113
+ safe-rlhf==0.0.1.dev0
114
+ dill==0.3.8
115
+ wandb==0.18.5
116
+ sentry-sdk==2.17.0
117
+ vllm==0.6.3.post1
118
+ nvidia-ml-py==12.560.30
119
+ platformdirs==4.3.6
120
+ aiohappyeyeballs==2.4.3
121
+ httpx==0.27.2
122
+ nvidia-nccl-cu12==2.20.5
123
+ torchvision==0.19.0
124
+ wheel==0.44.0
125
+ annotated-types==0.7.0
126
+ networkx==3.4.2
127
+ opencv-python-headless==4.10.0.84
128
+ tensorboard-data-server==0.7.2
129
+ nvidia-cudnn-cu12==9.1.0.70
130
+ python-dateutil==2.9.0.post0
131
+ fonttools==4.54.1
132
+ deepspeed==0.15.3
133
+ tiktoken==0.7.0
134
+ transformers==4.45.2
135
+ huggingface-hub==0.26.1
136
+ python-dotenv==1.0.1
137
+ datasets==3.0.2
138
+ jiter==0.6.1
139
+ multiprocess==0.70.16
140
+ pycountry==24.6.1
141
+ starlette==0.41.0
142
+ psutil==6.1.0
143
+ ninja==1.11.1.1
144
+ gitdb==4.0.11
145
+ nvidia-cuda-nvrtc-cu12==12.1.105
146
+ aiohttp==3.10.10
147
+ certifi==2024.8.30
148
+ Markdown==3.7
149
+ jaraco.functools==4.0.1
150
+ platformdirs==4.2.2
151
+ typing_extensions==4.12.2
152
+ autocommand==2.2.2
153
+ importlib_metadata==8.0.0
154
+ inflect==7.3.1
155
+ backports.tarfile==1.2.0
156
+ typeguard==4.3.0
157
+ importlib_resources==6.4.0
158
+ jaraco.text==3.12.1
159
+ wheel==0.43.0
160
+ zipp==3.19.2
161
+ packaging==24.1
162
+ jaraco.context==5.3.0
163
+ tomli==2.0.1
164
+ more-itertools==10.3.0
165
+ jaraco.collections==5.1.0
wandb/run-20241028_201718-oidiwtgb/files/wandb-metadata.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.15.0-122-generic-x86_64-with-glibc2.35",
3
+ "python": "3.11.10",
4
+ "startedAt": "2024-10-28T20:17:18.027884Z",
5
+ "args": [
6
+ "--local_rank=0",
7
+ "--train_datasets",
8
+ "correction-plus::/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027.json",
9
+ "--model_name_or_path",
10
+ "/mnt/data/hantao/models/Llama-3.1-8B-Instruct",
11
+ "--max_length",
12
+ "4096",
13
+ "--trust_remote_code",
14
+ "True",
15
+ "--epochs",
16
+ "3",
17
+ "--per_device_train_batch_size",
18
+ "4",
19
+ "--per_device_eval_batch_size",
20
+ "4",
21
+ "--gradient_accumulation_steps",
22
+ "2",
23
+ "--gradient_checkpointing",
24
+ "--learning_rate",
25
+ "2e-5",
26
+ "--lr_scheduler_type",
27
+ "cosine",
28
+ "--lr_warmup_ratio",
29
+ "0.03",
30
+ "--weight_decay",
31
+ "0.0",
32
+ "--seed",
33
+ "42",
34
+ "--output_dir",
35
+ "/mnt/data/hantao/stream_output/1029_general_alpaca_8b",
36
+ "--log_type",
37
+ "wandb",
38
+ "--log_project",
39
+ "stream_aligner",
40
+ "--zero_stage",
41
+ "3",
42
+ "--offload",
43
+ "none",
44
+ "--bf16",
45
+ "True",
46
+ "--tf32",
47
+ "True",
48
+ "--save_interval",
49
+ "500",
50
+ "--save_16bit"
51
+ ],
52
+ "program": "-m safe_rlhf.finetune.__main__",
53
+ "email": "[email protected]",
54
+ "root": "/mnt/data/hantao/stream_output/1029_general_alpaca_8b",
55
+ "host": "bd-7",
56
+ "username": "saev",
57
+ "executable": "/home/saev/miniconda3/envs/hantao_stream/bin/python",
58
+ "cpu_count": 56,
59
+ "cpu_count_logical": 112,
60
+ "gpu": "NVIDIA A100-SXM4-80GB",
61
+ "gpu_count": 8,
62
+ "disk": {
63
+ "/": {
64
+ "total": "3779092922368",
65
+ "used": "3061809508352"
66
+ }
67
+ },
68
+ "memory": {
69
+ "total": "1082030702592"
70
+ },
71
+ "cpu": {
72
+ "count": 56,
73
+ "countLogical": 112
74
+ },
75
+ "gpu_nvidia": [
76
+ {
77
+ "name": "NVIDIA A100-SXM4-80GB",
78
+ "memoryTotal": "85899345920",
79
+ "cudaCores": 6912,
80
+ "architecture": "Ampere"
81
+ },
82
+ {
83
+ "name": "NVIDIA A100-SXM4-80GB",
84
+ "memoryTotal": "85899345920",
85
+ "cudaCores": 6912,
86
+ "architecture": "Ampere"
87
+ },
88
+ {
89
+ "name": "NVIDIA A100-SXM4-80GB",
90
+ "memoryTotal": "85899345920",
91
+ "cudaCores": 6912,
92
+ "architecture": "Ampere"
93
+ },
94
+ {
95
+ "name": "NVIDIA A100-SXM4-80GB",
96
+ "memoryTotal": "85899345920",
97
+ "cudaCores": 6912,
98
+ "architecture": "Ampere"
99
+ },
100
+ {
101
+ "name": "NVIDIA A100-SXM4-80GB",
102
+ "memoryTotal": "85899345920",
103
+ "cudaCores": 6912,
104
+ "architecture": "Ampere"
105
+ },
106
+ {
107
+ "name": "NVIDIA A100-SXM4-80GB",
108
+ "memoryTotal": "85899345920",
109
+ "cudaCores": 6912,
110
+ "architecture": "Ampere"
111
+ },
112
+ {
113
+ "name": "NVIDIA A100-SXM4-80GB",
114
+ "memoryTotal": "85899345920",
115
+ "cudaCores": 6912,
116
+ "architecture": "Ampere"
117
+ },
118
+ {
119
+ "name": "NVIDIA A100-SXM4-80GB",
120
+ "memoryTotal": "85899345920",
121
+ "cudaCores": 6912,
122
+ "architecture": "Ampere"
123
+ }
124
+ ],
125
+ "cudaVersion": "12.4"
126
+ }
wandb/run-20241028_201718-oidiwtgb/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/step":8796,"train/loss":0.005512164440006018,"train/lr":0,"train/epoch":3,"_timestamp":1.7301539919327292e+09,"_runtime":7388.654268922,"_step":8796,"_wandb":{"runtime":7388}}
wandb/run-20241028_201718-oidiwtgb/logs/debug-internal.log ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2024-10-28T20:17:18.03178695Z","level":"INFO","msg":"using version","core version":"0.18.5"}
2
+ {"time":"2024-10-28T20:17:18.03182537Z","level":"INFO","msg":"created symlink","path":"/mnt/data/hantao/stream_output/1029_general_alpaca_8b/wandb/run-20241028_201718-oidiwtgb/logs/debug-core.log"}
3
+ {"time":"2024-10-28T20:17:18.145947312Z","level":"INFO","msg":"created new stream","id":"oidiwtgb"}
4
+ {"time":"2024-10-28T20:17:18.145984312Z","level":"INFO","msg":"stream: started","id":"oidiwtgb"}
5
+ {"time":"2024-10-28T20:17:18.146095623Z","level":"INFO","msg":"sender: started","stream_id":"oidiwtgb"}
6
+ {"time":"2024-10-28T20:17:18.146160223Z","level":"INFO","msg":"handler: started","stream_id":{"value":"oidiwtgb"}}
7
+ {"time":"2024-10-28T20:17:18.146047192Z","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"oidiwtgb"}}
8
+ {"time":"2024-10-28T20:17:18.690659896Z","level":"INFO","msg":"Starting system monitor"}
9
+ {"time":"2024-10-28T22:20:26.682175893Z","level":"INFO","msg":"Stopping system monitor"}
10
+ {"time":"2024-10-28T22:20:26.684155623Z","level":"INFO","msg":"Stopped system monitor"}
11
+ {"time":"2024-10-28T22:20:27.222985066Z","level":"WARN","msg":"No job ingredients found, not creating job artifact"}
12
+ {"time":"2024-10-28T22:20:27.223025096Z","level":"WARN","msg":"No source type found, not creating job artifact"}
13
+ {"time":"2024-10-28T22:20:27.223036736Z","level":"INFO","msg":"sender: sendDefer: no job artifact to save"}
14
+ {"time":"2024-10-28T22:20:27.683053302Z","level":"INFO","msg":"handler: operation stats","stats":{"operations":[{"desc":"uploading wandb-summary.json","runtime_seconds":0.419228961,"progress":"183B/183B"},{"desc":"uploading output.log","runtime_seconds":0.148623508,"progress":"64.0KB/184.2KB"},{"desc":"uploading config.yaml","runtime_seconds":0.148599098,"progress":"2.2KB/2.2KB"}],"total_operations":3}}
15
+ {"time":"2024-10-28T22:20:28.277908208Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
16
+ {"time":"2024-10-28T22:20:29.889792431Z","level":"INFO","msg":"stream: closing","id":"oidiwtgb"}
17
+ {"time":"2024-10-28T22:20:29.889831071Z","level":"INFO","msg":"handler: closed","stream_id":{"value":"oidiwtgb"}}
18
+ {"time":"2024-10-28T22:20:29.889874332Z","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"oidiwtgb"}}
19
+ {"time":"2024-10-28T22:20:29.889895492Z","level":"INFO","msg":"sender: closed","stream_id":"oidiwtgb"}
20
+ {"time":"2024-10-28T22:20:29.889991772Z","level":"INFO","msg":"stream: closed","id":"oidiwtgb"}
wandb/run-20241028_201718-oidiwtgb/logs/debug.log ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
2
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Configure stats pid to 745177
3
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Loading settings from /home/saev/.config/wandb/settings
4
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Loading settings from /home/saev/hantao/stream_aligner/safe-rlhf-lht/scripts/wandb/settings
5
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Loading settings from environment variables: {'api_key': '***REDACTED***'}
6
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
7
+ 2024-10-28 20:17:18,026 WARNING MainThread:745177 [wandb_setup.py:_flush():79] Could not find program at -m safe_rlhf.finetune.__main__
8
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m safe_rlhf.finetune.__main__'}
9
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_setup.py:_flush():79] Applying login settings: {}
10
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/data/hantao/stream_output/1029_general_alpaca_8b/wandb/run-20241028_201718-oidiwtgb/logs/debug.log
11
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/data/hantao/stream_output/1029_general_alpaca_8b/wandb/run-20241028_201718-oidiwtgb/logs/debug-internal.log
12
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():621] calling init triggers
13
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
14
+ config: {'model_name_or_path': '/mnt/data/hantao/models/Llama-3.1-8B-Instruct', 'max_length': 4096, 'trust_remote_code': True, 'train_datasets': [('correction-plus', {'proportion': 1.0, 'path': '/home/saev/hantao/stream_aligner/stream_annotation/data/train_general_1027.json'})], 'eval_datasets': None, 'epochs': 3, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'gradient_accumulation_steps': 2, 'gradient_checkpointing': True, 'lr': 2e-05, 'lr_scheduler_type': <SchedulerType.COSINE: 'cosine'>, 'lr_warmup_ratio': 0.03, 'weight_decay': 0.0, 'seed': 42, 'fp16': False, 'bf16': True, 'tf32': True, 'eval_strategy': 'epoch', 'eval_interval': 1000000, 'need_eval': False, 'eval_split_ratio': None, 'output_dir': '/mnt/data/hantao/stream_output/1029_general_alpaca_8b', 'log_type': 'wandb', 'log_dir': '/mnt/data/hantao/stream_output/1029_general_alpaca_8b', 'log_project': 'stream_aligner', 'log_run_name': 'sft-2024-10-28-20-17-17', 'save_16bit': True, 'save_interval': 500, 'local_rank': 0, 'zero_stage': 3, 'offload': 'none', 'deepspeed': False, 'deepspeed_config': None, 'deepscale': False, 'deepscale_config': None, 'global_rank': 0, 'device': device(type='cuda', index=0), 'num_update_steps_per_epoch': 1466, 'total_training_steps': 4398}
15
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():671] starting backend
16
+ 2024-10-28 20:17:18,026 INFO MainThread:745177 [wandb_init.py:init():675] sending inform_init request
17
+ 2024-10-28 20:17:18,027 INFO MainThread:745177 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-10-28 20:17:18,027 INFO MainThread:745177 [wandb_init.py:init():688] backend started and connected
19
+ 2024-10-28 20:17:18,030 INFO MainThread:745177 [wandb_init.py:init():783] updated telemetry
20
+ 2024-10-28 20:17:18,030 INFO MainThread:745177 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
21
+ 2024-10-28 20:17:18,686 INFO MainThread:745177 [wandb_init.py:init():867] starting run threads in backend
22
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_console_start():2463] atexit reg
23
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_redirect():2311] redirect: wrap_raw
24
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_redirect():2376] Wrapping output streams.
25
+ 2024-10-28 20:17:18,784 INFO MainThread:745177 [wandb_run.py:_redirect():2401] Redirects installed.
26
+ 2024-10-28 20:17:18,785 INFO MainThread:745177 [wandb_init.py:init():911] run started, returning control to user process
27
+ 2024-10-28 22:20:26,678 INFO MainThread:745177 [wandb_run.py:_finish():2158] finishing run htlou/stream_aligner/oidiwtgb
28
+ 2024-10-28 22:20:26,679 INFO MainThread:745177 [wandb_run.py:_atexit_cleanup():2426] got exitcode: 0
29
+ 2024-10-28 22:20:26,679 INFO MainThread:745177 [wandb_run.py:_restore():2408] restore
30
+ 2024-10-28 22:20:26,679 INFO MainThread:745177 [wandb_run.py:_restore():2414] restore done
31
+ 2024-10-28 22:20:29,876 INFO MainThread:745177 [wandb_run.py:_footer_history_summary_info():3975] rendering history
32
+ 2024-10-28 22:20:29,879 INFO MainThread:745177 [wandb_run.py:_footer_history_summary_info():4007] rendering summary
33
+ 2024-10-28 22:20:29,888 INFO MainThread:745177 [wandb_run.py:_footer_sync_info():3934] logging synced files
wandb/run-20241028_201718-oidiwtgb/run-oidiwtgb.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22115c6bf6acb059746bb05f4e2461e55cd06b96d3502b9f878b0d8e4370f704
3
+ size 12489416