Jinfeng-sun's workspace
Runs
23
Name
5 visualized
_attn_implementation_autoset
_name_or_path
accelerator_config.even_batches
accelerator_config.non_blocking
accelerator_config.split_batches
accelerator_config.use_seedable_sampler
architectures
attention_dropout
attn_dropout_prob
auto_map.AutoConfig
auto_map.AutoModelForCausalLM
batch_eval_metrics
bf16
bos_token_id
data_args.buffer_size
data_args.cutoff_len
data_args.dataset
data_args.dataset_dir
data_args.ignore_pad_token_for_loss
data_args.image_dir
data_args.mask_history
data_args.mix_strategy
data_args.neat_packing
data_args.overwrite_cache
data_args.packing
data_args.preprocessing_batch_size
data_args.preprocessing_num_workers
data_args.streaming
data_args.template
data_args.train_on_prompt
data_args.val_size
data_seed
dataloader_persistent_workers
ddp_backend
ddp_broadcast_buffers
ddp_bucket_cap_mb
ddp_find_unused_parameters
debug
deepspeed
do_eval
emb_dropout_prob
eos_token_id
eval_accumulation_steps
eval_batch_size
eval_do_concat_batches
eval_on_start
eval_steps
eval_strategy
eval_use_gather_object
evaluation_strategy
finetuning_args.additional_target
true
/mnt/public/base_llms/hub/Qwen/Qwen2.5-7B-Instruct
true
false
false
true
["Qwen2ForCausalLM"]
0
-
-
-
false
true
151643
16384
5000
["zhengwen_dataset_v8"]
../data
true
../data
false
concat
false
true
false
1000
64
false
qwen
false
0.05
-
false
-
-
-
-
[]
-
true
-
151645
-
-
true
false
490
steps
false
steps
["embed_tokens","lm_head"]
true
/mnt/public/base_llms/hub/Qwen/Qwen2.5-7B-Instruct
true
false
false
true
["Qwen2ForCausalLM"]
0
-
-
-
false
true
151643
16384
5000
["zhengwen_dataset_v8"]
../data
true
../data
false
concat
false
true
false
1000
64
false
qwen
false
0.05
-
false
-
-
-
-
[]
-
true
-
151645
-
-
true
false
490
steps
false
steps
["embed_tokens","lm_head"]
true
/mnt/base_llms/hub/Qwen/Qwen2.5-7B-Instruct
true
false
false
true
["Qwen2ForCausalLM"]
0
-
-
-
false
true
151643
16384
5000
["zhengwen_dataset_v8"]
../data
true
../data
false
concat
false
true
false
1000
64
false
qwen
false
0.05
-
false
-
-
-
-
[]
-
true
-
151645
-
-
true
false
490
steps
false
steps
["embed_tokens","lm_head"]
true
/mnt/base_llms/hub/Qwen/Qwen2___5-14B-Instruct
true
false
false
true
["Qwen2ForCausalLM"]
0
-
-
-
false
true
151643
16384
1024
["nature_standard_qa_dataset_v1","common_sft_cn_v1","common_sft_en_v1"]
../data
true
../data
false
concat
false
true
false
1000
64
false
qwen
false
0.05
-
false
-
-
-
-
[]
deepspeed/ds_z3_config.json
true
-
151645
-
-
true
false
90
steps
false
steps
["embed_tokens","lm_head"]
true
/workspace/share_data/base_llms/qwen/Qwen2.5-14B-Instruct
true
false
false
true
["Qwen2ForCausalLM"]
0
-
-
-
false
true
151643
16384
1024
["nature_standard_qa_dataset_v1","common_sft_cn_v1","common_sft_en_v1"]
../data
true
../data
false
concat
false
true
false
1000
64
false
qwen
false
0.05
-
false
-
-
-
-
[]
deepspeed/ds_z3_config.json
true
-
151645
-
-
true
false
90
steps
false
steps
["embed_tokens","lm_head"]
true
/mnt/base_llms/hub/Qwen/Qwen2___5-14B-Instruct
true
false
false
true
["Qwen2ForCausalLM"]
0
-
-
-
false
true
151643
16384
1024
["nature_standard_qa_dataset_v1","common_sft_cn_v1","common_sft_en_v1"]
../data
true
../data
false
concat
false
true
false
1000
64
false
qwen
false
0.05
-
false
-
-
-
-
[]
deepspeed/ds_z3_config.json
true
-
151645
-
-
true
false
90
steps
false
steps
["embed_tokens","lm_head"]
-
/root/sunjinfeng/base_llms/luoshu/lluoshu-7B
true
-
false
true
["Qwen2ForCausalLM"]
0
-
-
-
-
true
151643
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
-
[]
-
true
-
151643
-
-
true
-
1
-
-
steps
-
-
/workspace/sunjinfeng/models/qwen/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
None
-
None
None
None
false
[]
None
false
0
-
None
8
-
-
None
-
-
no
-
-
/workspace/share_data/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/workspace/sunjinfeng/models/qwen/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
None
-
None
None
None
false
[]
None
false
0
-
None
8
-
-
None
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/workspace/share_data/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
None
-
None
None
None
false
[]
None
false
0
-
None
8
-
-
None
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
-
/home/ma-user/work/sunjinfeng/base_llms/Qwen-7B-Chat
-
-
-
-
["QWenLMHeadModel"]
-
0
configuration_qwen.QWenConfig
modeling_qwen.QWenLMHeadModel
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
false
-
-
-
false
[]
-
false
0
-
-
-
-
-
-
-
-
no
-
1-20
of 23