|
|
---
|
|
|
license: apache-2.0
|
|
|
base_model:
|
|
|
- Qwen/Qwen2.5-7B
|
|
|
library_name: transformers
|
|
|
language:
|
|
|
- zho
|
|
|
- eng
|
|
|
- fra
|
|
|
- spa
|
|
|
- por
|
|
|
- deu
|
|
|
- ita
|
|
|
- rus
|
|
|
- jpn
|
|
|
- kor
|
|
|
- vie
|
|
|
- tha
|
|
|
- ara
|
|
|
---
|
|
|
|
|
|
```
|
|
|
base_model: Qwen/Qwen2.5-7B
|
|
|
model_type: AutoModelForCausalLM
|
|
|
tokenizer_type: AutoTokenizer
|
|
|
|
|
|
load_in_8bit: false
|
|
|
load_in_4bit: false
|
|
|
strict: false
|
|
|
|
|
|
datasets:
|
|
|
- path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
|
|
|
type: sharegpt
|
|
|
conversation: chatml
|
|
|
- path: NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered
|
|
|
type: sharegpt
|
|
|
conversation: chatml
|
|
|
- path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
|
|
|
type: sharegpt
|
|
|
conversation: chatml
|
|
|
- path: NewEden/Gryphe-Sonnet-3.5-35k-Subset
|
|
|
type: sharegpt
|
|
|
conversation: chatml
|
|
|
- path: Nitral-AI/Reasoning-1shot_ShareGPT
|
|
|
type: sharegpt
|
|
|
conversation: chatml
|
|
|
- path: Nitral-AI/GU_Instruct-ShareGPT
|
|
|
type: sharegpt
|
|
|
conversation: chatml
|
|
|
- path: Nitral-AI/Medical_Instruct-ShareGPT
|
|
|
type: sharegpt
|
|
|
conversation: chatml
|
|
|
|
|
|
chat_template: chatml
|
|
|
|
|
|
val_set_size: 0.01
|
|
|
output_dir: ./outputs/out
|
|
|
|
|
|
adapter:
|
|
|
lora_r:
|
|
|
lora_alpha:
|
|
|
lora_dropout:
|
|
|
lora_target_linear:
|
|
|
|
|
|
sequence_len: 8192
|
|
|
# sequence_len: 32768
|
|
|
sample_packing: true
|
|
|
eval_sample_packing: false
|
|
|
pad_to_sequence_len: true
|
|
|
|
|
|
plugins:
|
|
|
- axolotl.integrations.liger.LigerPlugin
|
|
|
liger_rope: true
|
|
|
liger_rms_norm: true
|
|
|
liger_swiglu: true
|
|
|
liger_fused_linear_cross_entropy: true
|
|
|
|
|
|
wandb_project: qwen7B
|
|
|
wandb_entity:
|
|
|
wandb_watch:
|
|
|
wandb_name: qwen7B
|
|
|
wandb_log_model:
|
|
|
|
|
|
gradient_accumulation_steps: 32
|
|
|
micro_batch_size: 1
|
|
|
num_epochs: 2
|
|
|
optimizer: adamw_bnb_8bit
|
|
|
lr_scheduler: cosine
|
|
|
learning_rate: 0.00001
|
|
|
weight_decay: 0.05
|
|
|
|
|
|
train_on_inputs: false
|
|
|
group_by_length: false
|
|
|
bf16: auto
|
|
|
fp16:
|
|
|
tf32: true
|
|
|
|
|
|
gradient_checkpointing: true
|
|
|
early_stopping_patience:
|
|
|
resume_from_checkpoint:
|
|
|
local_rank:
|
|
|
logging_steps: 1
|
|
|
xformers_attention:
|
|
|
flash_attention: true
|
|
|
|
|
|
warmup_ratio: 0.1
|
|
|
evals_per_epoch: 4
|
|
|
eval_table_size:
|
|
|
eval_max_new_tokens: 128
|
|
|
saves_per_epoch: 2
|
|
|
|
|
|
debug:
|
|
|
deepspeed:
|
|
|
fsdp:
|
|
|
fsdp_config:
|
|
|
|
|
|
special_tokens:
|
|
|
pad_token: <pad>
|
|
|
``` |
