Hugging Face's logo

carsonpoole
/
Qwen2-37B-Pruned

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
Qwen2-37B-Pruned / README.md
carsonpoole's picture
carsonpoole
Model save
0ec8825 verified
preview code
|
raw
history blame contribute delete
3.64 kB
metadata
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: carsonpoole/Qwen2-72B-Instruct-Every-Other-Layer
model-index:
  - name: Qwen2-37B-Pruned
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: carsonpoole/Qwen2-72B-Instruct-Every-Other-Layer
trust_remote_code: false

load_in_8bit: false
load_in_4bit: true # Changed to false
strict: false

datasets:
  - path: teknium/OpenHermes-2.5
    # type:
    #   system_prompt: ""
    #   system_format: "{system}"
    #   field_system: system
    #   field_instruction: human
    #   field_input: system
    #   field_output: gpt
    #   format: |-
    #     User: {instruction} {input}
    #     Assistant:
    #   no_input_format: "{instruction} "
    type: sharegpt

dataset_prepared_path:
val_set_size: 0
output_dir: ./outputs/out

sequence_len: 8192
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

hub_model_id: carsonpoole/Qwen2-37B-Pruned # Specify the repository name for pushing to the Hub
hub_strategy: every_save # Push checkpoint to the Hub on every save

wandb_project: forefront-research
wandb_entity: helloforefront
wandb_watch:
wandb_name: qwen2-37b-pruned-v0_3_2
wandb_log_model:

adapter: qlora
lora_model_dir:
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: true
group_by_length: false
bf16: auto
fp16:
tf32: true

hf_use_auth_token: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
max_steps: 192
debug:
deepspeed:
weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:

Qwen2-37B-Pruned

This model is a fine-tuned version of carsonpoole/Qwen2-72B-Instruct-Every-Other-Layer on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 192

Training results

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1