axolotl version: 0.4.1
base_model: Qwen/Qwen2-7B
trust_remote_code: true
chat_template: chatml
load_in_8bit: false
# load_in_4bit: true
strict: false
datasets:
- path: arcee-ai/MyAlee-Education-Instructions-V2
type: sharegpt
field_messages: messages
- path: Crystalcareai/Orca-Reka
type: alpaca
dataset_prepared_path:
val_set_size: 0
output_dir: ./outputs/out
sequence_len: 16384
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
# adapter: qlora
# lora_model_dir:
# lora_r: 32
# lora_alpha: 64
# lora_dropout: 0.05
# lora_target_linear: true
# lora_fan_in_fan_out:
# wandb_project: qwen2-education
# wandb_entity:
# wandb_watch:
# wandb_name:
# wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 5
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 1e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: 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
evals_per_epoch: 0
saves_per_epoch: 1
max_total_saves: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
# 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:
pad_token: "<|endoftext|>"
eos_token: "<|im_end|>"
outputs/out
This model is a fine-tuned version of Qwen/Qwen2-7B 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 5
Training results
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1