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

arcee-ai/MyAlee-Qwen-Instruct-v2-16k-v1

outputs/out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

arcee-ai/
MyAlee-Qwen-Instruct-v2-16k-v1