See axolotl config

axolotl version: 0.4.1

base_model: Qwen/Qwen2.5-Coder-7B
trust_remote_code: false

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: nyxkrage/erebus-87k-fim-8k
    data_files: data/*
    type:
      field_instruction: prefix
      field_input: suffix
      field_output: middle
      format: "<|fim_suffix|>{input}<|fim_prefix|>{instruction}<|fim_middle|>"
dataset_prepared_path:
val_set_size: 0
output_dir: /workspace/data/output 

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

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwen2.5-coder-7b-erebus-fim
wandb_entity: kragelund
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00005

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

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

hub_model_id: NyxKrage/Qwen2.5-Coder-7B-Erebus-FIM
hub_strategy: all_checkpoints

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

warmup_steps: 100
evals_per_epoch: 1
saves_per_epoch: 4
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.1
special_tokens:

Qwen2.5-Coder-7B-Erebus-FIM

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 4

Training results

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1