adapter: lora
base_model: ByteDance-Seed/Seed-Coder-8B-Instruct
bf16: true
dataset_prepared_path: last_run_prepared

# Dataset configuration for instruction/input/output format
datasets:
- chat_template: tokenizer_default
  field_messages: messages
  message_field_content: content
  message_field_role: role
  path: data_sft_region.jsonl
  roles:
    assistant:
    - assistant
    system:
    - system
    user:
    - user
  type: chat_template

debug: null
deepspeed: /osmosis/zero2.json
early_stopping_patience: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
group_by_length: false
learning_rate: 0.0001
liger_fused_linear_cross_entropy: true
liger_glu_activation: true
liger_layer_norm: true
liger_rms_norm: true
liger_rope: true
load_in_4bit: false
load_in_8bit: false
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1
micro_batch_size: 4
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_torch
output_dir: ./out-NC-seedcoder
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
resume_from_checkpoint: null
sample_packing: false
save_steps: 60
save_total_limit: 100
sequence_len: 8192
# special_tokens:
#   eos_token: <|im_end|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_entity: test-aa
wandb_project: seedcoder
wandb_log_model: null
wandb_name: updated-data-pattern
wandb_watch: null
warmup_ratio: 0.05
weight_decay: 0.0
xformers_attention: null

out-NC-seedcoder

This model is a fine-tuned version of ByteDance-Seed/Seed-Coder-8B-Instruct on the data_sft_region.jsonl 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: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 28
training_steps: 568

Training results

Framework versions

PEFT 0.17.1
Transformers 4.57.1
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

pandyamarut/SC-tab

out-NC-seedcoder

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

pandyamarut/
SC-tab