base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
trust_remote_code: false

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: qwen_25
datasets:
  - path: data/raft_train_iter1_0_1000
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant", "ai"]
      system: ["system"]

dataset_prepared_path:
val_set_size: 0.0
output_dir: /shared/storage-01/jiarui14/EM-CoT/Online-DPO-R1/outputs/Qwen1.5B-Inst_numina_raft1_orig_eos

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

# wandb_project: huggingface
# wandb_entity: zzzzzaa
# wandb_watch:
# wandb_name: qwen_test
# wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 1e-5

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

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

warmup_ratio: 0.05
saves_per_epoch: 1
evals_per_epoch: 0
debug:
weight_decay: 0.01
fsdp:
fsdp_config:
# special_tokens:
#   bos_token: "<|im_start|>"
#   eos_token: "<|im_end|>"
#   pad_token: "<|endoftext|>"


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

shared/storage-01/jiarui14/EM-CoT/Online-DPO-R1/outputs/Qwen1.5B-Inst_numina_raft1_orig_eos

This model is a fine-tuned version of Qwen/Qwen2.5-Math-1.5B-Instruct 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
gradient_accumulation_steps: 64
total_train_batch_size: 64
optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 3.0

Training results

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

FlippyDora/Qwen1.5B-Inst_numina_raft1_orig_eos

shared/storage-01/jiarui14/EM-CoT/Online-DPO-R1/outputs/Qwen1.5B-Inst_numina_raft1_orig_eos

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

FlippyDora/
Qwen1.5B-Inst_numina_raft1_orig_eos