adrian27513/gsm8k_1

See axolotl config

axolotl version: 0.12.2

base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: openai/gsm8k
    split: train
    name: main
    type:
      system_prompt: ""
      field_system: system
      field_instruction: question
      field_output: answer
      format: "Question:{instruction}\nAnswer:"
      no_input_format: "Question:{instruction}\nAnswer:"

output_dir: ./gsm8k_patch

sequence_len: 512
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

adapter: lora
lora_model_dir:


lora_r: 8
lora_alpha: 16
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 48
num_epochs: 5
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 20.0
loss_watchdog_patience: 5

warmup_steps: 30
evals_per_epoch: 0
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

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

gsm8k_patch

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the openai/gsm8k 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: 0.0002
• train_batch_size: 48
• eval_batch_size: 48
• seed: 42
• 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: 30
• training_steps: 305

Training results

Framework versions

• PEFT 0.17.0
• Transformers 4.55.2
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4