See axolotl config
axolotl version: 0.4.0
base_model: wenbopan/Faro-Yi-9B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_llama_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
rl: dpo
datasets:
- path: theIndividual/UltraInteractPair_axolotl
split: train
type: chatml
val_set_size: 0.1
output_dir: results/Faro-Yi-9B-DPO
sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false
adapter: lora
lora_model_dir:
lora_r: 16
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
lora_fan_in_fan_out:
lora_target_modules:
- k_proj
- gate_proj
- v_proj
- up_proj
- q_proj
- o_proj
- down_proj
wandb_project: faro-yi-dpo
wandb_entity:
wandb_name:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilion: 0.00001
lr_scheduler: linear
learning_rate: 1e-6
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
gradient_checkpoint_kwargs:
use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
eval_steps:
eval_table_size:
eval_table_max_new_tokens: 128
save_steps: 45
debug:
deepspeed:
weight_decay: 0.1
special_tokens:
save_safetensors: true
dataloader_num_workers: 16
dataloader_pin_memory: true
results/Faro-Yi-9B-DPO
This model is a fine-tuned version of wenbopan/Faro-Yi-9B on an unknown 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-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 109761
Training results
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.17.1
- Tokenizers 0.15.0
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for theIndividual/Faro-Yi-9B-DPO
Base model
wenbopan/Faro-Yi-9B
Finetuned
this model