See axolotl config
axolotl version: 0.3.0
base_model: HuggingFaceH4/mistral-7b-sft-beta
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
rl: kto_pair
datasets:
- path: winglian/deita-nectar
split: train_dpo
type: zephyr.nectar
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./zephyr-deita-kto-3ep
save_total_limit: 3
hub_model_id: openaccess-ai-collective/kto-zephyr-deita-nectar
adapter: lora
lora_model_dir:
sequence_len: 2048
sample_packing: false
pad_to_sequence_len: false
lora_r: 128
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
lora_fan_in_fan_out:
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
wandb_project: dpo-zephyr-deita-nectar
wandb_entity: oaaic
wandb_watch:
wandb_run_id: kto-3ep
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilion: 0.00001
lr_scheduler: cosine
learning_rate: 1.0e-5
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: true
gradient_checkpointing: 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
fsdp:
fsdp_config:
special_tokens:
save_safetensors: true
dataloader_num_workers: 16
dataloader_pin_memory: true
zephyr-deita-kto-3ep
This model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta 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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 1615
Training results
Framework versions
- PEFT 0.7.0
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 3