base_model: Crystalcareai/CrystalMistral-13b
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

rl: dpo
datasets:
  - path: Crystalcareai/truthyDPO-intel
    split: train
    type: chatml.intel
  - path: Crystalcareai/distilabel-intel-orca-dpo-pairs_intel_format
    split: train
    type: chatml.intel

dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./qlora-out

## You can optionally freeze the entire model and unfreeze a subset of parameters
unfrozen_parameters:
#  - lm_head.*
#  - model.embed_tokens.*
#  - model.layers.2[0-9]+.block_sparse_moe.gate.*
#  - model.layers.2[0-9]+.block_sparse_moe.experts.*
#  - model.layers.3[0-9]+.block_sparse_moe.gate.*
#  - model.layers.3[0-9]+.block_sparse_moe.experts.*

model_config:
  output_router_logits: true

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
#lora_target_modules:
#  - gate
#  - q_proj
#  - k_proj
#  - v_proj
#  - o_proj
#  - w1
#  - w2
#  - w3

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 1
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:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: 
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

qlora-out

This model is a fine-tuned version of Crystalcareai/CrystalMistral-13b 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: 0.0002
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 64
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 217

Training results

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.2+cu118
Datasets 2.17.0
Tokenizers 0.15.0

Crystalcareai/CrystalMistral-2x7B-Lora

qlora-out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Crystalcareai/
CrystalMistral-2x7B-Lora