base_model: Qwen/Qwen1.5-0.5B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true


load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: silk-road/ChatHaruhi-RolePlaying
    type: "completion"
dataset_prepared_path: 
val_set_size: 0.00
output_dir: ./outputs/out

sequence_len: 250
sample_packing: true
pad_to_sequence_len: true
save_safetensors: true
gpu_memory_limit: 80GiB

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00005

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: false   #toggle

warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: #deepspeed_configs/zero2.json # multi-gpu only
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:

outputs/out

This model is a fine-tuned version of Qwen/Qwen1.5-0.5B 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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1

Training results

Framework versions

Transformers 4.40.2
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1

Primeness/primelive3

outputs/out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Primeness/
primelive3