base_model: openlm-research/open_llama_3b_v2
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
push_dataset_to_hub:
datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
adapter: qlora
lora_model_dir:
sequence_len: 1024
sample_packing: true
lora_r: 8
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./qlora-out
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_32bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: false
fp16: true
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
gptq_groupsize:
gptq_model_v1:
warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

qlora-out

This model is a fine-tuned version of openlm-research/open_llama_3b_v2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1425

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: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2567	0.0	1	1.3470
1.0032	0.25	107	1.1363
1.0994	0.5	214	1.1272
1.3518	0.75	321	1.1147
1.1638	1.0	428	1.1096
1.1003	1.23	535	1.1364
0.7622	1.48	642	1.1427
1.8904	1.73	749	1.1425

Framework versions

PEFT 0.9.0
Transformers 4.38.2
Pytorch 2.1.2+cu118
Datasets 2.18.0
Tokenizers 0.15.0

balajipitchumani/axol-openllmama-1k-qlora

qlora-out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

balajipitchumani/
axol-openllmama-1k-qlora