PEFT
PyTorch
Safetensors
llama
Generated from Trainer

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: pints-ai/1.5-Pints-16K-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: tangledgroup/tangled-llama-pints-1.5b-v0.1-dataset
    type: sharegpt
    conversation: chatml
chat_template: chatml
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
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:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
# optimizer: paged_adamw_32bit
optimizer: adamw_torch_fused
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: 15.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 3
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

tangledgroup/tangled-llama-pints-1.5b-v0.1-instruct

This model is a fine-tuned version of pints-ai/1.5-Pints-16K-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0998

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.1867 0.0041 1 1.2217
1.147 0.3347 82 1.1398
1.1475 0.6694 164 1.1236
1.1831 1.0041 246 1.1143
1.1513 1.3194 328 1.1087
1.0978 1.6541 410 1.1045
1.085 1.9888 492 1.1015
1.0014 2.3041 574 1.1004
0.9882 2.6388 656 1.0998

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 4.18
IFEval (0-Shot) 15.09
BBH (3-Shot) 3.84
MATH Lvl 5 (4-Shot) 0.08
GPQA (0-shot) 0.00
MuSR (0-shot) 4.85
MMLU-PRO (5-shot) 1.21
Downloads last month
0
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for tangledlabs/tangled-llama-pints-1.5b-v0.1-instruct

Adapter
(2)
this model

Dataset used to train tangledlabs/tangled-llama-pints-1.5b-v0.1-instruct

Collection including tangledlabs/tangled-llama-pints-1.5b-v0.1-instruct