Hugging Face's logo

fats-fme
/
3542da96-d2a9-4445-926c-b6490a0c20f3

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
3542da96-d2a9-4445-926c-b6490a0c20f3 / README.md
fats-fme's picture
fats-fme
End of training
f087be2 verified
preview code
|
raw
history blame contribute delete
3.97 kB
metadata
library_name: peft
license: apache-2.0
base_model: OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 3542da96-d2a9-4445-926c-b6490a0c20f3
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - d4f6a0ff9603756d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/d4f6a0ff9603756d_train_data.json
  type:
    field_input: rejected
    field_instruction: prompt
    field_output: accepted
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
double_quant: true
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: fats-fme/3542da96-d2a9-4445-926c-b6490a0c20f3
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 75GB
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/d4f6a0ff9603756d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
quant_type: nf4
resume_from_checkpoint: null
s2_attention: null
sample_packing: true
save_steps: 50
saves_per_epoch: null
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 531498cc-50af-4561-a3ba-60a0eb4190d6
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 531498cc-50af-4561-a3ba-60a0eb4190d6
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null

3542da96-d2a9-4445-926c-b6490a0c20f3

This model is a fine-tuned version of OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.7002

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • training_steps: 100

Training results

Training Loss Epoch Step Validation Loss
42.8562 0.0017 1 5.4856
34.6317 0.0843 50 4.2333
22.2685 0.1686 100 2.7002

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1