Hugging Face's logo

lesso05
/
6ac18656-7089-44f3-a529-5f76c1b9c7e5

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
6ac18656-7089-44f3-a529-5f76c1b9c7e5 / README.md
lesso05's picture
lesso05
End of training
2fcf410 verified
preview code
|
raw
history blame
3.94 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: 6ac18656-7089-44f3-a529-5f76c1b9c7e5
    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
datasets:
- data_files:
  - 1a801d7a901fba69_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1a801d7a901fba69_train_data.json
  type:
    field_instruction: anchor
    field_output: positive
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: lesso05/6ac18656-7089-44f3-a529-5f76c1b9c7e5
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 25
micro_batch_size: 2
mlflow_experiment_name: /tmp/1a801d7a901fba69_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: eb13509f-b013-45d7-a9b2-7208ff33e7b7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: eb13509f-b013-45d7-a9b2-7208ff33e7b7
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

6ac18656-7089-44f3-a529-5f76c1b9c7e5

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: 2.3117

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: 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: 10
  • training_steps: 25

Training results

Training Loss Epoch Step Validation Loss
12.5795 0.0006 1 3.1219
10.3859 0.0029 5 3.0465
9.6618 0.0058 10 2.6850
9.9671 0.0087 15 2.4641
8.0892 0.0116 20 2.3354
10.2569 0.0145 25 2.3117

Framework versions

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