Hugging Face's logo

jssky
/
e7b79a88-7469-44e1-a9dd-89bc6a5f195a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e7b79a88-7469-44e1-a9dd-89bc6a5f195a / README.md
jssky's picture
jssky
End of training
79e4ac8 verified
preview code
|
raw
history blame contribute delete
3.86 kB
metadata
library_name: peft
license: llama3
base_model: NousResearch/Hermes-3-Llama-3.1-8B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: e7b79a88-7469-44e1-a9dd-89bc6a5f195a
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.5.2

adapter: lora
base_model: NousResearch/Hermes-3-Llama-3.1-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 56d86ad0aa08fd84_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/56d86ad0aa08fd84_train_data.json
  type:
    field_instruction: text
    field_output: transcription_normalised
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: jssky/e7b79a88-7469-44e1-a9dd-89bc6a5f195a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/56d86ad0aa08fd84_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
sequence_len: 2048
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: e7b79a88-7469-44e1-a9dd-89bc6a5f195a
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e7b79a88-7469-44e1-a9dd-89bc6a5f195a
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: true

e7b79a88-7469-44e1-a9dd-89bc6a5f195a

This model is a fine-tuned version of NousResearch/Hermes-3-Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0042

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • total_eval_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_TORCH 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: 2
  • training_steps: 50

Training results

Training Loss Epoch Step Validation Loss
1.134 0.0354 1 2.4975
0.0149 0.8850 25 0.0096
0.0054 1.7699 50 0.0042

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.3
  • Pytorch 2.3.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3