Hugging Face's logo

Nexspear
/
9e540d9e-5ec2-42c0-b780-b9e11a06e391

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
9e540d9e-5ec2-42c0-b780-b9e11a06e391 / README.md
Nexspear's picture
Nexspear
End of training
9292fa3 verified
preview code
|
raw
history blame contribute delete
4.26 kB
metadata
library_name: peft
base_model: unsloth/Hermes-3-Llama-3.1-8B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 9e540d9e-5ec2-42c0-b780-b9e11a06e391
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Hermes-3-Llama-3.1-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 15160cecae42f4a0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/15160cecae42f4a0_train_data.json
  type:
    field_input: src
    field_instruction: prompt
    field_output: tgt
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: Nexspear/9e540d9e-5ec2-42c0-b780-b9e11a06e391
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/15160cecae42f4a0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 881d25a8-b8b9-4102-ad7e-27d5b99cca9f
wandb_project: Gradients-On-Four
wandb_run: your_name
wandb_runid: 881d25a8-b8b9-4102-ad7e-27d5b99cca9f
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

9e540d9e-5ec2-42c0-b780-b9e11a06e391

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

  • Loss: 0.6514

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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: 100

Training results

Training Loss Epoch Step Validation Loss
No log 0.0003 1 1.7632
1.862 0.0027 9 1.5972
1.0289 0.0054 18 0.9071
0.8101 0.0081 27 0.7250
0.6856 0.0108 36 0.6866
0.566 0.0135 45 0.6685
0.7163 0.0162 54 0.6605
0.5931 0.0189 63 0.6569
0.6376 0.0216 72 0.6536
0.6189 0.0243 81 0.6521
0.6504 0.0269 90 0.6514
0.6782 0.0296 99 0.6514

Framework versions

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