Hugging Face's logo

robiulawaldev
/
0a0d75c1-3af9-40be-856e-ab3a34e28b48

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
0a0d75c1-3af9-40be-856e-ab3a34e28b48 / README.md
robiulawaldev's picture
robiulawaldev
End of training
38102be verified
preview code
|
raw
history blame
4.12 kB
metadata
library_name: peft
license: apache-2.0
base_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 0a0d75c1-3af9-40be-856e-ab3a34e28b48
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - eac6340f135c05d0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/eac6340f135c05d0_train_data.json
  type:
    field_input: section
    field_instruction: link
    field_output: text
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: robiulawaldev/0a0d75c1-3af9-40be-856e-ab3a34e28b48
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
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: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 7091
micro_batch_size: 4
mlflow_experiment_name: /tmp/eac6340f135c05d0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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: 500
saves_per_epoch: null
sequence_len: 512
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: 384f84de-b0ed-4412-b41f-491ce44b0964
wandb_project: SN56-36
wandb_run: your_name
wandb_runid: 384f84de-b0ed-4412-b41f-491ce44b0964
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

0a0d75c1-3af9-40be-856e-ab3a34e28b48

This model is a fine-tuned version of NousResearch/Nous-Hermes-2-Mistral-7B-DPO on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9169

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 50
  • training_steps: 7091

Training results

Training Loss Epoch Step Validation Loss
No log 0.0001 1 1.8379
7.223 0.0312 500 1.8268
7.3156 0.0624 1000 1.8398
7.3141 0.0936 1500 1.8749
7.4454 0.1248 2000 1.9169

Framework versions

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