Hugging Face's logo

lesso18
/
ecc2b8dc-3f2b-485b-ad43-af7d64536eea

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ecc2b8dc-3f2b-485b-ad43-af7d64536eea / README.md
lesso18's picture
lesso18
End of training
c3916b6 verified
preview code
|
raw
history blame
4.32 kB
metadata
library_name: peft
license: apache-2.0
base_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: ecc2b8dc-3f2b-485b-ad43-af7d64536eea
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f580edf688d697f0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f580edf688d697f0_train_data.json
  type:
    field_input: essay
    field_instruction: prompt
    field_output: evaluation
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: true
hub_model_id: lesso18/ecc2b8dc-3f2b-485b-ad43-af7d64536eea
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000218
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/G.O.D/f580edf688d697f0_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: 50
saves_per_epoch: null
seed: 180
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: 25202894-ba9f-4341-936a-2f5d69bcd96c
wandb_project: 18a
wandb_run: your_name
wandb_runid: 25202894-ba9f-4341-936a-2f5d69bcd96c
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

ecc2b8dc-3f2b-485b-ad43-af7d64536eea

This model is a fine-tuned version of NousResearch/Nous-Hermes-2-SOLAR-10.7B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3961

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: 0.000218
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 180
  • gradient_accumulation_steps: 2
  • 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: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0002 1 0.9534
0.5504 0.0104 50 0.5831
0.6452 0.0208 100 0.5537
0.5554 0.0312 150 0.5378
0.566 0.0416 200 0.5338
0.4541 0.0520 250 0.5013
0.4437 0.0624 300 0.4651
0.4195 0.0728 350 0.4388
0.4642 0.0832 400 0.4156
0.3864 0.0936 450 0.3997
0.4153 0.1040 500 0.3961

Framework versions

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