Hugging Face's logo

besimray
/
miner_id_2_ba9938bd-5490-4a39-90ab-976131f92334_1730940658

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
miner_id_2_ba9938bd-5490-4a39-90ab-976131f92334_1730940658 / README.md
besimray's picture
besimray
End of training
b1a8e95 verified
preview code
|
raw
history blame contribute delete
4.46 kB
metadata
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-1B-Instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: miner_id_2_ba9938bd-5490-4a39-90ab-976131f92334_1730940658
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Llama-3.2-1B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - databricks-dolly-15k_train_data.json
  ds_type: json
  path: /workspace/input_data/databricks-dolly-15k_train_data.json
  type:
    field_input: instruction
    field_instruction: context
    field_output: response
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 10
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hours_to_complete: 5
hub_model_id: besimray/miner_id_2_ba9938bd-5490-4a39-90ab-976131f92334_1730940658
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: 32
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: 500
micro_batch_size: 1
mlflow_experiment_name: /tmp/databricks-dolly-15k_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
save_steps: 10
save_strategy: steps
sequence_len: 4096
started_at: '2024-11-07T00:50:58.115572'
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: besimray24-rayon
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: ba9938bd-5490-4a39-90ab-976131f92334
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

miner_id_2_ba9938bd-5490-4a39-90ab-976131f92334_1730940658

This model is a fine-tuned version of unsloth/Llama-3.2-1B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6064

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
1.9521 0.0003 1 2.3526
2.1819 0.0028 10 2.1240
2.7934 0.0056 20 1.7092
1.6372 0.0085 30 1.6834
2.644 0.0113 40 1.6503
1.315 0.0141 50 1.6434
1.3254 0.0169 60 1.6338
1.3705 0.0198 70 1.6126
2.1504 0.0226 80 1.6024
1.8115 0.0254 90 1.6072
1.4758 0.0282 100 1.6011
1.756 0.0311 110 1.6046
1.4979 0.0339 120 1.6037
1.3798 0.0367 130 1.5969
1.4788 0.0395 140 1.6231
1.1614 0.0424 150 1.6199
1.3886 0.0452 160 1.6064

Framework versions

  • PEFT 0.13.2
  • Transformers 4.45.2
  • Pytorch 2.3.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.1