Hugging Face's logo

kokovova
/
d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7 / README.md
kokovova's picture
kokovova
End of training
8f0488a verified
preview code
|
raw
history blame contribute delete
4.22 kB
metadata
library_name: peft
base_model: Korabbit/llama-2-ko-7b
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Korabbit/llama-2-ko-7b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1c2d230e0db4aaf5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1c2d230e0db4aaf5_train_data.json
  type:
    field_input: transcript
    field_instruction: text_description
    field_output: text
    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: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: kokovova/d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 76GiB
max_steps: 20
micro_batch_size: 2
mlflow_experiment_name: /tmp/1c2d230e0db4aaf5_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: 10
sequence_len: 2048
special_tokens:
  pad_token: </s>
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: d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7
warmup_steps: 10
weight_decay: 0.1
xformers_attention: true

d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7

This model is a fine-tuned version of Korabbit/llama-2-ko-7b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1537

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_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: 10
  • training_steps: 20

Training results

Training Loss Epoch Step Validation Loss
0.9264 0.0006 1 0.9885
0.8253 0.0012 2 0.9858
1.0454 0.0024 4 0.9375
0.8906 0.0036 6 0.7199
0.5989 0.0048 8 0.4512
0.4002 0.0060 10 0.3309
0.2537 0.0072 12 0.2452
0.2539 0.0083 14 0.2000
0.2893 0.0095 16 0.1798
0.0675 0.0107 18 0.1585
0.178 0.0119 20 0.1537

Framework versions

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