Hugging Face's logo

auxyus
/
59ab009f-b3fb-4ead-b672-26020e6a03ed

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
59ab009f-b3fb-4ead-b672-26020e6a03ed / README.md
auxyus's picture
auxyus
End of training
51990fe verified
preview code
|
raw
history blame contribute delete
4.3 kB
metadata
library_name: peft
license: apache-2.0
base_model: NousResearch/Yarn-Solar-10b-64k
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 59ab009f-b3fb-4ead-b672-26020e6a03ed
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Solar-10b-64k
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2c60d1a3849a4622_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2c60d1a3849a4622_train_data.json
  type:
    field_instruction: context
    field_output: level_2
    format: '{instruction}'
    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: auxyus/59ab009f-b3fb-4ead-b672-26020e6a03ed
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
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_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/2c60d1a3849a4622_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
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: techspear-hub
wandb_mode: online
wandb_name: 2a6a97c4-432a-41ab-9b20-a8b3df6d9a1e
wandb_project: Gradients-On-Two
wandb_run: your_name
wandb_runid: 2a6a97c4-432a-41ab-9b20-a8b3df6d9a1e
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

59ab009f-b3fb-4ead-b672-26020e6a03ed

This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-64k on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4800

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: 0.0001
  • 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 0.0004 1 1.3354
4.104 0.0034 9 0.9019
2.6246 0.0068 18 0.6228
2.0675 0.0102 27 0.5624
2.0244 0.0136 36 0.5298
2.0372 0.0171 45 0.5147
1.9989 0.0205 54 0.5036
1.864 0.0239 63 0.4941
1.6868 0.0273 72 0.4859
1.9805 0.0307 81 0.4824
1.9752 0.0341 90 0.4805
1.9794 0.0375 99 0.4800

Framework versions

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