Hugging Face's logo

Romain-XV
/
e1295422-33d1-418d-8db4-e49a26e847f4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e1295422-33d1-418d-8db4-e49a26e847f4 / README.md
Romain-XV's picture
Romain-XV
End of training
7b81c2b verified
preview code
|
raw
history blame contribute delete
4.04 kB
metadata
library_name: peft
license: apache-2.0
base_model: TinyLlama/TinyLlama_v1.1
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: e1295422-33d1-418d-8db4-e49a26e847f4
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: TinyLlama/TinyLlama_v1.1
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 34542386cf9ff6e7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/34542386cf9ff6e7_train_data.json
  type:
    field_instruction: prompt
    field_output: chosen
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Romain-XV/e1295422-33d1-418d-8db4-e49a26e847f4
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.3
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: 1440
micro_batch_size: 4
mlflow_experiment_name: /tmp/34542386cf9ff6e7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 100
sequence_len: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
use_rslora: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 52987ac5-8a92-4496-9508-29834e828667
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 52987ac5-8a92-4496-9508-29834e828667
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

e1295422-33d1-418d-8db4-e49a26e847f4

This model is a fine-tuned version of TinyLlama/TinyLlama_v1.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3796

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: 8
  • 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: 626

Training results

Training Loss Epoch Step Validation Loss
3.3969 0.0032 1 3.1280
1.5127 0.3197 100 1.5581
1.4175 0.6395 200 1.4744
1.4373 0.9592 300 1.4215
1.4912 1.2790 400 1.4003
1.3954 1.5987 500 1.3844
1.3309 1.9185 600 1.3796

Framework versions

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