Hugging Face's logo

lesso03
/
328c1851-044d-4fb4-9045-a30ff40d2cda

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
328c1851-044d-4fb4-9045-a30ff40d2cda / README.md
lesso03's picture
lesso03
End of training
31bfa0e verified
preview code
|
raw
history blame contribute delete
4.32 kB
metadata
library_name: peft
license: apache-2.0
base_model: echarlaix/tiny-random-mistral
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 328c1851-044d-4fb4-9045-a30ff40d2cda
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: echarlaix/tiny-random-mistral
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 7be75e765b6d2ec2_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7be75e765b6d2ec2_train_data.json
  type:
    field_input: intent
    field_instruction: instruction
    field_output: response
    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: lesso03/328c1851-044d-4fb4-9045-a30ff40d2cda
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000203
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/7be75e765b6d2ec2_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: 30
sequence_len: 512
special_tokens:
  pad_token: </s>
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: 244e1727-7637-4e33-9f83-39dfefe631b6
wandb_project: 03a
wandb_run: your_name
wandb_runid: 244e1727-7637-4e33-9f83-39dfefe631b6
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

328c1851-044d-4fb4-9045-a30ff40d2cda

This model is a fine-tuned version of echarlaix/tiny-random-mistral on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 10.3014

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: 0.000203
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 30
  • 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 0.0000 1 10.3786
20.7365 0.0014 50 10.3626
20.6138 0.0028 100 10.3084
20.6024 0.0042 150 10.3063
20.6026 0.0056 200 10.3051
20.5976 0.0070 250 10.3033
20.581 0.0084 300 10.3023
20.5916 0.0098 350 10.3018
20.5852 0.0112 400 10.3015
20.5984 0.0126 450 10.3015
20.5889 0.0140 500 10.3014

Framework versions

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