Hugging Face's logo

kk-aivio
/
5e7e2c0e-8aac-4b5e-ab80-3f839aacd4f2

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
5e7e2c0e-8aac-4b5e-ab80-3f839aacd4f2 / README.md
kk-aivio's picture
kk-aivio
End of training
66536c0 verified
preview code
|
raw
history blame
4.37 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/mistral-7b-v0.2
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 5e7e2c0e-8aac-4b5e-ab80-3f839aacd4f2
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/mistral-7b-v0.2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f197bd44e7fa6f6b_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f197bd44e7fa6f6b_train_data.json
  type:
    field_instruction: en_US
    field_output: de_DE
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: kk-aivio/5e7e2c0e-8aac-4b5e-ab80-3f839aacd4f2
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 7093
micro_batch_size: 4
mlflow_experiment_name: /tmp/f197bd44e7fa6f6b_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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: 150
saves_per_epoch: null
sequence_len: 512
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: b7a36e78-afef-45bc-9ca4-3c3e30d103d5
wandb_project: SN56-11
wandb_run: your_name
wandb_runid: b7a36e78-afef-45bc-9ca4-3c3e30d103d5
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

5e7e2c0e-8aac-4b5e-ab80-3f839aacd4f2

This model is a fine-tuned version of unsloth/mistral-7b-v0.2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9910

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: 4
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 50
  • training_steps: 7093

Training results

Training Loss Epoch Step Validation Loss
No log 0.0011 1 2.4869
4.1608 0.1628 150 1.2086
4.0351 0.3256 300 1.1388
3.9054 0.4883 450 1.1612
3.793 0.6511 600 1.1402
3.7102 0.8139 750 1.0409
3.6446 0.9767 900 1.1195
2.6203 1.1394 1050 0.9639
2.7976 1.3022 1200 0.9496
2.9429 1.4650 1350 0.9774
2.9373 1.6278 1500 0.9679
3.0521 1.7906 1650 0.9910

Framework versions

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