Hugging Face's logo

lesso11
/
21e6f667-1b4f-43b3-9117-44b455ed8d1b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
21e6f667-1b4f-43b3-9117-44b455ed8d1b / README.md
lesso11's picture
lesso11
End of training
1e2a5e4 verified
preview code
|
raw
history blame
4.35 kB
metadata
library_name: peft
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 21e6f667-1b4f-43b3-9117-44b455ed8d1b
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - e4907ed61d75280e_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e4907ed61d75280e_train_data.json
  type:
    field_input: evidence
    field_instruction: question
    field_output: SQL
    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: lesso11/21e6f667-1b4f-43b3-9117-44b455ed8d1b
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000211
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 128
lora_dropout: 0.05
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: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/G.O.D/e4907ed61d75280e_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: 110
sequence_len: 512
special_tokens:
  pad_token: <|eot_id|>
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: 44729f2d-08fe-4adb-b03b-065116691d72
wandb_project: 11a
wandb_run: your_name
wandb_runid: 44729f2d-08fe-4adb-b03b-065116691d72
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

21e6f667-1b4f-43b3-9117-44b455ed8d1b

This model is a fine-tuned version of Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2209

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: 0.000211
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 110
  • 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 0.0006 1 1.6972
0.6301 0.0307 50 0.7841
0.5207 0.0613 100 0.7849
0.4508 0.0920 150 0.5248
0.3927 0.1226 200 0.5356
0.3716 0.1533 250 0.3826
0.3506 0.1839 300 0.3516
0.326 0.2146 350 0.2691
0.2517 0.2452 400 0.2358
0.2535 0.2759 450 0.2240
0.3353 0.3066 500 0.2209

Framework versions

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