Hugging Face's logo

vertings6
/
60987d4d-4c21-4430-9cee-ca268d2c1362

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
60987d4d-4c21-4430-9cee-ca268d2c1362 / README.md
vertings6's picture
vertings6
End of training
582ee67 verified
preview code
|
raw
history blame contribute delete
4.16 kB
metadata
library_name: peft
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 60987d4d-4c21-4430-9cee-ca268d2c1362
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - a84d6d236b5e1544_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/a84d6d236b5e1544_train_data.json
  type:
    field_input: ''
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: vertings6/60987d4d-4c21-4430-9cee-ca268d2c1362
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
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_memory:
  0: 79GiB
max_steps: 30
micro_batch_size: 4
mlflow_experiment_name: /tmp/a84d6d236b5e1544_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 1024
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: f64a5563-6776-4c7a-86c0-b07b3fcc4f06
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f64a5563-6776-4c7a-86c0-b07b3fcc4f06
warmup_steps: 5
weight_decay: 0.001
xformers_attention: true

60987d4d-4c21-4430-9cee-ca268d2c1362

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: 1.4155

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_TORCH 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: cosine
  • lr_scheduler_warmup_steps: 5
  • training_steps: 30

Training results

Training Loss Epoch Step Validation Loss
No log 0.0001 1 1.7336
1.4334 0.0004 5 1.5950
1.5183 0.0008 10 1.5017
1.4379 0.0013 15 1.4593
1.4376 0.0017 20 1.4310
1.4327 0.0021 25 1.4185
1.3517 0.0025 30 1.4155

Framework versions

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