Hugging Face's logo

VERSIL91
/
f90426c4-9feb-46bd-9d44-6f44764f060d

PEFT
Safetensors
falcon
axolotl
Generated from Trainer
Model card Files Community
f90426c4-9feb-46bd-9d44-6f44764f060d / README.md
VERSIL91's picture
VERSIL91
End of training
c24796e verified
preview code
|
raw
history blame contribute delete
4.11 kB
metadata
library_name: peft
base_model: katuni4ka/tiny-random-falcon-40b
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: f90426c4-9feb-46bd-9d44-6f44764f060d
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

accelerate_config:
  dynamo_backend: inductor
  mixed_precision: fp16
  num_machines: 1
  num_processes: auto
  use_cpu: false
adapter: lora
base_model: katuni4ka/tiny-random-falcon-40b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 33eb588516be126a_train_data.json
  ds_type: json
  field: content
  path: /workspace/input_data/33eb588516be126a_train_data.json
  type: completion
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: false
hub_model_id: VERSIL91/f90426c4-9feb-46bd-9d44-6f44764f060d
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_memory:
  0: 70GiB
  1: 70GiB
  2: 70GiB
  3: 70GiB
  4: 70GiB
  5: 70GiB
  6: 70GiB
  7: 70GiB
max_steps: 20
micro_batch_size: 1
mlflow_experiment_name: /tmp/33eb588516be126a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
quantization_config:
  llm_int8_enable_fp32_cpu_offload: true
  load_in_8bit: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 4056
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: true
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: f90426c4-9feb-46bd-9d44-6f44764f060d
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f90426c4-9feb-46bd-9d44-6f44764f060d
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

f90426c4-9feb-46bd-9d44-6f44764f060d

This model is a fine-tuned version of katuni4ka/tiny-random-falcon-40b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 11.0496

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • total_eval_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: 10
  • training_steps: 15

Training results

Training Loss Epoch Step Validation Loss
177.4688 0.0696 1 11.0825
177.3516 0.2783 4 11.0793
177.1875 0.5565 8 11.0689
176.9453 0.8348 12 11.0496

Framework versions

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