Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-llama-fast-tokenizer
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 4
dataset_prepared_path: null
datasets:
- data_files:
  - b91f9e23a399766c_train_data.json
  ds_type: json
  format: custom
  num_proc: 4
  path: /workspace/input_data/b91f9e23a399766c_train_data.json
  streaming: true
  type:
    field_input: tweet
    field_instruction: conspiracy_theory
    field_output: label
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: balanced
do_eval: true
early_stopping_patience: 1
eval_batch_size: 1
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: dsakerkwq/e4b336e7-ad81-4eb7-b0b2-f60c4faf1a31
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
  1: 75GB
  2: 75GB
  3: 75GB
max_steps: 50
micro_batch_size: 2
mixed_precision: bf16
mlflow_experiment_name: /tmp/b91f9e23a399766c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
save_strategy: steps
sequence_len: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: e4b336e7-ad81-4eb7-b0b2-f60c4faf1a31
wandb_project: Public_TuningSN
wandb_runid: e4b336e7-ad81-4eb7-b0b2-f60c4faf1a31
warmup_ratio: 0.04
weight_decay: 0.01
xformers_attention: null

e4b336e7-ad81-4eb7-b0b2-f60c4faf1a31

This model is a fine-tuned version of fxmarty/tiny-llama-fast-tokenizer on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 10.3025

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: 2
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • total_eval_batch_size: 4
  • 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: 2
  • training_steps: 50

Training results

Training Loss Epoch Step Validation Loss
10.3777 0.0205 1 10.3610
10.3471 0.5128 25 10.3234
10.1867 1.0256 50 10.3025

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
11
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for 1-lock/e4b336e7-ad81-4eb7-b0b2-f60c4faf1a31

Adapter
(289)
this model