See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-llama-fast-tokenizer
bf16: auto
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - d3349562b563ed08_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/d3349562b563ed08_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 8
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: nttx/4c61c612-f68a-4a61-b1db-226144634c97
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: false
load_in_8bit: false
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
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GB
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/d3349562b563ed08_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 50
saves_per_epoch: null
sequence_len: 1028
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: 4c61c612-f68a-4a61-b1db-226144634c97
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4c61c612-f68a-4a61-b1db-226144634c97
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

4c61c612-f68a-4a61-b1db-226144634c97

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: 10.3404

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 10
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
10.3783	0.0000	1	10.3763
10.371	0.0010	25	10.3679
10.3495	0.0020	50	10.3477
10.3448	0.0030	75	10.3447
10.3486	0.0040	100	10.3428
10.3425	0.0050	125	10.3412
10.3466	0.0060	150	10.3407
10.3417	0.0070	175	10.3402
10.346	0.0080	200	10.3404

Framework versions

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