alicegoesdown/79535aea-f15b-45ba-964a-88d60ff18985

See axolotl config

axolotl version: 0.4.1

adapter: lora
bf16: auto
chat_template: llama3
dataset_prepared_path: null
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
gradient_clipping: 0.1
group_by_length: false
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5.0e-07
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: linear
max_steps: 200
micro_batch_size: 128
mlflow_experiment_name: /tmp/aed51b8e2c089967_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
saves_per_epoch: 1
sequence_len: 4096
special_tokens:
  pad_token: </PAD>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.25
wandb_entity: null
wandb_mode: online
wandb_name: 6a8f76dd-7262-490a-905c-7b83c0f56891
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 6a8f76dd-7262-490a-905c-7b83c0f56891
warmup_steps: 5
weight_decay: 0.1
xformers_attention: true

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-07
• train_batch_size: 128
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• 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: 5
• training_steps: 200

Framework versions

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