See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-random-GemmaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 5357759852985b4d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/5357759852985b4d_train_data.json
  type:
    field_input: Complex_CoT
    field_instruction: Question
    field_output: Response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
ddp_timeout: 1800
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: true
group_by_length: true
hub_model_id: leixa/cb23749c-41bd-433d-b1a2-5a43063165ff
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 10
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: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 1350
micro_batch_size: 4
mlflow_experiment_name: /tmp/5357759852985b4d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-08
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
relora_prune_ratio: 0.9
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 150
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: acopia-grant
wandb_mode: online
wandb_name: 4825c224-af5c-46aa-8cf7-640b49b5a593
wandb_project: Gradients-On-112
wandb_run: your_name
wandb_runid: 4825c224-af5c-46aa-8cf7-640b49b5a593
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

cb23749c-41bd-433d-b1a2-5a43063165ff

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

• Loss: 12.3842

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 50
• training_steps: 1350

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0007	1	12.4576
12.4467	0.1037	150	12.4457
12.4044	0.2073	300	12.4063
12.3992	0.3110	450	12.4015
12.3953	0.4147	600	12.3995
12.3932	0.5183	750	12.3981
12.3875	0.6220	900	12.3910
12.3829	0.7256	1050	12.3873
12.3854	0.8293	1200	12.3856
12.3777	0.9330	1350	12.3842

Framework versions

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