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:
  - fdd6181bd48eebb0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/fdd6181bd48eebb0_train_data.json
  type:
    field_instruction: Question
    field_output: Answers
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: leixa/253e5da3-67e8-4a03-bcf6-3a989947b827
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: 3
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_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/fdd6181bd48eebb0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 3ce43b7c-a05f-4c96-a0ad-4322c88107a2
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3ce43b7c-a05f-4c96-a0ad-4322c88107a2
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

253e5da3-67e8-4a03-bcf6-3a989947b827

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: 12.4497

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0011	1	12.4516
12.452	0.0101	9	12.4515
12.4495	0.0202	18	12.4513
12.4446	0.0304	27	12.4511
12.4518	0.0405	36	12.4509
12.4482	0.0506	45	12.4506
12.4545	0.0607	54	12.4503
12.4512	0.0708	63	12.4501
12.4473	0.0810	72	12.4499
12.4494	0.0911	81	12.4498
12.448	0.1012	90	12.4497
12.4518	0.1113	99	12.4497

Framework versions

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