See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: peft-internal-testing/tiny-dummy-qwen2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2565ffe651f90884_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2565ffe651f90884_train_data.json
  type:
    field_instruction: problem
    field_output: solution
    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/6f19134b-9185-4a66-a15c-4f930e612488
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/2565ffe651f90884_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: 3cd3bb3d-3a3e-49be-ba36-7bf371cc737e
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3cd3bb3d-3a3e-49be-ba36-7bf371cc737e
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

6f19134b-9185-4a66-a15c-4f930e612488

This model is a fine-tuned version of peft-internal-testing/tiny-dummy-qwen2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.9292

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	0.0029	1	11.9304
11.9308	0.0257	9	11.9303
11.9311	0.0514	18	11.9301
11.9303	0.0770	27	11.9300
11.9318	0.1027	36	11.9298
11.9321	0.1284	45	11.9296
11.9309	0.1541	54	11.9295
11.9288	0.1797	63	11.9294
11.9302	0.2054	72	11.9293
11.9304	0.2311	81	11.9293
11.9318	0.2568	90	11.9292
11.9309	0.2825	99	11.9292

Framework versions

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