See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 087d599e672c4327_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/087d599e672c4327_train_data.json
  type:
    field_instruction: text
    field_output: target
    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: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: leixa/b5e3b30f-8c85-40e4-a77c-348caf2796b1
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: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 8
mlflow_experiment_name: /tmp/087d599e672c4327_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: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: b5e3b30f-8c85-40e4-a77c-348caf2796b1
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b5e3b30f-8c85-40e4-a77c-348caf2796b1
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

b5e3b30f-8c85-40e4-a77c-348caf2796b1

This model is a fine-tuned version of HuggingFaceH4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.1692

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: 249

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0121	1	10.3879
10.3796	0.2538	21	10.3731
10.3365	0.5076	42	10.3385
10.3116	0.7613	63	10.3101
11.7642	1.0181	84	10.2648
10.2853	1.2719	105	10.2290
10.3627	1.5257	126	10.2053
10.2634	1.7795	147	10.1889
10.1856	2.0363	168	10.1790
10.1798	2.2900	189	10.1730
10.178	2.5438	210	10.1701
10.1815	2.7976	231	10.1692

Framework versions

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