See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: llamafactory/tiny-random-Llama-3
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 212cea8e8d3699da_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/212cea8e8d3699da_train_data.json
  type:
    field_input: doc
    field_instruction: original_text
    field_output: edited_summary
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: eddysang/cbcb9ea7-77b5-40fd-baaf-f3a66d36d225
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.00015
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/212cea8e8d3699da_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
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: 2048
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: yaudayah0
wandb_mode: online
wandb_name: b1daaa76-ce91-488a-8876-44fa4641b938
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b1daaa76-ce91-488a-8876-44fa4641b938
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

cbcb9ea7-77b5-40fd-baaf-f3a66d36d225

This model is a fine-tuned version of llamafactory/tiny-random-Llama-3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.7350

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: 0.00015
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0167	1	11.7636
11.7637	0.1501	9	11.7632
11.7614	0.3002	18	11.7618
11.7598	0.4502	27	11.7591
11.7557	0.6003	36	11.7550
11.75	0.7504	45	11.7490
11.7445	0.9005	54	11.7427
11.7571	1.0511	63	11.7384
11.7745	1.2011	72	11.7363
11.8078	1.3512	81	11.7354
11.6771	1.5013	90	11.7350
11.6701	1.6514	99	11.7350

Framework versions

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