See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: TinyLlama/TinyLlama_v1.1
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 9c68b8852acf0a5d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/9c68b8852acf0a5d_train_data.json
  type:
    field_input: search_results
    field_instruction: question
    field_output: entity_pages
    format: '{instruction} {input}'
    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: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56m1/54d5788c-3298-475b-b699-7fb4fb2f6d0e
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
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_memory:
  0: 77GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/9c68b8852acf0a5d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
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: sn56-miner
wandb_mode: disabled
wandb_name: 54d5788c-3298-475b-b699-7fb4fb2f6d0e
wandb_project: god
wandb_run: 13qc
wandb_runid: 54d5788c-3298-475b-b699-7fb4fb2f6d0e
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

54d5788c-3298-475b-b699-7fb4fb2f6d0e

This model is a fine-tuned version of TinyLlama/TinyLlama_v1.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001

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
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH 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
5.5327	0.0004	1	5.4303
2.2586	0.0035	9	1.8565
0.1298	0.0070	18	0.0813
0.0043	0.0105	27	0.0034
0.0003	0.0140	36	0.0003
0.0001	0.0175	45	0.0001
0.0001	0.0210	54	0.0001
0.0001	0.0245	63	0.0001
0.0001	0.0280	72	0.0001
0.0001	0.0315	81	0.0001
0.0001	0.0350	90	0.0001
0.0001	0.0385	99	0.0001

Framework versions

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