See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Maykeye/TinyLLama-v0
bf16: false
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - c792edbe8c150e3a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c792edbe8c150e3a_train_data.json
  type:
    field_instruction: review
    field_output: hotel_name
    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: false
group_by_length: false
hub_model_id: lesso07/06703743-b448-4998-9385-0bc215f249b4
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: 70GiB
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/c792edbe8c150e3a_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: null
wandb_mode: online
wandb_name: 06703743-b448-4998-9385-0bc215f249b4
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 06703743-b448-4998-9385-0bc215f249b4
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

06703743-b448-4998-9385-0bc215f249b4

This model is a fine-tuned version of Maykeye/TinyLLama-v0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.4284

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
11.6536	0.0001	1	11.6205
11.211	0.0005	5	11.6085
11.4237	0.0009	10	11.4879
11.7681	0.0014	15	11.2687
11.2202	0.0018	20	11.0410
10.8986	0.0023	25	10.8392
10.6923	0.0027	30	10.6785
10.388	0.0032	35	10.5567
10.5503	0.0036	40	10.4781
10.3776	0.0041	45	10.4392
10.4492	0.0045	50	10.4284

Framework versions

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