See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/gemma-2-2b-it
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 868fde04833ea01a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/868fde04833ea01a_train_data.json
  type:
    field_instruction: query
    field_output: ori_review
    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: sn56b2/2327c3cb-8a20-4add-8f38-5c9959fe4d1a
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/868fde04833ea01a_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
seed: 1382632242
sequence_len: 1024
shuffle: true
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: true
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: null
wandb_project: god
wandb_run: jj40
wandb_runid: null
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

2327c3cb-8a20-4add-8f38-5c9959fe4d1a

This model is a fine-tuned version of unsloth/gemma-2-2b-it on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9935

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: 1382632242
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_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	0.0064	1	2.9625
2.6523	0.0576	9	2.4110
2.2509	0.1152	18	2.1677
2.1129	0.1728	27	2.0721
2.0687	0.2304	36	2.0363
2.0631	0.288	45	2.0197
2.011	0.3456	54	2.0081
2.0663	0.4032	63	2.0011
2.026	0.4608	72	1.9973
2.0234	0.5184	81	1.9946
1.998	0.576	90	1.9935
1.9926	0.6336	99	1.9935

Framework versions

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