See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Qwen2-1.5B-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 5753f3c5acde918d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/5753f3c5acde918d_train_data.json
  type:
    field_input: schema
    field_instruction: question
    field_output: cypher
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/cb5b55b0-f6fa-4a32-8d4a-02fb26201718
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 2520
micro_batch_size: 4
mlflow_experiment_name: /tmp/5753f3c5acde918d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.04
wandb_entity: null
wandb_mode: online
wandb_name: 1dbeaf97-afde-4a0c-afd3-dfbf2c7987f0
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1dbeaf97-afde-4a0c-afd3-dfbf2c7987f0
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

cb5b55b0-f6fa-4a32-8d4a-02fb26201718

This model is a fine-tuned version of unsloth/Qwen2-1.5B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1059

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• 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: 2520

Training results

Training Loss	Epoch	Step	Validation Loss
1.6969	0.0008	1	1.6098
0.4332	0.0761	100	0.2090
0.1992	0.1523	200	0.1816
0.1562	0.2284	300	0.1728
0.1789	0.3045	400	0.1590
0.1462	0.3806	500	0.1553
0.1774	0.4568	600	0.1499
0.1231	0.5329	700	0.1417
0.1018	0.6090	800	0.1428
0.1009	0.6851	900	0.1363
0.1109	0.7613	1000	0.1336
0.0817	0.8374	1100	0.1286
0.1356	0.9135	1200	0.1236
0.1017	0.9896	1300	0.1218
0.0497	1.0659	1400	0.1205
0.0685	1.1421	1500	0.1170
0.0673	1.2182	1600	0.1144
0.0937	1.2943	1700	0.1126
0.0473	1.3704	1800	0.1117
0.0866	1.4466	1900	0.1106
0.0867	1.5227	2000	0.1086
0.0936	1.5988	2100	0.1084
0.0609	1.6749	2200	0.1071
0.0852	1.7511	2300	0.1062
0.0563	1.8272	2400	0.1060
0.107	1.9033	2500	0.1059

Framework versions

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