See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: katuni4ka/tiny-random-qwen1.5-moe
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - a5ffd4a12886ce24_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/a5ffd4a12886ce24_train_data.json
  type:
    field_input: thinking
    field_instruction: prompt
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: true
hub_model_id: lesso01/4a1a8aee-716b-4928-a5f0-b5bc65f7f0c1
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000201
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
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_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/a5ffd4a12886ce24_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 50
saves_per_epoch: null
seed: 10
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: f66709ae-7dde-4697-98bf-305cdca7fc8a
wandb_project: 01a
wandb_run: your_name
wandb_runid: f66709ae-7dde-4697-98bf-305cdca7fc8a
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

4a1a8aee-716b-4928-a5f0-b5bc65f7f0c1

This model is a fine-tuned version of katuni4ka/tiny-random-qwen1.5-moe on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.8484

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: 0.000201
• train_batch_size: 4
• eval_batch_size: 4
• seed: 10
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0005	1	11.9408
11.9242	0.0269	50	11.9172
11.8615	0.0538	100	11.8722
11.8503	0.0807	150	11.8583
11.8433	0.1076	200	11.8548
11.8428	0.1344	250	11.8525
11.8378	0.1613	300	11.8506
11.8462	0.1882	350	11.8490
11.8346	0.2151	400	11.8487
11.8375	0.2420	450	11.8483
11.8383	0.2689	500	11.8484

Framework versions

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