adapter: qlora
base_model: katuni4ka/tiny-random-qwen1.5-moe
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 24f2917b1e8719ab_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/24f2917b1e8719ab_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    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: 1
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 64
gradient_checkpointing: true
mmax_grad_norm: 1.0
group_by_length: false
hub_model_id: error577/02001972-ac38-42ec-9a07-fb362ee48010
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5e-4
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 200
micro_batch_size: 2
mlflow_experiment_name: /tmp/24f2917b1e8719ab_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: 1
dataloader_num_workers: 6
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.02
wandb_entity: null
wandb_mode: online
wandb_name: 4ebbaf02-604e-44d5-970d-bbaeba7dd647
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4ebbaf02-604e-44d5-970d-bbaeba7dd647
warmup_steps: 10
weight_decay: 1e-5
xformers_attention: null

02001972-ac38-42ec-9a07-fb362ee48010

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: 11.8350

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: 0.0005
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 64
total_train_batch_size: 128
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: 200

Training results

Training Loss	Epoch	Step	Validation Loss
11.9347	0.0008	1	11.9336
11.8583	0.0517	67	11.8427
11.8448	0.1035	134	11.8350

Framework versions

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