adapter: lora
base_model: bigscience/bloomz-560m
bf16: true
chat_template: llama3
dataloader_num_workers: 0
dataloader_pin_memory: false
dataset_info: 8b1fc91e-7ccc-43a1-90dd-3576e16ab144
dataset_prepared_path: null
datasets:
- data_files:
  - 68b8ac40055058fb_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_input: input
    field_instruction: instruct
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
ddp_broadcast_buffers: false
ddp_bucket_cap_mb: 25
ddp_timeout: 7200
debug: null
deepspeed: null
evaluation_strategy: 'no'
flash_attention: false
flash_attn_cross_entropy: false
flash_attn_rms_norm: false
fp16: false
fsdp: null
fsdp_config: null
gpu_memory_limit: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
group_by_length: false
hub_model_commit_message: Training checkpoint - step {current_step}
hub_model_id: dada22231/9520e68d-45c4-4d41-be88-742e7e101bf8
hub_model_revision: main
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 256
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_modules_to_save:
- embed_tokens
- lm_head
lora_r: 128
lora_target_linear: true
lr_scheduler: constant_with_warmup
max_memory: null
max_steps: 1500
micro_batch_size: 8
mlflow_experiment_name: /tmp/68b8ac40055058fb_train_data.json
model_type: AutoModelForCausalLM
optimizer: adamw_torch_fused
output_dir: ./outputs
pad_to_sequence_len: true
push_dataset_card: false
push_to_hub: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: true
save_lora_adapter: false
save_merged_lora_model: true
save_only_model: true
save_safetensors: true
save_steps: 75
save_strategy: steps
save_total_limit: 5
sequence_len: 4096
special_tokens: null
strict: false
tf32: true
tokenizer_type: AutoTokenizer
torch_compile: false
torch_compile_backend: inductor
train_on_inputs: false
trust_remote_code: true
val_set_size: 0
wandb_entity: null
wandb_mode: online
wandb_name: 8b1fc91e-7ccc-43a1-90dd-3576e16ab144
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 8b1fc91e-7ccc-43a1-90dd-3576e16ab144
warmup_steps: 150
weight_decay: 0.01
xformers_attention: null

9520e68d-45c4-4d41-be88-742e7e101bf8

This model is a fine-tuned version of bigscience/bloomz-560m on an unknown dataset.

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 150
training_steps: 1500

Training results

Framework versions

PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.7.1+cu128
Datasets 3.6.0
Tokenizers 0.21.1