adapter: lora
base_model: NousResearch/Yarn-Solar-10b-32k
bf16: auto
dataset_prepared_path: null
datasets:
- data_files:
  - 65d9e80afe69aff1_train_data.json
  ds_type: json
  format: custom
  path: /root/G.O.D-test/core/data/65d9e80afe69aff1_train_data.json
  type:
    field_input: documents
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
eval_max_new_tokens: 128
eval_steps: 0
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 6
gradient_checkpointing: false
group_by_length: false
hub_model_id: souging/2a201699-8567-4cd4-ae99-f620dd547f24
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000202
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 1
mlflow_experiment_name: /tmp/65d9e80afe69aff1_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: false
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 0
saves_per_epoch: null
sequence_len: 1920
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
wandb_entity: null
wandb_mode: online
wandb_name: a1a050a4-6a01-49dd-9cd7-289119b180f3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: a1a050a4-6a01-49dd-9cd7-289119b180f3
warmup_steps: 100
weight_decay: 0.01
xformers_attention: null

2a201699-8567-4cd4-ae99-f620dd547f24

This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-32k on the None 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: 0.000202
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 6
total_train_batch_size: 48
total_eval_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: 100
training_steps: 500

Training results

Framework versions

PEFT 0.13.2
Transformers 4.46.0
Pytorch 2.5.0+cu124
Datasets 3.0.1
Tokenizers 0.20.3