adapter: lora
base_model: NousResearch/Yarn-Solar-10b-32k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 8fb3d9b83047e053_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8fb3d9b83047e053_train_data.json
  type:
    field_instruction: question
    field_output: cypher
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: DeepDream2045/245e615d-30b2-47bd-b663-26afcd9423d4
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/8fb3d9b83047e053_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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
sequence_len: 1024
special_tokens:
  pad_token: </s>
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: offline
wandb_name: f884ce51-5d78-4646-aab1-f06f3e0a2018
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f884ce51-5d78-4646-aab1-f06f3e0a2018
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

245e615d-30b2-47bd-b663-26afcd9423d4

This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-32k on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1548

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: 0.0001
train_batch_size: 8
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
0.3233	0.0381	50	0.4412
0.33	0.0762	100	0.2992
0.2855	0.1143	150	0.1936
0.3255	0.1524	200	0.1548

Framework versions

PEFT 0.14.0
Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3