adapter: qlora
auto_resume_from_checkpoints: true
base_model: NousResearch/Yarn-Llama-2-13b-64k
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - 4a23fa968cd83e6d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/4a23fa968cd83e6d_train_data.json
  type:
    field_input: context
    field_instruction: instruction
    field_output: response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 100
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: error577/f8c0b1ac-e22f-453b-a9de-55b1d061ecf5
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 128
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_grad_norm: 1.0
max_steps: null
micro_batch_size: 1
mlflow_experiment_name: /tmp/4a23fa968cd83e6d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_4bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 256
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.005
wandb_entity: null
wandb_mode: online
wandb_name: b0f51ff1-f5b7-4063-a58c-292276a1df84
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b0f51ff1-f5b7-4063-a58c-292276a1df84
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

f8c0b1ac-e22f-453b-a9de-55b1d061ecf5

This model is a fine-tuned version of NousResearch/Yarn-Llama-2-13b-64k on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1454

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_4BIT 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: 30
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	1.3424
5.4045	0.0139	100	1.1391
6.0195	0.0277	200	1.1402
5.4938	0.0416	300	1.1124
5.5688	0.0554	400	1.1158
4.9104	0.0693	500	1.1073
5.9828	0.0831	600	1.1404
4.3952	0.0970	700	1.1078
5.7456	0.1108	800	1.1454

Framework versions

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