adapter: qlora
auto_resume_from_checkpoints: true
base_model: NousResearch/Yarn-Solar-10b-64k
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - e224932d8b45d574_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e224932d8b45d574_train_data.json
  type:
    field_input: context
    field_instruction: question-X
    field_output: answer-Y
    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: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: error577/a45b6164-dde4-47fb-90d0-d964f95f9eb4
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.3
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: 1500
micro_batch_size: 1
mlflow_experiment_name: /tmp/e224932d8b45d574_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 50
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
sequence_len: 512
special_tokens:
  pad_token: </s>
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: e530fa08-b3a6-41ec-bf7d-091271f6471f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e530fa08-b3a6-41ec-bf7d-091271f6471f
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

a45b6164-dde4-47fb-90d0-d964f95f9eb4

This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-64k on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.9855

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: 0.0003
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
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: 1500

Training results

Training Loss	Epoch	Step	Validation Loss
48.8289	0.0005	1	4.1194
36.7849	0.0239	50	1.8699
29.1492	0.0478	100	1.9692
33.2009	0.0717	150	1.9885
33.2941	0.0956	200	1.9855

Framework versions

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