adapter: lora
base_model: NousResearch/Yarn-Mistral-7b-128k
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 4ce7fe5624cfa15f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/4ce7fe5624cfa15f_train_data.json
  type:
    field_input: scenario
    field_instruction: detailed_dilemma
    field_output: response_string
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: false
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: infogeo/c52aef5b-e8e5-4af4-b6e7-9b623ff9403c
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 79GiB
max_steps: 30
micro_batch_size: 4
mlflow_experiment_name: /tmp/4ce7fe5624cfa15f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 88e7358e-af39-4bf3-a98d-27331c772103
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 88e7358e-af39-4bf3-a98d-27331c772103
warmup_steps: 5
weight_decay: 0.001
xformers_attention: true

c52aef5b-e8e5-4af4-b6e7-9b623ff9403c

This model is a fine-tuned version of NousResearch/Yarn-Mistral-7b-128k on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9286

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 5
training_steps: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0044	1	1.2572
4.8761	0.0221	5	1.1598
4.0401	0.0443	10	1.0539
3.7532	0.0664	15	0.9952
3.7029	0.0886	20	0.9551
3.6511	0.1107	25	0.9333
3.6428	0.1329	30	0.9286

Framework versions

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