See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Llama-2-7b-128k
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 71c2b1c590a6b73c_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/71c2b1c590a6b73c_train_data.json
  type:
    field_instruction: prompt
    field_output: response-suggestion
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config:
  max_steps: 50
  weight_decay: 0.01
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: tarabukinivan/40d8bef6-9de2-42a6-a844-99a8ab1c3dfe
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 10
micro_batch_size: 2
mlflow_experiment_name: /tmp/71c2b1c590a6b73c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 40d8bef6-9de2-42a6-a844-99a8ab1c3dfe
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 40d8bef6-9de2-42a6-a844-99a8ab1c3dfe
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

40d8bef6-9de2-42a6-a844-99a8ab1c3dfe

This model is a fine-tuned version of NousResearch/Yarn-Llama-2-7b-128k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8710

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
3.3084	0.0028	1	0.9298
3.7996	0.0055	2	0.9299
3.847	0.0083	3	0.9285
3.777	0.0111	4	0.9258
3.934	0.0139	5	0.9222
2.815	0.0166	6	0.9167
3.9234	0.0194	7	0.9078
3.9952	0.0222	8	0.8971
3.596	0.0249	9	0.8856
4.2805	0.0277	10	0.8710

Framework versions

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