See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Llama-2-13b-64k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - ce3bdc168ad52814_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/ce3bdc168ad52814_train_data.json
  type:
    field_instruction: source
    field_output: target
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: mamung/9cb62fc7-0ac3-42e5-bc0b-90f53e4fd44d
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: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/ce3bdc168ad52814_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
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: eddysang
wandb_mode: online
wandb_name: de94f85f-b3ef-454b-946d-36a0048fcce8
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: de94f85f-b3ef-454b-946d-36a0048fcce8
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

9cb62fc7-0ac3-42e5-bc0b-90f53e4fd44d

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: 1.4141

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: 32
• total_train_batch_size: 64
• 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-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 24

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.1270	1	2.0506
No log	0.2540	2	2.0502
72.85	0.5079	4	2.0330
70.0527	0.7619	6	1.9663
70.0527	1.0357	8	1.8222
65.8492	1.2897	10	1.7053
59.236	1.5437	12	1.6379
59.236	1.7976	14	1.5586
53.3035	2.0714	16	1.4871
50.0182	2.3254	18	1.4484
50.0182	2.5794	20	1.4445
45.2756	2.8333	22	1.4258
43.3774	3.1071	24	1.4141

Framework versions

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