See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Llama-2-7b-128k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 62850aee15c39860_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/62850aee15c39860_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    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: tryingpro/1eb5439f-8cd3-4f7a-94b9-abcd11123a56
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
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 90
micro_batch_size: 2
mlflow_experiment_name: /tmp/62850aee15c39860_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: tryingpro-unicourt
wandb_mode: online
wandb_name: d6d48812-926a-4af7-a9a9-fcf438e7f6df
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d6d48812-926a-4af7-a9a9-fcf438e7f6df
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

1eb5439f-8cd3-4f7a-94b9-abcd11123a56

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: 0.7598

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: 90

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0020	1	1.3284
43.3345	0.0162	8	1.1918
35.4878	0.0325	16	0.9614
29.5876	0.0487	24	0.8608
25.3693	0.0649	32	0.8221
27.2901	0.0811	40	0.8000
25.6231	0.0974	48	0.7859
24.7209	0.1136	56	0.7749
22.6814	0.1298	64	0.7678
22.8434	0.1460	72	0.7634
27.5242	0.1623	80	0.7606
24.803	0.1785	88	0.7598

Framework versions

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