You can deploy this model and start earning money today!

mamung/
cd3941b2-a0f6-4e25-8879-fab8c706722e

Name: cd3941b2-a0f6-4e25-8879-fab8c706722e
Availability: InStock

generated_from_trainer

custom_code

NousResearch/Yarn-Llama-2-13b-64k

adapter

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: NousResearch/Yarn-Llama-2-13b-64k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cf90cb0f5b731459_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/cf90cb0f5b731459_train_data.json
  type:
    field_input: all_generated_responses
    field_instruction: prompt
    field_output: prompt_id
    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: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: mamung/cd3941b2-a0f6-4e25-8879-fab8c706722e
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.00015
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 5
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
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_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/cf90cb0f5b731459_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 2.0e-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: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: eddysang
wandb_mode: online
wandb_name: b4af4ed4-752f-42f5-962a-20a8188b7265
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b4af4ed4-752f-42f5-962a-20a8188b7265
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

cd3941b2-a0f6-4e25-8879-fab8c706722e

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: 3.0082

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: 0.00015
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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=2e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	3.6039
14.3332	0.0051	9	3.2921
12.6275	0.0102	18	3.1451
12.2373	0.0154	27	3.0337
12.1554	0.0205	36	3.0176
12.1096	0.0256	45	3.0244
12.1179	0.0307	54	3.0137
12.0188	0.0358	63	3.0160
12.0055	0.0409	72	3.0124
12.0456	0.0461	81	3.0105
12.0674	0.0512	90	3.0080
12.0761	0.0563	99	3.0082

Framework versions

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