You can deploy this model and start earning money today!

mamung/
7ce3d22d-df99-4892-a631-2e477a73226b

Name: 7ce3d22d-df99-4892-a631-2e477a73226b
Availability: InStock

generated_from_trainer

custom_code

NousResearch/Yarn-Llama-2-7b-64k

adapter

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: NousResearch/Yarn-Llama-2-7b-64k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f1e15533c6ee6483_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f1e15533c6ee6483_train_data.json
  type:
    field_input: situation_json
    field_instruction: request
    field_output: response
    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: mamung/7ce3d22d-df99-4892-a631-2e477a73226b
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: 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/f1e15533c6ee6483_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: 70604e57-ea0f-482d-8b68-f5336baa92cb
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 70604e57-ea0f-482d-8b68-f5336baa92cb
warmup_steps: 20
weight_decay: 0.01
xformers_attention: false

7ce3d22d-df99-4892-a631-2e477a73226b

This model is a fine-tuned version of NousResearch/Yarn-Llama-2-7b-64k on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9310

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: 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0205	1	1.5634
44.2059	0.1847	9	1.2084
34.4429	0.3695	18	1.0298
32.1806	0.5542	27	0.9721
31.5782	0.7389	36	0.9546
30.8712	0.9237	45	0.9401
30.4898	1.1142	54	0.9376
26.7144	1.2989	63	0.9387
28.7992	1.4836	72	0.9332
28.6384	1.6684	81	0.9315
26.8185	1.8531	90	0.9312
27.5144	2.0436	99	0.9310

Framework versions

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