You can deploy this model and start earning money today!

sn56/
850afb75-70f4-45ff-b164-f637c5381fbe

Name: 850afb75-70f4-45ff-b164-f637c5381fbe
Availability: InStock

generated_from_trainer

peft-internal-testing/tiny-dummy-qwen2

adapter

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: peft-internal-testing/tiny-dummy-qwen2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2a7b266cd8acd573_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2a7b266cd8acd573_train_data.json
  type:
    field_input: rewritten_intent
    field_instruction: intent
    field_output: snippet
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56/850afb75-70f4-45ff-b164-f637c5381fbe
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 8
mlflow_experiment_name: /tmp/2a7b266cd8acd573_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
seed: 3061630371
sequence_len: 1024
shuffle: true
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: true
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: null
wandb_project: god
wandb_run: lxg5
wandb_runid: null
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

850afb75-70f4-45ff-b164-f637c5381fbe

This model is a fine-tuned version of peft-internal-testing/tiny-dummy-qwen2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 11.9295

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 3061630371
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_BNB 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: 60

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.05	1	11.9326
11.931	0.25	5	11.9326
11.9296	0.5	10	11.9324
11.9299	0.75	15	11.9321
11.9302	1.0	20	11.9318
11.9298	1.25	25	11.9314
11.9287	1.5	30	11.9310
11.9283	1.75	35	11.9305
11.9302	2.0	40	11.9302
11.9274	2.25	45	11.9298
11.9278	2.5	50	11.9296
11.9293	2.75	55	11.9296
11.9267	3.0	60	11.9295

Framework versions

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