You can deploy this model and start earning money today!

ivangrapher/
316bae3e-a17f-4aec-a192-e286202ca352

generated_from_trainer

peft-internal-testing/tiny-dummy-qwen2

adapter

4-bit

bitsandbytes

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:
  - c97ac490508cd842_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c97ac490508cd842_train_data.json
  type:
    field_input: cot
    field_instruction: query
    field_output: response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 256
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: ivangrapher/316bae3e-a17f-4aec-a192-e286202ca352
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 75GiB
max_steps: 40
micro_batch_size: 4
mlflow_experiment_name: /tmp/c97ac490508cd842_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 20
sequence_len: 1024
strict: true
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: d3fbaf7f-09ff-402e-b347-2eff8a768f9c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d3fbaf7f-09ff-402e-b347-2eff8a768f9c
warmup_steps: 20
weight_decay: 0.01
xformers_attention: true

316bae3e-a17f-4aec-a192-e286202ca352

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: 11.9313

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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: 20
training_steps: 40

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	11.9321
11.9309	0.0007	5	11.9321
11.9313	0.0014	10	11.9320
11.9326	0.0021	15	11.9319
11.9306	0.0028	20	11.9318
11.9327	0.0035	25	11.9316
11.9313	0.0042	30	11.9314
11.9308	0.0049	35	11.9313
11.9309	0.0056	40	11.9313

Framework versions

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