See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: peft-internal-testing/tiny-dummy-qwen2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 3d12e1f5d945cd9c_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/3d12e1f5d945cd9c_train_data.json
  type:
    field_input: Description
    field_instruction: Prompt
    field_output: GT
    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: Nexspear/f7f3017a-cb89-4189-ad3e-a453af365aba
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: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 72GB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/3d12e1f5d945cd9c_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
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: f7f3017a-cb89-4189-ad3e-a453af365aba
wandb_project: Gradients-On-Four
wandb_run: your_name
wandb_runid: f7f3017a-cb89-4189-ad3e-a453af365aba
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

f7f3017a-cb89-4189-ad3e-a453af365aba

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: 11.8708

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: 42
• gradient_accumulation_steps: 4
• total_train_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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0146	1	11.9209
11.9298	0.0730	5	11.9199
11.9292	0.1460	10	11.9165
11.9164	0.2190	15	11.9107
11.9177	0.2920	20	11.9026
11.9069	0.3650	25	11.8931
11.8926	0.4380	30	11.8841
11.8888	0.5109	35	11.8770
11.8843	0.5839	40	11.8727
11.8779	0.6569	45	11.8710
11.8762	0.7299	50	11.8708

Framework versions

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