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:
  - 99df1874b14c82c5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/99df1874b14c82c5_train_data.json
  type:
    field_instruction: article
    field_output: highlights
    format: '{instruction}'
    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: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: dixedus/e818abc9-5296-4278-9a9c-1a91d4568237
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: 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_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/99df1874b14c82c5_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: 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: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 7300b597-8657-4111-8e68-a8076a2b70da
wandb_project: Gradients-On-Eight
wandb_run: your_name
wandb_runid: 7300b597-8657-4111-8e68-a8076a2b70da
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

e818abc9-5296-4278-9a9c-1a91d4568237

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: 11.9201

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: 200

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	11.9311
11.9299	0.0018	17	11.9308
11.9305	0.0037	34	11.9304
11.9312	0.0055	51	11.9298
11.928	0.0073	68	11.9286
11.9265	0.0092	85	11.9269
11.9252	0.0110	102	11.9245
11.9247	0.0129	119	11.9225
11.9205	0.0147	136	11.9212
11.9201	0.0165	153	11.9205
11.9205	0.0184	170	11.9202
11.9207	0.0202	187	11.9201

Framework versions

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