See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Llama-3.2-1B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- path: mhenrichsen/alpaca_2k_test
  type: alpaca
debug: null
deepspeed: null
early_stopping_patience: 10
eval_max_new_tokens: 128
eval_steps: 20
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: besimray/miner_id_1_383a850e-bb15-45a2-8f4b-fc96eb001a74_1729712965
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 10000
micro_batch_size: 10
mlflow_experiment_name: mhenrichsen/alpaca_2k_test
model_type: LlamaForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: miner_id_besimray
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 20
save_strategy: steps
sequence_len: 4096
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: besimray24-rayon
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 383a850e-bb15-45a2-8f4b-fc96eb001a74
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

miner_id_1_383a850e-bb15-45a2-8f4b-fc96eb001a74_1729712965

This model is a fine-tuned version of unsloth/Llama-3.2-1B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5010

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: 10
• eval_batch_size: 10
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 40
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 4750

Training results

Training Loss	Epoch	Step	Validation Loss
1.2983	0.0211	1	1.2586
1.3601	0.4211	20	1.1757
1.2034	0.8421	40	1.1567
1.1302	1.2632	60	1.1534
1.0958	1.6842	80	1.1512
1.0285	2.1053	100	1.1653
1.1265	2.5263	120	1.1785
1.0215	2.9474	140	1.1921
0.8495	3.3684	160	1.2673
0.901	3.7895	180	1.2611
0.7058	4.2105	200	1.3737
0.7428	4.6316	220	1.3824
0.4866	5.0526	240	1.4475
0.5298	5.4737	260	1.5484
0.5671	5.8947	280	1.5010

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.4.1+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1