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: 3
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: false
hub_model_id: besimray/miner_id_1_383a850e-bb15-45a2-8f4b-fc96eb001a74_1729770655
hub_strategy: checkpoint
hub_token: null
learning_rate: 2.0e-05
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: 8
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: 5
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: 5
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: 0.0
xformers_attention: null

miner_id_1_383a850e-bb15-45a2-8f4b-fc96eb001a74_1729770655

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: 1.1623

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: 2e-05
train_batch_size: 10
eval_batch_size: 10
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 950

Training results

Training Loss	Epoch	Step	Validation Loss
1.3316	0.0053	1	1.2586
1.1351	0.0263	5	1.2596
1.2604	0.0526	10	1.2566
1.5396	0.0789	15	1.2454
1.4895	0.1053	20	1.2336
1.1625	0.1316	25	1.2236
1.3554	0.1579	30	1.2150
1.3275	0.1842	35	1.2100
1.1912	0.2105	40	1.2058
1.2335	0.2368	45	1.2030
1.0253	0.2632	50	1.1979
1.1242	0.2895	55	1.1970
0.9963	0.3158	60	1.1910
1.0977	0.3421	65	1.1919
1.1263	0.3684	70	1.1880
1.2144	0.3947	75	1.1860
1.3055	0.4211	80	1.1839
1.1513	0.4474	85	1.1818
1.0702	0.4737	90	1.1819
1.2561	0.5	95	1.1797
1.1373	0.5263	100	1.1775
1.2136	0.5526	105	1.1780
1.3591	0.5789	110	1.1771
1.5703	0.6053	115	1.1744
1.1601	0.6316	120	1.1754
1.1412	0.6579	125	1.1748
1.1449	0.6842	130	1.1731
1.1706	0.7105	135	1.1736
1.0503	0.7368	140	1.1730
1.1938	0.7632	145	1.1730
1.4802	0.7895	150	1.1710
1.1359	0.8158	155	1.1688
1.3575	0.8421	160	1.1709
1.0188	0.8684	165	1.1685
1.147	0.8947	170	1.1684
0.9949	0.9211	175	1.1668
1.3082	0.9474	180	1.1673
1.1995	0.9737	185	1.1654
1.2346	1.0	190	1.1654
1.0948	1.0263	195	1.1660
1.3838	1.0526	200	1.1643
0.9594	1.0789	205	1.1644
1.1423	1.1053	210	1.1635
1.1774	1.1316	215	1.1645
1.0085	1.1579	220	1.1642
1.0912	1.1842	225	1.1611
1.193	1.2105	230	1.1627
1.2437	1.2368	235	1.1640
1.1814	1.2632	240	1.1623

Framework versions

PEFT 0.13.2
Transformers 4.45.2
Pytorch 2.3.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1