metadata
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-1B-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: miner1_60c4f9de-24ff-4eeb-a041-3c142f4f4888_1731086176
results: []
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:
- data_files:
- MATH-Hard_train_data.json
ds_type: json
path: /workspace/input_data/MATH-Hard_train_data.json
type:
field_input: solution
field_instruction: type
field_output: problem
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 1
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: 4
gradient_checkpointing: true
group_by_length: false
hours_to_complete: 4
hub_model_id: besimray/miner1_60c4f9de-24ff-4eeb-a041-3c142f4f4888_1731086176
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: 32
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: 500
micro_batch_size: 2
mlflow_experiment_name: /tmp/MATH-Hard_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
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: 10
save_strategy: steps
sequence_len: 4096
started_at: '2024-11-08T17:16:16.217205'
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: besimray24-rayon
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 60c4f9de-24ff-4eeb-a041-3c142f4f4888
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
miner1_60c4f9de-24ff-4eeb-a041-3c142f4f4888_1731086176
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: 0.8877
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- 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: 10
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7576 | 0.0024 | 1 | 1.4666 |
| 1.191 | 0.0119 | 5 | 1.4214 |
| 0.4449 | 0.0239 | 10 | 1.1578 |
| 1.6707 | 0.0358 | 15 | 1.0529 |
| 0.9342 | 0.0477 | 20 | 1.0087 |
| 1.1447 | 0.0597 | 25 | 0.9941 |
| 1.331 | 0.0716 | 30 | 0.9711 |
| 0.9763 | 0.0835 | 35 | 0.9544 |
| 0.6841 | 0.0955 | 40 | 0.9494 |
| 0.7273 | 0.1074 | 45 | 0.9417 |
| 0.766 | 0.1193 | 50 | 0.9387 |
| 0.9841 | 0.1313 | 55 | 0.9331 |
| 0.8733 | 0.1432 | 60 | 0.9313 |
| 0.64 | 0.1551 | 65 | 0.9237 |
| 1.3638 | 0.1671 | 70 | 0.9212 |
| 0.8958 | 0.1790 | 75 | 0.9195 |
| 0.8923 | 0.1909 | 80 | 0.9134 |
| 1.1555 | 0.2029 | 85 | 0.9122 |
| 0.7069 | 0.2148 | 90 | 0.9102 |
| 0.9398 | 0.2267 | 95 | 0.9005 |
| 1.1527 | 0.2387 | 100 | 0.8966 |
| 1.0022 | 0.2506 | 105 | 0.8951 |
| 0.7001 | 0.2625 | 110 | 0.8915 |
| 0.6991 | 0.2745 | 115 | 0.8872 |
| 1.1245 | 0.2864 | 120 | 0.8851 |
| 1.0224 | 0.2983 | 125 | 0.8877 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.3.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.3