See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/Llama-3.2-3B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 5284e565a80f1175_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/5284e565a80f1175_train_data.json
type:
field_input: Complex_CoT
field_instruction: Question
field_output: Response
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
device_map:
? ''
: 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/2195b42e-55a3-4d53-8953-df1e1b9bc67f
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
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: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1122
micro_batch_size: 4
mlflow_experiment_name: /tmp/5284e565a80f1175_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 100
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 992ec895-1f75-4a0a-a06b-75880a82fff7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 992ec895-1f75-4a0a-a06b-75880a82fff7
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
2195b42e-55a3-4d53-8953-df1e1b9bc67f
This model is a fine-tuned version of unsloth/Llama-3.2-3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7690
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- 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: 1122
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.064 | 0.0014 | 1 | 1.2040 |
0.9431 | 0.1371 | 100 | 0.8307 |
0.6877 | 0.2742 | 200 | 0.8106 |
0.7727 | 0.4112 | 300 | 0.7981 |
0.839 | 0.5483 | 400 | 0.7886 |
0.8113 | 0.6854 | 500 | 0.7816 |
0.8437 | 0.8225 | 600 | 0.7765 |
0.83 | 0.9596 | 700 | 0.7711 |
0.5437 | 1.0966 | 800 | 0.7719 |
0.8655 | 1.2337 | 900 | 0.7704 |
0.6449 | 1.3708 | 1000 | 0.7692 |
0.7251 | 1.5079 | 1100 | 0.7690 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.