metadata
library_name: peft
license: apache-2.0
base_model: unsloth/SmolLM2-1.7B-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: b368c922-3f39-4946-92ff-329b272ceb41
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/SmolLM2-1.7B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 0c1367355c2510f8_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/0c1367355c2510f8_train_data.json
type:
field_instruction: instruction
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: robiulawaldev/b368c922-3f39-4946-92ff-329b272ceb41
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 14965
micro_batch_size: 4
mlflow_experiment_name: /tmp/0c1367355c2510f8_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
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: 500
saves_per_epoch: null
sequence_len: 512
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: a6d954dd-91ca-429a-9051-83e5cd6e3724
wandb_project: SN56-36
wandb_run: your_name
wandb_runid: a6d954dd-91ca-429a-9051-83e5cd6e3724
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null
b368c922-3f39-4946-92ff-329b272ceb41
This model is a fine-tuned version of unsloth/SmolLM2-1.7B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2566
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: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 50
- training_steps: 14965
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0002 | 1 | 0.6366 |
| 0.2955 | 0.0814 | 500 | 0.2978 |
| 0.2791 | 0.1627 | 1000 | 0.2879 |
| 0.283 | 0.2441 | 1500 | 0.2800 |
| 0.2736 | 0.3255 | 2000 | 0.2734 |
| 0.2768 | 0.4068 | 2500 | 0.2695 |
| 0.2699 | 0.4882 | 3000 | 0.2670 |
| 0.2636 | 0.5695 | 3500 | 0.2636 |
| 0.2505 | 0.6509 | 4000 | 0.2614 |
| 0.252 | 0.7323 | 4500 | 0.2607 |
| 0.2611 | 0.8136 | 5000 | 0.2593 |
| 0.2602 | 0.8950 | 5500 | 0.2575 |
| 0.2508 | 0.9764 | 6000 | 0.2556 |
| 0.2216 | 1.0577 | 6500 | 0.2587 |
| 0.2375 | 1.1391 | 7000 | 0.2572 |
| 0.2349 | 1.2205 | 7500 | 0.2566 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1