Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/SmolLM2-360M
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cc847fde626c1721_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/cc847fde626c1721_train_data.json
  type:
    field_instruction: prompt
    field_output: gold_standard_solution
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 2
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: auxyus/1d6701e0-dbc2-4e65-b1ff-a410d732e307
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 10
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 900
micro_batch_size: 4
mlflow_experiment_name: /tmp/cc847fde626c1721_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-08
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: 150
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: acopia-grant
wandb_mode: online
wandb_name: e963cca6-269f-49f4-85bb-aa32c3266353
wandb_project: Gradients-On-2
wandb_run: your_name
wandb_runid: e963cca6-269f-49f4-85bb-aa32c3266353
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

1d6701e0-dbc2-4e65-b1ff-a410d732e307

This model is a fine-tuned version of unsloth/SmolLM2-360M on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7444

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: 5e-05
  • 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=0.999,adam_epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 50
  • training_steps: 900

Training results

Training Loss Epoch Step Validation Loss
No log 0.0000 1 0.9740
0.8246 0.0033 150 0.8201
0.7934 0.0065 300 0.7873
0.7753 0.0098 450 0.7701
0.7602 0.0130 600 0.7581
0.7137 0.0163 750 0.7495
0.7321 0.0195 900 0.7444

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
10
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.

Model tree for auxyus/1d6701e0-dbc2-4e65-b1ff-a410d732e307

Adapter
(251)
this model