36d0bfa5-a5fc-47c8-9fd2-dd89bc4589a8

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.10.0.dev0

adapter: lora
base_model: unsloth/SmolLM2-1.7B-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 70d991d912fc0e95_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_instruction: instruct
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
dpo:
  beta: 0.1
  enabled: true
  group_by_length: false
  rank_loss: true
  reference_model: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 3
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: vermoney/36d0bfa5-a5fc-47c8-9fd2-dd89bc4589a8
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 2.0e-06
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 96
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 48
lora_target_linear: true
lr_scheduler: cosine
max_steps: 280
micro_batch_size: 6
mixed_precision: bf16
mlflow_experiment_name: /tmp/70d991d912fc0e95_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: eb847f20-dfd3-4bc3-98a6-d05a0c333efa
wandb_project: s56-9
wandb_run: your_name
wandb_runid: eb847f20-dfd3-4bc3-98a6-d05a0c333efa
warmup_steps: 40
weight_decay: 0.02
xformers_attention: false

</details><br>

36d0bfa5-a5fc-47c8-9fd2-dd89bc4589a8

This model is a fine-tuned version of unsloth/SmolLM2-1.7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9458

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-06
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 3
• total_train_batch_size: 18
• 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: 40
• training_steps: 280

Training results

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.5.1+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1