See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/SmolLM-135M-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 163d1306df9f0f7b_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/163d1306df9f0f7b_train_data.json
  type:
    field_input: solution
    field_instruction: source
    field_output: problem
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
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: ardaspear/40c13460-3889-4d9e-8da4-53606e09165f
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_modules_to_save:
- lm_head
lora_r: 64
lora_target_linear: true
loraplus_lr_ratio: 8
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/163d1306df9f0f7b_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
peft_use_rslora: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 150
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: e4e7eecb-43be-4a77-a1bc-f47664db38c7
wandb_project: Gradients-On-Five
wandb_run: your_name
wandb_runid: e4e7eecb-43be-4a77-a1bc-f47664db38c7
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

40c13460-3889-4d9e-8da4-53606e09165f

This model is a fine-tuned version of unsloth/SmolLM-135M-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4217

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0000	1	2.1999
2.1896	0.0020	50	2.2728
2.1038	0.0039	100	1.9503
2.0384	0.0059	150	1.8037
1.9925	0.0078	200	1.7413
1.9255	0.0098	250	1.6795
1.9064	0.0118	300	1.6157
1.8035	0.0137	350	1.5517
1.8422	0.0157	400	1.4989
1.7643	0.0176	450	1.4563
1.7853	0.0196	500	1.4327
1.7609	0.0216	550	1.4233
1.7423	0.0235	600	1.4217

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1