See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_resume_from_checkpoints: true
base_model: unsloth/SmolLM-135M
bf16: auto
chat_template: llama3
dataset_prepared_path: null
dataset_processes: 6
datasets:
- data_files:
  - 2bc15e36d15fd7bb_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2bc15e36d15fd7bb_train_data.json
  type:
    field_input: input_context
    field_instruction: instruction
    field_output: errors
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 200
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/efa08785-37e5-449c-a19f-8216090b2975
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: 1
lora_alpha: 256
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 128
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: null
micro_batch_size: 16
mlflow_experiment_name: /tmp/2bc15e36d15fd7bb_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 6
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: 200
sequence_len: 256
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: 036991fa-1613-4222-9412-ca29030050ca
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 036991fa-1613-4222-9412-ca29030050ca
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

efa08785-37e5-449c-a19f-8216090b2975

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

• Loss: 0.8019

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• 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: 30
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss
2.2713	0.0032	1	2.2751
0.9207	0.6494	200	0.8987
0.8315	1.2987	400	0.8501
0.774	1.9481	600	0.8295
0.7518	2.5974	800	0.8220
0.7775	3.2468	1000	0.8225
0.789	3.8961	1200	0.8111
0.7835	4.5455	1400	0.8064
0.7918	5.1948	1600	0.8031
0.7909	5.8442	1800	0.8019

Framework versions

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