See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/SmolLM-135M
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cfd662e681882a2e_train_data.json
  ds_type: json
  field: prompt
  path: /workspace/input_data/cfd662e681882a2e_train_data.json
  type: completion
debug: null
deepspeed: null
early_stopping_patience: null
ema_decay: 0.9992
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: JoshMe1/b5a55e73-beb1-45c6-9c93-daf0dbb09e0b
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
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: cosine
max_steps: 123
micro_batch_size: 4
mlflow_experiment_name: /tmp/cfd662e681882a2e_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
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: 4
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
use_ema: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: cab8d1ac-0275-4fc8-ad90-7609295d6160
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: cab8d1ac-0275-4fc8-ad90-7609295d6160
warmup_steps: 10
weight_decay: 0.01
xformers_attention: true

b5a55e73-beb1-45c6-9c93-daf0dbb09e0b

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: 3.4245

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: 0.0001
• 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=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 123

Training results

Training Loss	Epoch	Step	Validation Loss
3.6122	0.0016	1	3.7131
3.7529	0.0129	8	3.7034
3.5859	0.0258	16	3.6368
3.4763	0.0386	24	3.5878
3.5527	0.0515	32	3.5532
3.4882	0.0644	40	3.5230
3.5766	0.0773	48	3.4981
3.1463	0.0902	56	3.4763
3.2064	0.1031	64	3.4595
3.2628	0.1159	72	3.4486
3.207	0.1288	80	3.4387
3.3083	0.1417	88	3.4335
3.4837	0.1546	96	3.4295
3.4568	0.1675	104	3.4264
3.5344	0.1804	112	3.4245
3.4208	0.1932	120	3.4245

Framework versions

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