See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/tinyllama
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - e029f217fa002728_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e029f217fa002728_train_data.json
  type:
    field_input: overview
    field_instruction: raw_text
    field_output: clean_text
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 400
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/cb7b7f17-09e9-4fe1-a403-8cfcd08f1c23
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
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
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 8702
micro_batch_size: 2
mlflow_experiment_name: /tmp/e029f217fa002728_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 400
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.04
wandb_entity: null
wandb_mode: online
wandb_name: f214cfe8-8866-498c-ad88-a995718d9d2d
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f214cfe8-8866-498c-ad88-a995718d9d2d
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

cb7b7f17-09e9-4fe1-a403-8cfcd08f1c23

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

• Loss: 0.1239

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 8702

Training results

Training Loss	Epoch	Step	Validation Loss
5.1078	0.0002	1	4.2512
0.0377	0.0897	400	0.1555
0.4174	0.1794	800	0.1444
0.0484	0.2690	1200	0.1452
0.0263	0.3587	1600	0.1334
0.891	0.4484	2000	0.1317
0.0199	0.5381	2400	0.1302
0.0252	0.6277	2800	0.1290
0.0114	0.7174	3200	0.1279
0.0236	0.8071	3600	0.1275
0.0526	0.8968	4000	0.1261
0.379	0.9864	4400	0.1254
0.014	1.0761	4800	0.1258
0.0125	1.1658	5200	0.1252
0.0377	1.2555	5600	0.1249
0.2576	1.3451	6000	0.1247
0.4384	1.4348	6400	0.1244
0.4103	1.5245	6800	0.1242
0.0122	1.6142	7200	0.1240
0.3834	1.7038	7600	0.1239
0.2488	1.7935	8000	0.1239
0.7307	1.8832	8400	0.1239

Framework versions

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