See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: llamafactory/tiny-random-Llama-3
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 311330e8a1d55a86_train_data.json
  ds_type: json
  field: issue
  path: /workspace/input_data/311330e8a1d55a86_train_data.json
  type: completion
debug: null
deepspeed: null
early_stopping_patience: null
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: false
group_by_length: false
hub_model_id: dzanbek/b6618d56-6c88-4033-ade8-8135764c1751
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: 32
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/311330e8a1d55a86_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optimizer: adamw_torch
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: 2028
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: b6618d56-6c88-4033-ade8-8135764c1751
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b6618d56-6c88-4033-ade8-8135764c1751
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

b6618d56-6c88-4033-ade8-8135764c1751

This model is a fine-tuned version of llamafactory/tiny-random-Llama-3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.7649

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_TORCH 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
11.7643	0.0050	1	11.7756
11.7739	0.0202	4	11.7754
11.7766	0.0403	8	11.7746
11.7763	0.0605	12	11.7733
11.7657	0.0806	16	11.7718
11.7821	0.1008	20	11.7703
11.7707	0.1209	24	11.7689
11.7642	0.1411	28	11.7676
11.7767	0.1612	32	11.7665
11.7722	0.1814	36	11.7657
11.7692	0.2015	40	11.7652
11.7605	0.2217	44	11.7650
11.7582	0.2418	48	11.7649

Framework versions

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