See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 8e4d5afe2599c5fb_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8e4d5afe2599c5fb_train_data.json
  type:
    field_input: categories
    field_instruction: title
    field_output: markdown
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
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: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: ardaspear/407aa2e3-9d77-4f21-a380-d0f9f45f42fe
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
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: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/8e4d5afe2599c5fb_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
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: 3e79335c-a5cb-432f-8f05-cbad1f162b34
wandb_project: Gradients-On-Five
wandb_run: your_name
wandb_runid: 3e79335c-a5cb-432f-8f05-cbad1f162b34
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

407aa2e3-9d77-4f21-a380-d0f9f45f42fe

This model is a fine-tuned version of HuggingFaceH4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.3565

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: 8
• eval_batch_size: 8
• 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=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0008	1	10.3803
10.3796	0.0129	17	10.3797
10.3792	0.0257	34	10.3785
10.3775	0.0386	51	10.3767
10.3744	0.0514	68	10.3736
10.3696	0.0643	85	10.3687
10.3638	0.0771	102	10.3634
10.362	0.0900	119	10.3598
10.3583	0.1028	136	10.3579
10.357	0.1157	153	10.3570
10.3572	0.1285	170	10.3566
10.3568	0.1414	187	10.3565

Framework versions

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