See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Xenova/tiny-random-Phi3ForCausalLM
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - 59716c9c4c29f66a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/59716c9c4c29f66a_train_data.json
  type:
    field_input: text_encoding
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: nttx/8f68d8b0-2c28-488e-88c7-95dae12ed223
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1500
micro_batch_size: 4
mlflow_experiment_name: /tmp/59716c9c4c29f66a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
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: 150
saves_per_epoch: null
sequence_len: 1024
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: e59de8f8-41d9-4aa7-9fa3-2f4cd7c59f6b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e59de8f8-41d9-4aa7-9fa3-2f4cd7c59f6b
warmup_steps: 50
weight_decay: 0.1
xformers_attention: null

8f68d8b0-2c28-488e-88c7-95dae12ed223

This model is a fine-tuned version of Xenova/tiny-random-Phi3ForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 9.7743

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=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 1500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0017	1	10.3561
9.8747	0.2604	150	9.8336
9.8098	0.5208	300	9.7942
9.7926	0.7812	450	9.7823
9.781	1.0417	600	9.7785
9.7784	1.3021	750	9.7763
9.7775	1.5625	900	9.7751
9.7766	1.8229	1050	9.7747
9.7743	2.0833	1200	9.7746
9.771	2.3438	1350	9.7743
9.7759	2.6042	1500	9.7743

Framework versions

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