See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
datasets:
- data_files:
  - c244936fc67eb04f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c244936fc67eb04f_train_data.json
  type:
    field_input: question
    field_instruction: problem
    field_output: solution
    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: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso07/609407d2-fc4b-4a5a-b01c-f95b3157d55f
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: 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_memory:
  0: 77GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/c244936fc67eb04f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 609407d2-fc4b-4a5a-b01c-f95b3157d55f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 609407d2-fc4b-4a5a-b01c-f95b3157d55f
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

609407d2-fc4b-4a5a-b01c-f95b3157d55f

This model is a fine-tuned version of HuggingFaceM4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.3493

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: 2
• total_train_batch_size: 16
• 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
10.3658	0.0006	1	10.3659
10.3666	0.0054	9	10.3652
10.3663	0.0108	18	10.3633
10.3626	0.0162	27	10.3613
10.3596	0.0216	36	10.3590
10.3566	0.0269	45	10.3565
10.3562	0.0323	54	10.3541
10.349	0.0377	63	10.3520
10.352	0.0431	72	10.3505
10.3494	0.0485	81	10.3497
10.349	0.0539	90	10.3493
10.348	0.0593	99	10.3493

Framework versions

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