See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - dd0f30e3221a1eab_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/dd0f30e3221a1eab_train_data.json
  type:
    field_instruction: text
    field_output: chosen
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: null
eval_max_new_tokens: 128
eval_strategy: steps
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: eddysang/35f4732e-c7e9-4dbc-a68c-ae85ce8bd0fe
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: 5
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 1
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/dd0f30e3221a1eab_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 2.0e-05
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: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: yaudayah0
wandb_mode: online
wandb_name: fad7684c-bc01-45e5-a7b7-96df8d9ecd42
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fad7684c-bc01-45e5-a7b7-96df8d9ecd42
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

35f4732e-c7e9-4dbc-a68c-ae85ce8bd0fe

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: 10.3457

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=2e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	10.3793
10.3792	0.0032	9	10.3781
10.3775	0.0064	18	10.3725
10.3665	0.0096	27	10.3572
10.3508	0.0128	36	10.3492
10.3466	0.0160	45	10.3471
10.3473	0.0192	54	10.3465
10.347	0.0224	63	10.3462
10.3475	0.0257	72	10.3460
10.3449	0.0289	81	10.3458
10.3455	0.0321	90	10.3457
10.3443	0.0353	99	10.3457

Framework versions

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