See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: JackFram/llama-160m
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 4cad4f74c7fcbf14_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/4cad4f74c7fcbf14_train_data.json
  type:
    field_input: concatenated_headline
    field_instruction: headline
    field_output: trends
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: bbytxt/d3798400-dab8-4ff1-9db4-d29585565f2b
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 3.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/4cad4f74c7fcbf14_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 5
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: 50
saves_per_epoch: null
sequence_len: 2048
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: null
wandb_mode: online
wandb_name: d3798400-dab8-4ff1-9db4-d29585565f2b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d3798400-dab8-4ff1-9db4-d29585565f2b
warmup_steps: 200
weight_decay: 0.0
xformers_attention: null

d3798400-dab8-4ff1-9db4-d29585565f2b

This model is a fine-tuned version of JackFram/llama-160m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 7.7403

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: 3e-05
• 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: 200
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
14.0369	0.0019	1	13.9245
12.7921	0.0931	50	12.7002
7.9208	0.1862	100	7.7403

Framework versions

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