See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: furiosa-ai/mlperf-gpt-j-6b
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 1658c92d35a47de0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1658c92d35a47de0_train_data.json
  type:
    field_instruction: content
    field_output: poem name
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: lesso13/9598486a-8127-4398-84ca-2db72cce54f6
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 45GiB
max_steps: 25
micro_batch_size: 2
mlflow_experiment_name: /tmp/1658c92d35a47de0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 10
sequence_len: 512
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: 2090fb09-7ba8-45e0-b775-4862d5c2b943
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 2090fb09-7ba8-45e0-b775-4862d5c2b943
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

9598486a-8127-4398-84ca-2db72cce54f6

This model is a fine-tuned version of furiosa-ai/mlperf-gpt-j-6b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6257

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss
8.8978	0.0006	1	2.0250
7.6277	0.0031	5	1.7564
6.1375	0.0062	10	1.0562
4.2725	0.0093	15	0.7319
3.6739	0.0123	20	0.6391
2.6951	0.0154	25	0.6257

Framework versions

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