See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: furiosa-ai/mlperf-gpt-j-6b
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cc43155183105214_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/cc43155183105214_train_data.json
  type:
    field_instruction: constraint
    field_output: ground_truth
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
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: true
hub_model_id: leixa/2cfc9c05-3858-4da9-bf19-fa1a3bb619a6
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: 10
lora_alpha: 64
lora_dropout: 0.2
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_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/cc43155183105214_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
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: techspear-hub
wandb_mode: online
wandb_name: 0c937939-0f0b-4663-ba53-8d70ea1cea3c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0c937939-0f0b-4663-ba53-8d70ea1cea3c
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

2cfc9c05-3858-4da9-bf19-fa1a3bb619a6

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: 0.0979

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: 4
• 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=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0023	1	3.0613
0.1262	0.1132	50	0.2472
0.0146	0.2264	100	0.2295
0.015	0.3396	150	0.1548
0.0447	0.4527	200	0.1378
0.0564	0.5659	250	0.1282
0.0218	0.6791	300	0.1148
0.0294	0.7923	350	0.1067
0.027	0.9055	400	0.1023
1.3084	1.0198	450	0.0997
1.1511	1.1330	500	0.0984
1.2	1.2462	550	0.0969
1.1926	1.3594	600	0.0979

Framework versions

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