See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: huggyllama/llama-7b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - e4f54eb5c17207cb_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e4f54eb5c17207cb_train_data.json
  type:
    field_instruction: sentence1
    field_output: sentence2
    format: '{instruction}'
    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: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: dimasik1987/fd33a073-1074-445c-9345-a5b1c5007d55
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: 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: 70GiB
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/e4f54eb5c17207cb_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optimizer: adamw_bnb_8bit
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: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: fd33a073-1074-445c-9345-a5b1c5007d55
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fd33a073-1074-445c-9345-a5b1c5007d55
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

fd33a073-1074-445c-9345-a5b1c5007d55

This model is a fine-tuned version of huggyllama/llama-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0004	1	nan
0.0	0.0016	4	nan
0.0	0.0032	8	nan
0.0	0.0047	12	nan
0.0	0.0063	16	nan
0.0	0.0079	20	nan
0.0	0.0095	24	nan
0.0	0.0110	28	nan
0.0	0.0126	32	nan
0.0	0.0142	36	nan
0.0	0.0158	40	nan
0.0	0.0173	44	nan
0.0	0.0189	48	nan

Framework versions

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