See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: codellama/CodeLlama-7b-Instruct-hf
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 337dbfc6dbb39788_train_data.json
  ds_type: json
  field: question
  path: /workspace/input_data/337dbfc6dbb39788_train_data.json
  type: completion
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 5
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 6
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik1987/d4a65b44-74ae-4eed-bcb3-2f0310c22f54
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 50
micro_batch_size: 4
mlflow_experiment_name: /tmp/337dbfc6dbb39788_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 4056
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_dtype: bfloat16
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: d4a65b44-74ae-4eed-bcb3-2f0310c22f54
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d4a65b44-74ae-4eed-bcb3-2f0310c22f54
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

d4a65b44-74ae-4eed-bcb3-2f0310c22f54

This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf 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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 24
• optimizer: Use OptimizerNames.ADAMW_TORCH 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	0.0010	1	nan
0.0	0.0039	4	nan
0.0	0.0078	8	nan
0.0	0.0117	12	nan
0.0	0.0156	16	nan
0.0	0.0195	20	nan
0.0	0.0234	24	nan
0.0	0.0273	28	nan
0.0	0.0312	32	nan
0.0	0.0351	36	nan
0.0	0.0390	40	nan
0.0	0.0429	44	nan
0.0	0.0468	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