See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: EleutherAI/pythia-1b
bf16: auto
datasets:
- data_files:
  - cf3a451ad5f57e3e_train_data.json
  ds_type: json
  format: custom
  path: cf3a451ad5f57e3e_train_data.json
  type:
    field: null
    field_input: original_code
    field_instruction: update_snippet
    field_output: final_code
    field_system: null
    format: null
    no_input_format: null
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_sample_packing: false
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: FatCat87/7d2f4acd-ec41-4940-b17f-5ffb945afa24
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_r: 32
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 2
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: ./outputs/out
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: 1
seed: 701
sequence_len: 4096
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0.1
wandb_entity: fatcat87-taopanda
wandb_log_model: null
wandb_mode: online
wandb_name: 7d2f4acd-ec41-4940-b17f-5ffb945afa24
wandb_project: subnet56
wandb_runid: 7d2f4acd-ec41-4940-b17f-5ffb945afa24
wandb_watch: null
warmup_ratio: 0.05
weight_decay: 0.0
xformers_attention: null

7d2f4acd-ec41-4940-b17f-5ffb945afa24

This model is a fine-tuned version of EleutherAI/pythia-1b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0526

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: 701
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 5
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
4.2604	0.0075	1	0.9479
1.8401	0.2547	34	0.1403
0.1249	0.5094	68	0.0728
0.0707	0.7640	102	0.0526

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1