pythia-160m-storytelling

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.4.1

base_model: EleutherAI/pythia-160m-deduped
load_in_8bit: 
datasets:
  - path: jtatman/storywriting_combined_instruct
    type: alpaca
dataset_prepared_path: ds-storytelling
chat_template: inst
val_set_size: 0.01
adapter: lora
lora_model_dir: 
sequence_len: 2048
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - query_key_value
lora_target_linear: true
lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
lora_modules_to_save:
  - embed_in
  - embed_out
  - lm_head
lora_on_cpu: false
# ReLoRA configuration
# # Must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed
# relora_steps: # Number of steps per ReLoRA restart
# relora_warmup_steps: # Number of per-restart warmup steps
# relora_anneal_steps: # Number of anneal steps for each relora cycle
# relora_prune_ratio: # threshold for optimizer magnitude when pruning
# relora_cpu_offload:  # True to perform lora weight merges on cpu during restarts, for modest gpu memory savings
relora_steps: 200
relora_warmup_steps: 10
relora_cpu_offload: false
wandb_project: pythia
wandb_entity:
wandb_watch:
wandb_name: pythia-160m-storytelling
wandb_log_model:
output_dir: ./outputs/lora-alpaca-pythia-160m-storytelling
gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 3
learning_rate: 0.004
lr_scheduler: cosine_with_restarts
#cosine_min_lr_ratio: 0.1
train_on_inputs: false
group_by_length: false
#bf16: auto
#fp16: true
#tf32: false
float16: true
flash_attn: 
xformers_attention: true
optimizer: paged_adamw_8bit
gpu_memory_limit: 8GiB
hub_model_id: jtatman/pythia-160m-storytelling 
early_stopping_patience: 3
#resume_from_checkpoint: outputs/lora-alpaca-pythia-125m/checkpoint-51040
auto_resume_from_checkpoints: true
local_rank:
weight_decay: 0.0
#evals_per_epoch: 4
eval_steps: 200
logging_steps: 1
save_steps: 200
save_total_limit: 5
warmup_steps: 100
tokens:
  - "[INST]"
  - "[/INST]"

</details><br>

pythia-160m-storytelling

This model is a fine-tuned version of EleutherAI/pythia-160m-deduped on the None dataset. It achieves the following results on the evaluation set:

• Loss: 5.0097

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: 0.004
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Training results

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1

Metrics

"Open LLM Leaderboard": {
  "exact_match,flexible-extract": 0.022,
  "exact_match_stderr,flexible-extract": 0.006566447781940106,
  "acc_norm,none": 0.318,
  "acc_norm_stderr,none": 0.014487919091408506,
  "acc,none": 0.2664044125478186,
  "acc_stderr,none": 0.003623534644130716,
  "bleu_diff,none": -0.6500479549286462,
  "bleu_diff_stderr,none": 0.6420841882903697,
  "rougeL_diff,none": -0.7765084899781842,
  "rougeL_diff_stderr,none": 1.0033586571635116,
  "exact_match,strict-match": 0.006,
  "exact_match_stderr,strict-match": 0.003457152557758373,
  "rouge2_acc,none": 0.192,
  "rouge2_acc_stderr,none": 0.017632180454360994,
  "rouge1_acc,none": 0.37,
  "rouge1_acc_stderr,none": 0.02161328916516578,
  "bleu_acc,none": 0.436,
  "bleu_acc_stderr,none": 0.0221989546414768,
  "rouge1_diff,none": -1.5563905118333812,
  "rouge1_diff_stderr,none": 1.022327995054994,
  "rouge2_diff,none": -3.3177627227020277,
  "rouge2_diff_stderr,none": 0.9477297777821475,
  "bleu_max,none": 15.229235419512532,
  "bleu_max_stderr,none": 0.6713582602539528,
  "rouge2_max,none": 16.487324929036955,
  "rouge2_max_stderr,none": 1.0171593586088354,
  "rouge1_max,none": 36.3549677399668,
  "rouge1_max_stderr,none": 0.9461627463383844,
  "rougeL_max,none": 33.87976960164143,
  "rougeL_max_stderr,none": 0.9366539036852334,
  "rougeL_acc,none": 0.386,
  "rougeL_acc_stderr,none": 0.021793529219281158,
  "alias": "Open LLM Leaderboard"
},