|
|
--- |
|
|
base_model: EleutherAI/pythia-160m-deduped |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- axolotl |
|
|
- relora |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: pythia-160m-storytelling |
|
|
results: [] |
|
|
datasets: |
|
|
- jtatman/storywriting_combined_instruct |
|
|
metrics: |
|
|
- accuracy |
|
|
- bleu |
|
|
- rouge |
|
|
--- |
|
|
|
|
|
<!-- 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"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
|
<details><summary>See axolotl config</summary> |
|
|
|
|
|
axolotl version: `0.4.1` |
|
|
```yaml |
|
|
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](https://huggingface.co/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 |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 5.5185 | 0.0012 | 1 | 4.8238 | |
|
|
| 4.2012 | 0.2348 | 200 | 4.1556 | |
|
|
| 4.4185 | 0.4696 | 400 | 4.8159 | |
|
|
| 5.0973 | 0.7043 | 600 | 5.0363 | |
|
|
| 8.1159 | 0.9391 | 800 | 8.4966 | |
|
|
| 6.7656 | 1.1739 | 1000 | 7.1575 | |
|
|
| 7.0548 | 1.4087 | 1200 | 7.3539 | |
|
|
| 5.9982 | 1.6445 | 1400 | 5.9954 | |
|
|
| 5.7662 | 1.8792 | 1600 | 6.0222 | |
|
|
| 4.8094 | 2.1140 | 1800 | 5.0097 | |
|
|
|
|
|
|
|
|
### 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" |
|
|
}, |
