264 lines
6.9 KiB
Markdown
264 lines
6.9 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: apache-2.0
|
|
datasets:
|
|
- teknium/OpenHermes-2.5
|
|
- abhinand/ultrachat_200k_sharegpt
|
|
model-index:
|
|
- name: TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: AI2 Reasoning Challenge (25-Shot)
|
|
type: ai2_arc
|
|
config: ARC-Challenge
|
|
split: test
|
|
args:
|
|
num_few_shot: 25
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 33.79
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: HellaSwag (10-Shot)
|
|
type: hellaswag
|
|
split: validation
|
|
args:
|
|
num_few_shot: 10
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 58.72
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MMLU (5-Shot)
|
|
type: cais/mmlu
|
|
config: all
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 24.52
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: TruthfulQA (0-shot)
|
|
type: truthful_qa
|
|
config: multiple_choice
|
|
split: validation
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: mc2
|
|
value: 36.22
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: Winogrande (5-shot)
|
|
type: winogrande
|
|
config: winogrande_xl
|
|
split: validation
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 60.93
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: GSM8k (5-shot)
|
|
type: gsm8k
|
|
config: main
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 5.38
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
|
|
name: Open LLM Leaderboard
|
|
---
|
|
|
|
# TinyLLaMA OpenHermes2.5 [Work in Progress]
|
|
|
|
This a finetune of TinyLLaMA base model finetuned on [OpenHermes 2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5) and [UltraChat 200k](https://huggingface.co/datasets/abhinand/ultrachat_200k_sharegpt) for a single epoch.
|
|
|
|
Training was generously supported by [Jarvislabs.ai](https://jarvislabs.ai/).
|
|
|
|
If you appreciate this work and would like to support its continued development, consider [buying me a coffee](https://www.buymeacoffee.com/abhinand.b). Your support is invaluable and greatly appreciated.
|
|
|
|
[](https://www.buymeacoffee.com/abhinand.b)
|
|
|
|
<details><summary>See axolotl config</summary>
|
|
|
|
axolotl version: `0.4.0`
|
|
```yaml
|
|
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: AutoTokenizer
|
|
trust_remote_code: true
|
|
is_llama_derived_model: true
|
|
|
|
# huggingface repo
|
|
datasets:
|
|
- path: teknium/OpenHermes-2.5
|
|
type: sharegpt
|
|
conversation: chatml
|
|
train_on_split: train
|
|
|
|
- path: abhinand/ultrachat_200k_sharegpt
|
|
type: sharegpt
|
|
conversation: chatml
|
|
train_on_split: train
|
|
|
|
load_in_4bit: false
|
|
load_in_8bit: false
|
|
bf16: true # require >=ampere
|
|
chat_template: chatml
|
|
|
|
dataset_prepared_path: last_run_prepared_path
|
|
hub_model_id: abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v1.0
|
|
group_by_length: false
|
|
|
|
val_set_size: 0.0
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_target_modules:
|
|
- q_proj
|
|
- v_proj
|
|
- k_proj
|
|
- o_proj
|
|
- gate_proj
|
|
- down_proj
|
|
- up_proj
|
|
lora_modules_to_save:
|
|
- embed_tokens
|
|
- lm_head
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
output_dir: /home/tiny-llama/trained_models
|
|
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 32
|
|
eval_batch_size: 32
|
|
num_epochs: 1
|
|
logging_steps: 1
|
|
save_steps: 50
|
|
save_total_limit: 3
|
|
|
|
save_safetensors: true
|
|
gradient_checkpointing: true
|
|
|
|
lr_scheduler: cosine
|
|
optimizer: "adamw_bnb_8bit"
|
|
adam_beta2: 0.95
|
|
adam_epsilon: 0.00001
|
|
weight_decay: 0.1
|
|
learning_rate: 0.0005
|
|
max_grad_norm: 1.0
|
|
warmup_ratio: 0.05
|
|
# warmup_steps: 100
|
|
|
|
flash_attention: true
|
|
|
|
# Resume from a specific checkpoint dir
|
|
resume_from_checkpoint:
|
|
# If resume_from_checkpoint isn't set and you simply want it to start where it left off.
|
|
# Be careful with this being turned on between different models.
|
|
# auto_resume_from_checkpoints: true
|
|
|
|
# wandb configuration if you're using it
|
|
# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`.
|
|
wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb
|
|
wandb_project: "tiny-llama-sft"
|
|
wandb_name:
|
|
wandb_run_id:
|
|
|
|
special_tokens:
|
|
bos_token: "<s>"
|
|
eos_token: "</s>"
|
|
unk_token: "<unk>"
|
|
tokens: # these are delimiters
|
|
- "<|im_start|>"
|
|
- "<|im_end|>"
|
|
|
|
```
|
|
|
|
</details>
|
|
|
|
## Training procedure
|
|
|
|
### Training hyperparameters
|
|
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 0.0005
|
|
- train_batch_size: 32
|
|
- eval_batch_size: 32
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 2
|
|
- total_train_batch_size: 64
|
|
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_steps: 476
|
|
- num_epochs: 1
|
|
|
|
### Framework versions
|
|
|
|
- PEFT 0.8.2
|
|
- Transformers 4.38.0.dev0
|
|
- Pytorch 2.0.1
|
|
- Datasets 2.16.1
|
|
- Tokenizers 0.15.0
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_abhinand__TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft)
|
|
|
|
| Metric |Value|
|
|
|---------------------------------|----:|
|
|
|Avg. |36.59|
|
|
|AI2 Reasoning Challenge (25-Shot)|33.79|
|
|
|HellaSwag (10-Shot) |58.72|
|
|
|MMLU (5-Shot) |24.52|
|
|
|TruthfulQA (0-shot) |36.22|
|
|
|Winogrande (5-shot) |60.93|
|
|
|GSM8k (5-shot) | 5.38|
|
|
|