93 lines
2.0 KiB
Markdown
93 lines
2.0 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
thumbnail: "url to a thumbnail used in social sharing"
|
|
tags:
|
|
- instruct
|
|
- openhermes
|
|
- tinyllama
|
|
license: apache-2.0
|
|
datasets:
|
|
- teknium/openhermes
|
|
metrics:
|
|
- metric1
|
|
- metric2
|
|
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
|
---
|
|
|
|
## TinyLlama 1.1B Instruct 3T
|
|
|
|
<img src="https://huggingface.co/gardner/TinyLlama-1.1B-Instruct-3T/resolve/main/tinyllama-1.1b-instruct.webp?download=true" alt="TinyLlama Instruct" />
|
|
|
|
This is the 3T base model trained on openhermes instruct dataset for 4 epochs. It is intended to be used for further finetuning.
|
|
|
|
[<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)
|
|
|
|
|
|
## Loss
|
|
|
|
<img src="https://huggingface.co/gardner/TinyLlama-1.1B-Instruct-3T/resolve/main/loss.webp?download=true" alt="Loss chart" />
|
|
|
|
|
|
## axolotl config file: lora.yml
|
|
|
|
```yaml
|
|
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
is_llama_derived_model: true
|
|
|
|
load_in_8bit: true
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: teknium/openhermes
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0.05
|
|
output_dir: ./tiny-llama-instruct-lora
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 4
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: true
|
|
fp16: false
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
``` |