---
license: other
tags:
- axolotl
- generated_from_trainer
base_model: chargoddard/internlm2-20b-llama
model-index:
- name: Stellaris-internlm2-20b-r512
  results: []
---

<!-- 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: `0.3.0`
```yaml
base_model: chargoddard/internlm2-20b-llama
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: ARB/arb_law.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: ARB/arb_math.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: ARB/arb_mcat_reading.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: ARB/arb_mcat_science.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: ARB/arb_physics.json
    ds_type: json
    type: alpaca
    conversation: chatml


dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./Weyaxi-test

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:

lora_r: 512
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: huggingface 
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

hub_model_id: Weyaxi/Weyaxi-test

gradient_accumulation_steps: 4 # change
micro_batch_size: 2 # change
num_epochs: 3
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

save_steps: 20
save_total_limit: 5

debug:
#deepspeed: deepspeed/zero3_bf16.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"
```

</details><br>

# Weyaxi-test

This model is a fine-tuned version of [chargoddard/internlm2-20b-llama](https://huggingface.co/chargoddard/internlm2-20b-llama) on the None dataset.

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure


The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3

### Training results



### Framework versions

- PEFT 0.7.0
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0