---
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: NousResearch/Llama-2-7b-hf
model-index:
- name: MathLlama-7b
results: []
---
[](https://github.com/OpenAccess-AI-Collective/axolotl)
See axolotl config
axolotl version: `0.3.0`
```yaml
base_model: NousResearch/Llama-2-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true
hub_model_id: MathLlama-7b
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: zorooo/Eval_Math_Derivatives
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./qlora-out-2
adapter: qlora
lora_model_dir:
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: axolotl_run_1_math_llama
wandb_entity:
wandb_watch:
wandb_name: math_llama_run2
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 5
optimizer: paged_adamw_32bit
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: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: ""
eos_token: ""
unk_token: ""
```
# MathLlama-7b
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1580
## 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: 0.0002
- 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: 100
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.952 | 0.04 | 1 | 0.9490 |
| 0.9351 | 0.27 | 7 | 0.9474 |
| 0.9431 | 0.54 | 14 | 0.9181 |
| 0.8078 | 0.82 | 21 | 0.7671 |
| 0.5693 | 1.06 | 28 | 0.5249 |
| 0.309 | 1.33 | 35 | 0.3288 |
| 0.2752 | 1.6 | 42 | 0.2607 |
| 0.2406 | 1.87 | 49 | 0.2267 |
| 0.2241 | 2.12 | 56 | 0.2068 |
| 0.2212 | 2.39 | 63 | 0.1932 |
| 0.1991 | 2.66 | 70 | 0.1842 |
| 0.173 | 2.93 | 77 | 0.1738 |
| 0.162 | 3.18 | 84 | 0.1711 |
| 0.1357 | 3.46 | 91 | 0.1681 |
| 0.15 | 3.73 | 98 | 0.1664 |
| 0.1553 | 4.0 | 105 | 0.1610 |
| 0.1263 | 4.25 | 112 | 0.1613 |
| 0.132 | 4.52 | 119 | 0.1580 |
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0