---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: phi-sft-out
  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: `0.4.0`
```yaml
base_model: microsoft/phi-2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: tatsu-lab/alpaca
    type: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./phi-sft-out

sequence_len: 2048
sample_packing: false  # currently unsupported
pad_to_sequence_len:

wandb_project: phi2
wandb_entity: oaaic
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 1
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 1e-5

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: true

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
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
resize_token_embeddings_to_32x: true
special_tokens:
  pad_token: "<|endoftext|>"


```

</details><br>

# phi-sft-out

This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9915

## 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 7
- gradient_accumulation_steps: 8
- total_train_batch_size: 224
- total_eval_batch_size: 28
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.4814        | 0.0   | 1    | 1.4537          |
| 1.3529        | 0.25  | 55   | 1.3007          |
| 1.2246        | 0.5   | 110  | 1.0940          |
| 1.0636        | 0.75  | 165  | 0.9949          |
| 1.0758        | 1.0   | 220  | 0.9915          |


### Framework versions

- Transformers 4.38.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.17.0
- Tokenizers 0.15.0