---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/phi-1_5
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-1_5
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: garage-bAInd/Open-Platypus
    type: alpaca

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

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter: qlora
lora_model_dir:
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_torch
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.000003

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: 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-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2548

## 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: 3e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.0668        | 0.0   | 1    | 1.2826          |
| 0.9408        | 0.25  | 580  | 1.2613          |
| 1.2121        | 0.5   | 1160 | 1.2559          |
| 0.9644        | 0.75  | 1740 | 1.2562          |
| 0.9582        | 1.0   | 2320 | 1.2556          |
| 1.0009        | 1.23  | 2900 | 1.2559          |
| 0.7816        | 1.48  | 3480 | 1.2556          |
| 0.9843        | 1.73  | 4060 | 1.2552          |
| 0.8877        | 1.98  | 4640 | 1.2559          |
| 0.8498        | 2.21  | 5220 | 1.2554          |
| 0.9163        | 2.46  | 5800 | 1.2550          |
| 1.0539        | 2.71  | 6380 | 1.2545          |
| 0.9533        | 2.96  | 6960 | 1.2547          |
| 0.6969        | 3.19  | 7540 | 1.2547          |
| 0.6204        | 3.44  | 8120 | 1.2547          |
| 0.891         | 3.69  | 8700 | 1.2548          |


### Framework versions

- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.17.0
- Tokenizers 0.15.0