---
license: mit
base_model: microsoft/phi-2
tags:
- axolotl
- generated_from_trainer
model-index:
- name: phi-2-logical-sft
  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

hub_model_id: MaziyarPanahi/phi-2-logical-sft
hf_use_auth_token: true


load_in_8bit: false
load_in_4bit: false
strict: false

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

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./phi-2-logical-sft-out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
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: 2
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-2-logical-sft

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: 1.0075

## 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
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 8
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.8319        | 0.0   | 1    | 1.0229          |
| 0.8799        | 0.25  | 71   | 1.0208          |
| 0.8349        | 0.5   | 142  | 1.0119          |
| 0.7798        | 0.76  | 213  | 1.0093          |
| 0.8317        | 1.01  | 284  | 1.0083          |
| 0.777         | 1.24  | 355  | 1.0080          |
| 0.7544        | 1.49  | 426  | 1.0075          |
| 0.7037        | 1.74  | 497  | 1.0075          |


### Framework versions

- Transformers 4.39.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.0