---
base_model: microsoft/Phi-3-mini-4k-instruct
library_name: peft
license: mit
tags:
- axolotl
- generated_from_trainer
model-index:
- name: phi3-nosys-gpt4ominiplans-27k-512rank
  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.1`
```yaml
# model and tokenizer
base_model: microsoft/Phi-3-mini-4k-instruct # change for model
trust_remote_code: true
sequence_len: 2048

strict: false

model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
bf16: auto
pad_to_sequence_len: true
save_safetensors: true


datasets:
  - path: verifiers-for-code/sampled_10k_from_27k
    type: completion
    field: text_nosys_phi
    train_on_split: train

val_set_size: 0.05

# lora
adapter: lora
lora_r: 512
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
  - embed_tokens
  - lm_head
use_rslora: true

# logging
wandb_project: valeris
wandb_name: phi3-nosys-gpt4ominiplans-27k-512rank

output_dir: ./outputs/phi3-nosys-gpt4ominiplans-27k-512rank

gradient_accumulation_steps: 2
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: true
micro_batch_size: 2
num_epochs: 1
eval_batch_size: 2
warmup_ratio: 0.05
learning_rate: 5e-6
lr_scheduler: cosine
optimizer: adamw_torch

hub_model_id: verifiers-for-code/phi3-nosys-gpt4ominiplans-27k-512rank
push_to_hub: true
hub_strategy: all_checkpoints
hub_always_push: true
evals_per_epoch: 8
saves_per_epoch: 4
logging_steps: 1
# eval_table_size: 10
# eval_max_new_tokens: 512

tokens: ["<thinking>", "</thinking>", "<plan>", "</plan>"]

special_tokens:
  pad_token: "<|endoftext|>"

```

</details><br>

# phi3-nosys-gpt4ominiplans-27k-512rank

This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8553

## 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: 5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 14
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.0833        | 0.0034 | 1    | 1.0330          |
| 1.0118        | 0.1279 | 38   | 0.9947          |
| 0.9884        | 0.2559 | 76   | 0.9393          |
| 0.9277        | 0.3838 | 114  | 0.8987          |
| 0.8411        | 0.5118 | 152  | 0.8723          |
| 0.8863        | 0.6397 | 190  | 0.8590          |
| 0.8637        | 0.7677 | 228  | 0.8557          |
| 0.9009        | 0.8956 | 266  | 0.8553          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.44.0.dev0
- Pytorch 2.4.0
- Datasets 2.19.1
- Tokenizers 0.19.1