---
license: mit
base_model: microsoft/Phi-3-medium-128k-instruct
tags:
- generated_from_trainer
model-index:
- name: outputs/phi3-medium-128k-14b.8e6
  results: []
---
**Exllamav2** quant (**exl2** / **3.0 bpw**) made with ExLlamaV2 v0.0.21

Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-2_2bpw_exl2)**</center> | <center>4032 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-2_5bpw_exl2)**</center> | <center>4500 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-3_0bpw_exl2)**</center> | <center>5312 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-3_5bpw_exl2)**</center> | <center>6124 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-3_75bpw_exl2)**</center> | <center>6531 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-4_0bpw_exl2)**</center> | <center>6937 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-4_25bpw_exl2)**</center> | <center>7340 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-5_0bpw_exl2)**</center> | <center>8554 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-6_0bpw_exl2)**</center> | <center>10210 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-6_5bpw_exl2)**</center> | <center>11018 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/shisa-ai_shisa-v1-phi3-14b-8_0bpw_exl2)**</center> | <center>12332 MB</center> | <center>8</center> |


<!-- 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-3-medium-128k-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: shisa-llama3-70b-v1.8e6

chat_template: chatml
datasets:
  - path: augmxnt/ultra-orca-boros-en-ja-v1
    type: sharegpt
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/phi3-medium-128k-14b.8e6

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
neftune_noise_alpha: 5

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: linear
learning_rate: 0.000008

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: axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
fsdp:
fsdp_config:
resize_token_embeddings_to_32x: true
special_tokens:
  pad_token: "<|endoftext|>"

```

</details><br>

# outputs/phi3-medium-128k-14b.8e6

This model is a fine-tuned version of [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3339

## 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: 8e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.8309        | 0.0021 | 1    | 2.3406          |
| 0.7688        | 0.2513 | 121  | 0.4958          |
| 0.6435        | 0.5026 | 242  | 0.3830          |
| 0.5286        | 0.7539 | 363  | 0.3626          |
| 0.5559        | 1.0052 | 484  | 0.3549          |
| 0.4651        | 1.2425 | 605  | 0.3486          |
| 0.5294        | 1.4938 | 726  | 0.3432          |
| 0.5453        | 1.7451 | 847  | 0.3392          |
| 0.5258        | 1.9964 | 968  | 0.3376          |
| 0.4805        | 2.2331 | 1089 | 0.3357          |
| 0.4552        | 2.4844 | 1210 | 0.3352          |
| 0.5358        | 2.7357 | 1331 | 0.3339          |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1