---
library_name: peft
tags:
- generated_from_trainer
datasets:
- Mielikki/Erebus-87k
- NewEden/Orion-Asstr-Stories-16K
base_model: unsloth_phi-4
model-index:
- name: phi4-pt-out-r1
  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: `0.6.0`
```yaml
base_model: unsloth_phi-4
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/Phi4-pretrain
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

  #plugins:
  #  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

  #cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Mielikki/Erebus-87k
    type: completion
    field: body
  - path: NewEden/Orion-Asstr-Stories-16K
    type: completion
    field: content
shuffle_merged_datasets: true
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./phi4-pt-out-r1

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16 
lora_dropout: 0.05
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

lora_modules_to_save:
 - embed_tokens
 - lm_head


wandb_project: mag-phi
wandb_entity:
wandb_watch:
wandb_name: attempt-01
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_ademamix_8bit
lr_scheduler: constant_with_warmup
learning_rate: 0.0001

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

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 4
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.01
fsdp:
fsdp_config:

```

</details><br>

# phi4-pt-out-r1

This model was trained from scratch on the Mielikki/Erebus-87k and the NewEden/Orion-Asstr-Stories-16K datasets.

## 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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.PAGED_ADEMAMIX_8BIT and the args are:
No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 10
- num_epochs: 1.0

### Training results



### Framework versions

- PEFT 0.14.0
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0