---
library_name: transformers
tags:
- generated_from_trainer
datasets:
- WokeAI/tankie-seed20-gens
model-index:
- name: model-output
  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: `0.15.0.dev0`
```yaml
# === Model Configuration ===
base_model: /root/Nanbeige4-3B-Thinking-2511
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false

# === Training Setup ===
num_epochs: 2
micro_batch_size: 2
gradient_accumulation_steps: 1
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

# === Hyperparameter Configuration ===
optimizer: adamw_torch_8bit
learning_rate: 5e-5
lr_scheduler: constant
weight_decay: 0.001
max_grad_norm: 0.1
warmup_ratio: 0.2
cosine_min_lr_ratio: 0.1

# === Data Configuration ===
datasets:
  - path: WokeAI/tankie-seed20-gens
    type: chat_template
    split: train
chat_template: tokenizer_default

dataset_prepared_path: last_run_prepared

# === Hardware Optimization ===
gradient_checkpointing: offload

# === Wandb Tracking ===
wandb_project: polititune-3-wip-warmup

# === Checkpointing ===
saves_per_epoch: 1

# === Advanced Settings ===
output_dir: ./model-output
bf16: auto
flash_attention: true
train_on_inputs: false
group_by_length: false
logging_steps: 1
trust_remote_code: false

fsdp:
  - auto_wrap
  - full_shard
fsdp_config:
  fsdp_version: 2
  fsdp_offload_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
  fsdp_state_dict_type: SHARDED_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_reshard_after_forward: true
  fsdp_activation_checkpointing: true # will disable if doesnt work


```

</details><br>

# model-output

This model was trained from scratch on the WokeAI/tankie-seed20-gens dataset.

## 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-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 8
- training_steps: 44

### Training results



### Framework versions

- Transformers 5.0.0
- Pytorch 2.8.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2