cursed-ds-9b-ep2

<!-- 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"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.10.0.dev0

# === Model Configuration ===
base_model: ByteDance-Seed/academic-ds-9B
load_in_8bit: false
load_in_4bit: false

# === Training Setup ===
num_epochs: 2
micro_batch_size: 2
gradient_accumulation_steps: 8
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

# === Hyperparameter Configuration ===
optimizer: apollo_adamw
# Apollo-mini configuration:
optim_args: "proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=200"
# Regular Apollo configuration:
# optim_args: 
optim_target_modules: all_linear
learning_rate: 1e-5
lr_scheduler: rex
weight_decay: 0.01
warmup_ratio: 0
max_grad_norm: 0.1

# === Data Configuration ===
datasets:
  - path: allura-forge/inkmix-v3.1
    type: chat_template
    split: train
    field_messages: conversations
    message_field_role: from
    message_field_content: value

dataset_prepared_path: last_run_prepared
chat_template_jinja: |
  {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}
  {{bos_token}}{% for message in messages %}
    {{'<|im_start|>' + message['role'] + '
    ' + message['content'] + '<|im_end|>' + '
    '}}
  {% endfor %}

# === Plugins ===
plugins:
  - axolotl.integrations.liger.LigerPlugin
#  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

# === Hardware Optimization ===
gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
#cut_cross_entropy: true

# === Wandb Tracking ===
wandb_project: bytedance-ds-9b-inkmix-v3

# === Checkpointing ===
saves_per_epoch: 2
save_total_limit: 3

# === Advanced Settings ===
output_dir: /mnt/persistent/ckpts
bf16: auto
flash_attention: true
train_on_inputs: false
group_by_length: false
logging_steps: 1
trust_remote_code: true
tokens:
  - '<|im_start|>'
special_tokens:
  eos_token: '<|im_end|>'

</details><br>

mnt/persistent/ckpts

This model is a fine-tuned version of ByteDance-Seed/academic-ds-9B on the allura-forge/inkmix-v3.1 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: 1e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.APOLLO_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=200
• lr_scheduler_type: cosine
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1