gemma-g

<!-- 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"/>

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

axolotl version: 0.4.0

base_model: 0x0dad0/nous_nb_20
model_type: GemmaForCausalLM
hub_model_id: gemma-g

load_in_8bit: false
load_in_4bit: false
strict: false


datasets:
  - path: tomaszki/gemma
  - path: tomaszki/gemma-1
  - path: tomaszki/gemma-2
  - path: tomaszki/gemma-3
  - path: tomaszki/gemma-4
  - path: tomaszki/gemma-5
  - path: tomaszki/gemma-6
  - path: tomaszki/gemma-7
  - path: tomaszki/gemma-8
  - path: tomaszki/gemma-9
  - path: tomaszki/gemma-10
  - path: tomaszki/gemma-11
  - path: tomaszki/gemma-12
  - path: tomaszki/gemma-13
  - path: tomaszki/gemma-14
  - path: tomaszki/gemma-15
  - path: tomaszki/gemma-16
  - path: tomaszki/gemma-17
  - path: tomaszki/gemma-18
  - path: tomaszki/gemma-19
  - path: tomaszki/gemma-20
  - path: tomaszki/gemma-21
  - path: tomaszki/gemma-22
  - path: tomaszki/gemma-23
  - path: tomaszki/gemma-24
  - path: tomaszki/gemma-25
  - path: tomaszki/gemma-26
  - path: tomaszki/gemma-27
  - path: tomaszki/gemma-28
  - path: tomaszki/gemma-29
  - path: tomaszki/gemma-30
  - path: tomaszki/gemma-31
  - path: tomaszki/gemma-32
  - path: tomaszki/gemma-33
  - path: tomaszki/gemma-34
  - path: tomaszki/gemma-35
  - path: tomaszki/gemma-36
  - path: tomaszki/gemma-42
val_set_size: 0.0
output_dir: out

sequence_len: 1024
sample_packing: false

wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 50
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_hf
lr_scheduler: cosine
learning_rate: 0.000001
cosine_min_lr_ratio: 0.5
max_grad_norm: 0.00001

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

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

warmup_steps: 0
saves_per_epoch: 1
debug:
deepspeed: #deepspeed_configs/zero2.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:

</details><br>

gemma-g

This model is a fine-tuned version of 0x0dad0/nous_nb_20 on the None 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-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 50
• total_train_batch_size: 800
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 2

Training results

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu118
• Datasets 2.17.1
• Tokenizers 0.15.0