File size: 1,390 Bytes
7c44227
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
---
language: 
  - en
tags:
  - NLP
license: mit
datasets:
  - TristanBehrens/bach_garland_2024-100K
base_model: None
---

# bach_garland_phariaplus - An xLSTM Model

![Trained with Helibrunna](banner.jpg)

Trained with [Helibrunna](https://github.com/AI-Guru/helibrunna) by [Dr. Tristan Behrens](https://de.linkedin.com/in/dr-tristan-behrens-734967a2).

## Configuration

```
training:
  model_name: bach_garland_phariaplus
  batch_size: 22
  lr: 0.001
  lr_warmup_steps: 1818
  lr_decay_until_steps: 18181
  lr_decay_factor: 0.001
  weight_decay: 0.1
  amp_precision: bfloat16
  weight_precision: float32
  enable_mixed_precision: true
  num_epochs: 8
  output_dir: output/bach_garland_phariaplus
  save_every_step: 500
  log_every_step: 10
  wandb_project: bach_garland
  torch_compile: false
model:
  type: pharia
  attention_bias: true
  attention_dropout: 0.0
  eos_token_id: 0
  bos_token_id: 127179
  pad_token_id: 1
  hidden_act: gelu
  hidden_size: 132
  initializer_range: 0.02
  intermediate_size: 264
  max_position_embeddings: 2048
  mlp_bias: true
  num_attention_heads: 6
  num_hidden_layers: 6
  num_key_value_heads: 6
  rope_scaling: null
  rope_theta: 1000000
  tie_word_embeddings: false
  use_cache: true
  context_length: 2048
  vocab_size: 178
dataset:
  hugging_face_id: TristanBehrens/bach_garland_2024-100K
tokenizer:
  type: whitespace
  fill_token: '[EOS]'

```