Views
No views yet
| Step | Checkpoint Type | Loss | Perplexity | Char Acc | Word Acc | Improvement vs Pre |
|---|---|---|---|---|---|---|
| Pre | pre_training | 1.1752 | 3.24 | 13.2% | 5.0% | +0.0% |
| 5,000 | checkpoint | 0.8849 | 2.42 | 9.4% | 4.4% | +24.7% |
| 10,000 | checkpoint | 0.8629 | 2.37 | 9.4% | 4.8% | +26.6% |
| 15,000 | checkpoint | 0.8549 | 2.35 | 9.9% | 4.9% | +27.3% |
| Step | Training Loss | Timestamp |
|---|---|---|
| 14,991 | 0.975032 | 2025-08-18T23:12 |
| 14,992 | 0.670720 | 2025-08-18T23:12 |
| 14,993 | 0.850654 | 2025-08-18T23:12 |
| 14,994 | 0.935257 | 2025-08-18T23:12 |
| 14,995 | 0.870635 | 2025-08-18T23:12 |
| 14,996 | 0.942344 | 2025-08-18T23:12 |
| 14,997 | 0.785241 | 2025-08-18T23:12 |
| 14,998 | 0.754749 | 2025-08-18T23:12 |
| 14,999 | 0.950578 | 2025-08-18T23:12 |
| 15,000 | 0.910276 | 2025-08-18T23:12 |
training_curves.png - 4-panel view: Training loss with eval points, Character accuracy, Word accuracy, Perplexityevaluation_comparison.png - 4-panel comparison: Loss, Character accuracy, Word accuracy, Perplexity across all checkpoints1from transformers import AutoModelForCausalLM, AutoTokenizer
2# For vision-language models, use appropriate imports
3
4model = AutoModelForCausalLM.from_pretrained("./model_step_15000")
5tokenizer = AutoTokenizer.from_pretrained("./model_step_15000")
6
7# Your inference code here1{
2 "dataset_name": "wjbmattingly/medieval-synthetic-dataset",
3 "model_name": "LiquidAI/LFM2-VL-450M",
4 "max_steps": 50000,
5 "eval_steps": 5000,
6 "num_accumulation_steps": 1,
7 "learning_rate": 1e-05,
8 "train_batch_size": 2,
9 "val_batch_size": 2,
10 "train_select_start": 0,
11 "train_select_end": 11000,
12 "val_select_start": 11001,
13 "val_select_end": 11100,
14 "train_field": "train",
15 "val_field": "train",
16 "image_column": "image",
17 "text_column": "text",
18 "user_text": "Transcribe this medieval manuscript page.",
19 "max_image_size": 200
20}