End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: answerdotai/ModernBERT-large
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: modernbert-dllm-tulu
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# modernbert-dllm-tulu
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.6432
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- total_train_batch_size: 128
|
| 45 |
+
- total_eval_batch_size: 128
|
| 46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| No log | 0.0332 | 200 | 1.7948 |
|
| 55 |
+
| No log | 0.0664 | 400 | 1.7504 |
|
| 56 |
+
| 1.7964 | 0.0997 | 600 | 1.7230 |
|
| 57 |
+
| 1.7964 | 0.1329 | 800 | 1.7046 |
|
| 58 |
+
| 1.717 | 0.1661 | 1000 | 1.6923 |
|
| 59 |
+
| 1.717 | 0.1993 | 1200 | 1.6827 |
|
| 60 |
+
| 1.717 | 0.2326 | 1400 | 1.6752 |
|
| 61 |
+
| 1.6662 | 0.2658 | 1600 | 1.6689 |
|
| 62 |
+
| 1.6662 | 0.2990 | 1800 | 1.6638 |
|
| 63 |
+
| 1.6667 | 0.3322 | 2000 | 1.6601 |
|
| 64 |
+
| 1.6667 | 0.3654 | 2200 | 1.6574 |
|
| 65 |
+
| 1.6667 | 0.3987 | 2400 | 1.6544 |
|
| 66 |
+
| 1.6626 | 0.4319 | 2600 | 1.6525 |
|
| 67 |
+
| 1.6626 | 0.4651 | 2800 | 1.6505 |
|
| 68 |
+
| 1.6472 | 0.4983 | 3000 | 1.6493 |
|
| 69 |
+
| 1.6472 | 0.5316 | 3200 | 1.6479 |
|
| 70 |
+
| 1.6472 | 0.5648 | 3400 | 1.6469 |
|
| 71 |
+
| 1.6354 | 0.5980 | 3600 | 1.6460 |
|
| 72 |
+
| 1.6354 | 0.6312 | 3800 | 1.6454 |
|
| 73 |
+
| 1.6457 | 0.6645 | 4000 | 1.6448 |
|
| 74 |
+
| 1.6457 | 0.6977 | 4200 | 1.6445 |
|
| 75 |
+
| 1.6457 | 0.7309 | 4400 | 1.6440 |
|
| 76 |
+
| 1.6404 | 0.7641 | 4600 | 1.6437 |
|
| 77 |
+
| 1.6404 | 0.7973 | 4800 | 1.6436 |
|
| 78 |
+
| 1.6472 | 0.8306 | 5000 | 1.6435 |
|
| 79 |
+
| 1.6472 | 0.8638 | 5200 | 1.6434 |
|
| 80 |
+
| 1.6472 | 0.8970 | 5400 | 1.6433 |
|
| 81 |
+
| 1.6394 | 0.9302 | 5600 | 1.6433 |
|
| 82 |
+
| 1.6394 | 0.9635 | 5800 | 1.6432 |
|
| 83 |
+
| 1.6313 | 0.9967 | 6000 | 1.6432 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.53.0
|
| 89 |
+
- Pytorch 2.7.1+cu126
|
| 90 |
+
- Datasets 3.6.0
|
| 91 |
+
- Tokenizers 0.21.2
|