Commit
•
802db3b
1
Parent(s):
e4aa87a
End of training
Browse files- README.md +77 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilbert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: finetuned-DSCS24-mitre-distilbert-base-uncased-fill-mask
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# finetuned-DSCS24-mitre-distilbert-base-uncased-fill-mask
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.9549
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 64
|
| 39 |
+
- eval_batch_size: 64
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: cosine
|
| 43 |
+
- num_epochs: 20
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 2.6456 | 1.0 | 65 | 2.3685 |
|
| 51 |
+
| 2.3833 | 2.0 | 130 | 2.2661 |
|
| 52 |
+
| 2.282 | 3.0 | 195 | 2.2728 |
|
| 53 |
+
| 2.1715 | 4.0 | 260 | 2.1675 |
|
| 54 |
+
| 2.1186 | 5.0 | 325 | 2.1354 |
|
| 55 |
+
| 2.0968 | 6.0 | 390 | 2.0318 |
|
| 56 |
+
| 2.0885 | 7.0 | 455 | 2.1233 |
|
| 57 |
+
| 2.0212 | 8.0 | 520 | 2.0152 |
|
| 58 |
+
| 1.9305 | 9.0 | 585 | 2.0134 |
|
| 59 |
+
| 1.9843 | 10.0 | 650 | 2.0334 |
|
| 60 |
+
| 1.9682 | 11.0 | 715 | 1.9611 |
|
| 61 |
+
| 1.9383 | 12.0 | 780 | 2.0051 |
|
| 62 |
+
| 1.9075 | 13.0 | 845 | 1.9790 |
|
| 63 |
+
| 1.9107 | 14.0 | 910 | 1.9532 |
|
| 64 |
+
| 1.9352 | 15.0 | 975 | 1.9677 |
|
| 65 |
+
| 1.9102 | 16.0 | 1040 | 1.9569 |
|
| 66 |
+
| 1.9065 | 17.0 | 1105 | 1.9143 |
|
| 67 |
+
| 1.8659 | 18.0 | 1170 | 1.9818 |
|
| 68 |
+
| 1.8807 | 19.0 | 1235 | 1.9321 |
|
| 69 |
+
| 1.9088 | 20.0 | 1300 | 1.9549 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.41.2
|
| 75 |
+
- Pytorch 2.3.0+cu121
|
| 76 |
+
- Datasets 2.19.2
|
| 77 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267954768
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32cb8de6b36fbe029064e9d4597e7a58327ca117fc2b832b71e626642d4a6a88
|
| 3 |
size 267954768
|