Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: bert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mitre-bert-base-uncased
|
| 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 |
+
# mitre-bert-base-uncased
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.1257
|
| 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: 5e-05
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 100
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 2.0301 | 2.72 | 1000 | 1.6360 |
|
| 50 |
+
| 1.4454 | 5.45 | 2000 | 1.4483 |
|
| 51 |
+
| 1.2259 | 8.17 | 3000 | 1.3658 |
|
| 52 |
+
| 1.0811 | 10.9 | 4000 | 1.2872 |
|
| 53 |
+
| 0.9744 | 13.62 | 5000 | 1.2763 |
|
| 54 |
+
| 0.8601 | 16.35 | 6000 | 1.2343 |
|
| 55 |
+
| 0.7918 | 19.07 | 7000 | 1.1792 |
|
| 56 |
+
| 0.7375 | 21.8 | 8000 | 1.1792 |
|
| 57 |
+
| 0.6806 | 24.52 | 9000 | 1.1332 |
|
| 58 |
+
| 0.6274 | 27.25 | 10000 | 1.1129 |
|
| 59 |
+
| 0.5803 | 29.97 | 11000 | 1.1239 |
|
| 60 |
+
| 0.5403 | 32.7 | 12000 | 1.1224 |
|
| 61 |
+
| 0.5028 | 35.42 | 13000 | 1.1344 |
|
| 62 |
+
| 0.4661 | 38.15 | 14000 | 1.1215 |
|
| 63 |
+
| 0.4463 | 40.87 | 15000 | 1.1453 |
|
| 64 |
+
| 0.4102 | 43.6 | 16000 | 1.0828 |
|
| 65 |
+
| 0.3866 | 46.32 | 17000 | 1.1044 |
|
| 66 |
+
| 0.3749 | 49.05 | 18000 | 1.1199 |
|
| 67 |
+
| 0.3554 | 51.77 | 19000 | 1.0722 |
|
| 68 |
+
| 0.3288 | 54.5 | 20000 | 1.1167 |
|
| 69 |
+
| 0.319 | 57.22 | 21000 | 1.1110 |
|
| 70 |
+
| 0.3064 | 59.95 | 22000 | 1.0821 |
|
| 71 |
+
| 0.2938 | 62.67 | 23000 | 1.0702 |
|
| 72 |
+
| 0.2741 | 65.4 | 24000 | 1.0373 |
|
| 73 |
+
| 0.2626 | 68.12 | 25000 | 1.1236 |
|
| 74 |
+
| 0.2525 | 70.84 | 26000 | 1.0831 |
|
| 75 |
+
| 0.2433 | 73.57 | 27000 | 1.0691 |
|
| 76 |
+
| 0.2376 | 76.29 | 28000 | 1.0647 |
|
| 77 |
+
| 0.2303 | 79.02 | 29000 | 1.0851 |
|
| 78 |
+
| 0.2164 | 81.74 | 30000 | 1.0864 |
|
| 79 |
+
| 0.2103 | 84.47 | 31000 | 1.0502 |
|
| 80 |
+
| 0.2049 | 87.19 | 32000 | 1.0644 |
|
| 81 |
+
| 0.2011 | 89.92 | 33000 | 1.0262 |
|
| 82 |
+
| 0.2024 | 92.64 | 34000 | 1.0738 |
|
| 83 |
+
| 0.1889 | 95.37 | 35000 | 1.0640 |
|
| 84 |
+
| 0.1846 | 98.09 | 36000 | 1.1257 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.38.2
|
| 90 |
+
- Pytorch 2.2.1+cu121
|
| 91 |
+
- Datasets 2.18.0
|
| 92 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.38.2"
|
| 5 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440600140
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea324dc3e69785bfa54c6d0252c5ccdced2e33cc9b9c679e80951bb39c9f0bbc
|
| 3 |
size 440600140
|
runs/Apr09_22-55-12_31568ff91b58/events.out.tfevents.1712703314.31568ff91b58.7415.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27eab9f0f7c40b5b0f9f5a981fac53bf71a809742c9ef2a21a325dea947edfd1
|
| 3 |
+
size 22462
|