Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: Hartunka/tiny_bert_km_20_v1
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- spearmanr
|
| 8 |
+
model-index:
|
| 9 |
+
- name: tiny_bert_km_20_v1_stsb
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# tiny_bert_km_20_v1_stsb
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Hartunka/tiny_bert_km_20_v1](https://huggingface.co/Hartunka/tiny_bert_km_20_v1) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.5107
|
| 21 |
+
- Pearson: 0.2682
|
| 22 |
+
- Spearmanr: 0.2598
|
| 23 |
+
- Combined Score: 0.2640
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 5e-05
|
| 43 |
+
- train_batch_size: 256
|
| 44 |
+
- eval_batch_size: 256
|
| 45 |
+
- seed: 10
|
| 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: 50
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
|
| 54 |
+
| 3.6231 | 1.0 | 23 | 2.1600 | 0.2054 | 0.1826 | 0.1940 |
|
| 55 |
+
| 2.0508 | 2.0 | 46 | 2.4199 | 0.1847 | 0.1774 | 0.1811 |
|
| 56 |
+
| 1.9051 | 3.0 | 69 | 2.3382 | 0.2217 | 0.2091 | 0.2154 |
|
| 57 |
+
| 1.7517 | 4.0 | 92 | 2.2891 | 0.2602 | 0.2525 | 0.2563 |
|
| 58 |
+
| 1.5284 | 5.0 | 115 | 2.3172 | 0.2782 | 0.2719 | 0.2750 |
|
| 59 |
+
| 1.3355 | 6.0 | 138 | 2.5107 | 0.2682 | 0.2598 | 0.2640 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.50.2
|
| 65 |
+
- Pytorch 2.2.1+cu121
|
| 66 |
+
- Datasets 2.18.0
|
| 67 |
+
- Tokenizers 0.21.1
|
logs/events.out.tfevents.1744640563.s_005_m.2701049.48
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 sha256:34d13f061685fc79007b62cde3a4e81b9e6695faf0c66b877b675f8c2e9eab23
|
| 3 |
+
size 9158
|