Commit ·
88c9986
1
Parent(s): 476f764
End of training
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# run_opt
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -45,30 +45,13 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_steps: 100
|
| 48 |
-
- num_epochs:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
-
| 7.
|
| 55 |
-
| 4.9321 | 1.1 | 200 | 2.1585 |
|
| 56 |
-
| 1.0026 | 1.65 | 300 | 0.3947 |
|
| 57 |
-
| 0.2259 | 2.2 | 400 | 0.1365 |
|
| 58 |
-
| 0.0801 | 2.75 | 500 | 0.0636 |
|
| 59 |
-
| 0.0369 | 3.29 | 600 | 0.0379 |
|
| 60 |
-
| 0.0212 | 3.84 | 700 | 0.0271 |
|
| 61 |
-
| 0.0135 | 4.39 | 800 | 0.0216 |
|
| 62 |
-
| 0.0103 | 4.94 | 900 | 0.0183 |
|
| 63 |
-
| 0.0077 | 5.49 | 1000 | 0.0163 |
|
| 64 |
-
| 0.0068 | 6.04 | 1100 | 0.0153 |
|
| 65 |
-
| 0.0057 | 6.59 | 1200 | 0.0147 |
|
| 66 |
-
| 0.0053 | 7.14 | 1300 | 0.0142 |
|
| 67 |
-
| 0.0048 | 7.69 | 1400 | 0.0140 |
|
| 68 |
-
| 0.0046 | 8.24 | 1500 | 0.0138 |
|
| 69 |
-
| 0.0045 | 8.79 | 1600 | 0.0137 |
|
| 70 |
-
| 0.0044 | 9.33 | 1700 | 0.0137 |
|
| 71 |
-
| 0.0044 | 9.88 | 1800 | 0.0137 |
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: bert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
|
|
| 15 |
|
| 16 |
# run_opt
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the wikitext dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 6.4719
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_steps: 100
|
| 48 |
+
- num_epochs: 1
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 7.7122 | 0.55 | 100 | 6.4719 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|