End of training
Browse files- README.md +20 -8
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,12 +4,25 @@ base_model: bert-base-uncased
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
-
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: ft-bert-with-swag
|
| 12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -19,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss:
|
| 23 |
-
- Accuracy: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -45,15 +58,14 @@ The following hyperparameters were used during training:
|
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
-
- num_epochs:
|
|
|
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
-
|
|
| 55 |
-
| 0.3776 | 2.0 | 4598 | 0.5692 | 0.7986 |
|
| 56 |
-
| 0.1457 | 3.0 | 6897 | 0.7690 | 0.8022 |
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
+
- text-classification
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: ft-bert-with-swag
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Multiple Choice
|
| 15 |
+
type: multiple-choice
|
| 16 |
+
dataset:
|
| 17 |
+
name: swag
|
| 18 |
+
type: text-classification
|
| 19 |
+
config: regular
|
| 20 |
+
split: train[:500]
|
| 21 |
+
args: regular
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.48
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.2843
|
| 36 |
+
- Accuracy: 0.48
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 58 |
- seed: 42
|
| 59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 1
|
| 62 |
+
- mixed_precision_training: Native AMP
|
| 63 |
|
| 64 |
### Training results
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| No log | 1.0 | 13 | 1.2843 | 0.48 |
|
|
|
|
|
|
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437955572
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5771565338e1dbf04b2bfe03d564d095dd748f5b8c9ada1c5ea1b3ec17fbd16d
|
| 3 |
size 437955572
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4155
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e0080780cc0e7e0f2288ea900b4a58540d97b41036f3acf646a8c998dbb389e
|
| 3 |
size 4155
|