End of training
Browse files- README.md +28 -1
- logs/events.out.tfevents.1697991938.7d63e3e09e40.959.0 +2 -2
- tokenizer.json +16 -2
README.md
CHANGED
|
@@ -4,9 +4,24 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- banking77
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: '11'
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,6 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# 11
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the banking77 dataset.
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -42,6 +60,15 @@ The following hyperparameters were used during training:
|
|
| 42 |
- num_epochs: 3
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
### Framework versions
|
| 46 |
|
| 47 |
- Transformers 4.27.1
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- banking77
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
model-index:
|
| 10 |
- name: '11'
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: banking77
|
| 17 |
+
type: banking77
|
| 18 |
+
config: default
|
| 19 |
+
split: test
|
| 20 |
+
args: default
|
| 21 |
+
metrics:
|
| 22 |
+
- name: F1
|
| 23 |
+
type: f1
|
| 24 |
+
value: 0.9326943887584157
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
# 11
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the banking77 dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2929
|
| 35 |
+
- F1: 0.9327
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
|
|
| 60 |
- num_epochs: 3
|
| 61 |
- mixed_precision_training: Native AMP
|
| 62 |
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 67 |
+
| 1.0651 | 1.0 | 626 | 0.7680 | 0.8465 |
|
| 68 |
+
| 0.3787 | 2.0 | 1252 | 0.3515 | 0.9241 |
|
| 69 |
+
| 0.1742 | 3.0 | 1878 | 0.2929 | 0.9327 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
- Transformers 4.27.1
|
logs/events.out.tfevents.1697991938.7d63e3e09e40.959.0
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 sha256:06c052472de89a2990d86314182d968ca5b81663aa11473a7b6de05ef3749898
|
| 3 |
+
size 11969
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|