Commit
•
bd4e8d1
1
Parent(s):
90cd637
End of training
Browse files
README.md
CHANGED
|
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: dadashzadeh/tiny-bert-Sentiment-persian
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
metrics:
|
| 7 |
-
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: tiny-bert-Sentiment-persian
|
| 10 |
results: []
|
|
@@ -16,9 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# tiny-bert-Sentiment-persian
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [dadashzadeh/tiny-bert-Sentiment-persian](https://huggingface.co/dadashzadeh/tiny-bert-Sentiment-persian) on an unknown dataset.
|
| 19 |
-
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.6505
|
| 21 |
-
- Accuracy: 0.7430
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -38,26 +33,12 @@ More information needed
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 2e-05
|
| 41 |
-
- train_batch_size:
|
| 42 |
-
- eval_batch_size:
|
| 43 |
-
- seed:
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
- num_epochs:
|
| 47 |
-
|
| 48 |
-
### Training results
|
| 49 |
-
|
| 50 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
-
| 0.6005 | 1.0 | 716 | 0.6749 | 0.7257 |
|
| 53 |
-
| 0.6088 | 2.0 | 1432 | 0.6620 | 0.7356 |
|
| 54 |
-
| 0.6056 | 3.0 | 2148 | 0.6506 | 0.7464 |
|
| 55 |
-
| 0.6029 | 4.0 | 2864 | 0.6562 | 0.7382 |
|
| 56 |
-
| 0.6032 | 5.0 | 3580 | 0.6517 | 0.7404 |
|
| 57 |
-
| 0.6024 | 6.0 | 4296 | 0.6458 | 0.7469 |
|
| 58 |
-
| 0.6 | 7.0 | 5012 | 0.6458 | 0.7482 |
|
| 59 |
-
| 0.6065 | 8.0 | 5728 | 0.6505 | 0.7430 |
|
| 60 |
-
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
|
|
|
| 3 |
base_model: dadashzadeh/tiny-bert-Sentiment-persian
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: tiny-bert-Sentiment-persian
|
| 8 |
results: []
|
|
|
|
| 14 |
# tiny-bert-Sentiment-persian
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [dadashzadeh/tiny-bert-Sentiment-persian](https://huggingface.co/dadashzadeh/tiny-bert-Sentiment-persian) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 2e-05
|
| 36 |
+
- train_batch_size: 22
|
| 37 |
+
- eval_batch_size: 22
|
| 38 |
+
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 11
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
### Framework versions
|
| 44 |
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17549828
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e14251c8989cee1f43a2393b79145bc166e8b2dbbb14a6303a2e22a2fa975347
|
| 3 |
size 17549828
|
runs/Jul11_01-46-24_0acce8ee3931/events.out.tfevents.1720662387.0acce8ee3931.378.18
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bdcba405dab734e291986eccb7bc7d5a272351c7e31a2c0801664dd9a775382
|
| 3 |
+
size 11831
|
runs/Jul11_01-46-24_0acce8ee3931/events.out.tfevents.1720662906.0acce8ee3931.378.19
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:021593a82dc9183eabc8ab309d8108e1bfa8eb85786e523ae4c712440e8b6de6
|
| 3 |
+
size 411
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fc80810f6c72c14ab6e9a1d75574ee1224c9fa41a516421f63247949e9fbc61
|
| 3 |
size 5112
|