Commit
•
2f86a67
1
Parent(s):
259593d
End of training
Browse files
README.md
CHANGED
@@ -3,6 +3,9 @@ license: apache-2.0
|
|
3 |
base_model: distilbert/distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: distilbert-base-uncased-IDMB-sentiment-analysis
|
8 |
results: []
|
@@ -14,6 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# distilbert-base-uncased-IDMB-sentiment-analysis
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -33,16 +40,27 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 5e-05
|
36 |
-
- train_batch_size:
|
37 |
-
- eval_batch_size:
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 8
|
40 |
-
- total_train_batch_size:
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 5
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
### Framework versions
|
47 |
|
48 |
- Transformers 4.38.2
|
|
|
3 |
base_model: distilbert/distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
- accuracy
|
9 |
model-index:
|
10 |
- name: distilbert-base-uncased-IDMB-sentiment-analysis
|
11 |
results: []
|
|
|
17 |
# distilbert-base-uncased-IDMB-sentiment-analysis
|
18 |
|
19 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3468
|
22 |
+
- F1: 0.7745
|
23 |
+
- Accuracy: 0.9373
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
- learning_rate: 5e-05
|
43 |
+
- train_batch_size: 4
|
44 |
+
- eval_batch_size: 4
|
45 |
- seed: 42
|
46 |
- gradient_accumulation_steps: 8
|
47 |
+
- total_train_batch_size: 32
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
- num_epochs: 5
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
|
57 |
+
| 0.239 | 1.0 | 1250 | 0.1846 | 0.7436 | 0.928 |
|
58 |
+
| 0.1181 | 2.0 | 2500 | 0.2053 | 0.7473 | 0.9277 |
|
59 |
+
| 0.0573 | 3.0 | 3750 | 0.2772 | 0.7570 | 0.9327 |
|
60 |
+
| 0.0269 | 4.0 | 5000 | 0.3206 | 0.7706 | 0.9363 |
|
61 |
+
| 0.0127 | 5.0 | 6250 | 0.3468 | 0.7745 | 0.9373 |
|
62 |
+
|
63 |
+
|
64 |
### Framework versions
|
65 |
|
66 |
- Transformers 4.38.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a31091705f9f85c14bc8a3f60270c20bb7c8058e668c41c68f10417982caba31
|
3 |
size 267832560
|
runs/Mar29_06-31-54_ccbf055a8264/events.out.tfevents.1711693915.ccbf055a8264.26.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23935e2f8670cc6615d34e5685039c830414d3eb4283051cd22d818e707e25b0
|
3 |
+
size 7961
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c0f25ba102ccc5877ca78c12501b7ec96c3b4674f1ab205eea55c327e6d9d5
|
3 |
size 4984
|