Model save
Browse files
README.md
CHANGED
@@ -15,12 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
19 |
-
- eval_runtime: 137.9044
|
20 |
-
- eval_samples_per_second: 78.199
|
21 |
-
- eval_steps_per_second: 4.887
|
22 |
-
- epoch: 1.0
|
23 |
-
- step: 5533
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -45,11 +40,22 @@ 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 |
### Framework versions
|
51 |
|
52 |
-
- Transformers 4.
|
53 |
-
- Pytorch 2.3.
|
54 |
-
- Datasets 2.
|
55 |
- Tokenizers 0.19.1
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.1104
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 5
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 12 | 4.5451 |
|
50 |
+
| No log | 2.0 | 24 | 3.0979 |
|
51 |
+
| No log | 3.0 | 36 | 2.4605 |
|
52 |
+
| No log | 4.0 | 48 | 2.1931 |
|
53 |
+
| No log | 5.0 | 60 | 2.1104 |
|
54 |
+
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
+
- Transformers 4.42.4
|
59 |
+
- Pytorch 2.3.1+cu121
|
60 |
+
- Datasets 2.21.0
|
61 |
- Tokenizers 0.19.1
|