End of training
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
base_model: distilbert/distilroberta-base
|
3 |
license: apache-2.0
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,33 +34,63 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate:
|
38 |
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| No log | 1.0 | 199 | 1.
|
50 |
-
| No log | 2.0 | 398 | 1.
|
51 |
-
| 1.
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
-
| 1.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
|
66 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert/distilroberta-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.7996
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 45
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 199 | 1.7128 |
|
50 |
+
| No log | 2.0 | 398 | 1.4856 |
|
51 |
+
| 1.8719 | 3.0 | 597 | 1.3661 |
|
52 |
+
| 1.8719 | 4.0 | 796 | 1.2638 |
|
53 |
+
| 1.8719 | 5.0 | 995 | 1.1847 |
|
54 |
+
| 1.3663 | 6.0 | 1194 | 1.1849 |
|
55 |
+
| 1.3663 | 7.0 | 1393 | 1.1757 |
|
56 |
+
| 1.2108 | 8.0 | 1592 | 1.1026 |
|
57 |
+
| 1.2108 | 9.0 | 1791 | 1.0826 |
|
58 |
+
| 1.2108 | 10.0 | 1990 | 1.0609 |
|
59 |
+
| 1.1079 | 11.0 | 2189 | 1.0221 |
|
60 |
+
| 1.1079 | 12.0 | 2388 | 1.0199 |
|
61 |
+
| 1.0428 | 13.0 | 2587 | 0.9990 |
|
62 |
+
| 1.0428 | 14.0 | 2786 | 1.0083 |
|
63 |
+
| 1.0428 | 15.0 | 2985 | 0.9905 |
|
64 |
+
| 0.9911 | 16.0 | 3184 | 0.9492 |
|
65 |
+
| 0.9911 | 17.0 | 3383 | 0.9526 |
|
66 |
+
| 0.9391 | 18.0 | 3582 | 0.9219 |
|
67 |
+
| 0.9391 | 19.0 | 3781 | 0.9228 |
|
68 |
+
| 0.9391 | 20.0 | 3980 | 0.9183 |
|
69 |
+
| 0.9078 | 21.0 | 4179 | 0.9276 |
|
70 |
+
| 0.9078 | 22.0 | 4378 | 0.8874 |
|
71 |
+
| 0.8727 | 23.0 | 4577 | 0.8856 |
|
72 |
+
| 0.8727 | 24.0 | 4776 | 0.8899 |
|
73 |
+
| 0.8727 | 25.0 | 4975 | 0.8836 |
|
74 |
+
| 0.8513 | 26.0 | 5174 | 0.8790 |
|
75 |
+
| 0.8513 | 27.0 | 5373 | 0.8835 |
|
76 |
+
| 0.8145 | 28.0 | 5572 | 0.8583 |
|
77 |
+
| 0.8145 | 29.0 | 5771 | 0.8498 |
|
78 |
+
| 0.8145 | 30.0 | 5970 | 0.8530 |
|
79 |
+
| 0.8085 | 31.0 | 6169 | 0.8409 |
|
80 |
+
| 0.8085 | 32.0 | 6368 | 0.8196 |
|
81 |
+
| 0.7783 | 33.0 | 6567 | 0.8311 |
|
82 |
+
| 0.7783 | 34.0 | 6766 | 0.8301 |
|
83 |
+
| 0.7783 | 35.0 | 6965 | 0.8370 |
|
84 |
+
| 0.7639 | 36.0 | 7164 | 0.8321 |
|
85 |
+
| 0.7639 | 37.0 | 7363 | 0.8226 |
|
86 |
+
| 0.757 | 38.0 | 7562 | 0.8361 |
|
87 |
+
| 0.757 | 39.0 | 7761 | 0.8236 |
|
88 |
+
| 0.757 | 40.0 | 7960 | 0.8255 |
|
89 |
+
| 0.7483 | 41.0 | 8159 | 0.8305 |
|
90 |
+
| 0.7483 | 42.0 | 8358 | 0.8057 |
|
91 |
+
| 0.7449 | 43.0 | 8557 | 0.8251 |
|
92 |
+
| 0.7449 | 44.0 | 8756 | 0.8014 |
|
93 |
+
| 0.7449 | 45.0 | 8955 | 0.7996 |
|
94 |
|
95 |
|
96 |
### Framework versions
|
runs/Jul16_07-53-18_97432323c9b1/events.out.tfevents.1721116400.97432323c9b1.282.0
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 sha256:5123eeffe33a40cdd69becf619c82e8d3ad9dc3177279ba5a791a8c42c9dfeb7
|
3 |
+
size 20959
|