liuyanchen1015
commited on
Commit
•
dee7adb
1
Parent(s):
ecadf54
update model card README.md
Browse files
README.md
CHANGED
@@ -3,19 +3,19 @@ license: mit
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
-
- name: mnli_IndE
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
-
# mnli_IndE
|
14 |
|
15 |
This model is a fine-tuned version of [WillHeld/roberta-base-mnli](https://huggingface.co/WillHeld/roberta-base-mnli) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
-
- Acc: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,29 +40,41 @@ The following hyperparameters were used during training:
|
|
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 | Acc |
|
48 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
+
- name: roberta-base-mnli_IndE
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
+
# roberta-base-mnli_IndE
|
14 |
|
15 |
This model is a fine-tuned version of [WillHeld/roberta-base-mnli](https://huggingface.co/WillHeld/roberta-base-mnli) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.7633
|
18 |
+
- Acc: 0.8517
|
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 | Acc |
|
48 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
49 |
+
| 0.3903 | 0.17 | 2000 | 0.4502 | 0.8359 |
|
50 |
+
| 0.3776 | 0.33 | 4000 | 0.4488 | 0.8378 |
|
51 |
+
| 0.3694 | 0.5 | 6000 | 0.4400 | 0.8408 |
|
52 |
+
| 0.3679 | 0.67 | 8000 | 0.4412 | 0.8395 |
|
53 |
+
| 0.3584 | 0.83 | 10000 | 0.4079 | 0.8514 |
|
54 |
+
| 0.3618 | 1.0 | 12000 | 0.4326 | 0.8433 |
|
55 |
+
| 0.2582 | 1.17 | 14000 | 0.4738 | 0.8459 |
|
56 |
+
| 0.2603 | 1.33 | 16000 | 0.4921 | 0.8468 |
|
57 |
+
| 0.2608 | 1.5 | 18000 | 0.4542 | 0.8498 |
|
58 |
+
| 0.2591 | 1.67 | 20000 | 0.4709 | 0.8483 |
|
59 |
+
| 0.263 | 1.83 | 22000 | 0.4955 | 0.8466 |
|
60 |
+
| 0.2611 | 2.0 | 24000 | 0.4829 | 0.8513 |
|
61 |
+
| 0.1802 | 2.17 | 26000 | 0.5470 | 0.8493 |
|
62 |
+
| 0.1819 | 2.33 | 28000 | 0.5523 | 0.8503 |
|
63 |
+
| 0.1847 | 2.5 | 30000 | 0.5160 | 0.8519 |
|
64 |
+
| 0.1886 | 2.67 | 32000 | 0.5229 | 0.8521 |
|
65 |
+
| 0.1877 | 2.83 | 34000 | 0.5024 | 0.8528 |
|
66 |
+
| 0.1839 | 3.0 | 36000 | 0.5456 | 0.8536 |
|
67 |
+
| 0.1322 | 3.17 | 38000 | 0.6997 | 0.8492 |
|
68 |
+
| 0.1385 | 3.33 | 40000 | 0.6212 | 0.8534 |
|
69 |
+
| 0.1326 | 3.5 | 42000 | 0.6629 | 0.8529 |
|
70 |
+
| 0.1355 | 3.67 | 44000 | 0.6448 | 0.8516 |
|
71 |
+
| 0.1332 | 3.83 | 46000 | 0.6411 | 0.8544 |
|
72 |
+
| 0.1372 | 4.0 | 48000 | 0.6574 | 0.8526 |
|
73 |
+
| 0.1056 | 4.17 | 50000 | 0.7427 | 0.8529 |
|
74 |
+
| 0.1053 | 4.33 | 52000 | 0.7466 | 0.8518 |
|
75 |
+
| 0.1062 | 4.5 | 54000 | 0.7734 | 0.8536 |
|
76 |
+
| 0.1056 | 4.67 | 56000 | 0.7623 | 0.8518 |
|
77 |
+
| 0.1072 | 4.83 | 58000 | 0.7633 | 0.8517 |
|
78 |
|
79 |
|
80 |
### Framework versions
|