nestorgonzalovich
commited on
Commit
•
c321630
1
Parent(s):
aff7d42
update model card README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 0.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -41,20 +41,28 @@ The following hyperparameters were used during training:
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: cosine
|
43 |
- lr_scheduler_warmup_steps: 400
|
44 |
-
- num_epochs:
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
-
| Training Loss | Epoch | Step
|
50 |
-
|
51 |
-
|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.4267
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: cosine
|
43 |
- lr_scheduler_warmup_steps: 400
|
44 |
+
- num_epochs: 10
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
51 |
+
| 0.5187 | 0.65 | 1000 | 0.6013 |
|
52 |
+
| 0.4429 | 1.31 | 2000 | 0.5585 |
|
53 |
+
| 0.3791 | 1.96 | 3000 | 0.5298 |
|
54 |
+
| 0.3316 | 2.62 | 4000 | 0.5153 |
|
55 |
+
| 0.2991 | 3.27 | 5000 | 0.5025 |
|
56 |
+
| 0.3066 | 3.93 | 6000 | 0.4808 |
|
57 |
+
| 0.2795 | 4.58 | 7000 | 0.4675 |
|
58 |
+
| 0.2599 | 5.24 | 8000 | 0.4594 |
|
59 |
+
| 0.2432 | 5.89 | 9000 | 0.4460 |
|
60 |
+
| 0.2282 | 6.54 | 10000 | 0.4431 |
|
61 |
+
| 0.2167 | 7.2 | 11000 | 0.4381 |
|
62 |
+
| 0.2075 | 7.85 | 12000 | 0.4291 |
|
63 |
+
| 0.2013 | 8.51 | 13000 | 0.4307 |
|
64 |
+
| 0.1977 | 9.16 | 14000 | 0.4266 |
|
65 |
+
| 0.1951 | 9.82 | 15000 | 0.4267 |
|
66 |
|
67 |
|
68 |
### Framework versions
|