End of training
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -42,13 +42,22 @@ The following hyperparameters were used during training:
|
|
42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
43 |
- lr_scheduler_type: linear
|
44 |
- lr_scheduler_warmup_steps: 500
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
-
| Training Loss | Epoch | Step
|
50 |
-
|
51 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0074
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
43 |
- lr_scheduler_type: linear
|
44 |
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 10
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
51 |
+
| 0.0284 | 1.0 | 3944 | 0.0180 |
|
52 |
+
| 0.001 | 2.0 | 7888 | 0.0245 |
|
53 |
+
| 0.0007 | 3.0 | 11832 | 0.0268 |
|
54 |
+
| 0.002 | 4.0 | 15776 | 0.0227 |
|
55 |
+
| 0.0006 | 5.0 | 19720 | 0.0131 |
|
56 |
+
| 0.0008 | 6.0 | 23664 | 0.0108 |
|
57 |
+
| 0.0006 | 7.0 | 27608 | 0.0084 |
|
58 |
+
| 0.0001 | 8.0 | 31552 | 0.0105 |
|
59 |
+
| 0.0001 | 9.0 | 35496 | 0.0089 |
|
60 |
+
| 0.0 | 10.0 | 39440 | 0.0074 |
|
61 |
|
62 |
|
63 |
### Framework versions
|