thymiantheherb
commited on
Commit
•
49586e6
1
Parent(s):
32929de
End of training
Browse files- README.md +9 -9
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Bleu: 0.
|
22 |
-
- Bertscore Precision: 0.
|
23 |
-
- Bertscore Recall: 0.
|
24 |
-
- Bertscore F1: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -44,18 +44,18 @@ The following hyperparameters were used during training:
|
|
44 |
- train_batch_size: 8
|
45 |
- eval_batch_size: 8
|
46 |
- seed: 42
|
|
|
|
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
-
- num_epochs:
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------------------:|:----------------:|:------------:|
|
56 |
-
|
|
57 |
-
| 4.0754 | 2.0 | 1288 | 3.8779 | 0.0099 | 0.1498 | 0.1654 | 0.1569 |
|
58 |
-
| 3.8277 | 3.0 | 1932 | 3.8114 | 0.0101 | 0.1499 | 0.1656 | 0.1571 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 4.0665
|
21 |
+
- Bleu: 0.0085
|
22 |
+
- Bertscore Precision: 0.1478
|
23 |
+
- Bertscore Recall: 0.1636
|
24 |
+
- Bertscore F1: 0.1550
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
44 |
- train_batch_size: 8
|
45 |
- eval_batch_size: 8
|
46 |
- seed: 42
|
47 |
+
- gradient_accumulation_steps: 2
|
48 |
+
- total_train_batch_size: 16
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 1
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------------------:|:----------------:|:------------:|
|
58 |
+
| 5.0162 | 1.0 | 3223 | 4.0665 | 0.0085 | 0.1478 | 0.1636 | 0.1550 |
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 327657928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29300574d12fdd5ebc15042cd87ab92c44f018161802c6d5d5d17c1eda221c16
|
3 |
size 327657928
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17db93795a362c9298df2f82088391ff7ea583f9b96abb0f083048e4907e3d2f
|
3 |
size 5048
|