Model save
Browse files
README.md
CHANGED
@@ -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/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 3.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,42 +34,38 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate: 0.
|
38 |
- train_batch_size: 16
|
39 |
- eval_batch_size: 32
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 500
|
44 |
-
-
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
-
| 5.
|
51 |
-
| 4.
|
52 |
-
| 4.
|
53 |
-
| 4.
|
54 |
-
| 4.
|
55 |
-
| 3.
|
56 |
-
| 3.
|
57 |
-
| 3.
|
58 |
-
| 3.
|
59 |
-
| 3.
|
60 |
-
| 3.
|
61 |
-
| 3.
|
62 |
-
| 3.
|
63 |
-
| 3.
|
64 |
-
| 3.
|
65 |
-
| 3.
|
66 |
-
| 3.
|
67 |
-
| 3.
|
68 |
-
| 3.
|
69 |
-
| 3.0586 | 4.19 | 20000 | 3.7184 |
|
70 |
-
| 3.0485 | 4.4 | 21000 | 3.7085 |
|
71 |
-
| 3.0446 | 4.61 | 22000 | 3.7014 |
|
72 |
-
| 3.0407 | 4.82 | 23000 | 3.6959 |
|
73 |
|
74 |
|
75 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.6213
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.001
|
38 |
- train_batch_size: 16
|
39 |
- eval_batch_size: 32
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 500
|
44 |
+
- training_steps: 19000
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 5.7274 | 0.21 | 1000 | 4.9308 |
|
51 |
+
| 4.7191 | 0.42 | 2000 | 4.5347 |
|
52 |
+
| 4.4579 | 0.63 | 3000 | 4.3432 |
|
53 |
+
| 4.2769 | 0.84 | 4000 | 4.1893 |
|
54 |
+
| 4.1086 | 1.05 | 5000 | 4.0861 |
|
55 |
+
| 3.9327 | 1.26 | 6000 | 3.9992 |
|
56 |
+
| 3.8812 | 1.47 | 7000 | 3.9216 |
|
57 |
+
| 3.8298 | 1.68 | 8000 | 3.8648 |
|
58 |
+
| 3.7785 | 1.89 | 9000 | 3.8126 |
|
59 |
+
| 3.6099 | 2.1 | 10000 | 3.7931 |
|
60 |
+
| 3.471 | 2.31 | 11000 | 3.7539 |
|
61 |
+
| 3.4651 | 2.52 | 12000 | 3.7141 |
|
62 |
+
| 3.4451 | 2.73 | 13000 | 3.6754 |
|
63 |
+
| 3.4251 | 2.94 | 14000 | 3.6327 |
|
64 |
+
| 3.1855 | 3.15 | 15000 | 3.6779 |
|
65 |
+
| 3.0962 | 3.36 | 16000 | 3.6757 |
|
66 |
+
| 3.0971 | 3.56 | 17000 | 3.6437 |
|
67 |
+
| 3.0816 | 3.77 | 18000 | 3.6287 |
|
68 |
+
| 3.0582 | 3.98 | 19000 | 3.6213 |
|
|
|
|
|
|
|
|
|
69 |
|
70 |
|
71 |
### 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:b7c7c6ac303206d745901d30f6a267247424b82b8898df54484ea329b67a92a5
|
3 |
size 327657928
|
runs/Mar30_20-39-35_gweltaz-NUC10i7FNK/events.out.tfevents.1711827585.gweltaz-NUC10i7FNK
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:d688021a3a593912cd02419fe1640aef650dbd8a831b1982199ef73d82542ba1
|
3 |
+
size 14444
|