update model card README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss:
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -34,11 +34,9 @@ More information needed
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 0.0001
|
37 |
-
- train_batch_size:
|
38 |
-
- eval_batch_size:
|
39 |
- seed: 42
|
40 |
-
- gradient_accumulation_steps: 8
|
41 |
-
- total_train_batch_size: 256
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -47,23 +45,13 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
-
| Training Loss | Epoch | Step
|
51 |
-
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
| 2.7413 | 1.92 | 3000 | 2.5568 |
|
58 |
-
| 2.5181 | 2.24 | 3500 | 2.4281 |
|
59 |
-
| 2.394 | 2.56 | 4000 | 2.3263 |
|
60 |
-
| 2.3157 | 2.88 | 4500 | 2.2393 |
|
61 |
-
| 2.1822 | 3.2 | 5000 | 2.1750 |
|
62 |
-
| 2.091 | 3.52 | 5500 | 2.1231 |
|
63 |
-
| 2.0489 | 3.84 | 6000 | 2.0844 |
|
64 |
-
| 1.9873 | 4.16 | 6500 | 2.0609 |
|
65 |
-
| 1.9335 | 4.48 | 7000 | 2.0487 |
|
66 |
-
| 1.9307 | 4.8 | 7500 | 2.0437 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.7110
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 128
|
38 |
+
- eval_batch_size: 256
|
39 |
- seed: 42
|
|
|
|
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: cosine
|
42 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 3.7436 | 1.0 | 12796 | 2.5429 |
|
51 |
+
| 2.3292 | 2.0 | 25592 | 2.0711 |
|
52 |
+
| 1.9439 | 3.0 | 38388 | 1.8447 |
|
53 |
+
| 1.7059 | 4.0 | 51184 | 1.7325 |
|
54 |
+
| 1.5775 | 5.0 | 63980 | 1.7110 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|