End of training
Browse files- .DS_Store +0 -0
- README.md +11 -7
- model.safetensors +1 -1
- runs/.DS_Store +0 -0
- runs/Apr01_23-56-54_johnathan-MacBook-Air.local/events.out.tfevents.1711987021.johnathan-MacBook-Air.local.8689.17 +2 -2
- runs/Apr01_23-56-54_johnathan-MacBook-Air.local/events.out.tfevents.1712051405.johnathan-MacBook-Air.local.8689.18 +3 -0
.DS_Store
CHANGED
|
Binary files a/.DS_Store and b/.DS_Store differ
|
|
|
README.md
CHANGED
|
@@ -15,12 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
-
|
| 19 |
-
- eval_runtime: 501.5658
|
| 20 |
-
- eval_samples_per_second: 39.811
|
| 21 |
-
- eval_steps_per_second: 4.976
|
| 22 |
-
- epoch: 0.01
|
| 23 |
-
- step: 295
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -39,7 +34,7 @@ More information needed
|
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
-
- learning_rate:
|
| 43 |
- train_batch_size: 8
|
| 44 |
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
|
@@ -47,6 +42,15 @@ The following hyperparameters were used during training:
|
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 3.0
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
### Framework versions
|
| 51 |
|
| 52 |
- Transformers 4.40.0.dev0
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 7.8908
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
- train_batch_size: 8
|
| 39 |
- eval_batch_size: 8
|
| 40 |
- seed: 42
|
|
|
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- num_epochs: 3.0
|
| 44 |
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 0.7267 | 1.0 | 7774 | 7.0874 |
|
| 50 |
+
| 0.3752 | 2.0 | 15548 | 7.5818 |
|
| 51 |
+
| 0.235 | 3.0 | 23322 | 7.8927 |
|
| 52 |
+
|
| 53 |
+
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.40.0.dev0
|
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:be1e252ac72db65e66d0ecdb62ff97fd39d723af116e993e44b52bf399e8d8d7
|
| 3 |
size 327657928
|
runs/.DS_Store
CHANGED
|
Binary files a/runs/.DS_Store and b/runs/.DS_Store differ
|
|
|
runs/Apr01_23-56-54_johnathan-MacBook-Air.local/events.out.tfevents.1711987021.johnathan-MacBook-Air.local.8689.17
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 sha256:4535867875e1ca046753142219f58e454bb96e985d6f92de6c87e24f2b11959b
|
| 3 |
+
size 15935
|
runs/Apr01_23-56-54_johnathan-MacBook-Air.local/events.out.tfevents.1712051405.johnathan-MacBook-Air.local.8689.18
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e788d153016d410cf0f7d1f5d2aa892b3056b29bf079ad422322bb68754c730
|
| 3 |
+
size 364
|