End of training
Browse files- README.md +20 -2
- pytorch_model.bin +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
language:
|
3 |
-
-
|
4 |
license: other
|
5 |
tags:
|
6 |
- generated_from_trainer
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# facebook/opt-125m-tldr
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the CarperAI/openai_summarize_tldr dataset.
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,10 +41,26 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
-
|
43 |
|
44 |
### Training results
|
45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
|
|
1 |
---
|
2 |
language:
|
3 |
+
- en
|
4 |
license: other
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
15 |
# facebook/opt-125m-tldr
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the CarperAI/openai_summarize_tldr dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.6296
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 1
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 2.7992 | 0.07 | 1000 | 2.7158 |
|
51 |
+
| 2.7437 | 0.14 | 2000 | 2.6938 |
|
52 |
+
| 2.732 | 0.21 | 3000 | 2.6797 |
|
53 |
+
| 2.7157 | 0.27 | 4000 | 2.6691 |
|
54 |
+
| 2.7071 | 0.34 | 5000 | 2.6620 |
|
55 |
+
| 2.6998 | 0.41 | 6000 | 2.6557 |
|
56 |
+
| 2.696 | 0.48 | 7000 | 2.6495 |
|
57 |
+
| 2.6902 | 0.55 | 8000 | 2.6451 |
|
58 |
+
| 2.6791 | 0.62 | 9000 | 2.6408 |
|
59 |
+
| 2.6823 | 0.69 | 10000 | 2.6379 |
|
60 |
+
| 2.6806 | 0.75 | 11000 | 2.6345 |
|
61 |
+
| 2.6746 | 0.82 | 12000 | 2.6330 |
|
62 |
+
| 2.6765 | 0.89 | 13000 | 2.6306 |
|
63 |
+
| 2.6738 | 0.96 | 14000 | 2.6296 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 501023389
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3e240e5a0a9456928cf328599fbe150d45ab9e357007f88b4ff51475f8552d0
|
3 |
size 501023389
|
training_args.bin
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 sha256:1b32937976471d534caba5f4110be1b43b782d31a91640b5d537296ce917b550
|
3 |
+
size 3579
|