G-R-A-V-I-T-Y
commited on
Commit
•
27a5696
1
Parent(s):
4c065f5
End of training
Browse files- README.md +26 -8
- adapter_model.safetensors +1 -1
- logs/events.out.tfevents.1717170370.Chris_PC.28696.1 +3 -0
- tokenizer.json +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
-
- Exact Match:
|
21 |
-
- Gen Len:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,14 +43,32 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
-
| Training Loss | Epoch | Step
|
51 |
-
|
52 |
-
|
|
53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7342
|
20 |
+
- Exact Match: 30.9591
|
21 |
+
- Gen Len: 3.6062
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 20
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-----------:|:-------:|
|
52 |
+
| 0.8221 | 1.0 | 4246 | 0.8269 | 20.5823 | 3.8789 |
|
53 |
+
| 0.7459 | 2.0 | 8492 | 0.7917 | 26.3525 | 3.6663 |
|
54 |
+
| 0.7727 | 3.0 | 12738 | 0.7775 | 30.8587 | 3.4217 |
|
55 |
+
| 0.758 | 4.0 | 16984 | 0.7652 | 26.5946 | 3.7380 |
|
56 |
+
| 0.7465 | 5.0 | 21230 | 0.7551 | 28.2601 | 3.6873 |
|
57 |
+
| 0.6693 | 6.0 | 25476 | 0.7524 | 30.0201 | 3.6045 |
|
58 |
+
| 0.6364 | 7.0 | 29722 | 0.7529 | 28.7208 | 3.6432 |
|
59 |
+
| 0.6907 | 8.0 | 33968 | 0.7474 | 29.9965 | 3.6177 |
|
60 |
+
| 0.8167 | 9.0 | 38214 | 0.7400 | 30.528 | 3.5908 |
|
61 |
+
| 0.7631 | 10.0 | 42460 | 0.7407 | 31.095 | 3.5620 |
|
62 |
+
| 0.7106 | 11.0 | 46706 | 0.7374 | 31.3962 | 3.5518 |
|
63 |
+
| 0.7018 | 12.0 | 50952 | 0.7383 | 30.4394 | 3.6223 |
|
64 |
+
| 0.6446 | 13.0 | 55198 | 0.7360 | 29.4354 | 3.6789 |
|
65 |
+
| 0.7872 | 14.0 | 59444 | 0.7355 | 30.2209 | 3.6359 |
|
66 |
+
| 0.8111 | 15.0 | 63690 | 0.7364 | 30.2622 | 3.6182 |
|
67 |
+
| 0.7027 | 16.0 | 67936 | 0.7346 | 29.8429 | 3.6637 |
|
68 |
+
| 0.7077 | 17.0 | 72182 | 0.7371 | 30.5398 | 3.6260 |
|
69 |
+
| 0.7806 | 18.0 | 76428 | 0.7342 | 31.03 | 3.5911 |
|
70 |
+
| 0.762 | 19.0 | 80674 | 0.7354 | 31.095 | 3.6043 |
|
71 |
+
| 0.6805 | 20.0 | 84920 | 0.7342 | 30.9591 | 3.6062 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7098016
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f65cc1a73390191cd078d52107a69347db3739da602527483ce11ab015b85ab
|
3 |
size 7098016
|
logs/events.out.tfevents.1717170370.Chris_PC.28696.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15a1aa2dcb10ed6e0a627a368dbf239c6f5eaf02f2f69b531853e272d3243414
|
3 |
+
size 1833540
|
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 10,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 10
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71e93ce59499b429e73c2cd993db27045ad34c650968d94bc3aaa389c7281edf
|
3 |
size 5304
|