sherif1311
commited on
Commit
•
27b1691
1
Parent(s):
214ec4f
End of training
Browse files
README.md
CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- F1: 99.
|
22 |
-
- Gen Len: 2.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -44,13 +44,17 @@ The following hyperparameters were used during training:
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- num_epochs:
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Gen Len |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
53 |
-
| 0.
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0042
|
21 |
+
- F1: 99.8333
|
22 |
+
- Gen Len: 2.3317
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 5
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Gen Len |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
53 |
+
| 0.014 | 1.0 | 675 | 0.0119 | 99.6662 | 2.335 |
|
54 |
+
| 0.0065 | 2.0 | 1350 | 0.0042 | 99.8333 | 2.3317 |
|
55 |
+
| 0.0 | 3.0 | 2025 | 0.0017 | 99.8333 | 2.3317 |
|
56 |
+
| 0.0 | 4.0 | 2700 | 0.0017 | 99.8333 | 2.3317 |
|
57 |
+
| 0.0 | 5.0 | 3375 | 0.0017 | 99.8333 | 2.3317 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
logs/events.out.tfevents.1720876011.nqu3lrojcj.821.2
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 sha256:2ef313a2dc617d0a2a29745b5df257ef1889257dcf14c24797a1ebec539fc62d
|
3 |
+
size 9218
|
logs/events.out.tfevents.1720878991.nqu3lrojcj.821.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8e1af967626090c21baec846e4f5a5c9bb5139c16b15544e938e0437905af53
|
3 |
+
size 456
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990345064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c080ab3f7b1e45f4ad8ccd5beb4892c6301ddeddbc607b12353020a4420b2267
|
3 |
size 990345064
|
tokenizer.json
CHANGED
@@ -1,14 +1,9 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 3,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": {
|
5 |
"strategy": {
|
6 |
+
"Fixed": 512
|
7 |
},
|
8 |
"direction": "Right",
|
9 |
"pad_to_multiple_of": null,
|