G-R-A-V-I-T-Y
commited on
Commit
•
74eb855
1
Parent(s):
71e44dd
End of training
Browse files- README.md +10 -7
- logs/events.out.tfevents.1716406930.Chris_PC.15220.5 +3 -0
- model.safetensors +1 -1
- tokenizer.json +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
-
- Exact Match:
|
20 |
-
- Gen Len:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -42,13 +42,16 @@ The following hyperparameters were used during training:
|
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
-
| Training Loss | Epoch | Step
|
50 |
-
|
51 |
-
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.8087
|
19 |
+
- Exact Match: 17.1569
|
20 |
+
- Gen Len: 4.0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 4
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
|
50 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-----------:|:-------:|
|
51 |
+
| 0.8486 | 1.0 | 4246 | 0.8367 | 30.085 | 3.0 |
|
52 |
+
| 0.8316 | 2.0 | 8492 | 0.8192 | 17.1569 | 4.0 |
|
53 |
+
| 0.8266 | 3.0 | 12738 | 0.8136 | 17.1569 | 4.0 |
|
54 |
+
| 0.818 | 4.0 | 16984 | 0.8087 | 17.1569 | 4.0 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
logs/events.out.tfevents.1716406930.Chris_PC.15220.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ecd06ff79fd58172c8fd5ed020aa2388894e4434ab503d10c3af55586ae74f9
|
3 |
+
size 14677
|
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:d3870a4602bddd8c32b606532b54ac3ff0719c22a29b57fb1e16b9a834c97d64
|
3 |
size 990345064
|
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 sha256:39a43dd6dbc5117c777bb057f2713e2fdd038819a6dfa4f153acecf3f8bc4cca
|
3 |
size 5304
|