pradeepmishra1107
commited on
Commit
•
167b411
1
Parent(s):
a672e7c
End of training
Browse files- README.md +2 -28
- pytorch_model.bin +1 -1
- tokenizer.json +16 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,8 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# model-pradeep-flan-t5-small
|
17 |
|
18 |
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the squad dataset.
|
19 |
-
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.1329
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -42,37 +40,13 @@ 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 | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| No log | 1.0 | 250 |
|
52 |
-
| 2.9785 | 2.0 | 500 | 1.7603 |
|
53 |
-
| 2.9785 | 3.0 | 750 | 1.4722 |
|
54 |
-
| 2.006 | 4.0 | 1000 | 1.3617 |
|
55 |
-
| 2.006 | 5.0 | 1250 | 1.2789 |
|
56 |
-
| 1.6474 | 6.0 | 1500 | 1.2341 |
|
57 |
-
| 1.6474 | 7.0 | 1750 | 1.2316 |
|
58 |
-
| 1.4551 | 8.0 | 2000 | 1.2106 |
|
59 |
-
| 1.4551 | 9.0 | 2250 | 1.1793 |
|
60 |
-
| 1.3309 | 10.0 | 2500 | 1.1819 |
|
61 |
-
| 1.3309 | 11.0 | 2750 | 1.1734 |
|
62 |
-
| 1.2264 | 12.0 | 3000 | 1.1587 |
|
63 |
-
| 1.2264 | 13.0 | 3250 | 1.1433 |
|
64 |
-
| 1.1625 | 14.0 | 3500 | 1.1390 |
|
65 |
-
| 1.1625 | 15.0 | 3750 | 1.1471 |
|
66 |
-
| 1.1101 | 16.0 | 4000 | 1.1345 |
|
67 |
-
| 1.1101 | 17.0 | 4250 | 1.1315 |
|
68 |
-
| 1.055 | 18.0 | 4500 | 1.1458 |
|
69 |
-
| 1.055 | 19.0 | 4750 | 1.1278 |
|
70 |
-
| 1.032 | 20.0 | 5000 | 1.1287 |
|
71 |
-
| 1.032 | 21.0 | 5250 | 1.1417 |
|
72 |
-
| 0.9976 | 22.0 | 5500 | 1.1390 |
|
73 |
-
| 0.9976 | 23.0 | 5750 | 1.1286 |
|
74 |
-
| 1.0106 | 24.0 | 6000 | 1.1336 |
|
75 |
-
| 1.0106 | 25.0 | 6250 | 1.1329 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
|
|
16 |
# model-pradeep-flan-t5-small
|
17 |
|
18 |
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the squad dataset.
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 1
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 250 | 5.1725 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242116870
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:554d33f89c381833cace541802224b330b109e33f371afb905fa68a7a55fb96f
|
3 |
size 242116870
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 384,
|
6 |
+
"strategy": "OnlySecond",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 384
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 0,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<pad>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:067980a05fa77a60ade7de4af71e375c3ffe40b6561544483cba8474c3b5922b
|
3 |
size 4536
|