AlexWang99
commited on
Commit
•
afb302f
1
Parent(s):
c974aac
End of training
Browse files
README.md
CHANGED
@@ -1,25 +1,19 @@
|
|
1 |
---
|
2 |
-
base_model: google/byt5-small
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
-
- name:
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
-
#
|
14 |
|
15 |
-
This model
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
-
|
18 |
-
- eval_runtime: 10.7864
|
19 |
-
- eval_samples_per_second: 927.092
|
20 |
-
- eval_steps_per_second: 1.205
|
21 |
-
- epoch: 32.0
|
22 |
-
- step: 64
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,13 +32,39 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
-
- train_batch_size:
|
43 |
- eval_batch_size: 800
|
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 |
### Framework versions
|
50 |
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
model-index:
|
5 |
+
- name: byt5_1k
|
6 |
results: []
|
7 |
---
|
8 |
|
9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
should probably proofread and complete it, then remove this comment. -->
|
11 |
|
12 |
+
# byt5_1k
|
13 |
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.0868
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0001
|
36 |
+
- train_batch_size: 400
|
37 |
- eval_batch_size: 800
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 20
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| No log | 1.0 | 3 | 0.1081 |
|
48 |
+
| No log | 2.0 | 6 | 0.0983 |
|
49 |
+
| No log | 3.0 | 9 | 0.1285 |
|
50 |
+
| 0.1432 | 4.0 | 12 | 0.0961 |
|
51 |
+
| 0.1432 | 5.0 | 15 | 0.1040 |
|
52 |
+
| 0.1432 | 6.0 | 18 | 0.1032 |
|
53 |
+
| 0.1488 | 7.0 | 21 | 0.0938 |
|
54 |
+
| 0.1488 | 8.0 | 24 | 0.0979 |
|
55 |
+
| 0.1488 | 9.0 | 27 | 0.0976 |
|
56 |
+
| 0.1375 | 10.0 | 30 | 0.0885 |
|
57 |
+
| 0.1375 | 11.0 | 33 | 0.0907 |
|
58 |
+
| 0.1375 | 12.0 | 36 | 0.0863 |
|
59 |
+
| 0.1375 | 13.0 | 39 | 0.0843 |
|
60 |
+
| 0.1297 | 14.0 | 42 | 0.0833 |
|
61 |
+
| 0.1297 | 15.0 | 45 | 0.0840 |
|
62 |
+
| 0.1297 | 16.0 | 48 | 0.0861 |
|
63 |
+
| 0.1241 | 17.0 | 51 | 0.0903 |
|
64 |
+
| 0.1241 | 18.0 | 54 | 0.0891 |
|
65 |
+
| 0.1241 | 19.0 | 57 | 0.0876 |
|
66 |
+
| 0.1185 | 20.0 | 60 | 0.0868 |
|
67 |
+
|
68 |
|
69 |
### Framework versions
|
70 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "AlexWang99/byt5_1k",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
logs/events.out.tfevents.1714285176.ip-10-25-205-144.266412.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b21af001fe5158c276dc24fdcff6d1e0b1dc82469343c4470940e188733512fb
|
3 |
+
size 25835
|
logs/events.out.tfevents.1714287609.ip-10-25-205-144.266412.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b94955ee84f5953be16af7990569559175738ccf0ab05b30e1681501329ca62
|
3 |
+
size 20569
|
logs/events.out.tfevents.1714289724.ip-10-25-205-144.266412.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ef606384881afd7ee6220395ef6dd0dab0b554a58bbf2b2d68dcd37ab52ad1c
|
3 |
+
size 11148
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1198571496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1d38312142676df106c129e100839b6de37257ace7652c5df8d40b1aa17cbdb
|
3 |
size 1198571496
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cab6b39dc088aa20d7417697114e95ffad3ae5054465ee82549b2fc0dc90a37d
|
3 |
size 4792
|