Nisit-Tripathi
commited on
Commit
•
57e124e
1
Parent(s):
1758519
End of training
Browse files- README.md +3 -3
- config.json +2 -1
- generation_config.json +1 -0
- model.safetensors +1 -1
- runs/Feb29_08-59-52_3ac49b49142d/events.out.tfevents.1709197194.3ac49b49142d.237.4 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# t5-small-finetuned-xsum
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
47 |
-
| No log | 1.0 | 7 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: t5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# t5-small-finetuned-xsum
|
15 |
|
16 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
47 |
+
| No log | 1.0 | 7 | 10.9618 | 2.3529 | 1.182 | 2.1176 | 2.3529 | 11.5 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
@@ -9,6 +9,7 @@
|
|
9 |
"d_model": 512,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
|
|
12 |
"dropout_rate": 0.1,
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "relu",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
9 |
"d_model": 512,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
+
"do_sample": true,
|
13 |
"dropout_rate": 0.1,
|
14 |
"eos_token_id": 1,
|
15 |
"feed_forward_proj": "relu",
|
generation_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"decoder_start_token_id": 0,
|
|
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
"transformers_version": "4.38.1"
|
|
|
1 |
{
|
2 |
"decoder_start_token_id": 0,
|
3 |
+
"do_sample": true,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
"transformers_version": "4.38.1"
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ca9fbdf1182af8a77f0321961a397074908a1f3afc060e14c070e0c2c36ae37
|
3 |
size 242041896
|
runs/Feb29_08-59-52_3ac49b49142d/events.out.tfevents.1709197194.3ac49b49142d.237.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d3bebcd5160b8e9b6cf4d5e53c97d14e9186691d3e56f9f361326f75e39a31c
|
3 |
+
size 6448
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3166f65aea834f3a039e2ec7bab4c05550e3a9cc2e7dc09c313dc6ec901e257
|
3 |
size 5048
|