End of training
Browse files- README.md +16 -18
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
base_model: t5-small
|
6 |
datasets:
|
7 |
- bills-summarization
|
8 |
metrics:
|
@@ -11,31 +11,29 @@ model-index:
|
|
11 |
- name: ft-t5-with-dill-sum
|
12 |
results:
|
13 |
- task:
|
14 |
-
type: summarization
|
15 |
name: Summarization
|
|
|
16 |
dataset:
|
17 |
name: billsum
|
18 |
type: bills-summarization
|
19 |
metrics:
|
20 |
-
-
|
21 |
-
|
22 |
-
|
23 |
---
|
24 |
|
25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
should probably proofread and complete it, then remove this comment. -->
|
27 |
|
28 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wit2024/Fine-tuning%20Distilbert%28t5%29/runs/78e1ikhm)
|
29 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wit2024/Fine-tuning%20Distilbert%28t5%29/runs/78e1ikhm)
|
30 |
# ft-t5-with-dill-sum
|
31 |
|
32 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
35 |
-
- Rouge1: 0.
|
36 |
-
- Rouge2: 0.
|
37 |
-
- Rougel: 0.
|
38 |
-
- Rougelsum: 0.
|
39 |
- Gen Len: 19.0
|
40 |
|
41 |
## Model description
|
@@ -68,16 +66,16 @@ The following hyperparameters were used during training:
|
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
70 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
79 |
|
80 |
-
- Transformers 4.41.
|
81 |
- Pytorch 2.3.0+cu121
|
82 |
- Datasets 2.19.1
|
83 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: t5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
datasets:
|
7 |
- bills-summarization
|
8 |
metrics:
|
|
|
11 |
- name: ft-t5-with-dill-sum
|
12 |
results:
|
13 |
- task:
|
|
|
14 |
name: Summarization
|
15 |
+
type: summarization
|
16 |
dataset:
|
17 |
name: billsum
|
18 |
type: bills-summarization
|
19 |
metrics:
|
20 |
+
- name: Rouge1
|
21 |
+
type: rouge
|
22 |
+
value: 0.0569
|
23 |
---
|
24 |
|
25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
should probably proofread and complete it, then remove this comment. -->
|
27 |
|
|
|
|
|
28 |
# ft-t5-with-dill-sum
|
29 |
|
30 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
|
31 |
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 6.9407
|
33 |
+
- Rouge1: 0.0569
|
34 |
+
- Rouge2: 0.0174
|
35 |
+
- Rougel: 0.05
|
36 |
+
- Rougelsum: 0.0501
|
37 |
- Gen Len: 19.0
|
38 |
|
39 |
## Model description
|
|
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
69 |
+
| 7.6259 | 1.0 | 62 | 7.2486 | 0.0458 | 0.0123 | 0.0417 | 0.0415 | 19.0 |
|
70 |
+
| 7.5212 | 2.0 | 124 | 7.0977 | 0.051 | 0.0143 | 0.0461 | 0.0461 | 19.0 |
|
71 |
+
| 7.3879 | 3.0 | 186 | 7.0064 | 0.0567 | 0.0176 | 0.0507 | 0.0507 | 19.0 |
|
72 |
+
| 7.2066 | 4.0 | 248 | 6.9585 | 0.0565 | 0.0173 | 0.05 | 0.0501 | 19.0 |
|
73 |
+
| 7.1841 | 5.0 | 310 | 6.9407 | 0.0569 | 0.0174 | 0.05 | 0.0501 | 19.0 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
77 |
|
78 |
+
- Transformers 4.41.1
|
79 |
- Pytorch 2.3.0+cu121
|
80 |
- Datasets 2.19.1
|
81 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -55,7 +55,7 @@
|
|
55 |
}
|
56 |
},
|
57 |
"torch_dtype": "float32",
|
58 |
-
"transformers_version": "4.41.
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 32128
|
61 |
}
|
|
|
55 |
}
|
56 |
},
|
57 |
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.41.1",
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 32128
|
61 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
-
"transformers_version": "4.41.
|
6 |
}
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.41.1"
|
6 |
}
|
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 sha256:88f6a6719aa9be96e39aad5384c4cda64d9d4a07fddbf45dfa98a058b1dfa26f
|
3 |
size 242041896
|
training_args.bin
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:b6370480b4fe6f1308bbfdec10e9ff54161b76a807804ef3002ee25da6d587b5
|
3 |
+
size 5240
|