DiwasDiwas
commited on
Commit
•
68e58da
1
Parent(s):
4a60e64
DiwasDiwas/t5-small-MedicoSummarizer
Browse files- README.md +22 -18
- all_results.json +10 -10
- model.safetensors +1 -1
- runs/Dec20_03-30-55_ef67406028e0/events.out.tfevents.1703043056.ef67406028e0.513.0 +3 -0
- runs/Dec20_03-30-55_ef67406028e0/events.out.tfevents.1703058313.ef67406028e0.513.1 +3 -0
- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -4
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,19 +15,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# t5-small-MedicoSummarizer
|
17 |
|
18 |
-
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 2.
|
21 |
-
- Rouge1: 0.
|
22 |
-
- Rouge2: 0.
|
23 |
-
- Rougel: 0.
|
24 |
-
- Rougelsum: 0.
|
25 |
-
- Gen Len: 123.
|
26 |
|
27 |
## Model description
|
28 |
|
29 |
-
|
30 |
-
So, you should rather load it on the pipeline and just try it !
|
31 |
|
32 |
## Intended uses & limitations
|
33 |
|
@@ -48,23 +47,28 @@ The following hyperparameters were used during training:
|
|
48 |
- seed: 42
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
-
- num_epochs:
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
-
| Training Loss | Epoch | Step
|
57 |
-
|
58 |
-
| 3.
|
59 |
-
| 3.
|
60 |
-
| 3.
|
61 |
-
| 3.
|
62 |
-
| 3.
|
|
|
|
|
|
|
|
|
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
- Transformers 4.35.2
|
68 |
-
- Pytorch 2.1.0+
|
69 |
- Datasets 2.15.0
|
70 |
- Tokenizers 0.15.0
|
|
|
15 |
|
16 |
# t5-small-MedicoSummarizer
|
17 |
|
18 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.8533
|
21 |
+
- Rouge1: 0.3234
|
22 |
+
- Rouge2: 0.0787
|
23 |
+
- Rougel: 0.1967
|
24 |
+
- Rougelsum: 0.1965
|
25 |
+
- Gen Len: 123.98
|
26 |
|
27 |
## Model description
|
28 |
|
29 |
+
More information needed
|
|
|
30 |
|
31 |
## Intended uses & limitations
|
32 |
|
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 10
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
57 |
+
| 3.2353 | 1.0 | 1563 | 2.9967 | 0.3034 | 0.0717 | 0.1837 | 0.1836 | 117.308 |
|
58 |
+
| 3.1623 | 2.0 | 3126 | 2.9421 | 0.3178 | 0.0763 | 0.1941 | 0.1941 | 121.529 |
|
59 |
+
| 3.1149 | 3.0 | 4689 | 2.9152 | 0.3223 | 0.078 | 0.1964 | 0.1964 | 123.223 |
|
60 |
+
| 3.1038 | 4.0 | 6252 | 2.8929 | 0.3245 | 0.0793 | 0.1979 | 0.1978 | 123.491 |
|
61 |
+
| 3.0728 | 5.0 | 7815 | 2.8802 | 0.3227 | 0.0777 | 0.1973 | 0.1972 | 123.6 |
|
62 |
+
| 3.0592 | 6.0 | 9378 | 2.8714 | 0.3213 | 0.0788 | 0.1966 | 0.1965 | 123.604 |
|
63 |
+
| 3.0448 | 7.0 | 10941 | 2.8635 | 0.3211 | 0.0776 | 0.1959 | 0.1957 | 123.632 |
|
64 |
+
| 3.0416 | 8.0 | 12504 | 2.8561 | 0.3204 | 0.0777 | 0.1957 | 0.1955 | 123.851 |
|
65 |
+
| 3.0324 | 9.0 | 14067 | 2.8548 | 0.3237 | 0.0788 | 0.1965 | 0.1963 | 123.934 |
|
66 |
+
| 3.0375 | 10.0 | 15630 | 2.8533 | 0.3234 | 0.0787 | 0.1967 | 0.1965 | 123.98 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
70 |
|
71 |
- Transformers 4.35.2
|
72 |
+
- Pytorch 2.1.0+cu121
|
73 |
- Datasets 2.15.0
|
74 |
- Tokenizers 0.15.0
|
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_gen_len": 123.
|
4 |
-
"eval_loss": 2.
|
5 |
-
"eval_rouge1": 0.
|
6 |
-
"eval_rouge2": 0.
|
7 |
-
"eval_rougeL": 0.
|
8 |
-
"eval_rougeLsum": 0.
|
9 |
-
"eval_runtime":
|
10 |
-
"eval_samples_per_second":
|
11 |
-
"eval_steps_per_second": 0.
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_gen_len": 123.98,
|
4 |
+
"eval_loss": 2.8532516956329346,
|
5 |
+
"eval_rouge1": 0.3234,
|
6 |
+
"eval_rouge2": 0.0787,
|
7 |
+
"eval_rougeL": 0.1967,
|
8 |
+
"eval_rougeLsum": 0.1965,
|
9 |
+
"eval_runtime": 167.6714,
|
10 |
+
"eval_samples_per_second": 5.964,
|
11 |
+
"eval_steps_per_second": 0.376
|
12 |
}
|
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 sha256:798869b617260d70b9385c41c02644adddd6f1b024c402b9352b4e9b55500e1c
|
3 |
size 242041896
|
runs/Dec20_03-30-55_ef67406028e0/events.out.tfevents.1703043056.ef67406028e0.513.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230b1cbd625d1c93a25550baab5d4ebf11b3e0699c1fa16ca3d34a9ca13c61e6
|
3 |
+
size 15690
|
runs/Dec20_03-30-55_ef67406028e0/events.out.tfevents.1703058313.ef67406028e0.513.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5cc31494c2312d2dd1d5058c04a7db0006be27d1e1ddd2d5d6c85df27057745
|
3 |
+
size 613
|
special_tokens_map.json
CHANGED
@@ -101,25 +101,7 @@
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
-
"eos_token":
|
105 |
-
|
106 |
-
|
107 |
-
"normalized": false,
|
108 |
-
"rstrip": false,
|
109 |
-
"single_word": false
|
110 |
-
},
|
111 |
-
"pad_token": {
|
112 |
-
"content": "<pad>",
|
113 |
-
"lstrip": false,
|
114 |
-
"normalized": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"single_word": false
|
117 |
-
},
|
118 |
-
"unk_token": {
|
119 |
-
"content": "<unk>",
|
120 |
-
"lstrip": false,
|
121 |
-
"normalized": false,
|
122 |
-
"rstrip": false,
|
123 |
-
"single_word": false
|
124 |
-
}
|
125 |
}
|
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
}
|
tokenizer_config.json
CHANGED
@@ -931,12 +931,8 @@
|
|
931 |
"clean_up_tokenization_spaces": true,
|
932 |
"eos_token": "</s>",
|
933 |
"extra_ids": 100,
|
934 |
-
"max_length": 128,
|
935 |
"model_max_length": 512,
|
936 |
"pad_token": "<pad>",
|
937 |
-
"stride": 0,
|
938 |
"tokenizer_class": "T5Tokenizer",
|
939 |
-
"truncation_side": "right",
|
940 |
-
"truncation_strategy": "longest_first",
|
941 |
"unk_token": "<unk>"
|
942 |
}
|
|
|
931 |
"clean_up_tokenization_spaces": true,
|
932 |
"eos_token": "</s>",
|
933 |
"extra_ids": 100,
|
|
|
934 |
"model_max_length": 512,
|
935 |
"pad_token": "<pad>",
|
|
|
936 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
937 |
"unk_token": "<unk>"
|
938 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6b9527ce9981eb9cdd15fed72f7b10e586f1e033ee34d9f0a1a68c59d14aa0d
|
3 |
size 4856
|