DiwasDiwas
commited on
Commit
•
c183299
1
Parent(s):
6e00e0b
DiwasDiwas/t5-small-MedicoSummarizer
Browse files- README.md +13 -20
- all_results.json +10 -10
- model.safetensors +1 -1
- runs/Dec13_09-17-55_a0182b6e7bc8/events.out.tfevents.1702459158.a0182b6e7bc8.229.0 +3 -0
- runs/Dec13_09-17-55_a0182b6e7bc8/events.out.tfevents.1702468321.a0182b6e7bc8.229.1 +3 -0
- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -4
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,14 +15,14 @@ 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:
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -37,8 +37,6 @@ More information needed
|
|
37 |
More information needed
|
38 |
|
39 |
## Training procedure
|
40 |
-
The inference engine doesn't do justice to its operation as the inference engine API doesn't work good for trainer checkpoints !
|
41 |
-
So, you should rather load it on the pipeline and just try it !
|
42 |
|
43 |
### Training hyperparameters
|
44 |
|
@@ -49,23 +47,18 @@ The following hyperparameters were used during training:
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
- mixed_precision_training: Native AMP
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
59 |
-
| 3.
|
60 |
-
| 3.
|
61 |
-
| 3.
|
62 |
-
| 3.
|
63 |
-
| 3.
|
64 |
-
| 3.153 | 6.0 | 3750 | 2.9855 | 0.3187 | 0.0703 | 0.1927 | 0.1926 | 122.33 |
|
65 |
-
| 3.1564 | 7.0 | 4375 | 2.9801 | 0.32 | 0.0706 | 0.1929 | 0.1928 | 122.479 |
|
66 |
-
| 3.136 | 8.0 | 5000 | 2.9747 | 0.3228 | 0.0727 | 0.1936 | 0.1935 | 122.804 |
|
67 |
-
| 3.1248 | 9.0 | 5625 | 2.9726 | 0.321 | 0.0721 | 0.1926 | 0.1925 | 122.685 |
|
68 |
-
| 3.1309 | 10.0 | 6250 | 2.9721 | 0.3222 | 0.0728 | 0.1933 | 0.1932 | 122.633 |
|
69 |
|
70 |
|
71 |
### Framework versions
|
|
|
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: 2.9048
|
21 |
+
- Rouge1: 0.3226
|
22 |
+
- Rouge2: 0.0771
|
23 |
+
- Rougel: 0.1964
|
24 |
+
- Rougelsum: 0.1967
|
25 |
+
- Gen Len: 123.675
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
37 |
More information needed
|
38 |
|
39 |
## Training procedure
|
|
|
|
|
40 |
|
41 |
### Training hyperparameters
|
42 |
|
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 5
|
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 |
+
| 3.231 | 1.0 | 1875 | 2.9942 | 0.3149 | 0.0721 | 0.1871 | 0.1873 | 119.685 |
|
58 |
+
| 3.153 | 2.0 | 3750 | 2.9426 | 0.3204 | 0.0758 | 0.1935 | 0.1936 | 122.484 |
|
59 |
+
| 3.1201 | 3.0 | 5625 | 2.9209 | 0.3215 | 0.0753 | 0.195 | 0.1951 | 123.496 |
|
60 |
+
| 3.1008 | 4.0 | 7500 | 2.9072 | 0.3232 | 0.0771 | 0.1969 | 0.1971 | 123.414 |
|
61 |
+
| 3.0925 | 5.0 | 9375 | 2.9048 | 0.3226 | 0.0771 | 0.1964 | 0.1967 | 123.675 |
|
|
|
|
|
|
|
|
|
|
|
62 |
|
63 |
|
64 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_gen_len":
|
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": 5.0,
|
3 |
+
"eval_gen_len": 123.675,
|
4 |
+
"eval_loss": 2.904787540435791,
|
5 |
+
"eval_rouge1": 0.3226,
|
6 |
+
"eval_rouge2": 0.0771,
|
7 |
+
"eval_rougeL": 0.1964,
|
8 |
+
"eval_rougeLsum": 0.1967,
|
9 |
+
"eval_runtime": 164.4164,
|
10 |
+
"eval_samples_per_second": 6.082,
|
11 |
+
"eval_steps_per_second": 0.383
|
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 sha256:959f21d96c94eb5fa45ea62693f65afd82444e2456585a779905bdc34e7a6192
|
3 |
size 242041896
|
runs/Dec13_09-17-55_a0182b6e7bc8/events.out.tfevents.1702459158.a0182b6e7bc8.229.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81cbfed76d9d8992dffdb43405223cff0bf7f704e2a7610ba2ac99efd57e6281
|
3 |
+
size 11023
|
runs/Dec13_09-17-55_a0182b6e7bc8/events.out.tfevents.1702468321.a0182b6e7bc8.229.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:421058a7b4a755f883a320e3f25b2a5c2650c7abefd8b0e4b82423d9cd621677
|
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 sha256:459e0ba38d7350474ee4d0d03e220420a9554159f87d4056a357225a48ee2a7a
|
3 |
size 4856
|