add model
Browse files- .gitignore +1 -0
- README.md +77 -0
- config.json +58 -0
- pytorch_model.bin +3 -0
- runs/Sep20_10-08-19_552a682d1acc/1632132524.5637326/events.out.tfevents.1632132524.552a682d1acc.74.1 +3 -0
- runs/Sep20_10-08-19_552a682d1acc/events.out.tfevents.1632132524.552a682d1acc.74.0 +3 -0
- runs/Sep20_10-41-09_552a682d1acc/1632134491.0041504/events.out.tfevents.1632134491.552a682d1acc.74.3 +3 -0
- runs/Sep20_10-41-09_552a682d1acc/1632134629.5022068/events.out.tfevents.1632134629.552a682d1acc.74.5 +3 -0
- runs/Sep20_10-41-09_552a682d1acc/events.out.tfevents.1632134490.552a682d1acc.74.2 +3 -0
- runs/Sep20_10-41-09_552a682d1acc/events.out.tfevents.1632134629.552a682d1acc.74.4 +3 -0
- runs/Sep20_10-49-34_552a682d1acc/1632135015.7760108/events.out.tfevents.1632135015.552a682d1acc.814.1 +3 -0
- runs/Sep20_10-49-34_552a682d1acc/events.out.tfevents.1632135015.552a682d1acc.814.0 +3 -0
- runs/Sep20_11-03-58_552a682d1acc/1632135871.4537623/events.out.tfevents.1632135871.552a682d1acc.814.3 +3 -0
- runs/Sep20_11-03-58_552a682d1acc/1632136882.4416242/events.out.tfevents.1632136882.552a682d1acc.814.5 +3 -0
- runs/Sep20_11-03-58_552a682d1acc/events.out.tfevents.1632135871.552a682d1acc.814.2 +3 -0
- runs/Sep20_11-03-58_552a682d1acc/events.out.tfevents.1632136882.552a682d1acc.814.4 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- xsum
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
+
model-index:
|
10 |
+
- name: t5-small-finetuned-xsum
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: xsum
|
17 |
+
type: xsum
|
18 |
+
args: default
|
19 |
+
metrics:
|
20 |
+
- name: Rouge1
|
21 |
+
type: rouge
|
22 |
+
value: 23.0533
|
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 |
+
# t5-small-finetuned-xsum
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the xsum dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 2.7967
|
33 |
+
- Rouge1: 23.0533
|
34 |
+
- Rouge2: 3.912
|
35 |
+
- Rougel: 17.8534
|
36 |
+
- Rougelsum: 17.8581
|
37 |
+
- Gen Len: 18.6878
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 2e-05
|
57 |
+
- train_batch_size: 8
|
58 |
+
- eval_batch_size: 8
|
59 |
+
- seed: 42
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- num_epochs: 1
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
69 |
+
| 3.0574 | 1.0 | 1276 | 2.7967 | 23.0533 | 3.912 | 17.8534 | 17.8581 | 18.6878 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.10.2
|
75 |
+
- Pytorch 1.9.0+cu102
|
76 |
+
- Datasets 1.12.1
|
77 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
+
"n_positions": 512,
|
19 |
+
"num_decoder_layers": 6,
|
20 |
+
"num_heads": 8,
|
21 |
+
"num_layers": 6,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"task_specific_params": {
|
26 |
+
"summarization": {
|
27 |
+
"early_stopping": true,
|
28 |
+
"length_penalty": 2.0,
|
29 |
+
"max_length": 200,
|
30 |
+
"min_length": 30,
|
31 |
+
"no_repeat_ngram_size": 3,
|
32 |
+
"num_beams": 4,
|
33 |
+
"prefix": "summarize: "
|
34 |
+
},
|
35 |
+
"translation_en_to_de": {
|
36 |
+
"early_stopping": true,
|
37 |
+
"max_length": 300,
|
38 |
+
"num_beams": 4,
|
39 |
+
"prefix": "translate English to German: "
|
40 |
+
},
|
41 |
+
"translation_en_to_fr": {
|
42 |
+
"early_stopping": true,
|
43 |
+
"max_length": 300,
|
44 |
+
"num_beams": 4,
|
45 |
+
"prefix": "translate English to French: "
|
46 |
+
},
|
47 |
+
"translation_en_to_ro": {
|
48 |
+
"early_stopping": true,
|
49 |
+
"max_length": 300,
|
50 |
+
"num_beams": 4,
|
51 |
+
"prefix": "translate English to Romanian: "
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.10.2",
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 32128
|
58 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89478fa473fcd5a138bb09bbd22f63d20aa1c8cbb484d9c53f5c999212710c62
|
3 |
+
size 242085627
|
runs/Sep20_10-08-19_552a682d1acc/1632132524.5637326/events.out.tfevents.1632132524.552a682d1acc.74.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:402498dcf24dc8dc4f82de543fd41acdd60f80b617760951a1f8b3270173b76a
|
3 |
+
size 4449
|
runs/Sep20_10-08-19_552a682d1acc/events.out.tfevents.1632132524.552a682d1acc.74.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b739024746ebcb72b76edc2e7d666a9d6f320352b54cf45d41fa6da4962959f7
|
3 |
+
size 3839
|
runs/Sep20_10-41-09_552a682d1acc/1632134491.0041504/events.out.tfevents.1632134491.552a682d1acc.74.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34e6ca6a0545491d8be7b3aca8583e699742ed1d2f8e2f3b33463b515236532d
|
3 |
+
size 4449
|
runs/Sep20_10-41-09_552a682d1acc/1632134629.5022068/events.out.tfevents.1632134629.552a682d1acc.74.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:400a1b167eea44102016f38ce0469e4f981be21a34cef3f4e686c8add7d02681
|
3 |
+
size 4449
|
runs/Sep20_10-41-09_552a682d1acc/events.out.tfevents.1632134490.552a682d1acc.74.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27e4ca020335753115210e25bbc254437c258454a470acd78c60aa13f86742d7
|
3 |
+
size 3837
|
runs/Sep20_10-41-09_552a682d1acc/events.out.tfevents.1632134629.552a682d1acc.74.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7edac3deb8b7a7cf3da61ff26130fc426710789c72d7e0cde613fa84b9ec151d
|
3 |
+
size 3837
|
runs/Sep20_10-49-34_552a682d1acc/1632135015.7760108/events.out.tfevents.1632135015.552a682d1acc.814.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:972986ba6d1ba7cf2091fd3dd5246ec4d77ba9a3f7938b5b9e234656480113d7
|
3 |
+
size 4449
|
runs/Sep20_10-49-34_552a682d1acc/events.out.tfevents.1632135015.552a682d1acc.814.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2d5223c9b196aef458514b1ae0b07095bea4bc00919885792da29efed5cf62a
|
3 |
+
size 3994
|
runs/Sep20_11-03-58_552a682d1acc/1632135871.4537623/events.out.tfevents.1632135871.552a682d1acc.814.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9534dd42b024177fa4f4c1c6cdda2baba8297a74dece345d5e5e223a4e84cbc
|
3 |
+
size 4449
|
runs/Sep20_11-03-58_552a682d1acc/1632136882.4416242/events.out.tfevents.1632136882.552a682d1acc.814.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fb63b2530550144331f3d0c6f56268f6f5dfdb058b6a12983694361faeba7a1
|
3 |
+
size 4449
|
runs/Sep20_11-03-58_552a682d1acc/events.out.tfevents.1632135871.552a682d1acc.814.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ade1b20eb3780ae709569307726bc896209563925e8282297d99c2d919b8f069
|
3 |
+
size 4151
|
runs/Sep20_11-03-58_552a682d1acc/events.out.tfevents.1632136882.552a682d1acc.814.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c46d66ef661e993c9941444b3a006edbfe118edf660dddf7e0598be0687cf174
|
3 |
+
size 5067
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c756158e6532b19552ff66adbda13b2615e7b3d7e614fb5d6a6a0e05cdb73f0d
|
3 |
+
size 2799
|