tym24 commited on
Commit
23befcb
·
verified ·
1 Parent(s): a21ff55

tym24/Model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-small
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: mt5-summarize-ja
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # mt5-summarize-ja
17
+
18
+ This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.0695
21
+ - Rouge1: 0.3667
22
+ - Rouge2: 0.1678
23
+ - Rougel: 0.2998
24
+ - Rougelsum: 0.3123
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 0.0005
44
+ - train_batch_size: 2
45
+ - eval_batch_size: 1
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 16
48
+ - total_train_batch_size: 32
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 90
52
+ - num_epochs: 10
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
57
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
58
+ | 3.3241 | 0.7 | 100 | 2.4795 | 0.2943 | 0.1245 | 0.2472 | 0.2471 |
59
+ | 2.7583 | 1.4 | 200 | 2.2710 | 0.3054 | 0.1152 | 0.2539 | 0.2576 |
60
+ | 2.5469 | 2.1 | 300 | 2.2936 | 0.3446 | 0.1493 | 0.2808 | 0.2887 |
61
+ | 2.5335 | 2.8 | 400 | 2.1913 | 0.3228 | 0.1270 | 0.2665 | 0.2725 |
62
+ | 2.4383 | 3.5 | 500 | 2.1507 | 0.3630 | 0.1671 | 0.3082 | 0.3144 |
63
+ | 2.3671 | 4.2 | 600 | 2.1338 | 0.3388 | 0.1493 | 0.2814 | 0.2880 |
64
+ | 2.349 | 4.9 | 700 | 2.1089 | 0.3621 | 0.1576 | 0.2980 | 0.3079 |
65
+ | 2.264 | 5.6 | 800 | 2.1353 | 0.3740 | 0.1784 | 0.3083 | 0.3157 |
66
+ | 2.1577 | 6.3 | 900 | 2.1101 | 0.3711 | 0.1716 | 0.3107 | 0.3166 |
67
+ | 2.1315 | 7.0 | 1000 | 2.0905 | 0.3862 | 0.1826 | 0.3198 | 0.3269 |
68
+ | 2.1418 | 7.7 | 1100 | 2.0893 | 0.3433 | 0.1621 | 0.2895 | 0.2963 |
69
+ | 2.0744 | 8.4 | 1200 | 2.0881 | 0.3778 | 0.1834 | 0.3130 | 0.3242 |
70
+ | 2.0944 | 9.1 | 1300 | 2.0709 | 0.3676 | 0.1688 | 0.3024 | 0.3140 |
71
+ | 2.1015 | 9.8 | 1400 | 2.0695 | 0.3667 | 0.1678 | 0.2998 | 0.3123 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.35.2
77
+ - Pytorch 2.1.0+cu121
78
+ - Datasets 2.17.0
79
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "length_penalty": 0.6,
20
+ "max_length": 128,
21
+ "model_type": "mt5",
22
+ "no_repeat_ngram_size": 2,
23
+ "num_beams": 15,
24
+ "num_decoder_layers": 8,
25
+ "num_heads": 6,
26
+ "num_layers": 8,
27
+ "pad_token_id": 0,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "tie_word_embeddings": false,
31
+ "tokenizer_class": "T5Tokenizer",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "use_cache": true,
35
+ "vocab_size": 250112
36
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "length_penalty": 0.6,
5
+ "max_length": 128,
6
+ "no_repeat_ngram_size": 2,
7
+ "num_beams": 15,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.35.2"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7fbfbee3d032d6bfeea8578310577cead733a4e1dbb50e6bccceb13f3c845d
3
+ size 1200729512
runs/Feb19_04-38-28_44c8b26f9f0d/events.out.tfevents.1708317508.44c8b26f9f0d.1239.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b593d806e6bda9219c924b95af049995e3b66c5e079e5e911a1c3ad674040303
3
+ size 33825
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9b5296bb1bdbcc33ccb40be1c81db3a36335a1c2b080a5368b48fb7a9eaa66
3
+ size 16330461
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<pad>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc3803913e344b03e3f92d8729d0d9fbf7e775e5faefcb2355bc55ba15c999f3
3
+ size 4664