Hasanur525 commited on
Commit
bbc5aca
1 Parent(s): cd6443c

End of training

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 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Hasanur525/deed-summarization_version_10
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - rouge
7
+ model-index:
8
+ - name: deed-summarization_version_11
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # deed-summarization_version_11
16
+
17
+ This model is a fine-tuned version of [Hasanur525/deed-summarization_version_10](https://huggingface.co/Hasanur525/deed-summarization_version_10) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2748
20
+ - Rouge1: 0.7615
21
+ - Rouge2: 0.3638
22
+ - Rougel: 0.7644
23
+ - Rougelsum: 0.7534
24
+ - Gen Len: 98.2164
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: 2e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 5000
50
+ - num_epochs: 25
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
56
+ | 1.1025 | 1.0 | 265 | 0.4128 | 0.3423 | 0.1522 | 0.3482 | 0.3493 | 98.4272 |
57
+ | 0.7311 | 2.0 | 530 | 0.4113 | 0.3324 | 0.1504 | 0.3405 | 0.3389 | 98.465 |
58
+ | 0.1826 | 3.0 | 795 | 0.4086 | 0.3511 | 0.1619 | 0.36 | 0.3585 | 98.328 |
59
+ | 0.6314 | 4.0 | 1060 | 0.4053 | 0.3198 | 0.1474 | 0.3222 | 0.3179 | 98.4565 |
60
+ | 0.4551 | 5.0 | 1325 | 0.4025 | 0.363 | 0.1659 | 0.3732 | 0.3694 | 98.3507 |
61
+ | 1.1978 | 6.0 | 1590 | 0.3960 | 0.3611 | 0.1386 | 0.3589 | 0.3577 | 98.3043 |
62
+ | 1.078 | 7.0 | 1855 | 0.3902 | 0.3158 | 0.1445 | 0.3112 | 0.3074 | 98.3809 |
63
+ | 0.2222 | 8.0 | 2120 | 0.3846 | 0.4959 | 0.2242 | 0.494 | 0.4793 | 98.2212 |
64
+ | 0.811 | 9.0 | 2385 | 0.3811 | 0.4641 | 0.2215 | 0.464 | 0.4499 | 98.2457 |
65
+ | 0.4816 | 10.0 | 2650 | 0.3713 | 0.436 | 0.217 | 0.439 | 0.4368 | 98.1881 |
66
+ | 0.2396 | 11.0 | 2915 | 0.3650 | 0.556 | 0.2677 | 0.5563 | 0.5475 | 98.2571 |
67
+ | 0.1897 | 12.0 | 3180 | 0.3601 | 0.6718 | 0.4061 | 0.6712 | 0.6631 | 98.1597 |
68
+ | 0.6071 | 13.0 | 3445 | 0.3498 | 0.5639 | 0.294 | 0.5623 | 0.5554 | 98.1096 |
69
+ | 0.3386 | 14.0 | 3710 | 0.3416 | 0.4915 | 0.2933 | 0.5002 | 0.4954 | 98.069 |
70
+ | 0.2921 | 15.0 | 3975 | 0.3342 | 0.4391 | 0.2676 | 0.4381 | 0.4342 | 97.7353 |
71
+ | 1.4814 | 16.0 | 4240 | 0.3261 | 0.5389 | 0.2966 | 0.5542 | 0.5466 | 98.0945 |
72
+ | 0.1891 | 17.0 | 4505 | 0.3167 | 0.4885 | 0.2725 | 0.5044 | 0.4923 | 98.2146 |
73
+ | 0.4877 | 18.0 | 4770 | 0.3090 | 0.6391 | 0.3774 | 0.6378 | 0.6224 | 98.2098 |
74
+ | 0.6804 | 19.0 | 5035 | 0.3016 | 0.766 | 0.4274 | 0.7649 | 0.7553 | 97.8828 |
75
+ | 0.1395 | 20.0 | 5300 | 0.2930 | 0.7208 | 0.3954 | 0.7478 | 0.7245 | 98.0955 |
76
+ | 0.4395 | 21.0 | 5565 | 0.2866 | 0.7457 | 0.406 | 0.7629 | 0.7453 | 97.9509 |
77
+ | 0.2215 | 22.0 | 5830 | 0.2820 | 0.6278 | 0.3099 | 0.6447 | 0.6288 | 98.0255 |
78
+ | 0.6845 | 23.0 | 6095 | 0.2775 | 0.7815 | 0.3541 | 0.7789 | 0.7629 | 98.1692 |
79
+ | 0.3637 | 24.0 | 6360 | 0.2753 | 0.819 | 0.3989 | 0.8195 | 0.8062 | 98.328 |
80
+ | 0.4836 | 25.0 | 6625 | 0.2748 | 0.7615 | 0.3638 | 0.7644 | 0.7534 | 98.2164 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.37.2
86
+ - Pytorch 2.1.0.dev20230811+cu121
87
+ - Datasets 2.17.0
88
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Hasanur525/deed-summarization_version_10",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
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": 500,
21
+ "model_type": "mt5",
22
+ "no_repeat_ngram_size": 2,
23
+ "num_beams": 4,
24
+ "num_decoder_layers": 12,
25
+ "num_heads": 12,
26
+ "num_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "relative_attention_max_distance": 128,
30
+ "relative_attention_num_buckets": 32,
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_class": "T5Tokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.37.2",
35
+ "use_cache": true,
36
+ "vocab_size": 250112
37
+ }
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": 100,
6
+ "no_repeat_ngram_size": 2,
7
+ "num_beams": 4,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.37.2"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6aa68bebab042abacdc5437a674b19a7670a6b90bffb7732ff425750df94de2
3
+ size 2329638768
runs/Feb19_21-44-22_WIN-F8FVB99PGRI/events.out.tfevents.1708407873.WIN-F8FVB99PGRI.18492.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c0fa2e14334ed2c23e90a03ce3d91f2df125bd9230c80b1686685f8d113519
3
+ size 1058084
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:e023441336081dc068f3193421d41ba92bbea7909d5114ab737dc7d9a3a54141
3
+ size 16315478
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 256,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_to_multiple_of": null,
36
+ "pad_token": "<pad>",
37
+ "pad_token_type_id": 0,
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "stride": 0,
41
+ "tokenizer_class": "T5Tokenizer",
42
+ "truncation_side": "right",
43
+ "truncation_strategy": "longest_first",
44
+ "unk_token": "<unk>"
45
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfe350779f15092d51c6741f4127cb6b2a7cff565a1f66af2079b688c53d2a0
3
+ size 4920