Hasanur525 commited on
Commit
75e30c1
1 Parent(s): 022f865

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 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: mt5_deed_sum_1
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_deed_sum_1
17
+
18
+ This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5951
21
+ - Rouge1: 0.0572
22
+ - Rouge2: 0.0
23
+ - Rougel: 0.0572
24
+ - Rougelsum: 0.0572
25
+ - Gen Len: 19.0
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 2e-05
45
+ - train_batch_size: 2
46
+ - eval_batch_size: 2
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_steps: 5000
51
+ - num_epochs: 25
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
56
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
57
+ | 24.1526 | 1.0 | 375 | 15.7524 | 0.7082 | 0.0 | 0.6842 | 0.6883 | 12.0881 |
58
+ | 11.2879 | 2.0 | 750 | 13.1581 | 0.7082 | 0.0 | 0.6842 | 0.6883 | 12.3208 |
59
+ | 10.5585 | 3.0 | 1125 | 7.4334 | 0.7082 | 0.0 | 0.6842 | 0.6883 | 17.1384 |
60
+ | 2.9668 | 4.0 | 1500 | 6.5357 | 0.7487 | 0.0 | 0.7176 | 0.7257 | 19.0 |
61
+ | 3.7198 | 5.0 | 1875 | 2.1303 | 0.7487 | 0.0 | 0.7176 | 0.7257 | 19.0 |
62
+ | 1.3383 | 6.0 | 2250 | 1.8675 | 0.7487 | 0.0 | 0.7176 | 0.7257 | 19.0 |
63
+ | 3.4973 | 7.0 | 2625 | 1.6299 | 0.7487 | 0.0 | 0.7176 | 0.7257 | 18.8994 |
64
+ | 11.7006 | 8.0 | 3000 | 4.6990 | 0.7487 | 0.0 | 0.7176 | 0.7257 | 19.0 |
65
+ | 0.4529 | 9.0 | 3375 | 1.0729 | 0.7487 | 0.0 | 0.7176 | 0.7257 | 19.0 |
66
+ | 1.2783 | 10.0 | 3750 | 0.9424 | 0.7487 | 0.0 | 0.7176 | 0.7257 | 19.0 |
67
+ | 0.7953 | 11.0 | 4125 | 0.8889 | 1.0108 | 0.2013 | 0.892 | 0.9014 | 19.0 |
68
+ | 0.9359 | 12.0 | 4500 | 0.7996 | 1.1489 | 0.3019 | 0.9952 | 0.9877 | 19.0 |
69
+ | 0.5759 | 13.0 | 4875 | 0.7622 | 0.1572 | 0.1144 | 0.1572 | 0.1572 | 19.0 |
70
+ | 0.1533 | 14.0 | 5250 | 0.7068 | 0.2144 | 0.1144 | 0.1715 | 0.1715 | 19.0 |
71
+ | 0.4524 | 15.0 | 5625 | 0.6760 | 0.3145 | 0.2287 | 0.3145 | 0.3145 | 19.0 |
72
+ | 1.0126 | 16.0 | 6000 | 0.6627 | 0.0 | 0.0 | 0.0 | 0.0 | 19.0 |
73
+ | 0.1065 | 17.0 | 6375 | 0.6391 | 0.3145 | 0.2287 | 0.3145 | 0.3145 | 19.0 |
74
+ | 0.2096 | 18.0 | 6750 | 0.6419 | 0.2144 | 0.1144 | 0.2144 | 0.2144 | 19.0 |
75
+ | 0.5649 | 19.0 | 7125 | 0.6261 | 0.1572 | 0.1144 | 0.1572 | 0.1572 | 19.0 |
76
+ | 0.125 | 20.0 | 7500 | 0.6139 | 0.1572 | 0.1144 | 0.1572 | 0.1572 | 19.0 |
77
+ | 0.5511 | 21.0 | 7875 | 0.6057 | 0.3145 | 0.2287 | 0.3145 | 0.3145 | 19.0 |
78
+ | 0.0759 | 22.0 | 8250 | 0.6029 | 0.3145 | 0.2287 | 0.3145 | 0.3145 | 19.0 |
79
+ | 0.3491 | 23.0 | 8625 | 0.5995 | 0.3145 | 0.2287 | 0.3145 | 0.3145 | 19.0 |
80
+ | 0.3735 | 24.0 | 9000 | 0.5936 | 0.1572 | 0.1144 | 0.1572 | 0.1572 | 19.0 |
81
+ | 0.3451 | 25.0 | 9375 | 0.5951 | 0.0572 | 0.0 | 0.0572 | 0.0572 | 19.0 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.37.2
87
+ - Pytorch 2.1.0.dev20230811+cu121
88
+ - Datasets 2.17.0
89
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
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
+ "model_type": "mt5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.2",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.37.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22efc3db7c3cfb263afa06c0b7650aa0950e96b87e9a25d1b4b8add9c0a9ea3e
3
+ size 2329638768
runs/Feb28_19-04-28_WIN-F8FVB99PGRI/events.out.tfevents.1709175886.WIN-F8FVB99PGRI.11136.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:170271793ad135a94cea05799db65aeb6b2808725273f6c9b6beb7ad71398450
3
+ size 1489643
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:b5918f100395a1a0b3cb2cdbe13e6d49293a7228cbecd2fb8f7ccc1ce3f34207
3
+ size 16330827
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:afcd8d090bce9034eb64e79fa3142d371dac5eede187eafd390e7f3315b21fc3
3
+ size 4856