napatswift commited on
Commit
8e01901
·
1 Parent(s): 8d37a83

napatswift/mt5-bud-seq2seq

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: napatswift/mt5-fixth
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,14 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # mt5-budget-seq
15
 
16
- This model is a fine-tuned version of [napatswift/mt5-fixth](https://huggingface.co/napatswift/mt5-fixth) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.0390
19
- - eval_runtime: 6.1075
20
- - eval_samples_per_second: 6.549
21
- - eval_steps_per_second: 6.549
22
- - epoch: 1.65
23
- - step: 402
24
 
25
  ## Model description
26
 
@@ -40,15 +35,22 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0005
43
- - train_batch_size: 1
44
  - eval_batch_size: 1
45
  - seed: 42
46
  - gradient_accumulation_steps: 16
47
- - total_train_batch_size: 16
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 10
51
- - num_epochs: 10
 
 
 
 
 
 
 
52
 
53
  ### Framework versions
54
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/flan-t5-base
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # mt5-budget-seq
15
 
16
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0238
 
 
 
 
 
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0005
38
+ - train_batch_size: 6
39
  - eval_batch_size: 1
40
  - seed: 42
41
  - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 96
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 10
46
+ - num_epochs: 5
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.1045 | 3.3 | 201 | 0.0238 |
53
+
54
 
55
  ### Framework versions
56
 
added_tokens.json CHANGED
@@ -1,25 +1,25 @@
1
  {
2
- "</amount>": 250100,
3
- "</fiscal_year>": 250101,
4
- "</fiscal_year_end_year>": 250102,
5
- "</fiscal_year_year>": 250103,
6
- "</line_item_amount>": 250104,
7
- "</line_item_bullet>": 250105,
8
- "</line_item_children>": 250106,
9
- "</line_item_fiscal_years>": 250107,
10
- "</line_item_name>": 250108,
11
- "</line_item_root>": 250109,
12
- "<amount>": 250110,
13
- "<begin>": 250111,
14
- "<begin_indent>": 250112,
15
- "<big_sep>": 250113,
16
- "<fiscal_year>": 250114,
17
- "<fiscal_year_end_year>": 250115,
18
- "<fiscal_year_year>": 250116,
19
- "<line_item_amount>": 250117,
20
- "<line_item_bullet>": 250118,
21
- "<line_item_children>": 250119,
22
- "<line_item_fiscal_years>": 250120,
23
- "<line_item_name>": 250121,
24
- "<line_item_root>": 250122
25
  }
 
1
  {
2
+ "</amount>": 32100,
3
+ "</fiscal_year>": 32101,
4
+ "</fiscal_year_end_year>": 32102,
5
+ "</fiscal_year_year>": 32103,
6
+ "</line_item_amount>": 32104,
7
+ "</line_item_bullet>": 32105,
8
+ "</line_item_children>": 32106,
9
+ "</line_item_fiscal_years>": 32107,
10
+ "</line_item_name>": 32108,
11
+ "</line_item_root>": 32109,
12
+ "<amount>": 32110,
13
+ "<begin>": 32111,
14
+ "<begin_indent>": 32112,
15
+ "<big_sep>": 32113,
16
+ "<fiscal_year>": 32114,
17
+ "<fiscal_year_end_year>": 32115,
18
+ "<fiscal_year_year>": 32116,
19
+ "<line_item_amount>": 32117,
20
+ "<line_item_bullet>": 32118,
21
+ "<line_item_children>": 32119,
22
+ "<line_item_fiscal_years>": 32120,
23
+ "<line_item_name>": 32121,
24
+ "<line_item_root>": 32122
25
  }
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "napatswift/mt5-fixth",
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,
@@ -16,17 +16,47 @@
16
  "is_encoder_decoder": true,
17
  "is_gated_act": true,
18
  "layer_norm_epsilon": 1e-06,
19
- "model_type": "mt5",
20
- "num_decoder_layers": 8,
21
- "num_heads": 6,
22
- "num_layers": 8,
 
 
23
  "pad_token_id": 0,
24
  "relative_attention_max_distance": 128,
25
  "relative_attention_num_buckets": 32,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  "tie_word_embeddings": false,
27
- "tokenizer_class": "T5Tokenizer",
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.33.3",
30
  "use_cache": true,
31
- "vocab_size": 250124
32
  }
 
1
  {
2
+ "_name_or_path": "google/flan-t5-base",
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
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,
 
16
  "is_encoder_decoder": true,
17
  "is_gated_act": true,
18
  "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
27
  "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
  "tie_word_embeddings": false,
 
58
  "torch_dtype": "float32",
59
  "transformers_version": "4.33.3",
60
  "use_cache": true,
61
+ "vocab_size": 32124
62
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9de51b6fccaa4cf2dcc1565ba777211e82c88fce4b102c7910dd132213a1df6b
3
- size 1200821765
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9746636c9f61901a70733adb8f6087ce4df3825eaa6963811bcf6c74babf6c96
3
+ size 990384309
special_tokens_map.json CHANGED
@@ -1,4 +1,106 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "eos_token": "</s>",
3
  "pad_token": "<pad>",
4
  "unk_token": "<unk>"
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
  "eos_token": "</s>",
105
  "pad_token": "<pad>",
106
  "unk_token": "<unk>"
spiece.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
- size 4309802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ded8087ed38e31d69b670456595183f4efca67fa94df4653c70fa5a7017ebee6
3
- size 16319677
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58c720ed83af78e2768b2cfa582aa15ea75630b56f0181045194419e7dbd805
3
+ size 2426696
tokenizer_config.json CHANGED
@@ -1,16 +1,112 @@
1
  {
2
- "additional_special_tokens": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "clean_up_tokenization_spaces": true,
4
  "eos_token": "</s>",
5
- "extra_ids": 0,
6
- "legacy": true,
7
- "max_length": 512,
8
- "model_max_length": 1000000000000000019884624838656,
9
  "pad_token": "<pad>",
10
  "sp_model_kwargs": {},
11
- "stride": 0,
12
  "tokenizer_class": "T5Tokenizer",
13
- "truncation_side": "right",
14
- "truncation_strategy": "longest_first",
15
  "unk_token": "<unk>"
16
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
 
 
108
  "pad_token": "<pad>",
109
  "sp_model_kwargs": {},
 
110
  "tokenizer_class": "T5Tokenizer",
 
 
111
  "unk_token": "<unk>"
112
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9711c5d3d0a69c972010153b7313e4f8ca0f06ec7916149b1716fc68c228220
3
- size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f98faa36e77f999a1860f54d527d0e79bff674283d7be7e59d075c46fa42df
3
+ size 4091