jalbarracin commited on
Commit
38d8d24
1 Parent(s): eff585e

Upload 7 files

Browse files

Final model after 20 epochs.

added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"<extra_id_42>": 30042, "<extra_id_26>": 30026, "<extra_id_17>": 30017, "<extra_id_84>": 30084, "<extra_id_38>": 30038, "<extra_id_86>": 30086, "<extra_id_19>": 30019, "<extra_id_7>": 30007, "<extra_id_96>": 30096, "<extra_id_73>": 30073, "<extra_id_68>": 30068, "<extra_id_59>": 30059, "<extra_id_43>": 30043, "<extra_id_91>": 30091, "<extra_id_97>": 30097, "<extra_id_29>": 30029, "<extra_id_25>": 30025, "<extra_id_70>": 30070, "<extra_id_61>": 30061, "<extra_id_51>": 30051, "<extra_id_30>": 30030, "<extra_id_93>": 30093, "<extra_id_60>": 30060, "<extra_id_47>": 30047, "<extra_id_49>": 30049, "<extra_id_18>": 30018, "<extra_id_75>": 30075, "<extra_id_58>": 30058, "<extra_id_32>": 30032, "<extra_id_6>": 30006, "<extra_id_92>": 30092, "<extra_id_85>": 30085, "<extra_id_44>": 30044, "<extra_id_69>": 30069, "<extra_id_53>": 30053, "<extra_id_71>": 30071, "<extra_id_9>": 30009, "<extra_id_87>": 30087, "<extra_id_0>": 30000, "<extra_id_66>": 30066, "<extra_id_31>": 30031, "<extra_id_2>": 30002, "<extra_id_64>": 30064, "<extra_id_90>": 30090, "<extra_id_46>": 30046, "<extra_id_5>": 30005, "<extra_id_62>": 30062, "<extra_id_65>": 30065, "<extra_id_79>": 30079, "<extra_id_80>": 30080, "<extra_id_21>": 30021, "<extra_id_3>": 30003, "<extra_id_50>": 30050, "<extra_id_67>": 30067, "<extra_id_23>": 30023, "<extra_id_33>": 30033, "<extra_id_72>": 30072, "<extra_id_98>": 30098, "<extra_id_1>": 30001, "<extra_id_81>": 30081, "<extra_id_4>": 30004, "<extra_id_77>": 30077, "<extra_id_28>": 30028, "<extra_id_10>": 30010, "<extra_id_45>": 30045, "<extra_id_63>": 30063, "<extra_id_40>": 30040, "<extra_id_34>": 30034, "<extra_id_20>": 30020, "<extra_id_14>": 30014, "<extra_id_12>": 30012, "<extra_id_37>": 30037, "<extra_id_22>": 30022, "<extra_id_74>": 30074, "<extra_id_88>": 30088, "<extra_id_83>": 30083, "<extra_id_36>": 30036, "<extra_id_35>": 30035, "<extra_id_41>": 30041, "<extra_id_48>": 30048, "<extra_id_39>": 30039, "<extra_id_24>": 30024, "<extra_id_99>": 30099, "<extra_id_54>": 30054, "<extra_id_55>": 30055, "<extra_id_78>": 30078, "<extra_id_94>": 30094, "<extra_id_56>": 30056, "<extra_id_15>": 30015, "<extra_id_11>": 30011, "<extra_id_27>": 30027, "<extra_id_13>": 30013, "<extra_id_16>": 30016, "<extra_id_52>": 30052, "<extra_id_95>": 30095, "<extra_id_82>": 30082, "<extra_id_76>": 30076, "<extra_id_8>": 30008, "<extra_id_57>": 30057, "<extra_id_89>": 30089}
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/instrut5/out/simplet5-mng-out",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "gradient_checkpointing": false,
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "mt5",
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "tie_word_embeddings": false,
25
+ "tokenizer_class": "T5Tokenizer",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.16.2",
28
+ "use_cache": true,
29
+ "vocab_size": 30000
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc51302d7c257084e3134274cff55d325989e29a24accb6ad706f6fac8656e56
3
+ size 977363917
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>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48736f27fd11cdd0fa7d958918dfc27afaa30814ad2cc535256e18ab1b9ad1e
3
+ size 764563
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>"], "special_tokens_map_file": "/root/.cache/huggingface/transformers/ae4a6ef97e7ad4e4a8293ff6b370274af5bffe9459c4d3bf60659b817215f0eb.294ebaa4cd17bb284635004c92d2c4d522ec488c828dcce0c2471b6f28e3fe82", "name_or_path": "/content/drive/MyDrive/instrut5/out/simplet5-mng-out", "tokenizer_class": "T5Tokenizer"}