mlegls commited on
Commit
c8d90ff
1 Parent(s): a448d65

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": null,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": null,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 256,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.21.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 58
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b248abb0032d56f3f6da3cc3919dc30b706d88bc61b71b54a735974d9aba8e8b
3
+ size 356185193
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "<pad>"
3
+ }
tokenizer.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 256,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<s>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<pad>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 2,
31
+ "content": "</s>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 3,
40
+ "content": "<unk>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 4,
49
+ "content": "<mask>",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ }
56
+ ],
57
+ "normalizer": null,
58
+ "pre_tokenizer": {
59
+ "type": "WhitespaceSplit"
60
+ },
61
+ "post_processor": null,
62
+ "decoder": null,
63
+ "model": {
64
+ "type": "WordLevel",
65
+ "vocab": {
66
+ "<s>": 0,
67
+ "<pad>": 1,
68
+ "</s>": 2,
69
+ "<unk>": 3,
70
+ "<mask>": 4,
71
+ "SWAP": 5,
72
+ "7": 6,
73
+ "9": 7,
74
+ "45": 8,
75
+ "15": 9,
76
+ "44": 10,
77
+ "14": 11,
78
+ "35": 12,
79
+ "33": 13,
80
+ "8": 14,
81
+ "20": 15,
82
+ "43": 16,
83
+ "34": 17,
84
+ "32": 18,
85
+ "6": 19,
86
+ "46": 20,
87
+ "16": 21,
88
+ "17": 22,
89
+ "11": 23,
90
+ "19": 24,
91
+ "21": 25,
92
+ "36": 26,
93
+ "42": 27,
94
+ "5": 28,
95
+ "37": 29,
96
+ "25": 30,
97
+ "30": 31,
98
+ "13": 32,
99
+ "12": 33,
100
+ "29": 34,
101
+ "31": 35,
102
+ "18": 36,
103
+ "39": 37,
104
+ "40": 38,
105
+ "26": 39,
106
+ "4": 40,
107
+ "28": 41,
108
+ "23": 42,
109
+ "24": 43,
110
+ "38": 44,
111
+ "22": 45,
112
+ "41": 46,
113
+ "10": 47,
114
+ "27": 48,
115
+ "47": 49,
116
+ "3": 50,
117
+ "48": 51,
118
+ "2": 52,
119
+ "49": 53,
120
+ "1": 54,
121
+ "50": 55,
122
+ "BURN": 56,
123
+ "MINT": 57
124
+ },
125
+ "unk_token": "<unk>"
126
+ }
127
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "tokenizer_class": "PreTrainedTokenizerFast"
3
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa9d12bcce45ed75118ce7fd778826eafd28ca6781e9cdfa100abd113660505
3
+ size 3311