Yova commited on
Commit
b57237a
1 Parent(s): 6ac4300

Training in progress, step 11200

Browse files
config.json CHANGED
@@ -8,7 +8,7 @@
8
  "d_model": 256,
9
  "decoder_start_token_id": 1,
10
  "dense_act_fn": "relu",
11
- "dropout_rate": 0.3,
12
  "eos_token_id": 1,
13
  "feed_forward_proj": "relu",
14
  "initializer_factor": 1.0,
@@ -25,5 +25,5 @@
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.35.2",
27
  "use_cache": true,
28
- "vocab_size": 52
29
  }
 
8
  "d_model": 256,
9
  "decoder_start_token_id": 1,
10
  "dense_act_fn": "relu",
11
+ "dropout_rate": 0.2,
12
  "eos_token_id": 1,
13
  "feed_forward_proj": "relu",
14
  "initializer_factor": 1.0,
 
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.35.2",
27
  "use_cache": true,
28
+ "vocab_size": 59
29
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:002881796d1b6745d1f31eccbe70512b959892f672ae1c6edf81e146c92f575b
3
- size 29447256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eecb6ccfcef7f6e31aa90f660099591f3bb022b900e48f00a261620812e3d00
3
+ size 29454424
special_tokens_map.json CHANGED
@@ -1,21 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<ITER>",
4
- "<3>",
5
- "<V>",
6
- "<SG>",
7
- "<OPT>",
8
- "<PROSP>",
9
- "<GRPL>",
10
- "<PL>",
11
- "<IND>",
12
- "<NOM>",
13
- "<PFV>",
14
- "<4>",
15
- "<IPFV>",
16
- "<2>",
17
- "<1>"
18
- ],
19
  "bos_token": {
20
  "content": "<s>",
21
  "lstrip": false,
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -31,145 +31,8 @@
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
- },
35
- "37": {
36
- "content": "<ITER>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "38": {
44
- "content": "<3>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "39": {
52
- "content": "<V>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "40": {
60
- "content": "<SG>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "41": {
68
- "content": "<OPT>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "42": {
76
- "content": "<PROSP>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "43": {
84
- "content": "<GRPL>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "44": {
92
- "content": "<PL>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "45": {
100
- "content": "<IND>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "46": {
108
- "content": "<NOM>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "47": {
116
- "content": "<PFV>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "48": {
124
- "content": "<4>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "49": {
132
- "content": "<IPFV>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "50": {
140
- "content": "<2>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "51": {
148
- "content": "<1>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
  }
155
  },
156
- "additional_special_tokens": [
157
- "<ITER>",
158
- "<3>",
159
- "<V>",
160
- "<SG>",
161
- "<OPT>",
162
- "<PROSP>",
163
- "<GRPL>",
164
- "<PL>",
165
- "<IND>",
166
- "<NOM>",
167
- "<PFV>",
168
- "<4>",
169
- "<IPFV>",
170
- "<2>",
171
- "<1>"
172
- ],
173
  "bos_token": "<s>",
174
  "clean_up_tokenization_spaces": true,
175
  "eos_token": "</s>",
 
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  }
35
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  "bos_token": "<s>",
37
  "clean_up_tokenization_spaces": true,
38
  "eos_token": "</s>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b96d5142b9173d25c4281529f4958afca5c57cbcdefc2fa89aee9ad7d213700
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eac177dd16217e0a05535b7837556cff9c02364fa00fcae7c914c3ebdb8e52e
3
  size 4728
vocab.json CHANGED
@@ -1 +1 @@
1
- {"\u0105": 0, "z": 1, "y": 2, "s": 3, " ": 4, "m": 5, "k": 6, "l": 7, "\u0119": 8, "i": 9, "b": 10, "j": 11, "n": 12, "d": 13, "\u012f": 14, "\u0301": 15, "w": 16, "t": 17, "\u02bc": 18, "\u01eb": 19, "o": 20, "\u00ed": 21, "a": 22, "c": 23, "h": 24, "\u0142": 25, "g": 26, "\u00f3": 27, "\u0144": 28, "\u00e9": 29, "e": 30, "\u00e1": 31, "x": 32}
 
1
+ {" ": 0, "3": 1, ";": 2, "\u0105": 3, "G": 4, "\u0142": 5, "s": 6, "\u00e1": 7, "R": 8, "\u00f3": 9, "\u0119": 10, "e": 11, "N": 12, "1": 13, "n": 14, "D": 15, "t": 16, "d": 17, "b": 18, "M": 19, "l": 20, "T": 21, "4": 22, "\u0144": 23, ")": 24, "w": 25, "(": 26, "\u012f": 27, "V": 28, "\u02bc": 29, "P": 30, "c": 31, "z": 32, "m": 33, ",": 34, "O": 35, "j": 36, "k": 37, "2": 38, "g": 39, "F": 40, "a": 41, "\u0301": 42, "h": 43, "i": 44, "x": 45, "L": 46, "\u01eb": 47, "\u00e9": 48, "\u00ed": 49, "y": 50, "E": 51, "I": 52, "S": 53, "o": 54}