Fibonacci162 commited on
Commit
ea5f9be
·
verified ·
1 Parent(s): 9028096

Training in progress, step 240

Browse files
config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 256,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 1024,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 4,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 4,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 52
83
+ },
84
+ "decoder_start_token_id": 2,
85
+ "encoder": {
86
+ "_attn_implementation_autoset": false,
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": null,
90
+ "attention_probs_dropout_prob": 0.1,
91
+ "bad_words_ids": null,
92
+ "begin_suppress_tokens": null,
93
+ "bos_token_id": null,
94
+ "chunk_size_feed_forward": 0,
95
+ "classifier_dropout": null,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "early_stopping": false,
101
+ "encoder_no_repeat_ngram_size": 0,
102
+ "eos_token_id": null,
103
+ "exponential_decay_length_penalty": null,
104
+ "finetuning_task": null,
105
+ "forced_bos_token_id": null,
106
+ "forced_eos_token_id": null,
107
+ "hidden_act": "gelu",
108
+ "hidden_dropout_prob": 0.1,
109
+ "hidden_size": 256,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 1024,
116
+ "is_decoder": false,
117
+ "is_encoder_decoder": false,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1
121
+ },
122
+ "layer_norm_eps": 1e-12,
123
+ "length_penalty": 1.0,
124
+ "max_length": 20,
125
+ "max_position_embeddings": 512,
126
+ "min_length": 0,
127
+ "model_type": "bert",
128
+ "no_repeat_ngram_size": 0,
129
+ "num_attention_heads": 4,
130
+ "num_beam_groups": 1,
131
+ "num_beams": 1,
132
+ "num_hidden_layers": 4,
133
+ "num_return_sequences": 1,
134
+ "output_attentions": false,
135
+ "output_hidden_states": false,
136
+ "output_scores": false,
137
+ "pad_token_id": 0,
138
+ "position_embedding_type": "absolute",
139
+ "prefix": null,
140
+ "problem_type": null,
141
+ "pruned_heads": {},
142
+ "remove_invalid_values": false,
143
+ "repetition_penalty": 1.0,
144
+ "return_dict": true,
145
+ "return_dict_in_generate": false,
146
+ "sep_token_id": null,
147
+ "suppress_tokens": null,
148
+ "task_specific_params": null,
149
+ "temperature": 1.0,
150
+ "tf_legacy_loss": false,
151
+ "tie_encoder_decoder": false,
152
+ "tie_word_embeddings": true,
153
+ "tokenizer_class": null,
154
+ "top_k": 50,
155
+ "top_p": 1.0,
156
+ "torch_dtype": null,
157
+ "torchscript": false,
158
+ "type_vocab_size": 2,
159
+ "typical_p": 1.0,
160
+ "use_bfloat16": false,
161
+ "use_cache": true,
162
+ "vocab_size": 52
163
+ },
164
+ "eos_token_id": 0,
165
+ "is_encoder_decoder": true,
166
+ "model_type": "encoder-decoder",
167
+ "pad_token_id": 3,
168
+ "torch_dtype": "float32",
169
+ "transformers_version": "4.48.3",
170
+ "unk_token_id": null
171
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6be372034bfea27513abbb26d40814c6c9328c9f8179d21a47d4c1524a5a74a
3
+ size 31205552
runs/Mar04_10-36-19_ded47e188c04/events.out.tfevents.1741084580.ded47e188c04.378.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c69fb58e40ac96ca31d11ff63bdcb4e8a6a749d9737cee476a16f864eaaaaf
3
+ size 27952
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[EOS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[EOS]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Whitespace"
46
+ },
47
+ "post_processor": {
48
+ "type": "TemplateProcessing",
49
+ "single": [
50
+ {
51
+ "Sequence": {
52
+ "id": "A",
53
+ "type_id": 0
54
+ }
55
+ },
56
+ {
57
+ "SpecialToken": {
58
+ "id": "[EOS]",
59
+ "type_id": 0
60
+ }
61
+ }
62
+ ],
63
+ "pair": [
64
+ {
65
+ "Sequence": {
66
+ "id": "A",
67
+ "type_id": 0
68
+ }
69
+ },
70
+ {
71
+ "Sequence": {
72
+ "id": "B",
73
+ "type_id": 1
74
+ }
75
+ }
76
+ ],
77
+ "special_tokens": {
78
+ "[EOS]": {
79
+ "id": "[EOS]",
80
+ "ids": [
81
+ 0
82
+ ],
83
+ "tokens": [
84
+ "[EOS]"
85
+ ]
86
+ }
87
+ }
88
+ },
89
+ "decoder": null,
90
+ "model": {
91
+ "type": "BPE",
92
+ "dropout": null,
93
+ "unk_token": "[UNK]",
94
+ "continuing_subword_prefix": null,
95
+ "end_of_word_suffix": null,
96
+ "fuse_unk": false,
97
+ "byte_fallback": false,
98
+ "ignore_merges": false,
99
+ "vocab": {
100
+ "[EOS]": 0,
101
+ "[UNK]": 1,
102
+ "[CLS]": 2,
103
+ "[PAD]": 3,
104
+ "+": 4,
105
+ "-": 5,
106
+ "0": 6,
107
+ "1": 7,
108
+ "2": 8,
109
+ "3": 9,
110
+ "4": 10,
111
+ "5": 11,
112
+ "6": 12,
113
+ "7": 13,
114
+ "8": 14,
115
+ "9": 15,
116
+ "99": 16,
117
+ "10": 17,
118
+ "98": 18,
119
+ "11": 19,
120
+ "12": 20,
121
+ "97": 21,
122
+ "96": 22,
123
+ "13": 23,
124
+ "95": 24,
125
+ "14": 25,
126
+ "94": 26,
127
+ "15": 27,
128
+ "93": 28,
129
+ "16": 29,
130
+ "17": 30,
131
+ "92": 31,
132
+ "18": 32,
133
+ "91": 33,
134
+ "19": 34,
135
+ "90": 35,
136
+ "20": 36,
137
+ "89": 37,
138
+ "88": 38,
139
+ "21": 39,
140
+ "22": 40,
141
+ "87": 41,
142
+ "86": 42,
143
+ "23": 43,
144
+ "24": 44,
145
+ "85": 45,
146
+ "25": 46,
147
+ "84": 47,
148
+ "26": 48,
149
+ "83": 49,
150
+ "27": 50,
151
+ "82": 51
152
+ },
153
+ "merges": [
154
+ [
155
+ "9",
156
+ "9"
157
+ ],
158
+ [
159
+ "1",
160
+ "0"
161
+ ],
162
+ [
163
+ "9",
164
+ "8"
165
+ ],
166
+ [
167
+ "1",
168
+ "1"
169
+ ],
170
+ [
171
+ "1",
172
+ "2"
173
+ ],
174
+ [
175
+ "9",
176
+ "7"
177
+ ],
178
+ [
179
+ "9",
180
+ "6"
181
+ ],
182
+ [
183
+ "1",
184
+ "3"
185
+ ],
186
+ [
187
+ "9",
188
+ "5"
189
+ ],
190
+ [
191
+ "1",
192
+ "4"
193
+ ],
194
+ [
195
+ "9",
196
+ "4"
197
+ ],
198
+ [
199
+ "1",
200
+ "5"
201
+ ],
202
+ [
203
+ "9",
204
+ "3"
205
+ ],
206
+ [
207
+ "1",
208
+ "6"
209
+ ],
210
+ [
211
+ "1",
212
+ "7"
213
+ ],
214
+ [
215
+ "9",
216
+ "2"
217
+ ],
218
+ [
219
+ "1",
220
+ "8"
221
+ ],
222
+ [
223
+ "9",
224
+ "1"
225
+ ],
226
+ [
227
+ "1",
228
+ "9"
229
+ ],
230
+ [
231
+ "9",
232
+ "0"
233
+ ],
234
+ [
235
+ "2",
236
+ "0"
237
+ ],
238
+ [
239
+ "8",
240
+ "9"
241
+ ],
242
+ [
243
+ "8",
244
+ "8"
245
+ ],
246
+ [
247
+ "2",
248
+ "1"
249
+ ],
250
+ [
251
+ "2",
252
+ "2"
253
+ ],
254
+ [
255
+ "8",
256
+ "7"
257
+ ],
258
+ [
259
+ "8",
260
+ "6"
261
+ ],
262
+ [
263
+ "2",
264
+ "3"
265
+ ],
266
+ [
267
+ "2",
268
+ "4"
269
+ ],
270
+ [
271
+ "8",
272
+ "5"
273
+ ],
274
+ [
275
+ "2",
276
+ "5"
277
+ ],
278
+ [
279
+ "8",
280
+ "4"
281
+ ],
282
+ [
283
+ "2",
284
+ "6"
285
+ ],
286
+ [
287
+ "8",
288
+ "3"
289
+ ],
290
+ [
291
+ "2",
292
+ "7"
293
+ ],
294
+ [
295
+ "8",
296
+ "2"
297
+ ]
298
+ ]
299
+ }
300
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[EOS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "clean_up_tokenization_spaces": false,
37
+ "cls_token": "[CLS]",
38
+ "eos_token": "[EOS]",
39
+ "extra_special_tokens": {},
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "tokenizer_class": "PreTrainedTokenizerFast"
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1225831262cea0e78502e9eddde05c31aeb8f43cf012c95b75e28ab3d1282f72
3
+ size 5496