folflo commited on
Commit
519f720
1 Parent(s): a3d2770

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bert-base-multilingual-cased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "directionality": "bidi",
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 512,
48
+ "min_length": 0,
49
+ "model_type": "bert",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 0,
60
+ "pooler_fc_size": 768,
61
+ "pooler_num_attention_heads": 12,
62
+ "pooler_num_fc_layers": 3,
63
+ "pooler_size_per_head": 128,
64
+ "pooler_type": "first_token_transform",
65
+ "position_embedding_type": "absolute",
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "type_vocab_size": 2,
86
+ "typical_p": 1.0,
87
+ "use_bfloat16": false,
88
+ "use_cache": true,
89
+ "vocab_size": 119547
90
+ },
91
+ "decoder_start_token_id": 2,
92
+ "early_stopping": true,
93
+ "encoder": {
94
+ "_name_or_path": "bert-base-multilingual-cased",
95
+ "add_cross_attention": false,
96
+ "architectures": [
97
+ "BertForMaskedLM"
98
+ ],
99
+ "attention_probs_dropout_prob": 0.1,
100
+ "bad_words_ids": null,
101
+ "begin_suppress_tokens": null,
102
+ "bos_token_id": null,
103
+ "chunk_size_feed_forward": 0,
104
+ "classifier_dropout": null,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "directionality": "bidi",
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_act": "gelu",
118
+ "hidden_dropout_prob": 0.1,
119
+ "hidden_size": 768,
120
+ "id2label": {
121
+ "0": "LABEL_0",
122
+ "1": "LABEL_1"
123
+ },
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 3072,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_eps": 1e-12,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "max_position_embeddings": 512,
136
+ "min_length": 0,
137
+ "model_type": "bert",
138
+ "no_repeat_ngram_size": 0,
139
+ "num_attention_heads": 12,
140
+ "num_beam_groups": 1,
141
+ "num_beams": 1,
142
+ "num_hidden_layers": 12,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": 0,
148
+ "pooler_fc_size": 768,
149
+ "pooler_num_attention_heads": 12,
150
+ "pooler_num_fc_layers": 3,
151
+ "pooler_size_per_head": 128,
152
+ "pooler_type": "first_token_transform",
153
+ "position_embedding_type": "absolute",
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "pruned_heads": {},
157
+ "remove_invalid_values": false,
158
+ "repetition_penalty": 1.0,
159
+ "return_dict": true,
160
+ "return_dict_in_generate": false,
161
+ "sep_token_id": null,
162
+ "suppress_tokens": null,
163
+ "task_specific_params": null,
164
+ "temperature": 1.0,
165
+ "tf_legacy_loss": false,
166
+ "tie_encoder_decoder": false,
167
+ "tie_word_embeddings": true,
168
+ "tokenizer_class": null,
169
+ "top_k": 50,
170
+ "top_p": 1.0,
171
+ "torch_dtype": null,
172
+ "torchscript": false,
173
+ "type_vocab_size": 2,
174
+ "typical_p": 1.0,
175
+ "use_bfloat16": false,
176
+ "use_cache": true,
177
+ "vocab_size": 119547
178
+ },
179
+ "eos_token_id": 3,
180
+ "is_encoder_decoder": true,
181
+ "length_penalty": 2.0,
182
+ "max_length": 256,
183
+ "min_length": 56,
184
+ "model_type": "encoder-decoder",
185
+ "no_repeat_ngram_size": 3,
186
+ "num_beams": 4,
187
+ "pad_token_id": 0,
188
+ "torch_dtype": "float32",
189
+ "transformers_version": "4.35.1",
190
+ "vocab_size": 119547
191
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a979f748be1999b5276b1a67f4352c4d18debc612ec0390a99f7b65c8493f70
3
+ size 1536844884
runs/Nov28_22-17-36_TENSOR-FLOWER/events.out.tfevents.1701206258.TENSOR-FLOWER.9200.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f2243d9b80b6f94c11a996c31e743d9559a1713296256509aca4d161931d5a
3
+ size 8927
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c37942da36d438a39c3f0a69027257a82de84c0da71f841cdef5e139056204ce
3
+ size 6264