heskielsvn commited on
Commit
0a556fd
1 Parent(s): bbadd67

Training in progress, step 16

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "c474ac484667302929b368bfff4c54a7973351c6",
3
+ "_name_or_path": "google/roberta2roberta_L-24_cnn_daily_mail",
4
+ "architectures": [
5
+ "EncoderDecoderModel"
6
+ ],
7
+ "bos_token_id": 2,
8
+ "decoder": {
9
+ "_name_or_path": "",
10
+ "add_cross_attention": true,
11
+ "architectures": [
12
+ "BertGenerationEncoder"
13
+ ],
14
+ "attention_probs_dropout_prob": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "directionality": "bidi",
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "gradient_checkpointing": false,
32
+ "hidden_act": "gelu",
33
+ "hidden_dropout_prob": 0.1,
34
+ "hidden_size": 1024,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 4096,
41
+ "is_decoder": true,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-12,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 512,
51
+ "min_length": 0,
52
+ "model_type": "bert-generation",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 16,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 24,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 0,
63
+ "position_embedding_type": "absolute",
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": false,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.31.0",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 50358
88
+ },
89
+ "decoder_start_token_id": 2,
90
+ "early_stopping": true,
91
+ "encoder": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": [
95
+ "BertGenerationDecoder"
96
+ ],
97
+ "attention_probs_dropout_prob": 0.1,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "directionality": "bidi",
105
+ "diversity_penalty": 0.0,
106
+ "do_sample": false,
107
+ "early_stopping": false,
108
+ "encoder_no_repeat_ngram_size": 0,
109
+ "eos_token_id": null,
110
+ "exponential_decay_length_penalty": null,
111
+ "finetuning_task": null,
112
+ "forced_bos_token_id": null,
113
+ "forced_eos_token_id": null,
114
+ "gradient_checkpointing": false,
115
+ "hidden_act": "gelu",
116
+ "hidden_dropout_prob": 0.1,
117
+ "hidden_size": 1024,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "initializer_range": 0.02,
123
+ "intermediate_size": 4096,
124
+ "is_decoder": false,
125
+ "is_encoder_decoder": false,
126
+ "label2id": {
127
+ "LABEL_0": 0,
128
+ "LABEL_1": 1
129
+ },
130
+ "layer_norm_eps": 1e-12,
131
+ "length_penalty": 1.0,
132
+ "max_length": 20,
133
+ "max_position_embeddings": 512,
134
+ "min_length": 0,
135
+ "model_type": "bert-generation",
136
+ "no_repeat_ngram_size": 0,
137
+ "num_attention_heads": 16,
138
+ "num_beam_groups": 1,
139
+ "num_beams": 1,
140
+ "num_hidden_layers": 24,
141
+ "num_return_sequences": 1,
142
+ "output_attentions": false,
143
+ "output_hidden_states": false,
144
+ "output_scores": false,
145
+ "pad_token_id": 0,
146
+ "position_embedding_type": "absolute",
147
+ "prefix": null,
148
+ "problem_type": null,
149
+ "pruned_heads": {},
150
+ "remove_invalid_values": false,
151
+ "repetition_penalty": 1.0,
152
+ "return_dict": false,
153
+ "return_dict_in_generate": false,
154
+ "sep_token_id": null,
155
+ "suppress_tokens": null,
156
+ "task_specific_params": null,
157
+ "temperature": 1.0,
158
+ "tf_legacy_loss": false,
159
+ "tie_encoder_decoder": false,
160
+ "tie_word_embeddings": true,
161
+ "tokenizer_class": null,
162
+ "top_k": 50,
163
+ "top_p": 1.0,
164
+ "torch_dtype": null,
165
+ "torchscript": false,
166
+ "transformers_version": "4.31.0",
167
+ "typical_p": 1.0,
168
+ "use_bfloat16": false,
169
+ "use_cache": true,
170
+ "vocab_size": 50358
171
+ },
172
+ "eos_token_id": 1,
173
+ "is_encoder_decoder": true,
174
+ "length_penalty": 2.0,
175
+ "max_length": 40,
176
+ "model_type": "encoder-decoder",
177
+ "no_repeat_ngram_size": 3,
178
+ "num_beams": 4,
179
+ "pad_token_id": 0,
180
+ "tie_encoder_decoder": true,
181
+ "torch_dtype": "float32",
182
+ "transformers_version": null,
183
+ "vocab_size": 50358
184
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46fddb539a7f3706d45b427e7090e457c714960da2715ffc23f376f9359f1e06
3
+ size 1821331489
runs/Jul19_12-42-23_fb1e2e73504b/events.out.tfevents.1689770553.fb1e2e73504b.427.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb493107d04440659710e149e3bcd767009c49dbe048a3ec74cb1e5439b919a1
3
+ size 9836
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce61409f896cb3b843a760b84b85ab3c47e86343c89487e3320c41c603047bdb
3
+ size 4155