Ayham commited on
Commit
dd2169c
1 Parent(s): e7b8216

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bert-base-uncased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": 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
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
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": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
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
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.12.0.dev0",
77
+ "type_vocab_size": 2,
78
+ "use_bfloat16": false,
79
+ "use_cache": true,
80
+ "vocab_size": 30522
81
+ },
82
+ "decoder_start_token_id": 101,
83
+ "early_stopping": true,
84
+ "encoder": {
85
+ "_name_or_path": "albert-base-v2",
86
+ "add_cross_attention": false,
87
+ "architectures": [
88
+ "AlbertForMaskedLM"
89
+ ],
90
+ "attention_probs_dropout_prob": 0,
91
+ "bad_words_ids": null,
92
+ "bos_token_id": 2,
93
+ "chunk_size_feed_forward": 0,
94
+ "classifier_dropout_prob": 0.1,
95
+ "cross_attention_hidden_size": null,
96
+ "decoder_start_token_id": null,
97
+ "diversity_penalty": 0.0,
98
+ "do_sample": false,
99
+ "down_scale_factor": 1,
100
+ "early_stopping": false,
101
+ "embedding_size": 128,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "eos_token_id": 3,
104
+ "finetuning_task": null,
105
+ "forced_bos_token_id": null,
106
+ "forced_eos_token_id": null,
107
+ "gap_size": 0,
108
+ "hidden_act": "gelu_new",
109
+ "hidden_dropout_prob": 0,
110
+ "hidden_size": 768,
111
+ "id2label": {
112
+ "0": "LABEL_0",
113
+ "1": "LABEL_1"
114
+ },
115
+ "initializer_range": 0.02,
116
+ "inner_group_num": 1,
117
+ "intermediate_size": 3072,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "layer_norm_eps": 1e-12,
125
+ "length_penalty": 1.0,
126
+ "max_length": 20,
127
+ "max_position_embeddings": 512,
128
+ "min_length": 0,
129
+ "model_type": "albert",
130
+ "net_structure_type": 0,
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 12,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_hidden_groups": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_memory_blocks": 0,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": 0,
143
+ "position_embedding_type": "absolute",
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "pruned_heads": {},
147
+ "remove_invalid_values": false,
148
+ "repetition_penalty": 1.0,
149
+ "return_dict": true,
150
+ "return_dict_in_generate": false,
151
+ "sep_token_id": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tie_encoder_decoder": false,
155
+ "tie_word_embeddings": true,
156
+ "tokenizer_class": null,
157
+ "top_k": 50,
158
+ "top_p": 1.0,
159
+ "torch_dtype": null,
160
+ "torchscript": false,
161
+ "transformers_version": "4.12.0.dev0",
162
+ "type_vocab_size": 2,
163
+ "use_bfloat16": false,
164
+ "vocab_size": 30000
165
+ },
166
+ "eos_token_id": 102,
167
+ "is_encoder_decoder": true,
168
+ "length_penalty": 2.0,
169
+ "max_length": 93,
170
+ "min_length": 35,
171
+ "model_type": "encoder-decoder",
172
+ "no_repeat_ngram_size": 3,
173
+ "num_beams": 4,
174
+ "pad_token_id": 0,
175
+ "torch_dtype": "float32",
176
+ "transformers_version": null,
177
+ "vocab_size": 30000
178
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66323f7fa0cef172ce3629fc697167625de517cfa5efe5e3a802aa99305dd95a
3
+ size 598413895
runs/Feb25_04-18-09_d955e209897a/1645762711.6654005/events.out.tfevents.1645762711.d955e209897a.126.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd55e6756a4ccdd4b7fdfb38c83d0522e1e87d2fb8fed391a3097352b09724b
3
+ size 4817
runs/Feb25_04-18-09_d955e209897a/events.out.tfevents.1645762711.d955e209897a.126.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a551b2b2ffbe0236260789c3f3bacdbb0932868a4f8618ebe1358baaceda376c
3
+ size 7530
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f9c2eb4334a1bb107f6994e34c6701743e085bf28ebfc8b5636737bba184a01
3
+ size 2991