Hugging Face's logo

salma-elshafey
/
mbert2mbert-finetuned-ar-to-en

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
Inference Endpoints
Model card Files Metrics Community
salma-elshafey commited on
Commit
b1039cf
•
1 Parent(s): 7f7e103

Training in progress, step 500

Browse files
Files changed (12) hide show
  1. .gitignore +1 -0
  2. config.json +187 -0
  3. pytorch_model.bin +3 -0
  4. runs/May23_16-40-45_db91f98c102f/1653324069.5677004/events.out.tfevents.1653324069.db91f98c102f.74.1 +3 -0
  5. runs/May23_16-40-45_db91f98c102f/events.out.tfevents.1653324069.db91f98c102f.74.0 +3 -0
  6. runs/May23_16-41-38_db91f98c102f/1653324107.122137/events.out.tfevents.1653324107.db91f98c102f.74.3 +3 -0
  7. runs/May23_16-41-38_db91f98c102f/events.out.tfevents.1653324107.db91f98c102f.74.2 +3 -0
  8. runs/May23_16-41-56_db91f98c102f/1653324125.0727985/events.out.tfevents.1653324125.db91f98c102f.74.5 +3 -0
  9. runs/May23_16-41-56_db91f98c102f/events.out.tfevents.1653324125.db91f98c102f.74.4 +3 -0
  10. runs/May23_16-42-15_db91f98c102f/1653324144.0336692/events.out.tfevents.1653324144.db91f98c102f.74.7 +3 -0
  11. runs/May23_16-42-15_db91f98c102f/events.out.tfevents.1653324144.db91f98c102f.74.6 +3 -0
  12. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bert-base-multilingual-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
+ "directionality": "bidi",
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "gelu",
29
+ "hidden_dropout_prob": 0.1,
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 512,
47
+ "min_length": 0,
48
+ "model_type": "bert",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 12,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 12,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": 0,
59
+ "pooler_fc_size": 768,
60
+ "pooler_num_attention_heads": 12,
61
+ "pooler_num_fc_layers": 3,
62
+ "pooler_size_per_head": 128,
63
+ "pooler_type": "first_token_transform",
64
+ "position_embedding_type": "absolute",
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "sep_token_id": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.19.2",
83
+ "type_vocab_size": 2,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": false,
87
+ "vocab_size": 105879
88
+ },
89
+ "decoder_start_token_id": 101,
90
+ "early_stopping": true,
91
+ "encoder": {
92
+ "_name_or_path": "bert-base-multilingual-uncased",
93
+ "add_cross_attention": false,
94
+ "architectures": [
95
+ "BertForMaskedLM"
96
+ ],
97
+ "attention_probs_dropout_prob": 0.1,
98
+ "bad_words_ids": null,
99
+ "bos_token_id": null,
100
+ "chunk_size_feed_forward": 0,
101
+ "classifier_dropout": null,
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
+ "hidden_act": "gelu",
115
+ "hidden_dropout_prob": 0.1,
116
+ "hidden_size": 768,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 3072,
123
+ "is_decoder": false,
124
+ "is_encoder_decoder": false,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "layer_norm_eps": 1e-12,
130
+ "length_penalty": 1.0,
131
+ "max_length": 20,
132
+ "max_position_embeddings": 512,
133
+ "min_length": 0,
134
+ "model_type": "bert",
135
+ "no_repeat_ngram_size": 0,
136
+ "num_attention_heads": 12,
137
+ "num_beam_groups": 1,
138
+ "num_beams": 1,
139
+ "num_hidden_layers": 12,
140
+ "num_return_sequences": 1,
141
+ "output_attentions": false,
142
+ "output_hidden_states": false,
143
+ "output_scores": false,
144
+ "pad_token_id": 0,
145
+ "pooler_fc_size": 768,
146
+ "pooler_num_attention_heads": 12,
147
+ "pooler_num_fc_layers": 3,
148
+ "pooler_size_per_head": 128,
149
+ "pooler_type": "first_token_transform",
150
+ "position_embedding_type": "absolute",
151
+ "prefix": null,
152
+ "problem_type": null,
153
+ "pruned_heads": {},
154
+ "remove_invalid_values": false,
155
+ "repetition_penalty": 1.0,
156
+ "return_dict": true,
157
+ "return_dict_in_generate": false,
158
+ "sep_token_id": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.19.2",
169
+ "type_vocab_size": 2,
170
+ "typical_p": 1.0,
171
+ "use_bfloat16": false,
172
+ "use_cache": true,
173
+ "vocab_size": 105879
174
+ },
175
+ "eos_token_id": 102,
176
+ "is_encoder_decoder": true,
177
+ "length_penalty": 2.0,
178
+ "max_length": 142,
179
+ "min_length": 56,
180
+ "model_type": "encoder-decoder",
181
+ "no_repeat_ngram_size": 3,
182
+ "num_beams": 4,
183
+ "pad_token_id": 0,
184
+ "torch_dtype": "float32",
185
+ "transformers_version": null,
186
+ "vocab_size": 105879
187
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91fe2e3495e75e912159beab7c56725eeab478c54e786738c1e50564eb44b229
3
+ size 1452935979
runs/May23_16-40-45_db91f98c102f/1653324069.5677004/events.out.tfevents.1653324069.db91f98c102f.74.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f834e39dc7c63c3644864fd89f662b558c449da8a672aaa49898925af09779be
3
+ size 5201
runs/May23_16-40-45_db91f98c102f/events.out.tfevents.1653324069.db91f98c102f.74.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad066e1385d4c3948beb5797f69e4888655d8c3420249ae75019f6c6f65a4c6
3
+ size 7929
runs/May23_16-41-38_db91f98c102f/1653324107.122137/events.out.tfevents.1653324107.db91f98c102f.74.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51d07e06b9c245410f1c81f29c41724c883d92eb09408f8c1482e85c64ba8c3
3
+ size 5201
runs/May23_16-41-38_db91f98c102f/events.out.tfevents.1653324107.db91f98c102f.74.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64ea994d64efd9a9e37d94f014c3c66ff126ba052cb0dd20de6f8f98179de256
3
+ size 7929
runs/May23_16-41-56_db91f98c102f/1653324125.0727985/events.out.tfevents.1653324125.db91f98c102f.74.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef71000c19b599c889186f48ba7264edb059836354320a18a52fff85f554cfaf
3
+ size 5201
runs/May23_16-41-56_db91f98c102f/events.out.tfevents.1653324125.db91f98c102f.74.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0176b89c77c2430db1a03e0157e7ad9ea59c8abb26d53a0c737e2da09bf3b224
3
+ size 7929
runs/May23_16-42-15_db91f98c102f/1653324144.0336692/events.out.tfevents.1653324144.db91f98c102f.74.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5d275e0ef874baecd891e158c8d9b30f5cfa0b71a6eec8a29a3823c1cb23a8
3
+ size 5201
runs/May23_16-42-15_db91f98c102f/events.out.tfevents.1653324144.db91f98c102f.74.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7fa834b3f06ea9fdd25e3ff5b228bb5e1cfcfd4bfe693c1980887c862cc79e
3
+ size 8243
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e9f18e25044fc09fb9c90ea78dcfc4e4f773b887e05dde6c99d8267b3541dc
3
+ size 3247