Hugging Face's logo

LinaAlhuri
/
clip-bert-lit-two-stages

Text-to-Image
Transformers
PyTorch
TensorBoard
Arabic
vision-text-dual-encoder
feature-extraction
Inference Endpoints
Model card Files Metrics Community
LinaAlhuri commited on
Commit
dd14477
•
1 Parent(s): 9486fa3

Training in progress, step 2000

Browse files
Files changed (8) hide show
  1. .gitignore +1 -0
  2. config.json +173 -0
  3. pytorch_model.bin +3 -0
  4. runs/Apr28_09-48-27_150-230-41-34/1682675317.4957235/events.out.tfevents.1682675317.150-230-41-34.392970.1 +3 -0
  5. runs/Apr28_09-48-27_150-230-41-34/events.out.tfevents.1682675317.150-230-41-34.392970.0 +3 -0
  6. runs/Apr28_09-49-19_150-230-41-34/1682675369.3414366/events.out.tfevents.1682675369.150-230-41-34.393238.1 +3 -0
  7. runs/Apr28_09-49-19_150-230-41-34/events.out.tfevents.1682675369.150-230-41-34.393238.0 +3 -0
  8. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./v1",
4
+ "architectures": [
5
+ "VisionTextDualEncoderModel"
6
+ ],
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "vision-text-dual-encoder",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "_name_or_path": "asafaya/bert-base-arabic",
12
+ "add_cross_attention": false,
13
+ "architectures": [
14
+ "BertForMaskedLM"
15
+ ],
16
+ "attention_probs_dropout_prob": 0.1,
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": null,
20
+ "chunk_size_feed_forward": 0,
21
+ "classifier_dropout": null,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": null,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "gradient_checkpointing": false,
34
+ "hidden_act": "gelu",
35
+ "hidden_dropout_prob": 0.1,
36
+ "hidden_size": 768,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "is_decoder": false,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "layer_norm_eps": 1e-12,
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "max_position_embeddings": 512,
53
+ "min_length": 0,
54
+ "model_type": "bert",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_attention_heads": 12,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 12,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_past": true,
64
+ "output_scores": false,
65
+ "pad_token_id": 0,
66
+ "position_embedding_type": "absolute",
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": null,
75
+ "suppress_tokens": null,
76
+ "task_specific_params": null,
77
+ "temperature": 1.0,
78
+ "tf_legacy_loss": false,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": true,
81
+ "tokenizer_class": null,
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": null,
85
+ "torchscript": false,
86
+ "transformers_version": "4.29.0.dev0",
87
+ "type_vocab_size": 2,
88
+ "typical_p": 1.0,
89
+ "use_bfloat16": false,
90
+ "use_cache": true,
91
+ "vocab_size": 32000
92
+ },
93
+ "torch_dtype": "float32",
94
+ "transformers_version": null,
95
+ "vision_config": {
96
+ "_name_or_path": "openai/clip-vit-base-patch32",
97
+ "add_cross_attention": false,
98
+ "architectures": null,
99
+ "attention_dropout": 0.0,
100
+ "bad_words_ids": null,
101
+ "begin_suppress_tokens": null,
102
+ "bos_token_id": null,
103
+ "chunk_size_feed_forward": 0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "dropout": 0.0,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "quick_gelu",
117
+ "hidden_size": 768,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": 224,
123
+ "initializer_factor": 1.0,
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-05,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "clip_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 12,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
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": null,
148
+ "patch_size": 32,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "projection_dim": 512,
152
+ "pruned_heads": {},
153
+ "remove_invalid_values": false,
154
+ "repetition_penalty": 1.0,
155
+ "return_dict": true,
156
+ "return_dict_in_generate": false,
157
+ "sep_token_id": null,
158
+ "suppress_tokens": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tf_legacy_loss": false,
162
+ "tie_encoder_decoder": false,
163
+ "tie_word_embeddings": true,
164
+ "tokenizer_class": null,
165
+ "top_k": 50,
166
+ "top_p": 1.0,
167
+ "torch_dtype": null,
168
+ "torchscript": false,
169
+ "transformers_version": "4.29.0.dev0",
170
+ "typical_p": 1.0,
171
+ "use_bfloat16": false
172
+ }
173
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333ac156bb6d4fbe91f6abea9af9300fc6101fd6ca3aade34be4db7fac6bdd78
3
+ size 795582555
runs/Apr28_09-48-27_150-230-41-34/1682675317.4957235/events.out.tfevents.1682675317.150-230-41-34.392970.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e924a5d49277f16702a70daf278a070a65f2a34ddb8311f0db9aa9370ff1a3
3
+ size 5936
runs/Apr28_09-48-27_150-230-41-34/events.out.tfevents.1682675317.150-230-41-34.392970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005feb31401cfb1d15b9933d09bdd1c3ea0c0806c68c5b4c652a93b9e569d053
3
+ size 8148
runs/Apr28_09-49-19_150-230-41-34/1682675369.3414366/events.out.tfevents.1682675369.150-230-41-34.393238.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403c4cbdc5530d8e83eb0b8fdda302543c27d7a2b49a793d669b2e4007e29a03
3
+ size 5936
runs/Apr28_09-49-19_150-230-41-34/events.out.tfevents.1682675369.150-230-41-34.393238.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1fcfecc9a2276c1db969f2740ce02d6ddee039b8bd7527ac6eb35d3a31ee6b
3
+ size 8303
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31798ae6d781cf56dcfa9e6c65fced521acb346ef1ab609fd9c9a536155a641e
3
+ size 3951