MahsaShahidi commited on
Commit
9484e68
1 Parent(s): b23ef22

Training in progress, step 7000

Browse files
Files changed (5) hide show
  1. .gitignore +1 -0
  2. config.json +182 -0
  3. preprocessor_config.json +17 -0
  4. pytorch_model.bin +3 -0
  5. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "HooshvareLab/bert-fa-base-uncased-clf-persiannews",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForSequenceClassification"
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": "persiannews",
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": "\u0627\u062c\u062a\u0645\u0627\u0639\u06cc",
32
+ "1": "\u0627\u0642\u062a\u0635\u0627\u062f\u06cc",
33
+ "2": "\u0628\u06cc\u0646 \u0627\u0644\u0645\u0644\u0644",
34
+ "3": "\u0633\u06cc\u0627\u0633\u06cc",
35
+ "4": "\u0639\u0644\u0645\u06cc \u0641\u0646\u0627\u0648\u0631\u06cc",
36
+ "5": "\u0641\u0631\u0647\u0646\u06af\u06cc \u0647\u0646\u0631\u06cc",
37
+ "6": "\u0648\u0631\u0632\u0634\u06cc",
38
+ "7": "\u067e\u0632\u0634\u06a9\u06cc"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "is_decoder": true,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "\u0627\u062c\u062a\u0645\u0627\u0639\u06cc": 0,
46
+ "\u0627\u0642\u062a\u0635\u0627\u062f\u06cc": 1,
47
+ "\u0628\u06cc\u0646 \u0627\u0644\u0645\u0644\u0644": 2,
48
+ "\u0633\u06cc\u0627\u0633\u06cc": 3,
49
+ "\u0639\u0644\u0645\u06cc \u0641\u0646\u0627\u0648\u0631\u06cc": 4,
50
+ "\u0641\u0631\u0647\u0646\u06af\u06cc \u0647\u0646\u0631\u06cc": 5,
51
+ "\u0648\u0631\u0632\u0634\u06cc": 6,
52
+ "\u067e\u0632\u0634\u06a9\u06cc": 7
53
+ },
54
+ "layer_norm_eps": 1e-12,
55
+ "length_penalty": 1.0,
56
+ "max_length": 20,
57
+ "max_position_embeddings": 512,
58
+ "min_length": 0,
59
+ "model_type": "bert",
60
+ "no_repeat_ngram_size": 0,
61
+ "num_attention_heads": 12,
62
+ "num_beam_groups": 1,
63
+ "num_beams": 1,
64
+ "num_hidden_layers": 12,
65
+ "num_return_sequences": 1,
66
+ "output_attentions": false,
67
+ "output_hidden_states": false,
68
+ "output_scores": false,
69
+ "pad_token_id": 0,
70
+ "position_embedding_type": "absolute",
71
+ "prefix": null,
72
+ "problem_type": null,
73
+ "pruned_heads": {},
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "return_dict": true,
77
+ "return_dict_in_generate": false,
78
+ "sep_token_id": null,
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": true,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": null,
87
+ "torchscript": false,
88
+ "transformers_version": "4.12.5",
89
+ "type_vocab_size": 2,
90
+ "use_bfloat16": false,
91
+ "use_cache": true,
92
+ "vocab_size": 100001
93
+ },
94
+ "decoder_start_token_id": 2,
95
+ "early_stopping": true,
96
+ "encoder": {
97
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
98
+ "add_cross_attention": false,
99
+ "architectures": [
100
+ "ViTModel"
101
+ ],
102
+ "attention_probs_dropout_prob": 0.0,
103
+ "bad_words_ids": null,
104
+ "bos_token_id": null,
105
+ "chunk_size_feed_forward": 0,
106
+ "cross_attention_hidden_size": null,
107
+ "decoder_start_token_id": null,
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
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "gelu",
117
+ "hidden_dropout_prob": 0.0,
118
+ "hidden_size": 768,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "image_size": 224,
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
+ "min_length": 0,
136
+ "model_type": "vit",
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": 16,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "pruned_heads": {},
152
+ "qkv_bias": true,
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
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tie_encoder_decoder": false,
161
+ "tie_word_embeddings": true,
162
+ "tokenizer_class": null,
163
+ "top_k": 50,
164
+ "top_p": 1.0,
165
+ "torch_dtype": null,
166
+ "torchscript": false,
167
+ "transformers_version": "4.12.5",
168
+ "use_bfloat16": false
169
+ },
170
+ "eos_token_id": 4,
171
+ "is_encoder_decoder": true,
172
+ "length_penalty": 2.0,
173
+ "max_length": 30,
174
+ "model_type": "vision-encoder-decoder",
175
+ "no_repeat_ngram_size": 3,
176
+ "num_beams": 4,
177
+ "pad_token_id": 0,
178
+ "tie_word_embeddings": false,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": null,
181
+ "vocab_size": 100001
182
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 224
17
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3eb62921c87e0e7bf920a9dc9e1cba1f3eb05a991d5eb976c3852317640c453
3
+ size 1111020587
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfebb0bf97ee97f3f6b1bb9277b813efc566b6b066d7c226a643a486bea99aa5
3
+ size 2927