Training in progress, step 120
Browse files- config.json +227 -227
- model.safetensors +1 -1
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,227 +1,227 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"VisionTextDualEncoderModel"
|
| 4 |
-
],
|
| 5 |
-
"cache_dir": null,
|
| 6 |
-
"logit_scale_init_value": 2.6592,
|
| 7 |
-
"model_type": "vision-text-dual-encoder",
|
| 8 |
-
"projection_dim": 512,
|
| 9 |
-
"revision": "main",
|
| 10 |
-
"text_config": {
|
| 11 |
-
"_name_or_path": "ckiplab/bert-base-chinese",
|
| 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 |
-
"directionality": "bidi",
|
| 25 |
-
"diversity_penalty": 0.0,
|
| 26 |
-
"do_sample": false,
|
| 27 |
-
"early_stopping": false,
|
| 28 |
-
"encoder_no_repeat_ngram_size": 0,
|
| 29 |
-
"eos_token_id": null,
|
| 30 |
-
"exponential_decay_length_penalty": null,
|
| 31 |
-
"finetuning_task": null,
|
| 32 |
-
"forced_bos_token_id": null,
|
| 33 |
-
"forced_eos_token_id": null,
|
| 34 |
-
"gradient_checkpointing": false,
|
| 35 |
-
"hidden_act": "gelu",
|
| 36 |
-
"hidden_dropout_prob": 0.1,
|
| 37 |
-
"hidden_size": 768,
|
| 38 |
-
"id2label": {
|
| 39 |
-
"0": "LABEL_0",
|
| 40 |
-
"1": "LABEL_1"
|
| 41 |
-
},
|
| 42 |
-
"initializer_range": 0.02,
|
| 43 |
-
"intermediate_size": 3072,
|
| 44 |
-
"is_decoder": false,
|
| 45 |
-
"is_encoder_decoder": false,
|
| 46 |
-
"label2id": {
|
| 47 |
-
"LABEL_0": 0,
|
| 48 |
-
"LABEL_1": 1
|
| 49 |
-
},
|
| 50 |
-
"layer_norm_eps": 1e-12,
|
| 51 |
-
"length_penalty": 1.0,
|
| 52 |
-
"max_length": 20,
|
| 53 |
-
"max_position_embeddings": 512,
|
| 54 |
-
"min_length": 0,
|
| 55 |
-
"model_type": "bert",
|
| 56 |
-
"no_repeat_ngram_size": 0,
|
| 57 |
-
"num_attention_heads": 12,
|
| 58 |
-
"num_beam_groups": 1,
|
| 59 |
-
"num_beams": 1,
|
| 60 |
-
"num_hidden_layers": 12,
|
| 61 |
-
"num_return_sequences": 1,
|
| 62 |
-
"output_attentions": false,
|
| 63 |
-
"output_hidden_states": false,
|
| 64 |
-
"output_scores": false,
|
| 65 |
-
"pad_token_id": 0,
|
| 66 |
-
"pooler_fc_size": 768,
|
| 67 |
-
"pooler_num_attention_heads": 12,
|
| 68 |
-
"pooler_num_fc_layers": 3,
|
| 69 |
-
"pooler_size_per_head": 128,
|
| 70 |
-
"pooler_type": "first_token_transform",
|
| 71 |
-
"position_embedding_type": "absolute",
|
| 72 |
-
"prefix": null,
|
| 73 |
-
"problem_type": null,
|
| 74 |
-
"pruned_heads": {},
|
| 75 |
-
"remove_invalid_values": false,
|
| 76 |
-
"repetition_penalty": 1.0,
|
| 77 |
-
"return_dict": true,
|
| 78 |
-
"return_dict_in_generate": false,
|
| 79 |
-
"sep_token_id": null,
|
| 80 |
-
"suppress_tokens": null,
|
| 81 |
-
"task_specific_params": null,
|
| 82 |
-
"temperature": 1.0,
|
| 83 |
-
"tf_legacy_loss": false,
|
| 84 |
-
"tie_encoder_decoder": false,
|
| 85 |
-
"tie_word_embeddings": true,
|
| 86 |
-
"tokenizer_class": "BertTokenizerFast",
|
| 87 |
-
"top_k": 50,
|
| 88 |
-
"top_p": 1.0,
|
| 89 |
-
"torch_dtype": null,
|
| 90 |
-
"torchscript": false,
|
| 91 |
-
"type_vocab_size": 2,
|
| 92 |
-
"typical_p": 1.0,
|
| 93 |
-
"use_bfloat16": false,
|
| 94 |
-
"use_cache": true,
|
| 95 |
-
"vocab_size": 21128
|
| 96 |
-
},
|
| 97 |
-
"token": null,
|
| 98 |
-
"torch_dtype": "float32",
|
| 99 |
-
"transformers_version": "4.
|
| 100 |
-
"trust_remote_code": false,
|
| 101 |
-
"vision_config": {
|
| 102 |
-
"_name_or_path": "microsoft/dit-base",
|
| 103 |
-
"add_cross_attention": false,
|
| 104 |
-
"add_fpn": false,
|
| 105 |
-
"architectures": [
|
| 106 |
-
"BeitForMaskedImageModeling"
|
| 107 |
-
],
|
| 108 |
-
"attention_probs_dropout_prob": 0.0,
|
| 109 |
-
"auxiliary_channels": 256,
|
| 110 |
-
"auxiliary_concat_input": false,
|
| 111 |
-
"auxiliary_loss_weight": 0.4,
|
| 112 |
-
"auxiliary_num_convs": 1,
|
| 113 |
-
"bad_words_ids": null,
|
| 114 |
-
"begin_suppress_tokens": null,
|
| 115 |
-
"bos_token_id": null,
|
| 116 |
-
"chunk_size_feed_forward": 0,
|
| 117 |
-
"cross_attention_hidden_size": null,
|
| 118 |
-
"decoder_start_token_id": null,
|
| 119 |
-
"diversity_penalty": 0.0,
|
| 120 |
-
"do_sample": false,
|
| 121 |
-
"drop_path_rate": 0.1,
|
| 122 |
-
"early_stopping": false,
|
| 123 |
-
"encoder_no_repeat_ngram_size": 0,
|
| 124 |
-
"eos_token_id": null,
|
| 125 |
-
"exponential_decay_length_penalty": null,
|
| 126 |
-
"finetuning_task": null,
|
| 127 |
-
"forced_bos_token_id": null,
|
| 128 |
-
"forced_eos_token_id": null,
|
| 129 |
-
"hidden_act": "gelu",
|
| 130 |
-
"hidden_dropout_prob": 0.0,
|
| 131 |
-
"hidden_size": 768,
|
| 132 |
-
"id2label": {
|
| 133 |
-
"0": "LABEL_0",
|
| 134 |
-
"1": "LABEL_1"
|
| 135 |
-
},
|
| 136 |
-
"image_size": 224,
|
| 137 |
-
"initializer_range": 0.02,
|
| 138 |
-
"intermediate_size": 3072,
|
| 139 |
-
"is_decoder": false,
|
| 140 |
-
"is_encoder_decoder": false,
|
| 141 |
-
"label2id": {
|
| 142 |
-
"LABEL_0": 0,
|
| 143 |
-
"LABEL_1": 1
|
| 144 |
-
},
|
| 145 |
-
"layer_norm_eps": 1e-12,
|
| 146 |
-
"layer_scale_init_value": 0.1,
|
| 147 |
-
"length_penalty": 1.0,
|
| 148 |
-
"max_length": 20,
|
| 149 |
-
"min_length": 0,
|
| 150 |
-
"model_type": "beit",
|
| 151 |
-
"no_repeat_ngram_size": 0,
|
| 152 |
-
"num_attention_heads": 12,
|
| 153 |
-
"num_beam_groups": 1,
|
| 154 |
-
"num_beams": 1,
|
| 155 |
-
"num_channels": 3,
|
| 156 |
-
"num_hidden_layers": 12,
|
| 157 |
-
"num_return_sequences": 1,
|
| 158 |
-
"out_features": [
|
| 159 |
-
"stage3",
|
| 160 |
-
"stage5",
|
| 161 |
-
"stage7",
|
| 162 |
-
"stage11"
|
| 163 |
-
],
|
| 164 |
-
"out_indices": [
|
| 165 |
-
3,
|
| 166 |
-
5,
|
| 167 |
-
7,
|
| 168 |
-
11
|
| 169 |
-
],
|
| 170 |
-
"output_attentions": false,
|
| 171 |
-
"output_hidden_states": false,
|
| 172 |
-
"output_scores": false,
|
| 173 |
-
"pad_token_id": null,
|
| 174 |
-
"patch_size": 16,
|
| 175 |
-
"pool_scales": [
|
| 176 |
-
1,
|
| 177 |
-
2,
|
| 178 |
-
3,
|
| 179 |
-
6
|
| 180 |
-
],
|
| 181 |
-
"prefix": null,
|
| 182 |
-
"problem_type": null,
|
| 183 |
-
"pruned_heads": {},
|
| 184 |
-
"remove_invalid_values": false,
|
| 185 |
-
"repetition_penalty": 1.0,
|
| 186 |
-
"reshape_hidden_states": true,
|
| 187 |
-
"return_dict": true,
|
| 188 |
-
"return_dict_in_generate": false,
|
| 189 |
-
"semantic_loss_ignore_index": 255,
|
| 190 |
-
"sep_token_id": null,
|
| 191 |
-
"stage_names": [
|
| 192 |
-
"stem",
|
| 193 |
-
"stage1",
|
| 194 |
-
"stage2",
|
| 195 |
-
"stage3",
|
| 196 |
-
"stage4",
|
| 197 |
-
"stage5",
|
| 198 |
-
"stage6",
|
| 199 |
-
"stage7",
|
| 200 |
-
"stage8",
|
| 201 |
-
"stage9",
|
| 202 |
-
"stage10",
|
| 203 |
-
"stage11",
|
| 204 |
-
"stage12"
|
| 205 |
-
],
|
| 206 |
-
"suppress_tokens": null,
|
| 207 |
-
"task_specific_params": null,
|
| 208 |
-
"temperature": 1.0,
|
| 209 |
-
"tf_legacy_loss": false,
|
| 210 |
-
"tie_encoder_decoder": false,
|
| 211 |
-
"tie_word_embeddings": true,
|
| 212 |
-
"tokenizer_class": null,
|
| 213 |
-
"top_k": 50,
|
| 214 |
-
"top_p": 1.0,
|
| 215 |
-
"torch_dtype": "float32",
|
| 216 |
-
"torchscript": false,
|
| 217 |
-
"typical_p": 1.0,
|
| 218 |
-
"use_absolute_position_embeddings": true,
|
| 219 |
-
"use_auxiliary_head": true,
|
| 220 |
-
"use_bfloat16": false,
|
| 221 |
-
"use_mask_token": true,
|
| 222 |
-
"use_mean_pooling": true,
|
| 223 |
-
"use_relative_position_bias": false,
|
| 224 |
-
"use_shared_relative_position_bias": false,
|
| 225 |
-
"vocab_size": 8192
|
| 226 |
-
}
|
| 227 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VisionTextDualEncoderModel"
|
| 4 |
+
],
|
| 5 |
+
"cache_dir": null,
|
| 6 |
+
"logit_scale_init_value": 2.6592,
|
| 7 |
+
"model_type": "vision-text-dual-encoder",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"revision": "main",
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "ckiplab/bert-base-chinese",
|
| 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 |
+
"directionality": "bidi",
|
| 25 |
+
"diversity_penalty": 0.0,
|
| 26 |
+
"do_sample": false,
|
| 27 |
+
"early_stopping": false,
|
| 28 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 29 |
+
"eos_token_id": null,
|
| 30 |
+
"exponential_decay_length_penalty": null,
|
| 31 |
+
"finetuning_task": null,
|
| 32 |
+
"forced_bos_token_id": null,
|
| 33 |
+
"forced_eos_token_id": null,
|
| 34 |
+
"gradient_checkpointing": false,
|
| 35 |
+
"hidden_act": "gelu",
|
| 36 |
+
"hidden_dropout_prob": 0.1,
|
| 37 |
+
"hidden_size": 768,
|
| 38 |
+
"id2label": {
|
| 39 |
+
"0": "LABEL_0",
|
| 40 |
+
"1": "LABEL_1"
|
| 41 |
+
},
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 3072,
|
| 44 |
+
"is_decoder": false,
|
| 45 |
+
"is_encoder_decoder": false,
|
| 46 |
+
"label2id": {
|
| 47 |
+
"LABEL_0": 0,
|
| 48 |
+
"LABEL_1": 1
|
| 49 |
+
},
|
| 50 |
+
"layer_norm_eps": 1e-12,
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 20,
|
| 53 |
+
"max_position_embeddings": 512,
|
| 54 |
+
"min_length": 0,
|
| 55 |
+
"model_type": "bert",
|
| 56 |
+
"no_repeat_ngram_size": 0,
|
| 57 |
+
"num_attention_heads": 12,
|
| 58 |
+
"num_beam_groups": 1,
|
| 59 |
+
"num_beams": 1,
|
| 60 |
+
"num_hidden_layers": 12,
|
| 61 |
+
"num_return_sequences": 1,
|
| 62 |
+
"output_attentions": false,
|
| 63 |
+
"output_hidden_states": false,
|
| 64 |
+
"output_scores": false,
|
| 65 |
+
"pad_token_id": 0,
|
| 66 |
+
"pooler_fc_size": 768,
|
| 67 |
+
"pooler_num_attention_heads": 12,
|
| 68 |
+
"pooler_num_fc_layers": 3,
|
| 69 |
+
"pooler_size_per_head": 128,
|
| 70 |
+
"pooler_type": "first_token_transform",
|
| 71 |
+
"position_embedding_type": "absolute",
|
| 72 |
+
"prefix": null,
|
| 73 |
+
"problem_type": null,
|
| 74 |
+
"pruned_heads": {},
|
| 75 |
+
"remove_invalid_values": false,
|
| 76 |
+
"repetition_penalty": 1.0,
|
| 77 |
+
"return_dict": true,
|
| 78 |
+
"return_dict_in_generate": false,
|
| 79 |
+
"sep_token_id": null,
|
| 80 |
+
"suppress_tokens": null,
|
| 81 |
+
"task_specific_params": null,
|
| 82 |
+
"temperature": 1.0,
|
| 83 |
+
"tf_legacy_loss": false,
|
| 84 |
+
"tie_encoder_decoder": false,
|
| 85 |
+
"tie_word_embeddings": true,
|
| 86 |
+
"tokenizer_class": "BertTokenizerFast",
|
| 87 |
+
"top_k": 50,
|
| 88 |
+
"top_p": 1.0,
|
| 89 |
+
"torch_dtype": null,
|
| 90 |
+
"torchscript": false,
|
| 91 |
+
"type_vocab_size": 2,
|
| 92 |
+
"typical_p": 1.0,
|
| 93 |
+
"use_bfloat16": false,
|
| 94 |
+
"use_cache": true,
|
| 95 |
+
"vocab_size": 21128
|
| 96 |
+
},
|
| 97 |
+
"token": null,
|
| 98 |
+
"torch_dtype": "float32",
|
| 99 |
+
"transformers_version": "4.42.3",
|
| 100 |
+
"trust_remote_code": false,
|
| 101 |
+
"vision_config": {
|
| 102 |
+
"_name_or_path": "microsoft/dit-base",
|
| 103 |
+
"add_cross_attention": false,
|
| 104 |
+
"add_fpn": false,
|
| 105 |
+
"architectures": [
|
| 106 |
+
"BeitForMaskedImageModeling"
|
| 107 |
+
],
|
| 108 |
+
"attention_probs_dropout_prob": 0.0,
|
| 109 |
+
"auxiliary_channels": 256,
|
| 110 |
+
"auxiliary_concat_input": false,
|
| 111 |
+
"auxiliary_loss_weight": 0.4,
|
| 112 |
+
"auxiliary_num_convs": 1,
|
| 113 |
+
"bad_words_ids": null,
|
| 114 |
+
"begin_suppress_tokens": null,
|
| 115 |
+
"bos_token_id": null,
|
| 116 |
+
"chunk_size_feed_forward": 0,
|
| 117 |
+
"cross_attention_hidden_size": null,
|
| 118 |
+
"decoder_start_token_id": null,
|
| 119 |
+
"diversity_penalty": 0.0,
|
| 120 |
+
"do_sample": false,
|
| 121 |
+
"drop_path_rate": 0.1,
|
| 122 |
+
"early_stopping": false,
|
| 123 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 124 |
+
"eos_token_id": null,
|
| 125 |
+
"exponential_decay_length_penalty": null,
|
| 126 |
+
"finetuning_task": null,
|
| 127 |
+
"forced_bos_token_id": null,
|
| 128 |
+
"forced_eos_token_id": null,
|
| 129 |
+
"hidden_act": "gelu",
|
| 130 |
+
"hidden_dropout_prob": 0.0,
|
| 131 |
+
"hidden_size": 768,
|
| 132 |
+
"id2label": {
|
| 133 |
+
"0": "LABEL_0",
|
| 134 |
+
"1": "LABEL_1"
|
| 135 |
+
},
|
| 136 |
+
"image_size": 224,
|
| 137 |
+
"initializer_range": 0.02,
|
| 138 |
+
"intermediate_size": 3072,
|
| 139 |
+
"is_decoder": false,
|
| 140 |
+
"is_encoder_decoder": false,
|
| 141 |
+
"label2id": {
|
| 142 |
+
"LABEL_0": 0,
|
| 143 |
+
"LABEL_1": 1
|
| 144 |
+
},
|
| 145 |
+
"layer_norm_eps": 1e-12,
|
| 146 |
+
"layer_scale_init_value": 0.1,
|
| 147 |
+
"length_penalty": 1.0,
|
| 148 |
+
"max_length": 20,
|
| 149 |
+
"min_length": 0,
|
| 150 |
+
"model_type": "beit",
|
| 151 |
+
"no_repeat_ngram_size": 0,
|
| 152 |
+
"num_attention_heads": 12,
|
| 153 |
+
"num_beam_groups": 1,
|
| 154 |
+
"num_beams": 1,
|
| 155 |
+
"num_channels": 3,
|
| 156 |
+
"num_hidden_layers": 12,
|
| 157 |
+
"num_return_sequences": 1,
|
| 158 |
+
"out_features": [
|
| 159 |
+
"stage3",
|
| 160 |
+
"stage5",
|
| 161 |
+
"stage7",
|
| 162 |
+
"stage11"
|
| 163 |
+
],
|
| 164 |
+
"out_indices": [
|
| 165 |
+
3,
|
| 166 |
+
5,
|
| 167 |
+
7,
|
| 168 |
+
11
|
| 169 |
+
],
|
| 170 |
+
"output_attentions": false,
|
| 171 |
+
"output_hidden_states": false,
|
| 172 |
+
"output_scores": false,
|
| 173 |
+
"pad_token_id": null,
|
| 174 |
+
"patch_size": 16,
|
| 175 |
+
"pool_scales": [
|
| 176 |
+
1,
|
| 177 |
+
2,
|
| 178 |
+
3,
|
| 179 |
+
6
|
| 180 |
+
],
|
| 181 |
+
"prefix": null,
|
| 182 |
+
"problem_type": null,
|
| 183 |
+
"pruned_heads": {},
|
| 184 |
+
"remove_invalid_values": false,
|
| 185 |
+
"repetition_penalty": 1.0,
|
| 186 |
+
"reshape_hidden_states": true,
|
| 187 |
+
"return_dict": true,
|
| 188 |
+
"return_dict_in_generate": false,
|
| 189 |
+
"semantic_loss_ignore_index": 255,
|
| 190 |
+
"sep_token_id": null,
|
| 191 |
+
"stage_names": [
|
| 192 |
+
"stem",
|
| 193 |
+
"stage1",
|
| 194 |
+
"stage2",
|
| 195 |
+
"stage3",
|
| 196 |
+
"stage4",
|
| 197 |
+
"stage5",
|
| 198 |
+
"stage6",
|
| 199 |
+
"stage7",
|
| 200 |
+
"stage8",
|
| 201 |
+
"stage9",
|
| 202 |
+
"stage10",
|
| 203 |
+
"stage11",
|
| 204 |
+
"stage12"
|
| 205 |
+
],
|
| 206 |
+
"suppress_tokens": null,
|
| 207 |
+
"task_specific_params": null,
|
| 208 |
+
"temperature": 1.0,
|
| 209 |
+
"tf_legacy_loss": false,
|
| 210 |
+
"tie_encoder_decoder": false,
|
| 211 |
+
"tie_word_embeddings": true,
|
| 212 |
+
"tokenizer_class": null,
|
| 213 |
+
"top_k": 50,
|
| 214 |
+
"top_p": 1.0,
|
| 215 |
+
"torch_dtype": "float32",
|
| 216 |
+
"torchscript": false,
|
| 217 |
+
"typical_p": 1.0,
|
| 218 |
+
"use_absolute_position_embeddings": true,
|
| 219 |
+
"use_auxiliary_head": true,
|
| 220 |
+
"use_bfloat16": false,
|
| 221 |
+
"use_mask_token": true,
|
| 222 |
+
"use_mean_pooling": true,
|
| 223 |
+
"use_relative_position_bias": false,
|
| 224 |
+
"use_shared_relative_position_bias": false,
|
| 225 |
+
"vocab_size": 8192
|
| 226 |
+
}
|
| 227 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 755501772
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4006debcb0fa65dc46aac84042ec613bef62981a3363c1d4bbb0d5ba66fb9123
|
| 3 |
size 755501772
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc9b235fdbf94d53fbddf8cb6a7481497bbada9f8075c7131170f69c25161cf7
|
| 3 |
size 5112
|