add korclip

config.json

@@ -0,0 +1,168 @@
+{
+  "architectures": [
+    "VisionTextDualEncoderModel"
+  ],
+  "logit_scale_init_value": 2.6592,
+  "model_type": "vision-text-dual-encoder",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "klue/roberta-large",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "roberta",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": "BertTokenizer",
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "vision_config": {
+    "_name_or_path": "openai/clip-vit-base-patch32",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 32,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

log.txt

@@ -0,0 +1,90 @@
+step: Resize image (224)
+***** Running training *****
+  Num examples = 414112
+  Num Epochs = 40
+  Instantaneous batch size per device = 240
+  Total train batch size = 240
+  Total optimization steps = 69000
+Epoch 1/40 - Train loss: 1.1374
+Epoch 1/40 - Top 1: 61.3591, Top 5: 95.0198
+Model saved to output/2024-10-27T04-15-51/bset
+Epoch 2/40 - Train loss: 0.6764
+Epoch 2/40 - Top 1: 57.1230, Top 5: 94.3750
+Epoch 3/40 - Train loss: 0.5364
+Epoch 3/40 - Top 1: 62.6587, Top 5: 95.5655
+Model saved to output/2024-10-27T04-15-51/bset
+Epoch 4/40 - Train loss: 0.4502
+Epoch 4/40 - Top 1: 59.2560, Top 5: 93.7202
+Epoch 5/40 - Train loss: 0.3864
+Epoch 5/40 - Top 1: 62.6389, Top 5: 94.5933
+Epoch 6/40 - Train loss: 0.3365
+Epoch 6/40 - Top 1: 54.2956, Top 5: 92.0734
+Epoch 7/40 - Train loss: 0.2953
+Epoch 7/40 - Top 1: 55.5952, Top 5: 91.4087
+Epoch 8/40 - Train loss: 0.2609
+Epoch 8/40 - Top 1: 59.7222, Top 5: 92.5694
+Epoch 9/40 - Train loss: 0.2329
+Epoch 9/40 - Top 1: 56.4583, Top 5: 93.7500
+Epoch 10/40 - Train loss: 0.2086
+Epoch 10/40 - Top 1: 56.5873, Top 5: 91.5575
+Epoch 11/40 - Train loss: 0.1881
+Epoch 11/40 - Top 1: 60.6944, Top 5: 92.2421
+Epoch 12/40 - Train loss: 0.1713
+Epoch 12/40 - Top 1: 49.0774, Top 5: 87.1627
+Epoch 13/40 - Train loss: 0.1557
+Epoch 13/40 - Top 1: 54.2758, Top 5: 89.9107
+Epoch 14/40 - Train loss: 0.1435
+Epoch 14/40 - Top 1: 53.4524, Top 5: 90.4067
+Epoch 15/40 - Train loss: 0.1307
+Epoch 15/40 - Top 1: 49.0079, Top 5: 87.0437
+Epoch 16/40 - Train loss: 0.1176
+Epoch 16/40 - Top 1: 55.2183, Top 5: 88.3135
+Epoch 17/40 - Train loss: 0.1087
+Epoch 17/40 - Top 1: 57.4802, Top 5: 90.7440
+Epoch 18/40 - Train loss: 0.1013
+Epoch 18/40 - Top 1: 53.0258, Top 5: 89.9107
+Epoch 19/40 - Train loss: 0.0918
+Epoch 19/40 - Top 1: 53.1647, Top 5: 90.4067
+Epoch 20/40 - Train loss: 0.0857
+Epoch 20/40 - Top 1: 50.6250, Top 5: 89.8313
+Epoch 21/40 - Train loss: 0.0792
+Epoch 21/40 - Top 1: 46.8750, Top 5: 86.8254
+Epoch 22/40 - Train loss: 0.0721
+Epoch 22/40 - Top 1: 45.2976, Top 5: 87.7778
+Epoch 23/40 - Train loss: 0.0669
+Epoch 23/40 - Top 1: 51.2202, Top 5: 89.5040
+Epoch 24/40 - Train loss: 0.0623
+Epoch 24/40 - Top 1: 47.9960, Top 5: 86.5675
+Epoch 25/40 - Train loss: 0.0578
+Epoch 25/40 - Top 1: 44.4345, Top 5: 87.3810
+Epoch 26/40 - Train loss: 0.0534
+Epoch 26/40 - Top 1: 49.0179, Top 5: 88.8294
+Epoch 27/40 - Train loss: 0.0503
+Epoch 27/40 - Top 1: 51.5476, Top 5: 89.5040
+Epoch 28/40 - Train loss: 0.0460
+Epoch 28/40 - Top 1: 55.8333, Top 5: 89.9107
+Epoch 29/40 - Train loss: 0.0423
+Epoch 29/40 - Top 1: 54.1270, Top 5: 89.8313
+Epoch 30/40 - Train loss: 0.0392
+Epoch 30/40 - Top 1: 50.6647, Top 5: 88.8492
+Epoch 31/40 - Train loss: 0.0375
+Epoch 31/40 - Top 1: 53.1448, Top 5: 89.0873
+Epoch 32/40 - Train loss: 0.0336
+Epoch 32/40 - Top 1: 50.9921, Top 5: 88.8889
+Epoch 33/40 - Train loss: 0.0316
+Epoch 33/40 - Top 1: 45.9325, Top 5: 84.7321
+Epoch 34/40 - Train loss: 0.0289
+Epoch 34/40 - Top 1: 50.4762, Top 5: 88.7004
+Epoch 35/40 - Train loss: 0.0273
+Epoch 35/40 - Top 1: 48.1250, Top 5: 87.3710
+Epoch 36/40 - Train loss: 0.0248
+Epoch 36/40 - Top 1: 45.8829, Top 5: 86.1111
+Epoch 37/40 - Train loss: 0.0232
+Epoch 37/40 - Top 1: 45.9425, Top 5: 85.1488
+Epoch 38/40 - Train loss: 0.0216
+Epoch 38/40 - Top 1: 46.0020, Top 5: 86.2698
+Epoch 39/40 - Train loss: 0.0200
+Epoch 39/40 - Top 1: 47.0139, Top 5: 86.3095
+Epoch 40/40 - Train loss: 0.0193
+Epoch 40/40 - Top 1: 47.5694, Top 5: 86.4286
+Model saved to output/2024-10-27T04-15-51/last

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f021d992e7dbfa9f9388ba7414b80ff0e440fe7ba3c2b0a3b6cbad6d3e4086
+size 1700195908

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}