diff --git a/checkpoint-1050/config.json b/checkpoint-1050/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-1050/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-1050/model.safetensors b/checkpoint-1050/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86cdf53212ae7c56c2622457396d4cf48e35fb12 --- /dev/null +++ b/checkpoint-1050/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f2b6621e7ebeb0b67bc2ecb5f439e7c577cdcb2467949e0cd9bf8c26c546ef9 +size 395500946 diff --git a/checkpoint-1050/optimizer.pt b/checkpoint-1050/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5747f8c87c587379d28b9fd2ffb5e9399325fd3d --- /dev/null +++ b/checkpoint-1050/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f9ec8230d44469733a9cdeeb0c0594dad6ed74530110984de7b20ad01c63e7 +size 791234373 diff --git a/checkpoint-1050/rng_state_0.pth b/checkpoint-1050/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..473c677f7d482adc5975c96bd7367b71fe76bb37 --- /dev/null +++ b/checkpoint-1050/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b740668cfb9dc7ee84cbb9e13435b87cf300fcbfd6a2e389d9f16f8a72b7d97 +size 15024 diff --git a/checkpoint-1050/rng_state_1.pth b/checkpoint-1050/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..d248ddc9c001877345ddb950627af0a2827db8ce --- /dev/null +++ b/checkpoint-1050/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5d78051dfe69221a867d385efb3ecc3b6375f0cb2bacab6e5bb10ab6868d2d +size 15024 diff --git a/checkpoint-1050/rng_state_2.pth b/checkpoint-1050/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d65cac89fed79b6d9e514566e9aca06418209d2 --- /dev/null +++ b/checkpoint-1050/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34155eefee2236edacbc515ce561bdacee16acff988dc90081ea1b9d34421a76 +size 15024 diff --git a/checkpoint-1050/rng_state_3.pth b/checkpoint-1050/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..c703bc1b8ba0b50ec1f819c70360b6ac7fa67e58 --- /dev/null +++ b/checkpoint-1050/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2422182cfbbe3bffcb4d5632c576d6496279f393065cc905f129f113756b510 +size 15024 diff --git a/checkpoint-1050/scheduler.pt b/checkpoint-1050/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5414199157f209ba8eff679d7259a8deca5b35ca --- /dev/null +++ b/checkpoint-1050/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea29bb64db0b322deb8dc393daa3d416b1e28b93aeeefda64af98905a12477c +size 1064 diff --git a/checkpoint-1050/trainer_state.json b/checkpoint-1050/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e8991236d34bbef9b9b88da00b20cf00e8c07a97 --- /dev/null +++ b/checkpoint-1050/trainer_state.json @@ -0,0 +1,47 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 9.210526315789474, + "eval_steps": 500, + "global_step": 1050, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.58894446575616e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1050/training_args.bin b/checkpoint-1050/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-1050/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-1200/config.json b/checkpoint-1200/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-1200/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-1200/model.safetensors b/checkpoint-1200/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8148d8c1112e32a409c7d59656360b8b98f20dc --- /dev/null +++ b/checkpoint-1200/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d65b2dae788a11f450d35b2bbf4082c2e122b23835d72b1aa3dc7b3f39c7029 +size 395500946 diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..3200aae8be1c2efd72843b254cedeff721c9b5dd --- /dev/null +++ b/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8d228ccb162fb5afa9c62d643b13492cf0660238be0cf14dfc5d445218afd6 +size 791234373 diff --git a/checkpoint-1200/rng_state_0.pth b/checkpoint-1200/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec29f3b34455bd6c2431897a0387f49714dc2073 --- /dev/null +++ b/checkpoint-1200/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71064d336d6b49f09d0529f14b641a00787314e98327cca4bfc498bc3f5f3716 +size 15024 diff --git a/checkpoint-1200/rng_state_1.pth b/checkpoint-1200/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3e1a536ff4e8a9aef18bcc6c3525ad8f671d626 --- /dev/null +++ b/checkpoint-1200/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfad6560257ac5b092f4634ffae8df913abec6da41eaed508f23bb6b186ef823 +size 15024 diff --git a/checkpoint-1200/rng_state_2.pth b/checkpoint-1200/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..6fbe7a8811ebda6d1e25a4093b993ed51b0c5385 --- /dev/null +++ b/checkpoint-1200/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d76ac88e898475d1ab3eabf8a88692ec4f3e8df865a1be2449a16cfe6f5b2ece +size 15024 diff --git a/checkpoint-1200/rng_state_3.pth b/checkpoint-1200/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c123bac1b5bc9baa42ad79ce377c39e9cd6546c --- /dev/null +++ b/checkpoint-1200/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0b6b3e4123f56f31ff0cb0b9a6c984d3ca4cbbb9f5b06e56e68073f1781be64 +size 15024 diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..50d7c900c33ead61b58a0710c9528f4f7437c028 --- /dev/null +++ b/checkpoint-1200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e94b6bc3cfbe6f99e1faf3dde400a7366aa17cb7bf3c3f28973da04feb617dc +size 1064 diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6e46df1da3ccefcfef316d001d92c3256e1b7e42 --- /dev/null +++ b/checkpoint-1200/trainer_state.json @@ -0,0 +1,47 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 10.526315789473685, + "eval_steps": 500, + "global_step": 1200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4.10165081800704e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-1200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-1350/config.json b/checkpoint-1350/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-1350/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-1350/model.safetensors b/checkpoint-1350/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af64925642f35d02c58ee0313a6c69e76c16d366 --- /dev/null +++ b/checkpoint-1350/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134e1cc8e4692630b451a3411f04d7ba38b56bd8a46c2cdf673cc770d22da068 +size 395500946 diff --git a/checkpoint-1350/optimizer.pt b/checkpoint-1350/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a4a7f6e75652f30f3bf2137156fa2e3c8500b8e --- /dev/null +++ b/checkpoint-1350/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692b39c89e032fa5e40638252334df74ff16248fb722085e28e5720e9676abed +size 791234373 diff --git a/checkpoint-1350/rng_state_0.pth b/checkpoint-1350/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..322added84938a6776872aafe3224258a29f1123 --- /dev/null +++ b/checkpoint-1350/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c712b27a277fdf51a15940f0d5261825bcf688236ac66ad3d9102d4fbb8d46c +size 15024 diff --git a/checkpoint-1350/rng_state_1.pth b/checkpoint-1350/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..16c82f50e92b85035e56f4e1b0e45c746dd5424b --- /dev/null +++ b/checkpoint-1350/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b34b0848d1ce5b6e35b85fe4457279bbbb118a4e6732f4975e3555f0a9c13f +size 15024 diff --git a/checkpoint-1350/rng_state_2.pth b/checkpoint-1350/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff4bde0603806be59c8bb41f1134679d17d8dc42 --- /dev/null +++ b/checkpoint-1350/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf204d4bdc04b0ae9e30d3009aafcb96c7df1e436cdc3f5d36a70cdffb2ee31c +size 15024 diff --git a/checkpoint-1350/rng_state_3.pth b/checkpoint-1350/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd1db6b3feef30bc1f245fa4c926ab445faceeec --- /dev/null +++ b/checkpoint-1350/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4e604ef7761bbc768b7f06f08e3b423067048ec6d693160b51954f235a9817 +size 15024 diff --git a/checkpoint-1350/scheduler.pt b/checkpoint-1350/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..977b3a9d94643befaa82076bb2e15e5cb5375d5d --- /dev/null +++ b/checkpoint-1350/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8855cf059e9d5b102856e5a67917b128ba159d332fddc355342c32713cabdaa6 +size 1064 diff --git a/checkpoint-1350/trainer_state.json b/checkpoint-1350/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..bab6e96b9525c9b009fd5b639dc6ae9af525b8e5 --- /dev/null +++ b/checkpoint-1350/trainer_state.json @@ -0,0 +1,47 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 11.842105263157894, + "eval_steps": 500, + "global_step": 1350, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4.61435717025792e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1350/training_args.bin b/checkpoint-1350/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-1350/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-150/config.json b/checkpoint-150/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-150/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-150/model.safetensors b/checkpoint-150/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42ce76c7ce3a45b797b25ecbe8796c199db3a423 --- /dev/null +++ b/checkpoint-150/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bdacdfc12239161a63d0028436913794406e1eec01cbbda57c83f928496b8f4 +size 395500946 diff --git a/checkpoint-150/optimizer.pt b/checkpoint-150/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ae17aa9b5ee2f7f8cfb9938e54846ca484288c8 --- /dev/null +++ b/checkpoint-150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918deb76fa78ca01d848d759bfc63ad7bc4e88a86381dcff84a2669afddcd905 +size 791234373 diff --git a/checkpoint-150/rng_state_0.pth b/checkpoint-150/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..494ab6a540fef08b06e74897f1b8a2bf8b47709c --- /dev/null +++ b/checkpoint-150/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a635ca5caa80755b34704e8bbff3e5df1c0cccb06f1635354297d71ea083bd35 +size 15024 diff --git a/checkpoint-150/rng_state_1.pth b/checkpoint-150/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..4b366315936b4335f2ba4d46f96034f819a82e9e --- /dev/null +++ b/checkpoint-150/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8213b192942aae6f5709c9ed51eb62688a72192a6858b32d4afc54c84204d7 +size 15024 diff --git a/checkpoint-150/rng_state_2.pth b/checkpoint-150/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..e7db5f00e69eea542d80476f40c1ad2b83d2789f --- /dev/null +++ b/checkpoint-150/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e7e9ca79771cea746ff3f4d8339aed212497978e46ac1e3d35ab17b25174b5 +size 15024 diff --git a/checkpoint-150/rng_state_3.pth b/checkpoint-150/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..3310957ccb9b885f830da21f357b790bc8f7b2ef --- /dev/null +++ b/checkpoint-150/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad95fe6fcf66aafa1048148bb431f019cc8d388c9791f775cabb4c310c2aaf9 +size 15024 diff --git a/checkpoint-150/scheduler.pt b/checkpoint-150/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..13105b765a880cb4ebbf58b3bfb956f9b5c694dc --- /dev/null +++ b/checkpoint-150/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce5bae3cb64fd53723a3321f91adab4bb027fc0059eaedd20a7e42d811810a88 +size 1064 diff --git a/checkpoint-150/trainer_state.json b/checkpoint-150/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9a70233fc73da8952bfc307c91fe74b839eea0fa --- /dev/null +++ b/checkpoint-150/trainer_state.json @@ -0,0 +1,32 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.3157894736842106, + "eval_steps": 500, + "global_step": 150, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5127063522508800.0, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-150/training_args.bin b/checkpoint-150/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-150/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-1500/config.json b/checkpoint-1500/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-1500/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-1500/model.safetensors b/checkpoint-1500/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..824139a0f9bf9bf9e05ab1d07bf5a768ea4ee5b6 --- /dev/null +++ b/checkpoint-1500/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e00086ab85ea7e6e76d94c54173cd57869143c60ab8399a849a42a574895c400 +size 395500946 diff --git a/checkpoint-1500/optimizer.pt b/checkpoint-1500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d0f1430945d13ab7c92f35a64e6fa8f65f3342f --- /dev/null +++ b/checkpoint-1500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796ed003429f2bea1547ec44913671a9ea73fc8d70fba60287b3da37cdc9f404 +size 791234373 diff --git a/checkpoint-1500/rng_state_0.pth b/checkpoint-1500/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8481d47e7fca750f01f68a8e41424e5b8f45fb28 --- /dev/null +++ b/checkpoint-1500/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df3e7ba8d88673bf105026bb505d2d376cd332817593448a2bc8b70b6246b86b +size 15024 diff --git a/checkpoint-1500/rng_state_1.pth b/checkpoint-1500/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..80db24fb09705e8c0f49cac2acc6dd1976a6c609 --- /dev/null +++ b/checkpoint-1500/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c58f4be4b82cd74b55929b151b47bf0c462fabc3d7d1da55ba06c37475adfce5 +size 15024 diff --git a/checkpoint-1500/rng_state_2.pth b/checkpoint-1500/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2a03320327384b9fa52daf62f2e86033c8f329e3 --- /dev/null +++ b/checkpoint-1500/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc3a3adf0911cfc95cff7e45e444ed3dff8e350dbc3534c08d0fa32413f51b4 +size 15024 diff --git a/checkpoint-1500/rng_state_3.pth b/checkpoint-1500/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..f97a9aefa5d1a125ec51e81eb3c5838c0e987304 --- /dev/null +++ b/checkpoint-1500/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65751324482e61631e121b96c97c04ded44a4bccf546c2ffdffbcc603ef93be +size 15024 diff --git a/checkpoint-1500/scheduler.pt b/checkpoint-1500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..c30111aca20faca4beb505155f4d108693763f62 --- /dev/null +++ b/checkpoint-1500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d536ffd212ec2d6c7b7e2554122dbdcf42d544b077a72c397931a02ddb8f6ab4 +size 1064 diff --git a/checkpoint-1500/trainer_state.json b/checkpoint-1500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..cb90b7c94ae220b3c41271897235b5319e80b441 --- /dev/null +++ b/checkpoint-1500/trainer_state.json @@ -0,0 +1,54 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 13.157894736842104, + "eval_steps": 500, + "global_step": 1500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5.1270635225088e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1500/training_args.bin b/checkpoint-1500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-1500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-1650/config.json b/checkpoint-1650/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-1650/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-1650/model.safetensors b/checkpoint-1650/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7b165079383f54278f89404e8c0cdbae72aa4d4 --- /dev/null +++ b/checkpoint-1650/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e44a8e692defd3e8d1549d0131fbd3c09dcab12ed24c300483f6f2df462166e +size 395500946 diff --git a/checkpoint-1650/optimizer.pt b/checkpoint-1650/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2a28985e0bee9b9f1268468d0f408ad792ee589 --- /dev/null +++ b/checkpoint-1650/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae093cc9a14c5d4cb863b39f2db2acc896839190a5e30aa79cd9527b980342df +size 791234373 diff --git a/checkpoint-1650/rng_state_0.pth b/checkpoint-1650/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..97990c04993f4dc1b12038b77eda66821e8d6019 --- /dev/null +++ b/checkpoint-1650/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a06946bd45cad62208443fef6a97ba79dad53626e4a05d4bb308bd82337312 +size 15024 diff --git a/checkpoint-1650/rng_state_1.pth b/checkpoint-1650/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5a49ba037c243108bcc427de2c498b0be81e164 --- /dev/null +++ b/checkpoint-1650/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d794b3faf12bee7f485d56b8434ec15d881e01788b86fe4bcfa8a9bae6087fe0 +size 15024 diff --git a/checkpoint-1650/rng_state_2.pth b/checkpoint-1650/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..51ef6bbce7200f1e2e20eaf7f6b4ff687b82f9af --- /dev/null +++ b/checkpoint-1650/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77ab086ff8f6a8d2fe875778720c6851f4f5ea8b00e57caed5c595df9176b8d +size 15024 diff --git a/checkpoint-1650/rng_state_3.pth b/checkpoint-1650/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..3222e916a71655cca2bb71aef67602352d3ac898 --- /dev/null +++ b/checkpoint-1650/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f73ab4ba38715f659720871b7e1dae710927cd2fc7b531e5198ac5d180f758 +size 15024 diff --git a/checkpoint-1650/scheduler.pt b/checkpoint-1650/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b472bdd5520c8221eae50d54cb9fa153ba35457 --- /dev/null +++ b/checkpoint-1650/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e509936ddeafc006d1ed6d2b7b64d8097f560fb8818f964879e215dd3c47e3f +size 1064 diff --git a/checkpoint-1650/trainer_state.json b/checkpoint-1650/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..7825f04e67dd87cf4abcb94a1077151812bfd49d --- /dev/null +++ b/checkpoint-1650/trainer_state.json @@ -0,0 +1,54 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 14.473684210526315, + "eval_steps": 500, + "global_step": 1650, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5.63976987475968e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1650/training_args.bin b/checkpoint-1650/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-1650/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-1800/config.json b/checkpoint-1800/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-1800/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-1800/model.safetensors b/checkpoint-1800/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a92391d38be968c97f03f819abc21d40d00e133b --- /dev/null +++ b/checkpoint-1800/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdd409ebac8d4e85cb7860a036faa8d991d2760efd11bcb7a03280d23a9308a0 +size 395500946 diff --git a/checkpoint-1800/optimizer.pt b/checkpoint-1800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e7208c12ef10af6791ae5ecabb5edf7f8cc6f82 --- /dev/null +++ b/checkpoint-1800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d976746ad0a0816cddd276c123f522fb56056dd0c56a2fbc9e23d09a1acf18f0 +size 791234373 diff --git a/checkpoint-1800/rng_state_0.pth b/checkpoint-1800/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..04489626883ef582aa88e74fe767dcf86abb05a2 --- /dev/null +++ b/checkpoint-1800/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff31c616fd68a73476357126e69a0bc51d0681235bcd960addf1d043e59b8296 +size 15024 diff --git a/checkpoint-1800/rng_state_1.pth b/checkpoint-1800/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e2d0558051c4768fc48dd72fb5549930dc82bb3 --- /dev/null +++ b/checkpoint-1800/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53a54748b77fac6570a172982f941e0d40e30a2d9811ae37b6a758424f7b5ad +size 15024 diff --git a/checkpoint-1800/rng_state_2.pth b/checkpoint-1800/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..52f2ea7aa4aca1fd6f00863fc32f73832f9d7c79 --- /dev/null +++ b/checkpoint-1800/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bf0af5180f5ceede29ef0793b3d86bc286c15c21f01b8a99c3afbb75b86825e +size 15024 diff --git a/checkpoint-1800/rng_state_3.pth b/checkpoint-1800/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed74b4a61c7bfde7e999369364eb131bd1b980f0 --- /dev/null +++ b/checkpoint-1800/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cea9d06ad9acdaeb331b391cd31b2df445ac739fbe868841d5a83e1c53558c +size 15024 diff --git a/checkpoint-1800/scheduler.pt b/checkpoint-1800/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..90ed3ebd5301309d0ea326dfc4417e2c669599fd --- /dev/null +++ b/checkpoint-1800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b152598ea2b0f9b5d44d5268c1743cedbcba5f9f448f1ae0d364beda72b0a64 +size 1064 diff --git a/checkpoint-1800/trainer_state.json b/checkpoint-1800/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..743008180a60671d8b5d093b38e91a2359397638 --- /dev/null +++ b/checkpoint-1800/trainer_state.json @@ -0,0 +1,54 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 15.789473684210526, + "eval_steps": 500, + "global_step": 1800, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.15247622701056e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1800/training_args.bin b/checkpoint-1800/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-1800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-1950/config.json b/checkpoint-1950/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-1950/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-1950/model.safetensors b/checkpoint-1950/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82d918490975487fbec2fe73304cca3c2c7f2534 --- /dev/null +++ b/checkpoint-1950/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245526e9b539514259ca845b72b54d779571ff2816e248480110c7e20f456014 +size 395500946 diff --git a/checkpoint-1950/optimizer.pt b/checkpoint-1950/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d99cd9b6777413b6e80d79d95a4095918e525d56 --- /dev/null +++ b/checkpoint-1950/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dae60e1379a806315f796850c346b799518455d0608dbcb61f2e5ddc00bdba1 +size 791234373 diff --git a/checkpoint-1950/rng_state_0.pth b/checkpoint-1950/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..001de92cd04950907aa8544b44cc8951fdcdb82c --- /dev/null +++ b/checkpoint-1950/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:172ba3bbbc1bdee4797bd6aa20e06e0fffe9223cf5fa33db15ccd4f495b7dd6d +size 15024 diff --git a/checkpoint-1950/rng_state_1.pth b/checkpoint-1950/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..3eb2ed8bb0e605a345b645c6a03b6952f9c6dc9f --- /dev/null +++ b/checkpoint-1950/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befbbfd172c9cfec5b2d7e99c58e9b057abd06fcdb888d752aa167df0892f30e +size 15024 diff --git a/checkpoint-1950/rng_state_2.pth b/checkpoint-1950/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..bff96711c395879c4e3c39d1a070605168fab970 --- /dev/null +++ b/checkpoint-1950/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a329af78aca42bd7a65db889091e8fe730a55c8d06bceb19b82c8b813c86cb79 +size 15024 diff --git a/checkpoint-1950/rng_state_3.pth b/checkpoint-1950/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..43f496b601a8b2beebe649cb31802328392089c3 --- /dev/null +++ b/checkpoint-1950/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2fddb8a0ff860563e6cc72e0e55b57a04be340154a15066ba3faaf0abac9f9e +size 15024 diff --git a/checkpoint-1950/scheduler.pt b/checkpoint-1950/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..74e7a4c867b63dd6ba69bb06ad8e0c91d8458fdf --- /dev/null +++ b/checkpoint-1950/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d20a9ab6524d16ded35cf9cf3e1c590b9350df31a53e66e619ab9041438cd24a +size 1064 diff --git a/checkpoint-1950/trainer_state.json b/checkpoint-1950/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..64b9887a1e7f20df15381a29b40116e148734438 --- /dev/null +++ b/checkpoint-1950/trainer_state.json @@ -0,0 +1,54 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 17.105263157894736, + "eval_steps": 500, + "global_step": 1950, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.66518257926144e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1950/training_args.bin b/checkpoint-1950/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-1950/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-2100/config.json b/checkpoint-2100/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-2100/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-2100/model.safetensors b/checkpoint-2100/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b07714827272e199cb82c4eeb0731cbef3f19031 --- /dev/null +++ b/checkpoint-2100/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0062ff766768cb2187a5ee122f7a292a520eeabf54709e857ef0413afcfb3cec +size 395500946 diff --git a/checkpoint-2100/optimizer.pt b/checkpoint-2100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c644003228f5f7ae4a1d8ad37434ff203ee81878 --- /dev/null +++ b/checkpoint-2100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6d2693d4bacb8e811dbc61811d00bd6a1c65c2140f10efbe8b11bfb9819274 +size 791234373 diff --git a/checkpoint-2100/rng_state_0.pth b/checkpoint-2100/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6eb851e055025c9e53eb7418046dde228b87de1 --- /dev/null +++ b/checkpoint-2100/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc1978db28cbc2cafcacfb01ee98797d512d5941020f5c92ad7e38badbfec141 +size 15024 diff --git a/checkpoint-2100/rng_state_1.pth b/checkpoint-2100/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..992aaba40a5478718937a59a8f25f7c0a0ccb594 --- /dev/null +++ b/checkpoint-2100/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af3b61b91bec4e0639614260128f11da37369fb94fa230e522c0939464d9847 +size 15024 diff --git a/checkpoint-2100/rng_state_2.pth b/checkpoint-2100/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..c278810bc48c1fae150835bca704447bcb7ae3ff --- /dev/null +++ b/checkpoint-2100/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b022e9f9e0aa3742f084f6f5e2ba4bb869d6b40e4b782f205d0cbc7eafa8dfa +size 15024 diff --git a/checkpoint-2100/rng_state_3.pth b/checkpoint-2100/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0581b2a7c4902b86b73d01b1262ec866b614389 --- /dev/null +++ b/checkpoint-2100/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8acbbea1cbe10fdc77c0004a68a723e0b3d7bc3081bf3914e87a99de455f7176 +size 15024 diff --git a/checkpoint-2100/scheduler.pt b/checkpoint-2100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..218da387b2b3a04ef66c69efab0985faaf1f03d0 --- /dev/null +++ b/checkpoint-2100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f1a8da393399adeace949e126476f280315c1d749fa78b6afcd37e9dbf9a21b +size 1064 diff --git a/checkpoint-2100/trainer_state.json b/checkpoint-2100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..39fb2eff24427df589e1b2a7966c973efeccb45d --- /dev/null +++ b/checkpoint-2100/trainer_state.json @@ -0,0 +1,61 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 18.42105263157895, + "eval_steps": 500, + "global_step": 2100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 7.17788893151232e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2100/training_args.bin b/checkpoint-2100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-2100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-2250/config.json b/checkpoint-2250/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-2250/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-2250/model.safetensors b/checkpoint-2250/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c882013350afcecb99980e5bd399011bd2b963a3 --- /dev/null +++ b/checkpoint-2250/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb587bb1d5ef25d820eaffeaefaaafa0aeeefcdf120a9fab4e456b8bd081a852 +size 395500946 diff --git a/checkpoint-2250/optimizer.pt b/checkpoint-2250/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..bcaed5531a29d0b35e9e068da99f10c9b1f47f63 --- /dev/null +++ b/checkpoint-2250/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3704d980a8adc3bfa4c0823162f49ddbd3e6e268c291ee500b5e60b637f3384f +size 791234373 diff --git a/checkpoint-2250/rng_state_0.pth b/checkpoint-2250/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..c33a83f3d01c6fe6daec356e5ddba500390a3039 --- /dev/null +++ b/checkpoint-2250/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1a9b86823b619bb3341463a41a8fd73fb75d653d892a2c4f8299960597eba7 +size 15024 diff --git a/checkpoint-2250/rng_state_1.pth b/checkpoint-2250/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b87a16d48eb4503820ac976ca56c97f10e9f28dc --- /dev/null +++ b/checkpoint-2250/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c998cf71d8d29aa2be3d58ed59f51aa1eca43063a1df96b5827ac7a49d3bb1 +size 15024 diff --git a/checkpoint-2250/rng_state_2.pth b/checkpoint-2250/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef0e8feaee3f88fdfd6b31be06b909b7f17cf4af --- /dev/null +++ b/checkpoint-2250/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0fa2e168a44cfc8dcd1725bf52f82d298fb3605f537e743264ffc14ee6881d +size 15024 diff --git a/checkpoint-2250/rng_state_3.pth b/checkpoint-2250/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ffab92f085d7cd2122a45c944ffeff5f507b350 --- /dev/null +++ b/checkpoint-2250/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7985f3e3a41b5431338de885058e356136a21d232f36c01ce62e94d9eb597579 +size 15024 diff --git a/checkpoint-2250/scheduler.pt b/checkpoint-2250/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..72bad3f1050e109019342025602ef580ac7dfd27 --- /dev/null +++ b/checkpoint-2250/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e45f544ee005ed5765e25d5a05977c93ab93658f6987887cfe821188f161aa90 +size 1064 diff --git a/checkpoint-2250/trainer_state.json b/checkpoint-2250/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..cb414dfd4d88b7b68129a3d4be9950eecafc48dd --- /dev/null +++ b/checkpoint-2250/trainer_state.json @@ -0,0 +1,61 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 19.736842105263158, + "eval_steps": 500, + "global_step": 2250, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 7.6905952837632e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2250/training_args.bin b/checkpoint-2250/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-2250/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-2400/config.json b/checkpoint-2400/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-2400/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-2400/model.safetensors b/checkpoint-2400/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a981f02df85522a6b7295779b8559d208ae43456 --- /dev/null +++ b/checkpoint-2400/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea33e12fe06af46986976d9bb0cae66cb8cbd63a97bcafe4fe3abfc66bd72f4 +size 395500946 diff --git a/checkpoint-2400/optimizer.pt b/checkpoint-2400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c7c7134717afd958d96052bdf9e75c34920ca06 --- /dev/null +++ b/checkpoint-2400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362d940c056a832a1e296b6e190ea59f8852acd5bda603ae2835a7dc8f2df8c0 +size 791234373 diff --git a/checkpoint-2400/rng_state_0.pth b/checkpoint-2400/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..576839d447441c3830dc0d755a90ed00eb1d2aa3 --- /dev/null +++ b/checkpoint-2400/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a671fe90afe4475e0c7cd79c8c900273cfc9a4259a100c4e22bd951357d694ba +size 15024 diff --git a/checkpoint-2400/rng_state_1.pth b/checkpoint-2400/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbf6a19130ae74c91fbd11ade93bc7aac14a00fc --- /dev/null +++ b/checkpoint-2400/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051210ca91cb4aae908377f819793102df878153aad70af22141b121e540bc30 +size 15024 diff --git a/checkpoint-2400/rng_state_2.pth b/checkpoint-2400/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..94838a00c6bd7495a1b75e091dce4194499a6e84 --- /dev/null +++ b/checkpoint-2400/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b280b843a6a29daa691b4e0a8be35b5f97078ad0cb8592d89f8ac4086d1f02 +size 15024 diff --git a/checkpoint-2400/rng_state_3.pth b/checkpoint-2400/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f8a7020552b5e6d12daf283c7125fce41bf42d9 --- /dev/null +++ b/checkpoint-2400/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2518d0d979a6dd78fb3072a112b52738769253ead5d8287c3f6d095171271f1e +size 15024 diff --git a/checkpoint-2400/scheduler.pt b/checkpoint-2400/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..50d18034e9992da15bb6d658000e1e3c10425e0f --- /dev/null +++ b/checkpoint-2400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4cd4553c9c0f271f0aaaac67b46756e0d3f33ce2c61971516f1c39ae6deab8 +size 1064 diff --git a/checkpoint-2400/trainer_state.json b/checkpoint-2400/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..06f9f9e9f3842c47bd86164144dd7d45a57b41ab --- /dev/null +++ b/checkpoint-2400/trainer_state.json @@ -0,0 +1,61 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 21.05263157894737, + "eval_steps": 500, + "global_step": 2400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 8.20330163601408e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2400/training_args.bin b/checkpoint-2400/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-2400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-2550/config.json b/checkpoint-2550/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-2550/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-2550/model.safetensors b/checkpoint-2550/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3011d4ab4bad39fe6501b9bf1af34e9311378740 --- /dev/null +++ b/checkpoint-2550/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1080d2c6ee633a66fe016d8bf646247801ef56042e6caf9990507c85a221dc3c +size 395500946 diff --git a/checkpoint-2550/optimizer.pt b/checkpoint-2550/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d49f9affe8f12862b4415d3bee8103a143802b9 --- /dev/null +++ b/checkpoint-2550/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a094674ff942315cdc36c5dd1b31b1b1152f9e80fa5de0ed6138a25c161ab7fc +size 791234373 diff --git a/checkpoint-2550/rng_state_0.pth b/checkpoint-2550/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..75382265a672d61f359b479b4d027db64e3b9c85 --- /dev/null +++ b/checkpoint-2550/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0969e3c1fe0a1b6298b3e115981fc3c3f9f49372aa494e9327c72f8940e67b5f +size 15024 diff --git a/checkpoint-2550/rng_state_1.pth b/checkpoint-2550/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..91e46380a435e6762c98756ba6108725086ab9eb --- /dev/null +++ b/checkpoint-2550/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb9f38c05ffcfc75a17e4226704ff48bec4dda7a1db09f226900831111befe8 +size 15024 diff --git a/checkpoint-2550/rng_state_2.pth b/checkpoint-2550/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d8c2d14cb3a64bab1a710d5906a95be239070fd --- /dev/null +++ b/checkpoint-2550/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de2c931060de9dcb507561490f24d73e1bf161178290838b6c9189077d72c8cc +size 15024 diff --git a/checkpoint-2550/rng_state_3.pth b/checkpoint-2550/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..12bd5f02865b2d0b8bdf26a26bc942edccfdb2e0 --- /dev/null +++ b/checkpoint-2550/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8394f004349f477f095146f256f475d51e56e7a3fed1cff15fe4e5f1679b30 +size 15024 diff --git a/checkpoint-2550/scheduler.pt b/checkpoint-2550/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7416c3b666f6d07496c510acebeca2aab83051c --- /dev/null +++ b/checkpoint-2550/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1024611e646527281e7c8c39efc59660b8646901164a6c741c5598c9b8853261 +size 1064 diff --git a/checkpoint-2550/trainer_state.json b/checkpoint-2550/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2391b2c59b9796ecfca97ddf7ef68283a2db4c57 --- /dev/null +++ b/checkpoint-2550/trainer_state.json @@ -0,0 +1,68 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 22.36842105263158, + "eval_steps": 500, + "global_step": 2550, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 8.71600798826496e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2550/training_args.bin b/checkpoint-2550/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-2550/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-2700/config.json b/checkpoint-2700/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-2700/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-2700/model.safetensors b/checkpoint-2700/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3bf96d829aa9e60657d7aff5a935a36f3636ef81 --- /dev/null +++ b/checkpoint-2700/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc28ef87e121a31797a982666b03aac13dec0f60fd6be28c55558ad863cec146 +size 395500946 diff --git a/checkpoint-2700/optimizer.pt b/checkpoint-2700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d26c4af405c2f02517f001170d0dae39fe7ea51 --- /dev/null +++ b/checkpoint-2700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1240f72470a9fe81bc67ca1453a34da589658b699712be16cbb51861c5bfedf8 +size 791234373 diff --git a/checkpoint-2700/rng_state_0.pth b/checkpoint-2700/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..e70078c84f46f1c45faee7004b0e4d8d0a381344 --- /dev/null +++ b/checkpoint-2700/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb63f23e5f99435be3f72d0ae8825231a083dacf3975b135dbebccc9758b672d +size 15024 diff --git a/checkpoint-2700/rng_state_1.pth b/checkpoint-2700/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb39f538f8629d03a743c6e1e0446a2f931beb01 --- /dev/null +++ b/checkpoint-2700/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453b6c59f1a1dea223a2d1d688e920c9b6f1bdc508087bffbdd7f6746f102bea +size 15024 diff --git a/checkpoint-2700/rng_state_2.pth b/checkpoint-2700/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..cdaa5e2aca05c5ddfbcfa7d80c68b2a2a5eb9545 --- /dev/null +++ b/checkpoint-2700/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a380bfda60164f9318e9849c45b4a52d9a1bd7231d2e4198a11809f663930ca +size 15024 diff --git a/checkpoint-2700/rng_state_3.pth b/checkpoint-2700/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba3463943fea084845c3b4379b35a6223ab4ad4e --- /dev/null +++ b/checkpoint-2700/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463c43ea095124301179b1cf18203ab1a00e1cd5805f22f58120188261738964 +size 15024 diff --git a/checkpoint-2700/scheduler.pt b/checkpoint-2700/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4066ad1f768eaa184c7bdff35503e8235580039f --- /dev/null +++ b/checkpoint-2700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b5b7127f270f8e75b4476b355b23241478ca5ceb2aa6c0c4d8c978986396af +size 1064 diff --git a/checkpoint-2700/trainer_state.json b/checkpoint-2700/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dbd376f9bc3b9167672cf0d22f28b4abf95de22f --- /dev/null +++ b/checkpoint-2700/trainer_state.json @@ -0,0 +1,68 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 23.68421052631579, + "eval_steps": 500, + "global_step": 2700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.22871434051584e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2700/training_args.bin b/checkpoint-2700/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-2700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-2850/config.json b/checkpoint-2850/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-2850/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-2850/model.safetensors b/checkpoint-2850/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f3ca2f7e773a2c3b4b9f0cb23dd1c46586676f3 --- /dev/null +++ b/checkpoint-2850/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743e85b882f63dab9670ced45e2f0c6654e1248d2e508b6510a6c4cbd90ce4e8 +size 395500946 diff --git a/checkpoint-2850/optimizer.pt b/checkpoint-2850/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..8226494eb70e2d471facb41af65c3f04226f3642 --- /dev/null +++ b/checkpoint-2850/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59457697135663606eed68dc711c0ce5926400f3364d7073b0e59d7116a6579e +size 791234373 diff --git a/checkpoint-2850/rng_state_0.pth b/checkpoint-2850/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..e9d5c050daccc3d14d602e1e048cf9ede05adbbf --- /dev/null +++ b/checkpoint-2850/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a93596946a38fa02c31bd8b9d9e31e5d0db87b3007b178af1aa68b3bc95ca9 +size 15024 diff --git a/checkpoint-2850/rng_state_1.pth b/checkpoint-2850/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1389915a92bc091086c2a3bb7c32d723f51bbbb6 --- /dev/null +++ b/checkpoint-2850/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:144533816fee2859206c043bf9ecfedc31fd5c4fc2030770d97917cd7efb4cf5 +size 15024 diff --git a/checkpoint-2850/rng_state_2.pth b/checkpoint-2850/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..996f4782136e95ed4b98b320a1e43ff1a0ae1bf2 --- /dev/null +++ b/checkpoint-2850/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6735f89d4de2a2886e2a5837d93f8b71621306b0eddfbf18c14033878c8a366 +size 15024 diff --git a/checkpoint-2850/rng_state_3.pth b/checkpoint-2850/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..07e93b4049a9aceee55ca5d4db69c76f9e11991a --- /dev/null +++ b/checkpoint-2850/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aef9de473010a2f33b80d38b8ed3ccfee65a168a49bc10ad1107383295e8c34f +size 15024 diff --git a/checkpoint-2850/scheduler.pt b/checkpoint-2850/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..099fd18e80857df45fb33168b268d0e635a289a0 --- /dev/null +++ b/checkpoint-2850/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90699037a5bbd181bed834964b07debc13a25ecef051fd241633aac8654c8d0a +size 1064 diff --git a/checkpoint-2850/trainer_state.json b/checkpoint-2850/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..acf1cf05cbaf398e5d1eeef6e5c8bf3459a43d72 --- /dev/null +++ b/checkpoint-2850/trainer_state.json @@ -0,0 +1,68 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 25.0, + "eval_steps": 500, + "global_step": 2850, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.74142069276672e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2850/training_args.bin b/checkpoint-2850/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-2850/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-300/config.json b/checkpoint-300/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-300/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-300/model.safetensors b/checkpoint-300/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7151ea773ce4560ca9bdf902e616e6755153cf80 --- /dev/null +++ b/checkpoint-300/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dee6ee00f41f85b8e67cd235ea54e48eb165cef5acdb3deefeba2d14451bbc0 +size 395500946 diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..473c1f4afac103c24b4b8658cd2293106294dda8 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a69e1afc1357065961800c6351f7f2c6a956518448172297b5570a1397d525e +size 791234373 diff --git a/checkpoint-300/rng_state_0.pth b/checkpoint-300/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..97336726bbca5a12272b9c79cbb798ea15d3ae35 --- /dev/null +++ b/checkpoint-300/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92824707c467a167fd5c8992680ef8f30dbd696ed6380df72b56ba07b8baf76e +size 15024 diff --git a/checkpoint-300/rng_state_1.pth b/checkpoint-300/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd7736d793a51fd2088060b9b9384bbb7f756854 --- /dev/null +++ b/checkpoint-300/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7ed3a6edc8fcd6724cd53926ad2af31ded8174ebb37a74dea072cc29cc4f3c +size 15024 diff --git a/checkpoint-300/rng_state_2.pth b/checkpoint-300/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d73aa5eb0747e22a2c19c1cc835d6d7a56a4d00 --- /dev/null +++ b/checkpoint-300/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7edc33330681aca0ef6116895a10aafd3f786d5ef801ab7d142c119f17e31a7 +size 15024 diff --git a/checkpoint-300/rng_state_3.pth b/checkpoint-300/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b58e6c4c6227a7527f5dc75326cf6cc539dcb31 --- /dev/null +++ b/checkpoint-300/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e610ec53414993b5eda9ab9263da5a4100b7623c699d73ce76db1d15d1e3f8ce +size 15024 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b359e8ee9f88813a417c1756cbc2871f5fbbce8d --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eb5f9a073d34c422bc9f347ffb7d7b0d6214412f6416a5391017e4dd129c0f7 +size 1064 diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..4c8c47325fdc9ccc5bd9fe225f10001595198dcf --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,32 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.6315789473684212, + "eval_steps": 500, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.02541270450176e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-3000/config.json b/checkpoint-3000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-3000/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-3000/model.safetensors b/checkpoint-3000/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..38b3c58cad66f89b53d5cfa62bc2caaffd84d7a6 --- /dev/null +++ b/checkpoint-3000/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5d5deab59f988905f1fa50c8580e39e311047a71270dbce6ad66c6ba7adb06 +size 395500946 diff --git a/checkpoint-3000/optimizer.pt b/checkpoint-3000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..a13213ad164258226f0ff6feeeb62431a3b67492 --- /dev/null +++ b/checkpoint-3000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dbe6ed1877181af159d8b0b958cacb5a69594de2c18c9ce0fe8977975095538 +size 791234373 diff --git a/checkpoint-3000/rng_state_0.pth b/checkpoint-3000/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..799a4cac4bd0bb538d7233f301eccf68187689f6 --- /dev/null +++ b/checkpoint-3000/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e669da02d6c493a1afa2a9b7000efb7a48f5472cfd49eb254dffd70a093bc63 +size 15024 diff --git a/checkpoint-3000/rng_state_1.pth b/checkpoint-3000/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1ffe222d603e13b3e305d676a8b9b89c4389b3f --- /dev/null +++ b/checkpoint-3000/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fbe79fddedc0c8d865aa89b10f52854e391720d0c45158950942647f5a1ce7b +size 15024 diff --git a/checkpoint-3000/rng_state_2.pth b/checkpoint-3000/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..c282bce3c06e5ee0f2aa7c903eaab400c2c640fb --- /dev/null +++ b/checkpoint-3000/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c339a6fe504b47d97184f1108be2a9844246de2bc3a471e99ed3f943fc765a7b +size 15024 diff --git a/checkpoint-3000/rng_state_3.pth b/checkpoint-3000/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..6eff8ab25eca7458bbcbd526f877408da3a6d5c9 --- /dev/null +++ b/checkpoint-3000/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d842e91e3d476ab884b3febb50b7390b0438b0ddb2354633d44c7855e06034 +size 15024 diff --git a/checkpoint-3000/scheduler.pt b/checkpoint-3000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a236ecd1cceae825db71843476ab626ce6a7b28c --- /dev/null +++ b/checkpoint-3000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7ddbc1b86b1b135c0a5602605b6441aeb6b65ecca2e13cdb841b1b60b81116c +size 1064 diff --git a/checkpoint-3000/trainer_state.json b/checkpoint-3000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b71202a0c43b9fb3a58c37d5129feb8a2737a255 --- /dev/null +++ b/checkpoint-3000/trainer_state.json @@ -0,0 +1,75 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 26.31578947368421, + "eval_steps": 500, + "global_step": 3000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.02541270450176e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3000/training_args.bin b/checkpoint-3000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-3000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-3150/config.json b/checkpoint-3150/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-3150/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-3150/model.safetensors b/checkpoint-3150/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0eb1b915cf55636af5a218f266afef19235dde49 --- /dev/null +++ b/checkpoint-3150/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbd4ab83e91cd75c8cdbbb4fb4fa094d73144544bcc631b5fca7dd664a255a9 +size 395500946 diff --git a/checkpoint-3150/optimizer.pt b/checkpoint-3150/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0c794fbbda06e2047fcdcc040895dcbda213b3f --- /dev/null +++ b/checkpoint-3150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df838c056b914a93844565867ddf3bc7cda66f8134a64431229bd17fd7ff37b5 +size 791234373 diff --git a/checkpoint-3150/rng_state_0.pth b/checkpoint-3150/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..a67ff724838d6fe0d972692d9d4c1eb03e04de61 --- /dev/null +++ b/checkpoint-3150/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45bb0510b82b88a17697e6e9d0f21467c1b487d4b49e0005d1ac19c97927aa3 +size 15024 diff --git a/checkpoint-3150/rng_state_1.pth b/checkpoint-3150/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6a4c789686ce408a4d3d43eae4394e55f2b79a9 --- /dev/null +++ b/checkpoint-3150/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1304b2d1d5a20cfbb9ba2935d194e394b9a40c20694698143ddb1454e77772d +size 15024 diff --git a/checkpoint-3150/rng_state_2.pth b/checkpoint-3150/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..419564bf45982e2ac711c1dfd5438ef961b29830 --- /dev/null +++ b/checkpoint-3150/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b4fe19460543e906b7bf19041f9d7ab141f789fb946ba1531d7ce071102183c +size 15024 diff --git a/checkpoint-3150/rng_state_3.pth b/checkpoint-3150/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..93f3e1c764223cba1444cb7aee32ccf5872c4ecf --- /dev/null +++ b/checkpoint-3150/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adbb3d8fb44ea1ea82f1d8f55b5a7b4342b583a7c73bbd617ae7f5db52779b7c +size 15024 diff --git a/checkpoint-3150/scheduler.pt b/checkpoint-3150/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ad6ae1cdccec055ac7c20612dd3539cd5100117 --- /dev/null +++ b/checkpoint-3150/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a4fd631260942d13b25d6f46455ae883658ae548d8263c87b2aa556d969722 +size 1064 diff --git a/checkpoint-3150/trainer_state.json b/checkpoint-3150/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a1f4b69f2c8f8680430c252b94d70528abeba04a --- /dev/null +++ b/checkpoint-3150/trainer_state.json @@ -0,0 +1,75 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 27.63157894736842, + "eval_steps": 500, + "global_step": 3150, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.076683339726848e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3150/training_args.bin b/checkpoint-3150/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-3150/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-3300/config.json b/checkpoint-3300/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-3300/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-3300/model.safetensors b/checkpoint-3300/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85df0a369fafde830573bf203888b5b9c4bca1a5 --- /dev/null +++ b/checkpoint-3300/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659b5a53850709ca127ca16570ada902594dc85a16fa363a85fb4011240bc07d +size 395500946 diff --git a/checkpoint-3300/optimizer.pt b/checkpoint-3300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2be4aa5940a8d923489a41a9b749baae81e5843 --- /dev/null +++ b/checkpoint-3300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:375d840f9fe960f70ed8ab243a5a74f4b994e1cc9f4fcd8267a8233cc1c0f773 +size 791234373 diff --git a/checkpoint-3300/rng_state_0.pth b/checkpoint-3300/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..98b865e238e6fa4cd8748167e4887c94c0019127 --- /dev/null +++ b/checkpoint-3300/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2310e4e56ea3fcdbb027fa58d7c3547aa35ca73547e317f5438cd08d55000bb7 +size 15024 diff --git a/checkpoint-3300/rng_state_1.pth b/checkpoint-3300/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..347b67fb186c7fbac4a556149491b9671a93c419 --- /dev/null +++ b/checkpoint-3300/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f7e802c0269c24c534c9a727230b445cf0b3e12bdc42a57a8775f5ddb402f7 +size 15024 diff --git a/checkpoint-3300/rng_state_2.pth b/checkpoint-3300/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..696fc85f8e9c74fc84f9bcb97fdb5e365da0347e --- /dev/null +++ b/checkpoint-3300/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74ee85e87847f66aba1b4ee714761e4311718f9d61eca2c52a0622265729f13 +size 15024 diff --git a/checkpoint-3300/rng_state_3.pth b/checkpoint-3300/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5250a358481bbd5c572b1a2ca7108a6cebb16fc --- /dev/null +++ b/checkpoint-3300/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9eb05325994bad0453ec8a2a43ec6dc2b11751e3c376ce7b018bb5b8718837 +size 15024 diff --git a/checkpoint-3300/scheduler.pt b/checkpoint-3300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..907735bf0996c964a37728c697d97027156a1840 --- /dev/null +++ b/checkpoint-3300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a57bcf4565f02f67c58a0dfcb865b3f581d491c3283d0a210c1156bb8bc5f77 +size 1064 diff --git a/checkpoint-3300/trainer_state.json b/checkpoint-3300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d2f342fcb46530bcb0f0de885bdc5f4676c2e172 --- /dev/null +++ b/checkpoint-3300/trainer_state.json @@ -0,0 +1,75 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 28.94736842105263, + "eval_steps": 500, + "global_step": 3300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.127953974951936e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3300/training_args.bin b/checkpoint-3300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-3300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-3450/config.json b/checkpoint-3450/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-3450/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-3450/model.safetensors b/checkpoint-3450/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6909c24360c16f689efeb330a0a719660dfb8d1 --- /dev/null +++ b/checkpoint-3450/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1d29b19404575cd74466331a198f7ef90912cb02ba9df6c253566e0aaae8d42 +size 395500946 diff --git a/checkpoint-3450/optimizer.pt b/checkpoint-3450/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..638a9058ee6a97d93498600feacf22dd173696e2 --- /dev/null +++ b/checkpoint-3450/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27bbea199aecc7b67f598add3686bc02c8a4e9630dc9d88131bc7c963b09ccab +size 791234373 diff --git a/checkpoint-3450/rng_state_0.pth b/checkpoint-3450/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..97c696f03263b078b8192177b00380982677792d --- /dev/null +++ b/checkpoint-3450/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2381dadf6aa73dc94724bb52fc9e742a7682f506e0f039740df1060e6b59646 +size 15024 diff --git a/checkpoint-3450/rng_state_1.pth b/checkpoint-3450/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..e431efa5a695600c6e6bb6f9f62534655dbb0f8c --- /dev/null +++ b/checkpoint-3450/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa0668e3dbe2249ae387ad2b059ea7a5a6cc7617badbc5204ff69c32723c44f1 +size 15024 diff --git a/checkpoint-3450/rng_state_2.pth b/checkpoint-3450/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..abcb50d5fce9fe3a0f636ecc3fc19fc417522078 --- /dev/null +++ b/checkpoint-3450/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9fc1ffc503b0b4c565905767fd092d6763012f76434e1bc55d31a590f62c5f +size 15024 diff --git a/checkpoint-3450/rng_state_3.pth b/checkpoint-3450/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b365c410ff5b782ee2d602ad5256cd90ce14545 --- /dev/null +++ b/checkpoint-3450/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ae5d20d16a4e2ab8d44a3b2313ce098876cc93f9d752d8da89ba42ed54cb4a +size 15024 diff --git a/checkpoint-3450/scheduler.pt b/checkpoint-3450/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f98b60dbc2cb9d45e2c1034827e5af773ee36d61 --- /dev/null +++ b/checkpoint-3450/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35950a80e776f9ebfcac152d39b53aa2df0c11a7b7df581c00298e35ce86b7a1 +size 1064 diff --git a/checkpoint-3450/trainer_state.json b/checkpoint-3450/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..5099fc841996923dcc5e5ce360771d5cdaea7fb2 --- /dev/null +++ b/checkpoint-3450/trainer_state.json @@ -0,0 +1,75 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 30.263157894736842, + "eval_steps": 500, + "global_step": 3450, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.179224610177024e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3450/training_args.bin b/checkpoint-3450/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-3450/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-3600/config.json b/checkpoint-3600/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-3600/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-3600/model.safetensors b/checkpoint-3600/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14e151312c2110020826c44791e860b79b01f204 --- /dev/null +++ b/checkpoint-3600/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f692cd21ac315274ccb4dd8964410ec7806bd6e5441d3942b1c12f58602de3d +size 395500946 diff --git a/checkpoint-3600/optimizer.pt b/checkpoint-3600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f08628f8af95787e2f67355d036384e2ad5edcc --- /dev/null +++ b/checkpoint-3600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64cd394d5c11baeaf5b10ac380f1d2bdb0ced7ed3b92d17a64116d3979165d61 +size 791234373 diff --git a/checkpoint-3600/rng_state_0.pth b/checkpoint-3600/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..767ed1cf4f152fa4d0fdf5e6edbe93cbc7d75348 --- /dev/null +++ b/checkpoint-3600/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f57c3da2ce201585e8069e139414b16aa49239fbd8dfbd7bb5b627da06f42d +size 15024 diff --git a/checkpoint-3600/rng_state_1.pth b/checkpoint-3600/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f1fe2a87a3cb330eb5110e2d7ef186348a617aba --- /dev/null +++ b/checkpoint-3600/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6335e08066c7535f54fe9ac38950fba891aa025b8001d6b16cf28ca7b742de3d +size 15024 diff --git a/checkpoint-3600/rng_state_2.pth b/checkpoint-3600/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..33b7fb5642ec8f41a4c9ecc0180b391f51cd2223 --- /dev/null +++ b/checkpoint-3600/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f309289f5820f6db2bb56af4e16c326fac7a1465a148a48e86a044dba26b64 +size 15024 diff --git a/checkpoint-3600/rng_state_3.pth b/checkpoint-3600/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ca519fdcc10627d79f84ea44c4a8386b56ffecd --- /dev/null +++ b/checkpoint-3600/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e8439191d93e8405682256d01b15496fbea6d10c4c4bb8a5f29fa9c55c2bdf +size 15024 diff --git a/checkpoint-3600/scheduler.pt b/checkpoint-3600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..312b1efaea6709d46058fc192d839747230b6462 --- /dev/null +++ b/checkpoint-3600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6544d072ec8360100d522ac875f9e071a51b847a134585210179e7dd80a2a7b2 +size 1064 diff --git a/checkpoint-3600/trainer_state.json b/checkpoint-3600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c3806aa6c8fe9b3f724a26a6ed03afcbaa98b873 --- /dev/null +++ b/checkpoint-3600/trainer_state.json @@ -0,0 +1,82 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 31.57894736842105, + "eval_steps": 500, + "global_step": 3600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + }, + { + "epoch": 30.70175438596491, + "grad_norm": 6.5, + "learning_rate": 3.666436212625509e-05, + "loss": 0.451, + "step": 3500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.230495245402112e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3600/training_args.bin b/checkpoint-3600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-3600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-3750/config.json b/checkpoint-3750/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-3750/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-3750/model.safetensors b/checkpoint-3750/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f56c8bf276669d78758f3d8f967780d59ddf8bc --- /dev/null +++ b/checkpoint-3750/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a8189fb92a17fc4b5559241dc8def5300b72e530c10fc343f03f3f7ae30d59 +size 395500946 diff --git a/checkpoint-3750/optimizer.pt b/checkpoint-3750/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d88e635b0ce5f0e86b9a583ca5e776bb4268827a --- /dev/null +++ b/checkpoint-3750/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de1c135f5ca118dea2de5b0c9d42e74e32466d0f2c94b490c8d7d236c952046f +size 791234373 diff --git a/checkpoint-3750/rng_state_0.pth b/checkpoint-3750/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..2b309c3cf1d04a911a711f90d631ecb4d9665ab5 --- /dev/null +++ b/checkpoint-3750/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a718dd3828b48cf11560909c78236154e9e408a562083edb925c79c469b3730b +size 15024 diff --git a/checkpoint-3750/rng_state_1.pth b/checkpoint-3750/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..559a0508a87c9f9315e61591d96f589e92e3dcb7 --- /dev/null +++ b/checkpoint-3750/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b4b1c96c19515c358f74051011e3e4410b7b8e6ecd58922eae604d569710465 +size 15024 diff --git a/checkpoint-3750/rng_state_2.pth b/checkpoint-3750/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b6017b3ac446bb13cfa461a35ea904ccbbb4f91 --- /dev/null +++ b/checkpoint-3750/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4543c0edfd71362f73ca4c485258e1b913db91bca79fa57d47cc7f256e4010b5 +size 15024 diff --git a/checkpoint-3750/rng_state_3.pth b/checkpoint-3750/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5dd2a92ed1efeac3708d6b858067ebfcd50bda8 --- /dev/null +++ b/checkpoint-3750/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a018983bdd4ce48f5b5199ad5199a9594119987d1ff27309ff2d225603f4b5dd +size 15024 diff --git a/checkpoint-3750/scheduler.pt b/checkpoint-3750/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d11bdb737d24cb3bd9d55556ed19516d03826e1c --- /dev/null +++ b/checkpoint-3750/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a2661bc39d641816434227ba4af98f63bc6ceef9168820ccb1d335f2a1371ee +size 1064 diff --git a/checkpoint-3750/trainer_state.json b/checkpoint-3750/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..5b5cdfde33a0a7ce2c5d12df6e56032fe5edfac0 --- /dev/null +++ b/checkpoint-3750/trainer_state.json @@ -0,0 +1,82 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 32.89473684210526, + "eval_steps": 500, + "global_step": 3750, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + }, + { + "epoch": 30.70175438596491, + "grad_norm": 6.5, + "learning_rate": 3.666436212625509e-05, + "loss": 0.451, + "step": 3500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.2817658806272e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3750/training_args.bin b/checkpoint-3750/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-3750/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-3900/config.json b/checkpoint-3900/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-3900/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-3900/model.safetensors b/checkpoint-3900/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..09b5daa5f372708bee1948d8f1b3a285ceb156a2 --- /dev/null +++ b/checkpoint-3900/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97a5fce980f5803b314ea9e68b107d35a8c935d5d8f95948535307f4c628c15 +size 395500946 diff --git a/checkpoint-3900/optimizer.pt b/checkpoint-3900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..19df04fa72d9cd5e30ca728e395529f23942ca90 --- /dev/null +++ b/checkpoint-3900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b88104ab55afb53721c43d8b9eef9b1eecde99eec387649bd52f38d017f52f3 +size 791234373 diff --git a/checkpoint-3900/rng_state_0.pth b/checkpoint-3900/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..e8c4a191310fbd6d99cdd3145431a99ebcc465ef --- /dev/null +++ b/checkpoint-3900/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38df670915e17254ea1301bec3836ede07e7952296a29b743f9c5ddf79190a66 +size 15024 diff --git a/checkpoint-3900/rng_state_1.pth b/checkpoint-3900/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9a8afe8d6e717fdb51ca95dece02055cc8bcdc2 --- /dev/null +++ b/checkpoint-3900/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6bf57e3b92ae47c807298209ed0f827a30154f28657f92e33c4e9ca8c35218b +size 15024 diff --git a/checkpoint-3900/rng_state_2.pth b/checkpoint-3900/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..8df3fb6e1de68946b59ff8758d8a74fdf2dad5da --- /dev/null +++ b/checkpoint-3900/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37765e8eaf91f20d2c45171298e885656e7ed25ebf2c88e9fe59a43e1654baef +size 15024 diff --git a/checkpoint-3900/rng_state_3.pth b/checkpoint-3900/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce5d9ee82792456ed73b647a2d2c0360f0177a5f --- /dev/null +++ b/checkpoint-3900/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056a7294ff6a41ffa33fa6e0257760b41fa2d6623e1988fdc65bd220217bfe87 +size 15024 diff --git a/checkpoint-3900/scheduler.pt b/checkpoint-3900/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9aee3d841270caee51a7364bc080af71954fd08f --- /dev/null +++ b/checkpoint-3900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd022bd11293a0f309e0bcaec88a28eda3d8fadc02784bec66c8e998b54576b1 +size 1064 diff --git a/checkpoint-3900/trainer_state.json b/checkpoint-3900/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..efbe9482ef3ff3a690c54de19842263fd825678c --- /dev/null +++ b/checkpoint-3900/trainer_state.json @@ -0,0 +1,82 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 34.21052631578947, + "eval_steps": 500, + "global_step": 3900, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + }, + { + "epoch": 30.70175438596491, + "grad_norm": 6.5, + "learning_rate": 3.666436212625509e-05, + "loss": 0.451, + "step": 3500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.333036515852288e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3900/training_args.bin b/checkpoint-3900/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-3900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-4050/config.json b/checkpoint-4050/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-4050/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-4050/model.safetensors b/checkpoint-4050/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a2b2eca9361ab29b85ff06cdf5f91d0d7d89d14 --- /dev/null +++ b/checkpoint-4050/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92ff9befe47df83ed957d516d5ddc64b404a43e28b0d27570e5708f4b9b8437 +size 395500946 diff --git a/checkpoint-4050/optimizer.pt b/checkpoint-4050/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..721a489debd596a36cd6ce9789c48556b825da78 --- /dev/null +++ b/checkpoint-4050/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc8f65c1ad77f934552bf21e4d68cbda46efeb04bff95fa87e56581b938f267 +size 791234373 diff --git a/checkpoint-4050/rng_state_0.pth b/checkpoint-4050/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..40f39023bf630bde1f32f79b6dd753e74c76a812 --- /dev/null +++ b/checkpoint-4050/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2e90a442036c24a378428238255a60587d60bb996ef6a8aa6f3ca09d00c4151 +size 15024 diff --git a/checkpoint-4050/rng_state_1.pth b/checkpoint-4050/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..a75e22dde4785ea78a4df9567c06789435860be3 --- /dev/null +++ b/checkpoint-4050/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1996d6c5b2c8d75c2084b56b416006447537ba281dc1026806631749201ca5 +size 15024 diff --git a/checkpoint-4050/rng_state_2.pth b/checkpoint-4050/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..5fcdfc66eb92e41ccc07253f9307b105f4461b0f --- /dev/null +++ b/checkpoint-4050/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c137ba84bc0f7091808409820b244dca1281c011d08ec6f8c217f5fc2e9cad +size 15024 diff --git a/checkpoint-4050/rng_state_3.pth b/checkpoint-4050/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..817bc8cb0141499566b08d6ff12f7620f9c0054a --- /dev/null +++ b/checkpoint-4050/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61d1023dfe248f50473c449614387b136f3496c0c602b9f8112070e65cf3366 +size 15024 diff --git a/checkpoint-4050/scheduler.pt b/checkpoint-4050/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..65b6d0e2840641602b058fea073341e538381fa8 --- /dev/null +++ b/checkpoint-4050/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd220bf52367f5f767e8c1803f5241c5754c9aa829db3ce1a0900407e002363d +size 1064 diff --git a/checkpoint-4050/trainer_state.json b/checkpoint-4050/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..598b2c4a75cfbaefc8b2256ee4f4cc11d5d2d237 --- /dev/null +++ b/checkpoint-4050/trainer_state.json @@ -0,0 +1,89 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 35.526315789473685, + "eval_steps": 500, + "global_step": 4050, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + }, + { + "epoch": 30.70175438596491, + "grad_norm": 6.5, + "learning_rate": 3.666436212625509e-05, + "loss": 0.451, + "step": 3500 + }, + { + "epoch": 35.08771929824562, + "grad_norm": 5.84375, + "learning_rate": 1.134947733186315e-05, + "loss": 0.2987, + "step": 4000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.384307151077376e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-4050/training_args.bin b/checkpoint-4050/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-4050/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-4200/config.json b/checkpoint-4200/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-4200/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-4200/model.safetensors b/checkpoint-4200/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..65dcc1061b541a23f98dfb5e9715f224027dd2a3 --- /dev/null +++ b/checkpoint-4200/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08d84c2adec78e589ebcbc8738e69516569c3f2e38c7d1e216114f9eb647632 +size 395500946 diff --git a/checkpoint-4200/optimizer.pt b/checkpoint-4200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7fd40a55828df29ef23aa8ebf2b18b39641ab52 --- /dev/null +++ b/checkpoint-4200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ccf6bdea6995f03bdfebc1664ffcd3b5843456a8616d5d5ac42379521b7417 +size 791234373 diff --git a/checkpoint-4200/rng_state_0.pth b/checkpoint-4200/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe3d1649d9eae442807f194526f4c2362c4bfe13 --- /dev/null +++ b/checkpoint-4200/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10947ca3ec926a477a22ce3df4984e61e7683c26d30375ff71a065adf6eb4384 +size 15024 diff --git a/checkpoint-4200/rng_state_1.pth b/checkpoint-4200/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..844fdc1abb96465511499f769a7ecd38ee6d1197 --- /dev/null +++ b/checkpoint-4200/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce27b2a039921ae08169ba9519c9529f0b1f4faec534c79fd45386cdfcb7044f +size 15024 diff --git a/checkpoint-4200/rng_state_2.pth b/checkpoint-4200/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e665c4d38f2364a6dfbbddb772ddd9a7eca87c2 --- /dev/null +++ b/checkpoint-4200/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250093733376e29a942e026ba77f03e3cb3d7d61de57b15b892ebe1aff11293b +size 15024 diff --git a/checkpoint-4200/rng_state_3.pth b/checkpoint-4200/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..a83febd8165c9618f4e5bd5071257e22cedae7df --- /dev/null +++ b/checkpoint-4200/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7916bf6f31222d80025ef0fc2aeb4722b495639e785c094be02daae91aa50bae +size 15024 diff --git a/checkpoint-4200/scheduler.pt b/checkpoint-4200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..851b88a9ef12addbbecd9c63c636455e277c5046 --- /dev/null +++ b/checkpoint-4200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f02c379461fc15ae0d6a84bb81b023802c24bbdcbf29020c2484160258965f +size 1064 diff --git a/checkpoint-4200/trainer_state.json b/checkpoint-4200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2ad7fb40ae5adfd6dc6df2a4a856c2130cb4671d --- /dev/null +++ b/checkpoint-4200/trainer_state.json @@ -0,0 +1,89 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 36.8421052631579, + "eval_steps": 500, + "global_step": 4200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + }, + { + "epoch": 30.70175438596491, + "grad_norm": 6.5, + "learning_rate": 3.666436212625509e-05, + "loss": 0.451, + "step": 3500 + }, + { + "epoch": 35.08771929824562, + "grad_norm": 5.84375, + "learning_rate": 1.134947733186315e-05, + "loss": 0.2987, + "step": 4000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.435577786302464e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-4200/training_args.bin b/checkpoint-4200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-4200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-4350/config.json b/checkpoint-4350/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-4350/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-4350/model.safetensors b/checkpoint-4350/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f95b96e594d5c2a4b22bf25c32c90051c3526b11 --- /dev/null +++ b/checkpoint-4350/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0e49cb3497e351c2ab88e6c90c2fef763cbb17d02d695577e946925a7fb9b9 +size 395500946 diff --git a/checkpoint-4350/optimizer.pt b/checkpoint-4350/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..147dc3eed58ef4a27b6b0523e72644e1d0ae8347 --- /dev/null +++ b/checkpoint-4350/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d6a9a13e95d68c514a0541cafb4c2f146bcb170c06fb612d0e2d6990f61423 +size 791234373 diff --git a/checkpoint-4350/rng_state_0.pth b/checkpoint-4350/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..f063e0d7f12647c4de053e56881ff7a1bff61c57 --- /dev/null +++ b/checkpoint-4350/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c667ad725fd031bf9eb0d0a357ad0c61f5a4c8f46bca6da40ff6cb3db56550 +size 15024 diff --git a/checkpoint-4350/rng_state_1.pth b/checkpoint-4350/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f7b7bc788484bee021c673bc11e030e1d5111c97 --- /dev/null +++ b/checkpoint-4350/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb86a0b1783d05658387edfd2b49436fafa40ea3b0d9a6d857283aac199e884d +size 15024 diff --git a/checkpoint-4350/rng_state_2.pth b/checkpoint-4350/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..15660ba845bbae4d9715b201e4178f844c128b78 --- /dev/null +++ b/checkpoint-4350/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82fd27d553d45a1d9760e596aad99d92bba626396d91da2c335b199fb357e9b0 +size 15024 diff --git a/checkpoint-4350/rng_state_3.pth b/checkpoint-4350/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..c77088164440a86103e6e81a3ae6e84dd0cf2d66 --- /dev/null +++ b/checkpoint-4350/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c126e80b288700d03f9c6213fb74a4e9f308ecf2d9b9a21041df0a47987b3f70 +size 15024 diff --git a/checkpoint-4350/scheduler.pt b/checkpoint-4350/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef80f5a501279dd61531d8ea20e9c068a4e4a5a2 --- /dev/null +++ b/checkpoint-4350/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bf0a11c95bd19a2d3864bd10577e877778abf11ae5dbfcf4e43d3d9700c13d +size 1064 diff --git a/checkpoint-4350/trainer_state.json b/checkpoint-4350/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..def992a35c5d1b8e751ad2ac5a79775a14757e4a --- /dev/null +++ b/checkpoint-4350/trainer_state.json @@ -0,0 +1,89 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 38.1578947368421, + "eval_steps": 500, + "global_step": 4350, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + }, + { + "epoch": 8.771929824561404, + "grad_norm": 10.625, + "learning_rate": 5e-05, + "loss": 1.9744, + "step": 1000 + }, + { + "epoch": 13.157894736842104, + "grad_norm": 21.625, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7097, + "step": 1500 + }, + { + "epoch": 17.54385964912281, + "grad_norm": 16.375, + "learning_rate": 0.0001, + "loss": 1.4299, + "step": 2000 + }, + { + "epoch": 21.92982456140351, + "grad_norm": 13.625, + "learning_rate": 9.087924065757919e-05, + "loss": 1.1377, + "step": 2500 + }, + { + "epoch": 26.31578947368421, + "grad_norm": 8.25, + "learning_rate": 6.6844492669611e-05, + "loss": 0.7634, + "step": 3000 + }, + { + "epoch": 30.70175438596491, + "grad_norm": 6.5, + "learning_rate": 3.666436212625509e-05, + "loss": 0.451, + "step": 3500 + }, + { + "epoch": 35.08771929824562, + "grad_norm": 5.84375, + "learning_rate": 1.134947733186315e-05, + "loss": 0.2987, + "step": 4000 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.486848421527552e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-4350/training_args.bin b/checkpoint-4350/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-4350/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-450/config.json b/checkpoint-450/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-450/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-450/model.safetensors b/checkpoint-450/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b1931b91bc5f97b507e4291c32b2578e25bc73e --- /dev/null +++ b/checkpoint-450/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d628887902a02d3124187b05c1bcd80648fa95f5482347ec0b3bcb1ccd323d5a +size 395500946 diff --git a/checkpoint-450/optimizer.pt b/checkpoint-450/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d285c984d09c1de36e3393a83ba17208b74190c --- /dev/null +++ b/checkpoint-450/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad85a779a0206b2fb6d1aa686820f816459e1a76db00826210f5b4399e855fe2 +size 791234373 diff --git a/checkpoint-450/rng_state_0.pth b/checkpoint-450/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..f108ce345cd9ebb419603e0f9da5dcc09b085c20 --- /dev/null +++ b/checkpoint-450/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e36d18af573791d9ae7bb1e60091bede56cbf266de7f51ad00315ef1b5d97f9 +size 15024 diff --git a/checkpoint-450/rng_state_1.pth b/checkpoint-450/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..874a2887a36725f913dbcde7272d18c65470c57f --- /dev/null +++ b/checkpoint-450/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b067d7c585e534077cca3bee770964aa86a3f34ee89075e65b34f6c0ff233ba1 +size 15024 diff --git a/checkpoint-450/rng_state_2.pth b/checkpoint-450/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4e0aa064ed345df0266a891e4da5d1e2aaf709a6 --- /dev/null +++ b/checkpoint-450/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437c58668142dba46a9a572f727f9714e20150c49c716018034c10da66fefa14 +size 15024 diff --git a/checkpoint-450/rng_state_3.pth b/checkpoint-450/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..9bfff89b1266d75975bc9707df63fa78647f22cd --- /dev/null +++ b/checkpoint-450/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ab50325967ac8472faafa77668ad3fbf79f63ae418e001a9c9ae5e04367516 +size 15024 diff --git a/checkpoint-450/scheduler.pt b/checkpoint-450/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b3c8f74a964f4b4f983a695211b77f74250ada7 --- /dev/null +++ b/checkpoint-450/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783ce5995ff03be5c8f962755ba566785ad0e94de58ca6127ad48a141184381e +size 1064 diff --git a/checkpoint-450/trainer_state.json b/checkpoint-450/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..567184eb31f492511d18bf9dbeec0d0aed32cae2 --- /dev/null +++ b/checkpoint-450/trainer_state.json @@ -0,0 +1,32 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.9473684210526314, + "eval_steps": 500, + "global_step": 450, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.53811905675264e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-450/training_args.bin b/checkpoint-450/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-450/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-600/config.json b/checkpoint-600/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-600/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-600/model.safetensors b/checkpoint-600/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..147f21c2d483d18dd0b71c905a64c473d8e74d35 --- /dev/null +++ b/checkpoint-600/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b3848c2ca29b874e583ca4b4e30b6e90609c53971bb8e9acccc506aadba4d7a +size 395500946 diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8a74f846a1b2a20117b3d6352a6cb51f5c69b22 --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ac8acfc9ac78a1643fe103c367a2ab4c0cac528cd56f354c0934224138237f +size 791234373 diff --git a/checkpoint-600/rng_state_0.pth b/checkpoint-600/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..14a37f7451b93d17a846fd45db21a2331e9ec040 --- /dev/null +++ b/checkpoint-600/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:211c7e456f4b3d94e9a7976667e756cfeda82a80b214c90be46fdda91e370a16 +size 15024 diff --git a/checkpoint-600/rng_state_1.pth b/checkpoint-600/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef1ee12fd138c55a6e6bdccf83046ae0474f2d08 --- /dev/null +++ b/checkpoint-600/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b62bff90d7be4797f330375882674e6f2af8f2d167e6885863d6854d1460d6f0 +size 15024 diff --git a/checkpoint-600/rng_state_2.pth b/checkpoint-600/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..c274a26f5ece4322fa6b8d4c8f4d1df0ea9dea6f --- /dev/null +++ b/checkpoint-600/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc2fd0dacda516860aaf48b7a7fce577dbba3a01451ee59e9e76030e1792276 +size 15024 diff --git a/checkpoint-600/rng_state_3.pth b/checkpoint-600/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..de43a9a359edb310f52fd7205f02c8c7f5a76799 --- /dev/null +++ b/checkpoint-600/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b17dbf8afee7f81707fd60dab54534c6fdb9de14b860ec64d45d2107d4c2253 +size 15024 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..059576272e310d7634891244269bf25e217de122 --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5f70e5c98503e775a869db4cbd097967e111966db1c1cbd92f2fac84af4a90 +size 1064 diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..8e154514b73f9f8f8f03503c0e88a34b24391961 --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,40 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.2631578947368425, + "eval_steps": 500, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.05082540900352e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-750/config.json b/checkpoint-750/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-750/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-750/model.safetensors b/checkpoint-750/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..784f990c99ec016ab6309ea7cecf10f56bbfaecb --- /dev/null +++ b/checkpoint-750/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce7f8a15de03d8cc7eafe4ec888f39c000ac121c845a995c37f7da2fc4433f2b +size 395500946 diff --git a/checkpoint-750/optimizer.pt b/checkpoint-750/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bbc7cae3866906127297c0c21bc46a966b01a0a --- /dev/null +++ b/checkpoint-750/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5944f69434f4bf561fba6388d838512b1066580655aac63be9df73a5331c54 +size 791234373 diff --git a/checkpoint-750/rng_state_0.pth b/checkpoint-750/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..88c5e3b8ced6e20e04a1a0913aa8ae47f4ff45a6 --- /dev/null +++ b/checkpoint-750/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6db4e8209a014c63649308b5b6ecc18d56bfbd6a0401491ed7f25fcd06ed384 +size 15024 diff --git a/checkpoint-750/rng_state_1.pth b/checkpoint-750/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..4637a54226df889695a1794f901b5a2f9ed6a219 --- /dev/null +++ b/checkpoint-750/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0047db84bc59512a5a6135d3cef8d0b736175d6fad11d222e971a1c3720add31 +size 15024 diff --git a/checkpoint-750/rng_state_2.pth b/checkpoint-750/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..63f0d0a4c005fd03e57f20d3988410ed31eb7803 --- /dev/null +++ b/checkpoint-750/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6089fd7f57a4f2878c7a9074223b900eee00726498484a774b22b32dd2e47fc9 +size 15024 diff --git a/checkpoint-750/rng_state_3.pth b/checkpoint-750/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..dd185e7face308041e5d2bdf61d746dea8c38878 --- /dev/null +++ b/checkpoint-750/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f30da07a46da31b22c241a6b2606b0ba3df2117a191a63d7cadc3df165a7f10 +size 15024 diff --git a/checkpoint-750/scheduler.pt b/checkpoint-750/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee2d791899a9b96d9268c8759ff12dd0e8214b24 --- /dev/null +++ b/checkpoint-750/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3edd6f228a56c3a7358f0170fc75d9b539e5c22b88e18d302eee6e42cc8492f4 +size 1064 diff --git a/checkpoint-750/trainer_state.json b/checkpoint-750/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d3c7483aa407018409377631ef93571c699102ca --- /dev/null +++ b/checkpoint-750/trainer_state.json @@ -0,0 +1,40 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 6.578947368421053, + "eval_steps": 500, + "global_step": 750, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.5635317612544e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-750/training_args.bin b/checkpoint-750/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-750/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/checkpoint-900/config.json b/checkpoint-900/config.json new file mode 100644 index 0000000000000000000000000000000000000000..339e99ee15e4f2246ace3f4d5c69230c89435aaf --- /dev/null +++ b/checkpoint-900/config.json @@ -0,0 +1,170 @@ +{ + "architectures": [ + "VisionTextDualEncoderModel" + ], + "cache_dir": null, + "logit_scale_init_value": 2.6592, + "model_type": "vision-text-dual-encoder", + "projection_dim": 512, + "text_config": { + "_name_or_path": "naver/splade-v3", + "add_cross_attention": false, + "architectures": [ + "BertForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "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": null, + "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": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "bert", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "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": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "type_vocab_size": 2, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 30522 + }, + "token": null, + "torch_dtype": "bfloat16", + "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 + } +} diff --git a/checkpoint-900/model.safetensors b/checkpoint-900/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d98342a383e2303666b620ca709874aa64b6b75d --- /dev/null +++ b/checkpoint-900/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68633b869ef5ddbea78b374f45ba64ae1dddfde94e145a39c7a5442f454bf9c8 +size 395500946 diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..bdcb4020de407f23c750c4cb77d033e4caa81549 --- /dev/null +++ b/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b5be49fbd46b8bf613160bbba1aa0fcdd95e1d959c0ef79f676e2d366c49d00 +size 791234373 diff --git a/checkpoint-900/rng_state_0.pth b/checkpoint-900/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..65338b6b911c0a730a713dcc1a29f977fa59f77c --- /dev/null +++ b/checkpoint-900/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6eb5d2f51a2589f8d06ba714752d15052657faa80e185b17fea983d9fe3c91 +size 15024 diff --git a/checkpoint-900/rng_state_1.pth b/checkpoint-900/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea60d1762fb0667a7d16ebd656d2d8967e63dd53 --- /dev/null +++ b/checkpoint-900/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b229864718f7c16425146c618f481ce9db21b2e63b18682dc25657832f4d151a +size 15024 diff --git a/checkpoint-900/rng_state_2.pth b/checkpoint-900/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..453bd81d4722f3a6fe826ba4a5d856eb5d40242b --- /dev/null +++ b/checkpoint-900/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e396cfb557d024a1b7a0ad05c0b9c2ae6283533ee2febf552fc0f43b6967a847 +size 15024 diff --git a/checkpoint-900/rng_state_3.pth b/checkpoint-900/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..8677a6ba0d73731fc46f7535af6a4ea78682b270 --- /dev/null +++ b/checkpoint-900/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db6b41f8dca5e4ad441d2eb4343fafb7b8cd14c59ed8de95c5d13c74884455d +size 15024 diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd81b544aef535f0df052057d4be177314dca078 --- /dev/null +++ b/checkpoint-900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8295821629c86da31821cd9eb93e5dbcd5a569344c12cdcfd3f6ec3611bd3062 +size 1064 diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d02ce2ca566ae23c25c4f72a193888ef17cfbc12 --- /dev/null +++ b/checkpoint-900/trainer_state.json @@ -0,0 +1,40 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 7.894736842105263, + "eval_steps": 500, + "global_step": 900, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 4.385964912280702, + "grad_norm": 9.875, + "learning_rate": 2.5e-05, + "loss": 2.8556, + "step": 500 + } + ], + "logging_steps": 500, + "max_steps": 4560, + "num_input_tokens_seen": 0, + "num_train_epochs": 40, + "save_steps": 150, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.07623811350528e+16, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbacea8e60beabf8581f9c3886c6adb042a76a80 --- /dev/null +++ b/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e9100099ba0bb9c54b10cf21ecd4a5866a98ab069d0b673a33313627e62133 +size 5304 diff --git a/runs/Jan17_09-50-46_meditron-fab-0-0/events.out.tfevents.1737107468.meditron-fab-0-0.22780.0 b/runs/Jan17_09-50-46_meditron-fab-0-0/events.out.tfevents.1737107468.meditron-fab-0-0.22780.0 new file mode 100644 index 0000000000000000000000000000000000000000..9d7441ff02a4f6492ea27aa0d2518a2388357368 --- /dev/null +++ b/runs/Jan17_09-50-46_meditron-fab-0-0/events.out.tfevents.1737107468.meditron-fab-0-0.22780.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90808c473b5cc097e4c60537657743bdfea48855bc1d74dcd2e697d04c09f5fb +size 10555