/cluster/work/cotterell/tamariucai/HuggingfaceCheckpoints/flava-wit/text10-vision10/bs4096_seed5501650_bf16-mixed/flava-epoch=00-step=11876.ckpt
2c89f9c
{ | |
"_commit_hash": null, | |
"architectures": [ | |
"FlavaForPreTraining" | |
], | |
"ce_ignore_index": -100, | |
"compile_submodels": true, | |
"global_backprop_contrastive": true, | |
"global_contrastive_weight": 1.0, | |
"hidden_size": 768, | |
"image_codebook_config": { | |
"_name_or_path": "", | |
"add_cross_attention": false, | |
"architectures": null, | |
"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, | |
"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, | |
"freeze": true, | |
"hidden_size": 256, | |
"id2label": { | |
"0": "LABEL_0", | |
"1": "LABEL_1" | |
}, | |
"initializer_range": 0.02, | |
"input_channels": 3, | |
"is_decoder": false, | |
"is_encoder_decoder": false, | |
"label2id": { | |
"LABEL_0": 0, | |
"LABEL_1": 1 | |
}, | |
"length_penalty": 1.0, | |
"max_length": 20, | |
"min_length": 0, | |
"model_type": "flava_image_codebook", | |
"no_repeat_ngram_size": 0, | |
"num_beam_groups": 1, | |
"num_beams": 1, | |
"num_blocks_per_group": 2, | |
"num_groups": 4, | |
"num_return_sequences": 1, | |
"output_attentions": false, | |
"output_hidden_states": false, | |
"output_scores": false, | |
"pad_token_id": null, | |
"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": null, | |
"torchscript": false, | |
"transformers_version": "4.29.2", | |
"typical_p": 1.0, | |
"use_bfloat16": false, | |
"vocab_size": 8192 | |
}, | |
"image_config": { | |
"_name_or_path": "", | |
"add_cross_attention": false, | |
"architectures": null, | |
"attention_probs_dropout_prob": 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, | |
"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": "gelu", | |
"hidden_dropout_prob": 0.0, | |
"hidden_size": 768, | |
"id2label": { | |
"0": "LABEL_0", | |
"1": "LABEL_1" | |
}, | |
"image_size": 224, | |
"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, | |
"mask_token": true, | |
"max_length": 20, | |
"min_length": 0, | |
"model_type": "flava_image_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": 16, | |
"prefix": null, | |
"problem_type": null, | |
"pruned_heads": {}, | |
"qkv_bias": true, | |
"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, | |
"transformers_version": "4.29.2", | |
"typical_p": 1.0, | |
"use_bfloat16": false, | |
"vocab_size": 8192 | |
}, | |
"init_codebook": true, | |
"initializer_factor": 1.0, | |
"initializer_range": 0.02, | |
"itm_weight": 1.0, | |
"layer_norm_eps": 1e-12, | |
"logit_scale_init_value": 2.6592, | |
"mim_weight": 1.0, | |
"mlm_weight": 1.0, | |
"mmm_image_weight": 1.0, | |
"mmm_text_weight": 1.0, | |
"model_type": "flava", | |
"multimodal_config": { | |
"_name_or_path": "", | |
"add_cross_attention": false, | |
"architectures": null, | |
"attention_probs_dropout_prob": 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, | |
"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": "gelu", | |
"hidden_dropout_prob": 0.0, | |
"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, | |
"min_length": 0, | |
"model_type": "flava_multimodal_model", | |
"no_repeat_ngram_size": 0, | |
"num_attention_heads": 12, | |
"num_beam_groups": 1, | |
"num_beams": 1, | |
"num_hidden_layers": 6, | |
"num_return_sequences": 1, | |
"output_attentions": false, | |
"output_hidden_states": false, | |
"output_scores": false, | |
"pad_token_id": null, | |
"prefix": null, | |
"problem_type": null, | |
"pruned_heads": {}, | |
"qkv_bias": true, | |
"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, | |
"transformers_version": "4.29.2", | |
"typical_p": 1.0, | |
"use_bfloat16": false, | |
"use_cls_token": true | |
}, | |
"projection_dim": 768, | |
"return_loss": true, | |
"skip_unmasked_multimodal_encoder": true, | |
"text_config": { | |
"_name_or_path": "", | |
"add_cross_attention": false, | |
"architectures": null, | |
"attention_probs_dropout_prob": 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, | |
"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": "gelu", | |
"hidden_dropout_prob": 0.0, | |
"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": "flava_text_model", | |
"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": {}, | |
"qkv_bias": true, | |
"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, | |
"transformers_version": "4.29.2", | |
"type_vocab_size": 2, | |
"typical_p": 1.0, | |
"use_bfloat16": false, | |
"vocab_size": 30522 | |
}, | |
"torch_dtype": "float32", | |
"transformers_version": null | |
} | |