update model weight

README.md

@@ -1,3 +0,0 @@
----
-license: mit
----

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.4329880177974701,
+    "eval_runtime": 208.8416,
+    "eval_samples_per_second": 239.416,
+    "eval_steps_per_second": 0.235,
+    "train_loss": 0.5196692755362847,
+    "train_runtime": 286003.5676,
+    "train_samples_per_second": 89.591,
+    "train_steps_per_second": 0.7
+}

config.json

@@ -0,0 +1,189 @@
+{
+  "architectures": [
+    "GenericExplainer"
+  ],
+  "backbone_config": {
+    "_commit_hash": "f4bf8a536816f4f7d5c8b7fbd4621396c195001f",
+    "_name_or_path": "facebook/vit-mae-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTMAEForPreTraining"
+    ],
+    "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_hidden_size": 512,
+    "decoder_intermediate_size": 2048,
+    "decoder_num_attention_heads": 16,
+    "decoder_num_hidden_layers": 8,
+    "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_ratio": 0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit_mae",
+    "no_repeat_ngram_size": 0,
+    "norm_pix_loss": true,
+    "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": "float32",
+    "torchscript": false,
+    "transformers_version": "4.16.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "explainerhead_layernum": 17,
+  "heatmap_patch_num_per_patch": 1,
+  "heatmap_size": 14,
+  "image_processor_name": "facebook/vit-mae-base",
+  "image_size": 224,
+  "lora": false,
+  "lora_dim": 32,
+  "mask_ratio": 0,
+  "perturb_radius": 2,
+  "target_encoder_config": {
+    "_commit_hash": "f4bf8a536816f4f7d5c8b7fbd4621396c195001f",
+    "_name_or_path": "facebook/vit-mae-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTMAEForPreTraining"
+    ],
+    "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_hidden_size": 512,
+    "decoder_intermediate_size": 2048,
+    "decoder_num_attention_heads": 16,
+    "decoder_num_hidden_layers": 8,
+    "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_ratio": 0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit_mae",
+    "no_repeat_ngram_size": 0,
+    "norm_pix_loss": true,
+    "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": "float32",
+    "torchscript": false,
+    "transformers_version": "4.16.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "target_hidden_size": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2"
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.4329880177974701,
+    "eval_runtime": 208.8416,
+    "eval_samples_per_second": 239.416,
+    "eval_steps_per_second": 0.235
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926569704edead3507819ad112842b84d186cec1878a8b38597ed3e30072dab0
+size 1325455189

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.5196692755362847,
+    "train_runtime": 286003.5676,
+    "train_samples_per_second": 89.591,
+    "train_steps_per_second": 0.7
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dae131bb4b25193284c08bbc2e9c0f5b54b8816498fd48eba1332735c4c9a7c
+size 4219