Training in progress, step 7000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,182 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "HooshvareLab/bert-fa-base-uncased-clf-persiannews",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForSequenceClassification"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": 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,
+    "finetuning_task": "persiannews",
+    "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": "\u0627\u062c\u062a\u0645\u0627\u0639\u06cc",
+      "1": "\u0627\u0642\u062a\u0635\u0627\u062f\u06cc",
+      "2": "\u0628\u06cc\u0646 \u0627\u0644\u0645\u0644\u0644",
+      "3": "\u0633\u06cc\u0627\u0633\u06cc",
+      "4": "\u0639\u0644\u0645\u06cc \u0641\u0646\u0627\u0648\u0631\u06cc",
+      "5": "\u0641\u0631\u0647\u0646\u06af\u06cc \u0647\u0646\u0631\u06cc",
+      "6": "\u0648\u0631\u0632\u0634\u06cc",
+      "7": "\u067e\u0632\u0634\u06a9\u06cc"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "\u0627\u062c\u062a\u0645\u0627\u0639\u06cc": 0,
+      "\u0627\u0642\u062a\u0635\u0627\u062f\u06cc": 1,
+      "\u0628\u06cc\u0646 \u0627\u0644\u0645\u0644\u0644": 2,
+      "\u0633\u06cc\u0627\u0633\u06cc": 3,
+      "\u0639\u0644\u0645\u06cc \u0641\u0646\u0627\u0648\u0631\u06cc": 4,
+      "\u0641\u0631\u0647\u0646\u06af\u06cc \u0647\u0646\u0631\u06cc": 5,
+      "\u0648\u0631\u0632\u0634\u06cc": 6,
+      "\u067e\u0632\u0634\u06a9\u06cc": 7
+    },
+    "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,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "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": "4.12.5",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 100001
+  },
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": 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,
+    "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,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "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,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "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": "4.12.5",
+    "use_bfloat16": false
+  },
+  "eos_token_id": 4,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 30,
+  "model_type": "vision-encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vocab_size": 100001
+}

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3eb62921c87e0e7bf920a9dc9e1cba1f3eb05a991d5eb976c3852317640c453
+size 1111020587

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfebb0bf97ee97f3f6b1bb9277b813efc566b6b066d7c226a643a486bea99aa5
+size 2927