Upload folder using huggingface_hub

checkpoint-180/config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "TaskClassifier"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "vqa",
+    "1": "captioning",
+    "2": "grounding",
+    "3": "geometry"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "captioning": 1,
+    "geometry": 3,
+    "grounding": 2,
+    "vqa": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-180/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eefc17988ca247acd050adb73dca3b4c625c1446ab62fbc83229aa91616b90f
+size 438873960

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b259203af7a81a37e580365c53ed814d49966368e04c09bb78c40b02a1d25700
+size 877874891

checkpoint-180/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa7df41239a87c0300a2a9b8288f2ae095bba9c56a6d14df65780ef1d2212de
+size 14645

checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f858239dd53091ca54316fa5e2d432ef7f33147995a0495e8a8158d81ddac891
+size 1465

checkpoint-180/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-180/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-180/trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_global_step": 180,
+  "best_metric": 0.9811938061938061,
+  "best_model_checkpoint": "task_classifier_output/checkpoint-180",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.90625,
+      "eval_f1": 0.9063951526529118,
+      "eval_loss": 1.2780158519744873,
+      "eval_runtime": 0.2861,
+      "eval_samples_per_second": 559.171,
+      "eval_steps_per_second": 17.474,
+      "step": 45
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.7980117201805115,
+      "learning_rate": 1.5644444444444448e-05,
+      "loss": 1.3336,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9375,
+      "eval_f1": 0.9384057761035448,
+      "eval_loss": 1.1573435068130493,
+      "eval_runtime": 0.2207,
+      "eval_samples_per_second": 724.836,
+      "eval_steps_per_second": 22.651,
+      "step": 90
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.1813886165618896,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 1.1986,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.975,
+      "eval_f1": 0.9749526335733233,
+      "eval_loss": 1.0562200546264648,
+      "eval_runtime": 0.2421,
+      "eval_samples_per_second": 660.969,
+      "eval_steps_per_second": 20.655,
+      "step": 135
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.406683325767517,
+      "learning_rate": 6.755555555555556e-06,
+      "loss": 1.0763,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.98125,
+      "eval_f1": 0.9811938061938061,
+      "eval_loss": 0.9907373189926147,
+      "eval_runtime": 0.2405,
+      "eval_samples_per_second": 665.339,
+      "eval_steps_per_second": 20.792,
+      "step": 180
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 74049218724096.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88d4bf5ff29db3aa978d322dd0c84e23f85369960fe3635abe7d0e92bd27b53
+size 5841

checkpoint-225/config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "TaskClassifier"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "vqa",
+    "1": "captioning",
+    "2": "grounding",
+    "3": "geometry"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "captioning": 1,
+    "geometry": 3,
+    "grounding": 2,
+    "vqa": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-225/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d510058b0e3740dbc8a7c8efa5a7fdc3ce35de2356947603feaa4b89dbf790
+size 438873960

checkpoint-225/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1bd01525284a5bab61c4d3a1fa47fe0ce205b26fcc2f497e5678e7a38b32211
+size 877874891

checkpoint-225/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02320410bed33459261a07d0bd60949b0914e43b3865a6176eda7693ef12ee62
+size 14645

checkpoint-225/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b2b5072c8b2d8aedeffbe6e5d3b5c704b67d5610d59ad55de2fbc822578341
+size 1465

checkpoint-225/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-225/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-225/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 180,
+  "best_metric": 0.9811938061938061,
+  "best_model_checkpoint": "task_classifier_output/checkpoint-180",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.90625,
+      "eval_f1": 0.9063951526529118,
+      "eval_loss": 1.2780158519744873,
+      "eval_runtime": 0.2861,
+      "eval_samples_per_second": 559.171,
+      "eval_steps_per_second": 17.474,
+      "step": 45
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.7980117201805115,
+      "learning_rate": 1.5644444444444448e-05,
+      "loss": 1.3336,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9375,
+      "eval_f1": 0.9384057761035448,
+      "eval_loss": 1.1573435068130493,
+      "eval_runtime": 0.2207,
+      "eval_samples_per_second": 724.836,
+      "eval_steps_per_second": 22.651,
+      "step": 90
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.1813886165618896,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 1.1986,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.975,
+      "eval_f1": 0.9749526335733233,
+      "eval_loss": 1.0562200546264648,
+      "eval_runtime": 0.2421,
+      "eval_samples_per_second": 660.969,
+      "eval_steps_per_second": 20.655,
+      "step": 135
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.406683325767517,
+      "learning_rate": 6.755555555555556e-06,
+      "loss": 1.0763,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.98125,
+      "eval_f1": 0.9811938061938061,
+      "eval_loss": 0.9907373189926147,
+      "eval_runtime": 0.2405,
+      "eval_samples_per_second": 665.339,
+      "eval_steps_per_second": 20.792,
+      "step": 180
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 2.066603899002075,
+      "learning_rate": 2.311111111111111e-06,
+      "loss": 1.0026,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.98125,
+      "eval_f1": 0.9811938061938061,
+      "eval_loss": 0.969234824180603,
+      "eval_runtime": 0.2384,
+      "eval_samples_per_second": 671.108,
+      "eval_steps_per_second": 20.972,
+      "step": 225
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 92565645494784.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-225/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88d4bf5ff29db3aa978d322dd0c84e23f85369960fe3635abe7d0e92bd27b53
+size 5841

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "TaskClassifier"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "vqa",
+    "1": "captioning",
+    "2": "grounding",
+    "3": "geometry"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "captioning": 1,
+    "geometry": 3,
+    "grounding": 2,
+    "vqa": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eefc17988ca247acd050adb73dca3b4c625c1446ab62fbc83229aa91616b90f
+size 438873960

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88d4bf5ff29db3aa978d322dd0c84e23f85369960fe3635abe7d0e92bd27b53
+size 5841