Upload 9 files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83b9c46c86ba410d5915ee9bf0fb539cc727836e56432c9bf9e0927c4aba246
+size 439794029

run_config.json

@@ -0,0 +1,47 @@
+{
+    "_CHeeSEArguments": "CHeeSEArguments",
+    "model_name_or_path": "dbmdz/bert-base-german-cased",
+    "dataset_path": "./dataset.py",
+    "metric_path": "./metric.py",
+    "task": "stance_detection",
+    "first_sentence_inputs": [
+        "question"
+    ],
+    "second_sentence_inputs": [
+        "title",
+        "snippet",
+        "paragraphs"
+    ],
+    "labels_to_predict": [
+        "stance"
+    ],
+    "_CHeeSETrainingArguments": "CHeeSETrainingArguments",
+    "do_train": true,
+    "do_eval": true,
+    "do_predict": true,
+    "do_cross_validation": false,
+    "output_dir": "/netscratch/schnitzler/bert",
+    "logging_dir": "/netscratch/schnitzler/bert",
+    "save_total_limit": 2,
+    "log_to_file": true,
+    "logging_strategy": "steps",
+    "logging_steps": 50,
+    "cross_validation_folds": 5,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 8,
+    "fp16": false,
+    "learning_rate": 3e-05,
+    "prediction_csv_kwargs": {
+        "index": false
+    },
+    "prediction_columns_to_include": [
+        "title",
+        "snippet",
+        "paragraphs",
+        "question",
+        "labels",
+        "stance"
+    ],
+    "overwrite_output_dir": true
+}

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "name_or_path": "dbmdz/bert-base-german-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 1196,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.874581939799331e-05,
+      "loss": 1.1476,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.7491638795986622e-05,
+      "loss": 0.9973,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.6237458193979933e-05,
+      "loss": 1.0316,
+      "step": 150
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.4983277591973243e-05,
+      "loss": 0.9801,
+      "step": 200
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.3729096989966557e-05,
+      "loss": 0.9947,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.2474916387959865e-05,
+      "loss": 0.9882,
+      "step": 300
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.122073578595318e-05,
+      "loss": 0.8896,
+      "step": 350
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.996655518394649e-05,
+      "loss": 0.7913,
+      "step": 400
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.87123745819398e-05,
+      "loss": 0.8249,
+      "step": 450
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.745819397993311e-05,
+      "loss": 0.7808,
+      "step": 500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.620401337792642e-05,
+      "loss": 0.7632,
+      "step": 550
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.4949832775919733e-05,
+      "loss": 0.7577,
+      "step": 600
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3695652173913042e-05,
+      "loss": 0.6454,
+      "step": 650
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.2441471571906355e-05,
+      "loss": 0.5908,
+      "step": 700
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.1187290969899665e-05,
+      "loss": 0.6114,
+      "step": 750
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 9.933110367892978e-06,
+      "loss": 0.6383,
+      "step": 800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.678929765886286e-06,
+      "loss": 0.6207,
+      "step": 850
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 7.424749163879599e-06,
+      "loss": 0.5649,
+      "step": 900
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 6.17056856187291e-06,
+      "loss": 0.4894,
+      "step": 950
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 4.916387959866221e-06,
+      "loss": 0.4434,
+      "step": 1000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 3.662207357859532e-06,
+      "loss": 0.3991,
+      "step": 1050
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 2.408026755852843e-06,
+      "loss": 0.4938,
+      "step": 1100
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 0.3628,
+      "step": 1150
+    },
+    {
+      "epoch": 4.0,
+      "step": 1196,
+      "total_flos": 2517491783958528.0,
+      "train_loss": 0.7212204247414069,
+      "train_runtime": 362.6132,
+      "train_samples_per_second": 26.386,
+      "train_steps_per_second": 3.298
+    }
+  ],
+  "max_steps": 1196,
+  "num_train_epochs": 4,
+  "total_flos": 2517491783958528.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67333a28e4f00c43e9463296a39729f46fe5c9db2cf32d65e5509c6350eceec2
+size 3631