Upload 10 files

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "LennartKeller/longformer-gottbert-base-8192-aw512",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": true,
+  "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": 8194,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 52009
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab7b8e22f71f71cc81317d4bc29a4bc3b78462606ed52064a639bf488deff2a
+size 612773004

run_config.json

@@ -0,0 +1,46 @@
+{
+    "_CHeeSEArguments": "CHeeSEArguments",
+    "model_name_or_path": "/netscratch/schnitzler/longformer",
+    "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": false,
+    "do_eval": true,
+    "do_predict": true,
+    "do_cross_validation": false,
+    "output_dir": "/netscratch/schnitzler/longformer",
+    "logging_dir": "/netscratch/schnitzler/longformer",
+    "save_total_limit": 3,
+    "log_to_file": true,
+    "logging_strategy": "steps",
+    "logging_steps": 50,
+    "cross_validation_folds": 5,
+    "save_steps": 1000,
+    "evaluation_strategy": "steps",
+    "eval_steps": 500,
+    "num_train_epochs": 12,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 8,
+    "learning_rate": 3e-05,
+    "prediction_columns_to_include": [
+        "title",
+        "snippet",
+        "paragraphs",
+        "question",
+        "labels",
+        "stance"
+    ],
+    "overwrite_output_dir": true
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "LennartKeller/longformer-gottbert-base-8192-aw512", "model_max_length": 8192, "tokenizer_class": "LongformerTokenizer"}

trainer_state.json

@@ -0,0 +1,191 @@
+{
+  "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": 2.8770903010033445e-05,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.7516722408026756e-05,
+      "loss": 1.297,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.626254180602007e-05,
+      "loss": 1.2396,
+      "step": 150
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.508361204013378e-05,
+      "loss": 1.1525,
+      "step": 200
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.382943143812709e-05,
+      "loss": 1.1361,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.2575250836120402e-05,
+      "loss": 1.0224,
+      "step": 300
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.1321070234113713e-05,
+      "loss": 0.9715,
+      "step": 350
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.0066889632107023e-05,
+      "loss": 1.0531,
+      "step": 400
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.8812709030100337e-05,
+      "loss": 0.981,
+      "step": 450
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.7558528428093648e-05,
+      "loss": 0.97,
+      "step": 500
+    },
+    {
+      "epoch": 1.67,
+      "eval_accuracy": 0.61875,
+      "eval_f1_macro": 0.4388243335611756,
+      "eval_f1_micro": 0.61875,
+      "eval_f1_unweighted_diskutierend": 0.47619047619047616,
+      "eval_f1_unweighted_ja-daf\u00fcr": 0.4912280701754386,
+      "eval_f1_unweighted_kein-bezug": 0.7878787878787878,
+      "eval_f1_unweighted_nein-dagegen": 0.0,
+      "eval_f1_weighted": 0.5780730234677603,
+      "eval_loss": 0.9460641145706177,
+      "eval_runtime": 61.5083,
+      "eval_samples_per_second": 2.601,
+      "step": 500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.6304347826086955e-05,
+      "loss": 0.9701,
+      "step": 550
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.5050167224080267e-05,
+      "loss": 0.9235,
+      "step": 600
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.379598662207358e-05,
+      "loss": 0.7441,
+      "step": 650
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.254180602006689e-05,
+      "loss": 0.8782,
+      "step": 700
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.1287625418060201e-05,
+      "loss": 0.8644,
+      "step": 750
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 1.0033444816053512e-05,
+      "loss": 0.7321,
+      "step": 800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.779264214046824e-06,
+      "loss": 0.8181,
+      "step": 850
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 7.525083612040134e-06,
+      "loss": 0.7836,
+      "step": 900
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 6.270903010033445e-06,
+      "loss": 0.653,
+      "step": 950
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 5.016722408026756e-06,
+      "loss": 0.6051,
+      "step": 1000
+    },
+    {
+      "epoch": 3.34,
+      "eval_accuracy": 0.6625,
+      "eval_f1_macro": 0.5549999999999999,
+      "eval_f1_micro": 0.6625,
+      "eval_f1_unweighted_diskutierend": 0.5333333333333333,
+      "eval_f1_unweighted_ja-daf\u00fcr": 0.56,
+      "eval_f1_unweighted_kein-bezug": 0.8266666666666667,
+      "eval_f1_unweighted_nein-dagegen": 0.3,
+      "eval_f1_weighted": 0.6507499999999999,
+      "eval_loss": 0.9401437044143677,
+      "eval_runtime": 61.357,
+      "eval_samples_per_second": 2.608,
+      "step": 1000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 3.762541806020067e-06,
+      "loss": 0.6435,
+      "step": 1050
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 2.508361204013378e-06,
+      "loss": 0.6506,
+      "step": 1100
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.254180602006689e-06,
+      "loss": 0.5699,
+      "step": 1150
+    },
+    {
+      "epoch": 4.0,
+      "step": 1196,
+      "total_flos": 1.180320018726912e+16,
+      "train_runtime": 10088.4778,
+      "train_samples_per_second": 0.119
+    }
+  ],
+  "max_steps": 1196,
+  "num_train_epochs": 4,
+  "total_flos": 1.180320018726912e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2231346afadb7f7d79206983c052e3ab24246d9a4124d0f683c9b71a1c1cc308
+size 2543