Upload folder using huggingface_hub

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "TUM/GottBERT_base_best",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-DF",
+    "2": "I-DF",
+    "3": "B-GF",
+    "4": "I-GF",
+    "5": "B-VF",
+    "6": "I-VF"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DF": 1,
+    "B-GF": 3,
+    "B-VF": 5,
+    "I-DF": 2,
+    "I-GF": 4,
+    "I-VF": 6,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52009
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16145fecd1a785c3ba0cd1adff01acdac5735ae64e3e0724c64ba1bfb52a23e
+size 501623188

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd409acf7f25b76c0738b6dbed2b4572afc4c6fabfbad855dc28f94c9715f05
+size 1003359418

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a0c5c299cf4cf4d2698b8536c2cc16b11a9f613f6883c3a39162f7c6bac6b5
+size 1064

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52008": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,172 @@
+{
+  "best_metric": 0.2843865156173706,
+  "best_model_checkpoint": "GottBERT_base_best-ner/checkpoint-1257",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 6285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39777247414478917,
+      "grad_norm": 4.0330352783203125,
+      "learning_rate": 1.9204455051710422e-05,
+      "loss": 0.5037,
+      "step": 500
+    },
+    {
+      "epoch": 0.7955449482895783,
+      "grad_norm": 2.907467842102051,
+      "learning_rate": 1.8408910103420846e-05,
+      "loss": 0.3731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8078049996882987,
+      "eval_loss": 0.2843865156173706,
+      "eval_precision": 0.8352455846332345,
+      "eval_recall": 0.7821100917431193,
+      "eval_runtime": 12.9482,
+      "eval_samples_per_second": 168.441,
+      "eval_steps_per_second": 21.084,
+      "step": 1257
+    },
+    {
+      "epoch": 1.1933174224343674,
+      "grad_norm": 2.206559896469116,
+      "learning_rate": 1.7613365155131266e-05,
+      "loss": 0.3204,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5910898965791567,
+      "grad_norm": 1.5945550203323364,
+      "learning_rate": 1.681782020684169e-05,
+      "loss": 0.3073,
+      "step": 2000
+    },
+    {
+      "epoch": 1.988862370723946,
+      "grad_norm": 1.0446829795837402,
+      "learning_rate": 1.602227525855211e-05,
+      "loss": 0.307,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8156653426017875,
+      "eval_loss": 0.30156955122947693,
+      "eval_precision": 0.8394225855901891,
+      "eval_recall": 0.7932158377595364,
+      "eval_runtime": 8.1081,
+      "eval_samples_per_second": 268.989,
+      "eval_steps_per_second": 33.67,
+      "step": 2514
+    },
+    {
+      "epoch": 2.386634844868735,
+      "grad_norm": 2.5688698291778564,
+      "learning_rate": 1.5226730310262532e-05,
+      "loss": 0.2549,
+      "step": 3000
+    },
+    {
+      "epoch": 2.7844073190135243,
+      "grad_norm": 18.080320358276367,
+      "learning_rate": 1.4431185361972953e-05,
+      "loss": 0.2533,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.8040672187043351,
+      "eval_loss": 0.34032005071640015,
+      "eval_precision": 0.8111793611793612,
+      "eval_recall": 0.7970787059391599,
+      "eval_runtime": 8.0649,
+      "eval_samples_per_second": 270.43,
+      "eval_steps_per_second": 33.85,
+      "step": 3771
+    },
+    {
+      "epoch": 3.1821797931583133,
+      "grad_norm": 11.492422103881836,
+      "learning_rate": 1.3635640413683375e-05,
+      "loss": 0.2407,
+      "step": 4000
+    },
+    {
+      "epoch": 3.579952267303103,
+      "grad_norm": 1.2842203378677368,
+      "learning_rate": 1.2840095465393797e-05,
+      "loss": 0.2038,
+      "step": 4500
+    },
+    {
+      "epoch": 3.977724741447892,
+      "grad_norm": 2.7960543632507324,
+      "learning_rate": 1.2044550517104217e-05,
+      "loss": 0.2341,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.809805475943655,
+      "eval_loss": 0.3722330927848816,
+      "eval_precision": 0.818237831176833,
+      "eval_recall": 0.8015451472718493,
+      "eval_runtime": 8.117,
+      "eval_samples_per_second": 268.696,
+      "eval_steps_per_second": 33.633,
+      "step": 5028
+    },
+    {
+      "epoch": 4.375497215592681,
+      "grad_norm": 20.861055374145508,
+      "learning_rate": 1.1249005568814639e-05,
+      "loss": 0.189,
+      "step": 5500
+    },
+    {
+      "epoch": 4.77326968973747,
+      "grad_norm": 1.1496546268463135,
+      "learning_rate": 1.045346062052506e-05,
+      "loss": 0.2001,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.828952933357501,
+      "eval_loss": 0.3225707411766052,
+      "eval_precision": 0.8298052497883149,
+      "eval_recall": 0.82810236600676,
+      "eval_runtime": 8.0107,
+      "eval_samples_per_second": 272.262,
+      "eval_steps_per_second": 34.08,
+      "step": 6285
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12570,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1349791452452520.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf84cfc2b3835740721f3380be5dec7ffa9993f4e145a968e8bd8d193c3a9e3
+size 5304