Upload 11 files

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "KBLab/bert-base-swedish-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50325
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ec311bc14948b01f0d85e75faa3200062f42812a292dafd7b059b720ddf5ee
+size 997701381

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46fab31bf8cb446cef45134dbb6bb8f0ebe9992033e978d2b6689e9aba220c21
+size 498835249

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000bfbff611c80c96b4bddf00ede8c98935f58107b05198c8d354e641f870f04
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfed719281a28fa473b46f285cac7b957b07614c8715dc9bc16309c2bd1e3cb6
+size 627

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 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": 0.8988173831404782,
+  "best_model_checkpoint": "/home/felix/kubhist2-testing/SuperLim-2-Testing/results/trainer_output/run-9c892_00006/checkpoint-720",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 720,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_krippendorff_interval": 0.8530320271374063,
+      "eval_loss": 0.6099120378494263,
+      "eval_rmse": 0.7809716463088989,
+      "eval_runtime": 172.8024,
+      "eval_samples_per_second": 8.675,
+      "eval_steps_per_second": 0.069,
+      "learning_rate": 2.872340425531915e-05,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_krippendorff_interval": 0.8847593598404591,
+      "eval_loss": 0.5006210803985596,
+      "eval_rmse": 0.707514762878418,
+      "eval_runtime": 204.4981,
+      "eval_samples_per_second": 7.33,
+      "eval_steps_per_second": 0.059,
+      "learning_rate": 2.5531914893617022e-05,
+      "step": 180
+    },
+    {
+      "epoch": 3.0,
+      "eval_krippendorff_interval": 0.8890608821312243,
+      "eval_loss": 0.47553256154060364,
+      "eval_rmse": 0.6895508170127869,
+      "eval_runtime": 237.8039,
+      "eval_samples_per_second": 6.304,
+      "eval_steps_per_second": 0.05,
+      "learning_rate": 2.2340425531914894e-05,
+      "step": 270
+    },
+    {
+      "epoch": 4.0,
+      "eval_krippendorff_interval": 0.8923376746095839,
+      "eval_loss": 0.4671941101551056,
+      "eval_rmse": 0.6834725737571716,
+      "eval_runtime": 204.1101,
+      "eval_samples_per_second": 7.344,
+      "eval_steps_per_second": 0.059,
+      "learning_rate": 1.914893617021277e-05,
+      "step": 360
+    },
+    {
+      "epoch": 5.0,
+      "eval_krippendorff_interval": 0.8954049836526707,
+      "eval_loss": 0.4449359178543091,
+      "eval_rmse": 0.6670365333557129,
+      "eval_runtime": 196.013,
+      "eval_samples_per_second": 7.647,
+      "eval_steps_per_second": 0.061,
+      "learning_rate": 1.5957446808510637e-05,
+      "step": 450
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 1.4184397163120568e-05,
+      "loss": 0.5805,
+      "step": 500
+    },
+    {
+      "epoch": 6.0,
+      "eval_krippendorff_interval": 0.8982659725855372,
+      "eval_loss": 0.43518519401550293,
+      "eval_rmse": 0.6596892476081848,
+      "eval_runtime": 193.2167,
+      "eval_samples_per_second": 7.758,
+      "eval_steps_per_second": 0.062,
+      "learning_rate": 1.2765957446808511e-05,
+      "step": 540
+    },
+    {
+      "epoch": 7.0,
+      "eval_krippendorff_interval": 0.8951961364533456,
+      "eval_loss": 0.4422130882740021,
+      "eval_rmse": 0.6649948954582214,
+      "eval_runtime": 211.7822,
+      "eval_samples_per_second": 7.078,
+      "eval_steps_per_second": 0.057,
+      "learning_rate": 9.574468085106385e-06,
+      "step": 630
+    },
+    {
+      "epoch": 8.0,
+      "eval_krippendorff_interval": 0.8988173831404782,
+      "eval_loss": 0.4380922019481659,
+      "eval_rmse": 0.6618611216545105,
+      "eval_runtime": 172.2164,
+      "eval_samples_per_second": 8.704,
+      "eval_steps_per_second": 0.07,
+      "learning_rate": 6.3829787234042555e-06,
+      "step": 720
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 900,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2090069679955200.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3e-05,
+    "per_device_train_batch_size": 32
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe16de34c5deed1c52e0ea0a8ef6eaef1254f295c948f5234aa095fbf52a9cb7
+size 4219