First release of the violence target model

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "RecordedFuture/Swedish-Sentiment-Violence-Targets",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "transformers_version": "4.5.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50325
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a15b3b9fa3871b6ab119f930c7c7f9399c869c52d4cac95c5d248e034c19038
+size 496497166

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3c97abf653f86973e5919c633a5a166c1682f1ce3dbe819f2f7270089d9bbb
+size 496679008

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "special_tokens_map_file": "/home/fmoller/.cache/huggingface/transformers/37f2eab7cd9b3716ce0160ea9562138ae9247fb3ea61a2fd0190b16d0970444e.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "KB/bert-base-swedish-cased", "do_basic_tokenize": true, "never_split": null}

trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "global_step": 2889,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8465466615600664,
+      "eval_f1": 0.1998114985862394,
+      "eval_loss": 0.3642980754375458,
+      "eval_precision": 0.21178821178821178,
+      "eval_recall": 0.18911685994647637,
+      "eval_runtime": 1.6416,
+      "eval_samples_per_second": 552.505,
+      "step": 321
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5e-05,
+      "loss": 0.45,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.84684454657645,
+      "eval_f1": 0.3082901554404145,
+      "eval_loss": 0.3635120987892151,
+      "eval_precision": 0.298744769874477,
+      "eval_recall": 0.3184656556645852,
+      "eval_runtime": 1.6545,
+      "eval_samples_per_second": 548.199,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8437805864079323,
+      "eval_f1": 0.36829066886870354,
+      "eval_loss": 0.4092691242694855,
+      "eval_precision": 0.34281322059953884,
+      "eval_recall": 0.39785905441570024,
+      "eval_runtime": 1.6673,
+      "eval_samples_per_second": 543.984,
+      "step": 963
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 3.9535370447886146e-05,
+      "loss": 0.2483,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8455678965062343,
+      "eval_f1": 0.38870703764320785,
+      "eval_loss": 0.5110172033309937,
+      "eval_precision": 0.35903250188964475,
+      "eval_recall": 0.423728813559322,
+      "eval_runtime": 1.6703,
+      "eval_samples_per_second": 543.031,
+      "step": 1284
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 2.9070740895772292e-05,
+      "loss": 0.1092,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8486744116770927,
+      "eval_f1": 0.38036267138434326,
+      "eval_loss": 0.6379175186157227,
+      "eval_precision": 0.37719298245614036,
+      "eval_recall": 0.3835860838537021,
+      "eval_runtime": 1.6777,
+      "eval_samples_per_second": 540.623,
+      "step": 1605
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.844972126473467,
+      "eval_f1": 0.37866887143447703,
+      "eval_loss": 0.7029163837432861,
+      "eval_precision": 0.35285053929121724,
+      "eval_recall": 0.4085637823371989,
+      "eval_runtime": 1.6834,
+      "eval_samples_per_second": 538.796,
+      "step": 1926
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 1.8606111343658436e-05,
+      "loss": 0.0527,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8428869313587812,
+      "eval_f1": 0.3695038321903994,
+      "eval_loss": 0.7574378252029419,
+      "eval_precision": 0.33726067746686306,
+      "eval_recall": 0.4085637823371989,
+      "eval_runtime": 1.7233,
+      "eval_samples_per_second": 526.308,
+      "step": 2247
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 8.141481791544579e-06,
+      "loss": 0.0231,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8464189965530448,
+      "eval_f1": 0.379746835443038,
+      "eval_loss": 0.876063346862793,
+      "eval_precision": 0.3501506024096386,
+      "eval_recall": 0.41480820695807313,
+      "eval_runtime": 1.6869,
+      "eval_samples_per_second": 537.678,
+      "step": 2568
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.845057236478148,
+      "eval_f1": 0.377831715210356,
+      "eval_loss": 0.9406481981277466,
+      "eval_precision": 0.3456698741672835,
+      "eval_recall": 0.41659232827832293,
+      "eval_runtime": 1.6868,
+      "eval_samples_per_second": 537.715,
+      "step": 2889
+    },
+    {
+      "epoch": 9.0,
+      "step": 2889,
+      "total_flos": 2225293713920448.0,
+      "train_runtime": 271.3259,
+      "train_samples_per_second": 10.648
+    }
+  ],
+  "max_steps": 2889,
+  "num_train_epochs": 9,
+  "total_flos": 2225293713920448.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01a74e9be4250b99ffdf2193834fec524552872c01901915c26906124cc3282
+size 2351