End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.979997105690534,
+    "eval_f1": 0.9379482534942355,
+    "eval_loss": 0.1315528005361557,
+    "eval_precision": 0.9340386115444618,
+    "eval_recall": 0.9418907624993855,
+    "eval_runtime": 22.5786,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 442.898,
+    "eval_steps_per_second": 36.938,
+    "test_accuracy": 0.9792432006306662,
+    "test_f1": 0.9409973905479849,
+    "test_loss": 0.13579198718070984,
+    "test_precision": 0.9374187647426948,
+    "test_recall": 0.9446034440941062,
+    "test_runtime": 24.1205,
+    "test_samples_per_second": 414.585,
+    "test_steps_per_second": 34.576,
+    "total_flos": 1404947975153976.0,
+    "train_loss": 0.054277180967462514,
+    "train_runtime": 938.8043,
+    "train_samples": 20000,
+    "train_samples_per_second": 106.518,
+    "train_steps_per_second": 8.878
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "KB/bert-base-swedish-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": "5",
+    "B-ORG": "3",
+    "B-PER": "1",
+    "I-LOC": "6",
+    "I-ORG": "4",
+    "I-PER": "2",
+    "O": "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50325
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.979997105690534,
+    "eval_f1": 0.9379482534942355,
+    "eval_loss": 0.1315528005361557,
+    "eval_precision": 0.9340386115444618,
+    "eval_recall": 0.9418907624993855,
+    "eval_runtime": 22.5786,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 442.898,
+    "eval_steps_per_second": 36.938
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c35d035c2c2fa167092628fad3a9753ecf2324fb6c58d73e25644f9acf6a6f
+size 496493361

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

test_results.json

@@ -0,0 +1,10 @@
+{
+    "test_accuracy": 0.9792432006306662,
+    "test_f1": 0.9409973905479849,
+    "test_loss": 0.13579198718070984,
+    "test_precision": 0.9374187647426948,
+    "test_recall": 0.9446034440941062,
+    "test_runtime": 24.1205,
+    "test_samples_per_second": 414.585,
+    "test_steps_per_second": 34.576
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "name_or_path": "KB/bert-base-swedish-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--KB--bert-base-swedish-cased/snapshots/81c7baa04742a30cb6732c181e678721868cb42e/special_tokens_map.json",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1404947975153976.0,
+    "train_loss": 0.054277180967462514,
+    "train_runtime": 938.8043,
+    "train_samples": 20000,
+    "train_samples_per_second": 106.518,
+    "train_steps_per_second": 8.878
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 8335,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.7000599880024e-05,
+      "loss": 0.2124,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.4001199760047995e-05,
+      "loss": 0.1387,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.100179964007199e-05,
+      "loss": 0.1202,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.800239952009598e-05,
+      "loss": 0.0785,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.500299940011998e-05,
+      "loss": 0.0632,
+      "step": 2500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.2003599280143974e-05,
+      "loss": 0.0647,
+      "step": 3000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.9004199160167967e-05,
+      "loss": 0.0554,
+      "step": 3500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.6004799040191963e-05,
+      "loss": 0.0355,
+      "step": 4000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.300539892021596e-05,
+      "loss": 0.0335,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.0005998800239953e-05,
+      "loss": 0.0318,
+      "step": 5000
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 1.700659868026395e-05,
+      "loss": 0.0136,
+      "step": 5500
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.4007198560287942e-05,
+      "loss": 0.0193,
+      "step": 6000
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 1.1007798440311939e-05,
+      "loss": 0.0145,
+      "step": 6500
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 8.008398320335933e-06,
+      "loss": 0.0086,
+      "step": 7000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 5.008998200359928e-06,
+      "loss": 0.0059,
+      "step": 7500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 2.009598080383923e-06,
+      "loss": 0.0052,
+      "step": 8000
+    },
+    {
+      "epoch": 5.0,
+      "step": 8335,
+      "total_flos": 1404947975153976.0,
+      "train_loss": 0.054277180967462514,
+      "train_runtime": 938.8043,
+      "train_samples_per_second": 106.518,
+      "train_steps_per_second": 8.878
+    }
+  ],
+  "max_steps": 8335,
+  "num_train_epochs": 5,
+  "total_flos": 1404947975153976.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c863290560ba4ff42f221a93c20f50077f12bfe86bc3437aa50ece107f4c82
+size 3311