New model

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9868826550770446,
+    "eval_f1": 0.963314567465136,
+    "eval_loss": 0.06651861220598221,
+    "eval_mem_cpu_alloc_delta": 33882112,
+    "eval_mem_cpu_peaked_delta": 13832192,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 57622016,
+    "eval_precision": 0.958272327964861,
+    "eval_recall": 0.9684101501812532,
+    "eval_runtime": 148.5083,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 67.336,
+    "init_mem_cpu_alloc_delta": 2071715840,
+    "init_mem_cpu_peaked_delta": 324276224,
+    "init_mem_gpu_alloc_delta": 440923648,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 819142656,
+    "train_mem_cpu_peaked_delta": 294813696,
+    "train_mem_gpu_alloc_delta": 1307043840,
+    "train_mem_gpu_peaked_delta": 5351086080,
+    "train_runtime": 6428.2486,
+    "train_samples": 122836,
+    "train_samples_per_second": 1.493
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "dbmdz/convbert-base-turkish-cased",
+  "architectures": [
+    "ConvBertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "conv_kernel_size": 9,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "head_ratio": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "convbert",
+  "num_attention_heads": 12,
+  "num_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "transformers_version": "4.6.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9868826550770446,
+    "eval_f1": 0.963314567465136,
+    "eval_loss": 0.06651861220598221,
+    "eval_mem_cpu_alloc_delta": 33882112,
+    "eval_mem_cpu_peaked_delta": 13832192,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 57622016,
+    "eval_precision": 0.958272327964861,
+    "eval_recall": 0.9684101501812532,
+    "eval_runtime": 148.5083,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 67.336
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1addbea45d38147cf9440f87a206f4e4f5b6f10ca7718effd6675059757e1442
+size 427411947

special_tokens_map.json

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

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, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "dbmdz/convbert-base-turkish-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_file": null}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "init_mem_cpu_alloc_delta": 2071715840,
+    "init_mem_cpu_peaked_delta": 324276224,
+    "init_mem_gpu_alloc_delta": 440923648,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 819142656,
+    "train_mem_cpu_peaked_delta": 294813696,
+    "train_mem_gpu_alloc_delta": 1307043840,
+    "train_mem_gpu_peaked_delta": 5351086080,
+    "train_runtime": 6428.2486,
+    "train_samples": 122836,
+    "train_samples_per_second": 1.493
+}

trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 9600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.739583333333333e-05,
+      "loss": 0.2081,
+      "step": 500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.4791666666666673e-05,
+      "loss": 0.1042,
+      "step": 1000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.21875e-05,
+      "loss": 0.0927,
+      "step": 1500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 0.0782,
+      "step": 2000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.697916666666667e-05,
+      "loss": 0.0551,
+      "step": 2500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.0522,
+      "step": 3000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.177083333333333e-05,
+      "loss": 0.049,
+      "step": 3500
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.0425,
+      "step": 4000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.6562500000000002e-05,
+      "loss": 0.0283,
+      "step": 4500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.3958333333333334e-05,
+      "loss": 0.0271,
+      "step": 5000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.1354166666666666e-05,
+      "loss": 0.0281,
+      "step": 5500
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.0203,
+      "step": 6000
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 1.6145833333333334e-05,
+      "loss": 0.0155,
+      "step": 6500
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.3541666666666666e-05,
+      "loss": 0.0161,
+      "step": 7000
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.09375e-05,
+      "loss": 0.0123,
+      "step": 7500
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0098,
+      "step": 8000
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 5.729166666666667e-06,
+      "loss": 0.0088,
+      "step": 8500
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 3.125e-06,
+      "loss": 0.0079,
+      "step": 9000
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 5.208333333333334e-07,
+      "loss": 0.0072,
+      "step": 9500
+    },
+    {
+      "epoch": 5.0,
+      "step": 9600,
+      "total_flos": 1.6084841463394584e+16,
+      "train_runtime": 6428.2486,
+      "train_samples_per_second": 1.493
+    }
+  ],
+  "max_steps": 9600,
+  "num_train_epochs": 5,
+  "total_flos": 1.6084841463394584e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b094d4e9d1c4e82dc1845fa0653eb07140c9ee01a958e046366751028beed77f
+size 2351