Upload 7 files

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOT_TOXIC",
+    "1": "TOXIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NOT_TOXIC": 0,
+    "TOXIC": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78faf60233d80e8760d142744d9d7f2b732ff6ddead56035cc1238820cdf4b53
+size 442499064

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a4a9a87e94ab5c0ffa302b3cae954c4d965f7258b58e0da4ce2a68a1210d10
+size 885119627

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53071cbc1db9cb49e529e4198670b75dcca21c3a8a13cc43fc703a7a3f9c52ad
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413c127045f3e18ab796d42b20f9fc87f15da1bd5f1ee34ed1bf26ab91cba015
+size 1465

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_global_step": 2550,
+  "best_metric": 0.08080464601516724,
+  "best_model_checkpoint": "./turkish-toxic-bert-full\\checkpoint-2550",
+  "epoch": 0.749173705471906,
+  "eval_steps": 850,
+  "global_step": 2550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.049944913698127064,
+      "grad_norm": 10.951066970825195,
+      "learning_rate": 9.941176470588236e-06,
+      "loss": 0.6808,
+      "step": 170
+    },
+    {
+      "epoch": 0.09988982739625413,
+      "grad_norm": 2.395719051361084,
+      "learning_rate": 1.9941176470588238e-05,
+      "loss": 0.2552,
+      "step": 340
+    },
+    {
+      "epoch": 0.1498347410943812,
+      "grad_norm": 31.97089385986328,
+      "learning_rate": 1.9657617504051864e-05,
+      "loss": 0.1784,
+      "step": 510
+    },
+    {
+      "epoch": 0.19977965479250825,
+      "grad_norm": 3.0786185264587402,
+      "learning_rate": 1.931320907617504e-05,
+      "loss": 0.1626,
+      "step": 680
+    },
+    {
+      "epoch": 0.24972456849063532,
+      "grad_norm": 36.20637893676758,
+      "learning_rate": 1.896880064829822e-05,
+      "loss": 0.163,
+      "step": 850
+    },
+    {
+      "epoch": 0.24972456849063532,
+      "eval_accuracy": 0.9607969151670951,
+      "eval_loss": 0.12955638766288757,
+      "eval_runtime": 632.0606,
+      "eval_samples_per_second": 12.309,
+      "eval_steps_per_second": 3.077,
+      "step": 850
+    },
+    {
+      "epoch": 0.2996694821887624,
+      "grad_norm": 13.24213695526123,
+      "learning_rate": 1.8624392220421394e-05,
+      "loss": 0.1494,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3496143958868895,
+      "grad_norm": 7.672886371612549,
+      "learning_rate": 1.8279983792544573e-05,
+      "loss": 0.1403,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3995593095850165,
+      "grad_norm": 1.0008550882339478,
+      "learning_rate": 1.7935575364667748e-05,
+      "loss": 0.133,
+      "step": 1360
+    },
+    {
+      "epoch": 0.4495042232831436,
+      "grad_norm": 15.496179580688477,
+      "learning_rate": 1.7591166936790924e-05,
+      "loss": 0.1059,
+      "step": 1530
+    },
+    {
+      "epoch": 0.49944913698127064,
+      "grad_norm": 13.099618911743164,
+      "learning_rate": 1.7246758508914102e-05,
+      "loss": 0.1281,
+      "step": 1700
+    },
+    {
+      "epoch": 0.49944913698127064,
+      "eval_accuracy": 0.9701799485861182,
+      "eval_loss": 0.0947001576423645,
+      "eval_runtime": 632.2141,
+      "eval_samples_per_second": 12.306,
+      "eval_steps_per_second": 3.076,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5493940506793977,
+      "grad_norm": 9.940011024475098,
+      "learning_rate": 1.6902350081037278e-05,
+      "loss": 0.1258,
+      "step": 1870
+    },
+    {
+      "epoch": 0.5993389643775248,
+      "grad_norm": 20.614500045776367,
+      "learning_rate": 1.6557941653160453e-05,
+      "loss": 0.0975,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6492838780756518,
+      "grad_norm": 12.049532890319824,
+      "learning_rate": 1.6213533225283632e-05,
+      "loss": 0.1297,
+      "step": 2210
+    },
+    {
+      "epoch": 0.699228791773779,
+      "grad_norm": 2.572075843811035,
+      "learning_rate": 1.5869124797406807e-05,
+      "loss": 0.1329,
+      "step": 2380
+    },
+    {
+      "epoch": 0.749173705471906,
+      "grad_norm": 7.409031391143799,
+      "learning_rate": 1.5524716369529983e-05,
+      "loss": 0.1162,
+      "step": 2550
+    },
+    {
+      "epoch": 0.749173705471906,
+      "eval_accuracy": 0.9699228791773779,
+      "eval_loss": 0.08080464601516724,
+      "eval_runtime": 632.5405,
+      "eval_samples_per_second": 12.3,
+      "eval_steps_per_second": 3.075,
+      "step": 2550
+    }
+  ],
+  "logging_steps": 170,
+  "max_steps": 10212,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2550,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5367465529344000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad9e7789c84d372eb69fd51aefe63212143529e5d7d184fbdcb86b517f95c2b
+size 5713