Upload 15 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# debug_squad
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.0

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 2,
+  "[MASK]": 4,
+  "[PAD]": 0,
+  "[SEP]": 3,
+  "[UNK]": 1
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 15.0,
+    "eval_exact_match": 2.270577105014191,
+    "eval_f1": 17.574782255214473,
+    "eval_runtime": 970.1857,
+    "eval_samples": 11143,
+    "eval_samples_per_second": 11.485,
+    "eval_steps_per_second": 1.436,
+    "train_loss": 0.29966140018222515,
+    "train_runtime": 616667.77,
+    "train_samples": 84377,
+    "train_samples_per_second": 2.052,
+    "train_steps_per_second": 0.064
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "savasy/bert-base-turkish-squad",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.34.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf25f3ca7237fd490a4858f2e7af8a73344c093c65087bef06acc5cf6608f316
+size 48562848

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "eval_exact_match": 2.270577105014191,
+    "eval_f1": 17.574782255214473,
+    "eval_runtime": 970.1857,
+    "eval_samples": 11143,
+    "eval_samples_per_second": 11.485,
+    "eval_steps_per_second": 1.436
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:070ab61aa5ffbd7c3b97e4dd885e8abc998c7bae929827fecf5b072d0794733b
+size 440181350

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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "train_loss": 0.29966140018222515,
+    "train_runtime": 616667.77,
+    "train_samples": 84377,
+    "train_samples_per_second": 2.052,
+    "train_steps_per_second": 0.064
+}

trainer_state.json

@@ -0,0 +1,502 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 39555,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.9620781190747064e-05,
+      "loss": 1.691,
+      "step": 500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.9241562381494123e-05,
+      "loss": 1.3596,
+      "step": 1000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.8862343572241182e-05,
+      "loss": 1.2355,
+      "step": 1500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8483124762988245e-05,
+      "loss": 1.1379,
+      "step": 2000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.8103905953735308e-05,
+      "loss": 1.0569,
+      "step": 2500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.7724687144482367e-05,
+      "loss": 0.886,
+      "step": 3000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.7345468335229427e-05,
+      "loss": 0.8132,
+      "step": 3500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.696624952597649e-05,
+      "loss": 0.8062,
+      "step": 4000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.6587030716723552e-05,
+      "loss": 0.7833,
+      "step": 4500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.620781190747061e-05,
+      "loss": 0.779,
+      "step": 5000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.582859309821767e-05,
+      "loss": 0.6686,
+      "step": 5500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.5449374288964734e-05,
+      "loss": 0.5732,
+      "step": 6000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.5070155479711797e-05,
+      "loss": 0.5754,
+      "step": 6500
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.4690936670458856e-05,
+      "loss": 0.5762,
+      "step": 7000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.4311717861205915e-05,
+      "loss": 0.5617,
+      "step": 7500
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 2.3932499051952978e-05,
+      "loss": 0.5578,
+      "step": 8000
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 2.3553280242700038e-05,
+      "loss": 0.4115,
+      "step": 8500
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 2.31740614334471e-05,
+      "loss": 0.4282,
+      "step": 9000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 2.279484262419416e-05,
+      "loss": 0.4324,
+      "step": 9500
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 2.2415623814941223e-05,
+      "loss": 0.4301,
+      "step": 10000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 2.2036405005688282e-05,
+      "loss": 0.4238,
+      "step": 10500
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 2.1657186196435345e-05,
+      "loss": 0.3113,
+      "step": 11000
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 2.1277967387182404e-05,
+      "loss": 0.3149,
+      "step": 11500
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 2.0898748577929467e-05,
+      "loss": 0.3164,
+      "step": 12000
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 2.0519529768676526e-05,
+      "loss": 0.3165,
+      "step": 12500
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 2.014031095942359e-05,
+      "loss": 0.3291,
+      "step": 13000
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 1.976109215017065e-05,
+      "loss": 0.2555,
+      "step": 13500
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 1.9381873340917708e-05,
+      "loss": 0.2403,
+      "step": 14000
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 1.900265453166477e-05,
+      "loss": 0.239,
+      "step": 14500
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 1.8623435722411833e-05,
+      "loss": 0.2374,
+      "step": 15000
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 1.8244216913158893e-05,
+      "loss": 0.2505,
+      "step": 15500
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 1.7864998103905952e-05,
+      "loss": 0.2215,
+      "step": 16000
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 1.7485779294653015e-05,
+      "loss": 0.1792,
+      "step": 16500
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 1.7106560485400078e-05,
+      "loss": 0.1811,
+      "step": 17000
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 1.6727341676147137e-05,
+      "loss": 0.1923,
+      "step": 17500
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 1.6348122866894197e-05,
+      "loss": 0.2011,
+      "step": 18000
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 1.596890405764126e-05,
+      "loss": 0.1877,
+      "step": 18500
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 1.5589685248388322e-05,
+      "loss": 0.144,
+      "step": 19000
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 1.5210466439135383e-05,
+      "loss": 0.1431,
+      "step": 19500
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 1.4831247629882443e-05,
+      "loss": 0.153,
+      "step": 20000
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 1.4452028820629504e-05,
+      "loss": 0.1555,
+      "step": 20500
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 1.4072810011376565e-05,
+      "loss": 0.1532,
+      "step": 21000
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 1.3693591202123626e-05,
+      "loss": 0.1235,
+      "step": 21500
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 1.3314372392870687e-05,
+      "loss": 0.1191,
+      "step": 22000
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 1.2935153583617748e-05,
+      "loss": 0.1241,
+      "step": 22500
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 1.2555934774364809e-05,
+      "loss": 0.118,
+      "step": 23000
+    },
+    {
+      "epoch": 8.91,
+      "learning_rate": 1.217671596511187e-05,
+      "loss": 0.1268,
+      "step": 23500
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 1.1797497155858931e-05,
+      "loss": 0.1087,
+      "step": 24000
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 1.1418278346605992e-05,
+      "loss": 0.0939,
+      "step": 24500
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 1.1039059537353053e-05,
+      "loss": 0.1023,
+      "step": 25000
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 1.0659840728100115e-05,
+      "loss": 0.103,
+      "step": 25500
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 1.0280621918847176e-05,
+      "loss": 0.106,
+      "step": 26000
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 9.901403109594235e-06,
+      "loss": 0.1004,
+      "step": 26500
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 9.522184300341298e-06,
+      "loss": 0.0823,
+      "step": 27000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 9.142965491088357e-06,
+      "loss": 0.0807,
+      "step": 27500
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 8.76374668183542e-06,
+      "loss": 0.0879,
+      "step": 28000
+    },
+    {
+      "epoch": 10.81,
+      "learning_rate": 8.38452787258248e-06,
+      "loss": 0.085,
+      "step": 28500
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 8.005309063329542e-06,
+      "loss": 0.0833,
+      "step": 29000
+    },
+    {
+      "epoch": 11.19,
+      "learning_rate": 7.6260902540766016e-06,
+      "loss": 0.0626,
+      "step": 29500
+    },
+    {
+      "epoch": 11.38,
+      "learning_rate": 7.2468714448236635e-06,
+      "loss": 0.0733,
+      "step": 30000
+    },
+    {
+      "epoch": 11.57,
+      "learning_rate": 6.867652635570725e-06,
+      "loss": 0.0723,
+      "step": 30500
+    },
+    {
+      "epoch": 11.76,
+      "learning_rate": 6.488433826317786e-06,
+      "loss": 0.0701,
+      "step": 31000
+    },
+    {
+      "epoch": 11.95,
+      "learning_rate": 6.109215017064847e-06,
+      "loss": 0.0761,
+      "step": 31500
+    },
+    {
+      "epoch": 12.14,
+      "learning_rate": 5.729996207811908e-06,
+      "loss": 0.0583,
+      "step": 32000
+    },
+    {
+      "epoch": 12.32,
+      "learning_rate": 5.350777398558969e-06,
+      "loss": 0.0558,
+      "step": 32500
+    },
+    {
+      "epoch": 12.51,
+      "learning_rate": 4.97155858930603e-06,
+      "loss": 0.0585,
+      "step": 33000
+    },
+    {
+      "epoch": 12.7,
+      "learning_rate": 4.592339780053091e-06,
+      "loss": 0.0607,
+      "step": 33500
+    },
+    {
+      "epoch": 12.89,
+      "learning_rate": 4.213120970800152e-06,
+      "loss": 0.0605,
+      "step": 34000
+    },
+    {
+      "epoch": 13.08,
+      "learning_rate": 3.833902161547213e-06,
+      "loss": 0.0511,
+      "step": 34500
+    },
+    {
+      "epoch": 13.27,
+      "learning_rate": 3.454683352294274e-06,
+      "loss": 0.0461,
+      "step": 35000
+    },
+    {
+      "epoch": 13.46,
+      "learning_rate": 3.075464543041335e-06,
+      "loss": 0.0475,
+      "step": 35500
+    },
+    {
+      "epoch": 13.65,
+      "learning_rate": 2.696245733788396e-06,
+      "loss": 0.052,
+      "step": 36000
+    },
+    {
+      "epoch": 13.84,
+      "learning_rate": 2.3170269245354572e-06,
+      "loss": 0.0508,
+      "step": 36500
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 1.9378081152825183e-06,
+      "loss": 0.0457,
+      "step": 37000
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 1.5585893060295792e-06,
+      "loss": 0.0427,
+      "step": 37500
+    },
+    {
+      "epoch": 14.41,
+      "learning_rate": 1.1793704967766403e-06,
+      "loss": 0.0397,
+      "step": 38000
+    },
+    {
+      "epoch": 14.6,
+      "learning_rate": 8.001516875237012e-07,
+      "loss": 0.038,
+      "step": 38500
+    },
+    {
+      "epoch": 14.79,
+      "learning_rate": 4.2093287827076224e-07,
+      "loss": 0.0434,
+      "step": 39000
+    },
+    {
+      "epoch": 14.98,
+      "learning_rate": 4.1714069017823285e-08,
+      "loss": 0.0413,
+      "step": 39500
+    },
+    {
+      "epoch": 15.0,
+      "step": 39555,
+      "total_flos": 3.307115466467021e+17,
+      "train_loss": 0.29966140018222515,
+      "train_runtime": 616667.77,
+      "train_samples_per_second": 2.052,
+      "train_steps_per_second": 0.064
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 39555,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 3.307115466467021e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c971e0d23e61c269507e026744a87946e989b0510f823ba590f5aaca30d6ad3d
+size 4472