initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,83 @@
+---
+language:
+- tr
+tags:
+- cefr
+- text-classification
+- turkish
+- language-level
+- bert
+license: mit
+base_model: dbmdz/bert-base-turkish-cased
+datasets:
+- custom
+metrics:
+- f1
+- accuracy
+---
+
+# Turkish CEFR Classifier 
+
+A Turkish text classifier for CEFR (Common European Framework of Reference) language proficiency levels, trained on spoken Turkish data.
+
+Fine-tuned from `dbmdz/bert-base-turkish-cased` on spoken Turkish YouTube transcripts.
+
+## Model Performance
+
+| Metric | Score |
+|--------|-------|
+| Macro F1 | 0.84 |
+| Accuracy | 0.86 |
+
+### Per-Class Performance
+
+| Level | Precision | Recall | F1 |
+|-------|-----------|--------|----|
+| A1 | 0.98 | 0.96 | 0.97 |
+| A2 | 0.89 | 0.82 | 0.85 |
+| B1 | 0.62 | 0.77 | 0.69 |
+| B2 | 0.76 | 0.71 | 0.73 |
+| C1 | 0.79 | 0.88 | 0.83 |
+| C2 | 1.00 | 0.95 | 0.97 |
+
+## Usage
+```python
+from transformers import pipeline
+
+classifier = pipeline(
+    "text-classification",
+    model="crklih/turkish-cefr-classifier"
+)
+
+result = classifier("Osmanlı Devleti'nin çöküşü çok boyutlu bir süreçtir.")
+# [{'label': 'B2', 'score': 0.95}]
+```
+
+## CEFR Levels
+
+| Level | Description |
+|-------|-------------|
+| A1 | Beginner — basic words and simple phrases |
+| A2 | Elementary — simple sentences on everyday topics |
+| B1 | Intermediate — familiar topics, some complex structures |
+| B2 | Upper-Intermediate — complex sentences, abstract topics |
+| C1 | Advanced — academic/technical language, complex structures |
+| C2 | Proficient — near-native, nuanced, rare vocabulary |
+
+## Training Data
+
+- Carefully curated Turkish spoken language phrases
+- Balanced distribution across all 6 CEFR levels
+- LLM-human agreement rate: **74.6%**
+
+## Intended Use
+
+- Turkish language learning applications
+- Content difficulty assessment
+- Educational content filtering by proficiency level
+
+## Limitations
+
+- Trained on **spoken** Turkish — may underperform on formal written text
+- B1/B2 boundary can be ambiguous (lowest per-class F1)
+- Short phrases with technical vocabulary may be underestimated

checkpoint-144/config.json

@@ -0,0 +1,45 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A1",
+    "1": "A2",
+    "2": "B1",
+    "3": "B2",
+    "4": "C1",
+    "5": "C2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "A1": 0,
+    "A2": 1,
+    "B1": 2,
+    "B2": 3,
+    "C1": 4,
+    "C2": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-144/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f22a313f40b96119325b68028c8fc5a53bd64cd745139706045c60d2de6ca0
+size 442511344

checkpoint-144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a022ce52b3becff96f2803c9ab3679a98ecadce4be819ec8fdadfec536079d
+size 885147019

checkpoint-144/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe3764909b088aa0f737580c536165c5687a496ff912394d764790623c9150d
+size 14645

checkpoint-144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e9d8975285d65f39790bb31bcfd7bcfdca3c21edd5bd2e5629085da0f74ea3
+size 1465

checkpoint-144/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 144,
+  "best_metric": 0.8097959456034935,
+  "best_model_checkpoint": "tr_cefr_model/checkpoint-144",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 7.169168949127197,
+      "learning_rate": 3.402777777777778e-05,
+      "loss": 1.475471954345703,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 8.856643676757812,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.736978759765625,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8310727496917386,
+      "eval_loss": 0.45614269375801086,
+      "eval_macro_f1": 0.8097959456034935,
+      "eval_runtime": 3.3586,
+      "eval_samples_per_second": 241.473,
+      "eval_steps_per_second": 7.741,
+      "step": 144
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 176951109035700.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402398fe542038252e67b0bddcac7c3edb3726cb7bb102b5a8f1fec3b57c2d78
+size 5201

checkpoint-288/config.json

@@ -0,0 +1,45 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A1",
+    "1": "A2",
+    "2": "B1",
+    "3": "B2",
+    "4": "C1",
+    "5": "C2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "A1": 0,
+    "A2": 1,
+    "B1": 2,
+    "B2": 3,
+    "C1": 4,
+    "C2": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-288/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0e4dd554b29d96580ad7a183fc1b258a194129de8227aa148cf941042510bb
+size 442511344

checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39be42cc285180a720570ca66c1ca8e58f2fb967ae6d4b86c227f3fb2c63de17
+size 885147019

checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73f5e08b0df6be48606aab3065653875e6b040711bfc92fb7d5bff874a36158
+size 14645

checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aff972fc6a5d1d5a9fd07ad763964cb290f42a3b6d1a8a93dafb359fb4edf4f
+size 1465

checkpoint-288/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_global_step": 288,
+  "best_metric": 0.8195809392350385,
+  "best_model_checkpoint": "tr_cefr_model/checkpoint-288",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 288,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 7.169168949127197,
+      "learning_rate": 3.402777777777778e-05,
+      "loss": 1.475471954345703,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 8.856643676757812,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.736978759765625,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8310727496917386,
+      "eval_loss": 0.45614269375801086,
+      "eval_macro_f1": 0.8097959456034935,
+      "eval_runtime": 3.3586,
+      "eval_samples_per_second": 241.473,
+      "eval_steps_per_second": 7.741,
+      "step": 144
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 8.417092323303223,
+      "learning_rate": 4.4058641975308644e-05,
+      "loss": 0.5094949340820313,
+      "step": 150
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 10.636765480041504,
+      "learning_rate": 4.020061728395062e-05,
+      "loss": 0.3846432113647461,
+      "step": 200
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 4.034689903259277,
+      "learning_rate": 3.6342592592592596e-05,
+      "loss": 0.35187114715576173,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.840937114673243,
+      "eval_loss": 0.4010525941848755,
+      "eval_macro_f1": 0.8195809392350385,
+      "eval_runtime": 4.0358,
+      "eval_samples_per_second": 200.95,
+      "eval_steps_per_second": 6.442,
+      "step": 288
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 353902218071400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402398fe542038252e67b0bddcac7c3edb3726cb7bb102b5a8f1fec3b57c2d78
+size 5201

checkpoint-432/config.json

@@ -0,0 +1,45 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A1",
+    "1": "A2",
+    "2": "B1",
+    "3": "B2",
+    "4": "C1",
+    "5": "C2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "A1": 0,
+    "A2": 1,
+    "B1": 2,
+    "B2": 3,
+    "C1": 4,
+    "C2": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-432/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25475cc2feb1bfbb8c0a713e6055d8adafd27bd6e78f310a9952a53302d69bdd
+size 442511344

checkpoint-432/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2236a795f6abd7cc224470aa14988f98e5d00f01335760634914881e84c32c16
+size 885147019

checkpoint-432/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efec8debf7e721110602fdf7b9bb732bab20326c0f8464ca3b6c662d94552aff
+size 14645

checkpoint-432/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2938ecef374ba7f5550da2b560afd72687412c26780c0ccff11a4d0c7ca915c
+size 1465

checkpoint-432/trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_global_step": 432,
+  "best_metric": 0.8409015472020808,
+  "best_model_checkpoint": "tr_cefr_model/checkpoint-432",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 432,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 7.169168949127197,
+      "learning_rate": 3.402777777777778e-05,
+      "loss": 1.475471954345703,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 8.856643676757812,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.736978759765625,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8310727496917386,
+      "eval_loss": 0.45614269375801086,
+      "eval_macro_f1": 0.8097959456034935,
+      "eval_runtime": 3.3586,
+      "eval_samples_per_second": 241.473,
+      "eval_steps_per_second": 7.741,
+      "step": 144
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 8.417092323303223,
+      "learning_rate": 4.4058641975308644e-05,
+      "loss": 0.5094949340820313,
+      "step": 150
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 10.636765480041504,
+      "learning_rate": 4.020061728395062e-05,
+      "loss": 0.3846432113647461,
+      "step": 200
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 4.034689903259277,
+      "learning_rate": 3.6342592592592596e-05,
+      "loss": 0.35187114715576173,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.840937114673243,
+      "eval_loss": 0.4010525941848755,
+      "eval_macro_f1": 0.8195809392350385,
+      "eval_runtime": 4.0358,
+      "eval_samples_per_second": 200.95,
+      "eval_steps_per_second": 6.442,
+      "step": 288
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 7.837789535522461,
+      "learning_rate": 3.248456790123457e-05,
+      "loss": 0.30520191192626955,
+      "step": 300
+    },
+    {
+      "epoch": 2.4305555555555554,
+      "grad_norm": 16.366289138793945,
+      "learning_rate": 2.8626543209876545e-05,
+      "loss": 0.19062673568725585,
+      "step": 350
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 10.572943687438965,
+      "learning_rate": 2.4768518518518518e-05,
+      "loss": 0.17465518951416015,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8569667077681874,
+      "eval_loss": 0.43521106243133545,
+      "eval_macro_f1": 0.8409015472020808,
+      "eval_runtime": 3.5999,
+      "eval_samples_per_second": 225.285,
+      "eval_steps_per_second": 7.222,
+      "step": 432
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 530853327107100.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-432/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402398fe542038252e67b0bddcac7c3edb3726cb7bb102b5a8f1fec3b57c2d78
+size 5201

checkpoint-576/config.json

@@ -0,0 +1,45 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A1",
+    "1": "A2",
+    "2": "B1",
+    "3": "B2",
+    "4": "C1",
+    "5": "C2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "A1": 0,
+    "A2": 1,
+    "B1": 2,
+    "B2": 3,
+    "C1": 4,
+    "C2": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-576/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f4bbda6c6dcb15c1654f6100d029c904eb7cde3eefd4f772721a647d386c87
+size 442511344

checkpoint-576/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c15b2e18eb9b408106772752d9ccc081d7f49152341eb6b29354522842cc68fb
+size 885147019

checkpoint-576/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098292b24aa22e3a4bac2d8fba1025dfa817f3d9c3a7d31a08959bec5c2c0b35
+size 14645

checkpoint-576/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f696cabb58d5abffc9d83bc649629f93344f2108ae20e443f6bde70642e1a5b
+size 1465

checkpoint-576/trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_global_step": 432,
+  "best_metric": 0.8409015472020808,
+  "best_model_checkpoint": "tr_cefr_model/checkpoint-432",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 576,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 7.169168949127197,
+      "learning_rate": 3.402777777777778e-05,
+      "loss": 1.475471954345703,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 8.856643676757812,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.736978759765625,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8310727496917386,
+      "eval_loss": 0.45614269375801086,
+      "eval_macro_f1": 0.8097959456034935,
+      "eval_runtime": 3.3586,
+      "eval_samples_per_second": 241.473,
+      "eval_steps_per_second": 7.741,
+      "step": 144
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 8.417092323303223,
+      "learning_rate": 4.4058641975308644e-05,
+      "loss": 0.5094949340820313,
+      "step": 150
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 10.636765480041504,
+      "learning_rate": 4.020061728395062e-05,
+      "loss": 0.3846432113647461,
+      "step": 200
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 4.034689903259277,
+      "learning_rate": 3.6342592592592596e-05,
+      "loss": 0.35187114715576173,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.840937114673243,
+      "eval_loss": 0.4010525941848755,
+      "eval_macro_f1": 0.8195809392350385,
+      "eval_runtime": 4.0358,
+      "eval_samples_per_second": 200.95,
+      "eval_steps_per_second": 6.442,
+      "step": 288
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 7.837789535522461,
+      "learning_rate": 3.248456790123457e-05,
+      "loss": 0.30520191192626955,
+      "step": 300
+    },
+    {
+      "epoch": 2.4305555555555554,
+      "grad_norm": 16.366289138793945,
+      "learning_rate": 2.8626543209876545e-05,
+      "loss": 0.19062673568725585,
+      "step": 350
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 10.572943687438965,
+      "learning_rate": 2.4768518518518518e-05,
+      "loss": 0.17465518951416015,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8569667077681874,
+      "eval_loss": 0.43521106243133545,
+      "eval_macro_f1": 0.8409015472020808,
+      "eval_runtime": 3.5999,
+      "eval_samples_per_second": 225.285,
+      "eval_steps_per_second": 7.222,
+      "step": 432
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 1.0359699726104736,
+      "learning_rate": 2.0910493827160497e-05,
+      "loss": 0.11967629432678223,
+      "step": 450
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 3.9629909992218018,
+      "learning_rate": 1.705246913580247e-05,
+      "loss": 0.07373532772064209,
+      "step": 500
+    },
+    {
+      "epoch": 3.8194444444444446,
+      "grad_norm": 11.68164348602295,
+      "learning_rate": 1.3194444444444446e-05,
+      "loss": 0.07481417655944825,
+      "step": 550
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8545006165228114,
+      "eval_loss": 0.5574570894241333,
+      "eval_macro_f1": 0.8349256329335901,
+      "eval_runtime": 3.6533,
+      "eval_samples_per_second": 221.99,
+      "eval_steps_per_second": 7.117,
+      "step": 576
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 707804436142800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-576/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402398fe542038252e67b0bddcac7c3edb3726cb7bb102b5a8f1fec3b57c2d78
+size 5201

checkpoint-720/config.json

@@ -0,0 +1,45 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A1",
+    "1": "A2",
+    "2": "B1",
+    "3": "B2",
+    "4": "C1",
+    "5": "C2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "A1": 0,
+    "A2": 1,
+    "B1": 2,
+    "B2": 3,
+    "C1": 4,
+    "C2": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-720/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d766c582b5fc8d9c93feb3d18fa0268c3a2f9adaf318df78e83e9740ee2db77
+size 442511344

checkpoint-720/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe871e7126c21b02aa1abc3bc12453d97732bc82bde721a86b734c5527f27d6
+size 885147019

checkpoint-720/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92e341226eaa2c94afb8739256cfe20e183491c446605a65d11b50812f60205
+size 14645

checkpoint-720/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d87c44cded5126a99537b8400f224ceb6893ecd2611f30cdd5304a3d95b50b
+size 1465

checkpoint-720/trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_global_step": 432,
+  "best_metric": 0.8409015472020808,
+  "best_model_checkpoint": "tr_cefr_model/checkpoint-432",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 7.169168949127197,
+      "learning_rate": 3.402777777777778e-05,
+      "loss": 1.475471954345703,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 8.856643676757812,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.736978759765625,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8310727496917386,
+      "eval_loss": 0.45614269375801086,
+      "eval_macro_f1": 0.8097959456034935,
+      "eval_runtime": 3.3586,
+      "eval_samples_per_second": 241.473,
+      "eval_steps_per_second": 7.741,
+      "step": 144
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 8.417092323303223,
+      "learning_rate": 4.4058641975308644e-05,
+      "loss": 0.5094949340820313,
+      "step": 150
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 10.636765480041504,
+      "learning_rate": 4.020061728395062e-05,
+      "loss": 0.3846432113647461,
+      "step": 200
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 4.034689903259277,
+      "learning_rate": 3.6342592592592596e-05,
+      "loss": 0.35187114715576173,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.840937114673243,
+      "eval_loss": 0.4010525941848755,
+      "eval_macro_f1": 0.8195809392350385,
+      "eval_runtime": 4.0358,
+      "eval_samples_per_second": 200.95,
+      "eval_steps_per_second": 6.442,
+      "step": 288
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 7.837789535522461,
+      "learning_rate": 3.248456790123457e-05,
+      "loss": 0.30520191192626955,
+      "step": 300
+    },
+    {
+      "epoch": 2.4305555555555554,
+      "grad_norm": 16.366289138793945,
+      "learning_rate": 2.8626543209876545e-05,
+      "loss": 0.19062673568725585,
+      "step": 350
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 10.572943687438965,
+      "learning_rate": 2.4768518518518518e-05,
+      "loss": 0.17465518951416015,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8569667077681874,
+      "eval_loss": 0.43521106243133545,
+      "eval_macro_f1": 0.8409015472020808,
+      "eval_runtime": 3.5999,
+      "eval_samples_per_second": 225.285,
+      "eval_steps_per_second": 7.222,
+      "step": 432
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 1.0359699726104736,
+      "learning_rate": 2.0910493827160497e-05,
+      "loss": 0.11967629432678223,
+      "step": 450
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 3.9629909992218018,
+      "learning_rate": 1.705246913580247e-05,
+      "loss": 0.07373532772064209,
+      "step": 500
+    },
+    {
+      "epoch": 3.8194444444444446,
+      "grad_norm": 11.68164348602295,
+      "learning_rate": 1.3194444444444446e-05,
+      "loss": 0.07481417655944825,
+      "step": 550
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8545006165228114,
+      "eval_loss": 0.5574570894241333,
+      "eval_macro_f1": 0.8349256329335901,
+      "eval_runtime": 3.6533,
+      "eval_samples_per_second": 221.99,
+      "eval_steps_per_second": 7.117,
+      "step": 576
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.23339875042438507,
+      "learning_rate": 9.33641975308642e-06,
+      "loss": 0.044644255638122556,
+      "step": 600
+    },
+    {
+      "epoch": 4.513888888888889,
+      "grad_norm": 0.32208141684532166,
+      "learning_rate": 5.4783950617283955e-06,
+      "loss": 0.024740686416625978,
+      "step": 650
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 7.574490547180176,
+      "learning_rate": 1.6203703703703703e-06,
+      "loss": 0.035383782386779784,
+      "step": 700
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8495684340320592,
+      "eval_loss": 0.6193735599517822,
+      "eval_macro_f1": 0.8288707814230315,
+      "eval_runtime": 3.6574,
+      "eval_samples_per_second": 221.745,
+      "eval_steps_per_second": 7.109,
+      "step": 720
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 884755545178500.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-720/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402398fe542038252e67b0bddcac7c3edb3726cb7bb102b5a8f1fec3b57c2d78
+size 5201

config.json

@@ -0,0 +1,45 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A1",
+    "1": "A2",
+    "2": "B1",
+    "3": "B2",
+    "4": "C1",
+    "5": "C2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "A1": 0,
+    "A2": 1,
+    "B1": 2,
+    "B2": 3,
+    "C1": 4,
+    "C2": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807a2fe8200d888a08f782f553b9079997f3a742e3a8a007f67c9d1c95e54f8c
+size 442511344

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402398fe542038252e67b0bddcac7c3edb3726cb7bb102b5a8f1fec3b57c2d78
+size 5201