Upload folder using huggingface_hub

README.md

@@ -1,176 +1,176 @@
----
-license: mit
-tags:
-- text-classification
-- cheese
-- texture
-- distilbert
-- transformers
-- fine-tuned
-datasets:
-- aslan-ng/cheese-text
-metrics:
-- accuracy
-model-index:
-- name: Cheese Texture Classifier (DistilBERT)
-  results:
-  - task:
-      type: text-classification
-      name: Cheese Texture Classification
-    dataset:
-      type: aslan-ng/cheese-text
-      name: Cheese Text Dataset
-    metrics:
-    - type: accuracy
-      value: 0.400
-      name: Test Accuracy
----
-
-# Cheese Texture Classifier (DistilBERT)
-
-**Model Creator**: Rumi Loghmani (@rlogh)  
-**Original Dataset**: aslan-ng/cheese-text (by Aslan Noorghasemi)
-
-This model performs 4-class texture classification on cheese descriptions using fine-tuned DistilBERT.
-
-## Model Description
-
-- **Architecture**: DistilBERT-base-uncased fine-tuned for sequence classification
-- **Task**: 4-class texture classification (hard, semi-hard, semi-soft, soft)
-- **Input**: Cheese description text (up to 512 tokens)
-- **Output**: 4-class probability distribution
-
-## Training Details
-
-### Data
-- **Dataset**: [aslan-ng/cheese-text](https://huggingface.co/datasets/aslan-ng/cheese-text) (original split: 100 samples)
-- **Train/Val/Test Split**: 70/15/15 (stratified)
-- **Text Source**: Cheese descriptions from the dataset
-- **Labels**: Texture categories (hard, semi-hard, semi-soft, soft)
-
-### Preprocessing
-- **Tokenization**: DistilBERT tokenizer with 512 max length
-- **Padding**: Max length padding
-- **Truncation**: Long descriptions truncated to 512 tokens
-
-### Training Setup
-- **Model**: distilbert-base-uncased
-- **Epochs**: 10
-- **Batch Size**: 8 (train/val)
-- **Learning Rate**: 2e-5
-- **Warmup Steps**: 10
-- **Weight Decay**: 0.01
-- **Optimizer**: AdamW
-- **Scheduler**: Linear warmup + linear decay
-- **Mixed Precision**: FP16 (if GPU available)
-- **Seed**: 42 (for reproducibility)
-
-### Hardware/Compute
-- **Training Device**: GPU (CUDA)
-- **Training Time**: ~5-10 minutes on GPU
-- **Model Size**: ~67M parameters
-- **Memory Usage**: ~2-4GB GPU memory
-
-## Performance
-
-- **Test Accuracy**: 0.400
-- **Test Loss**: 1.274
-
-### Class-wise Performance
-              precision    recall  f1-score   support
-
-        hard       0.50      0.33      0.40         3
-   semi-hard       0.33      0.50      0.40         4
-   semi-soft       0.33      0.50      0.40         4
-        soft       1.00      0.25      0.40         4
-
-    accuracy                           0.40        15
-   macro avg       0.54      0.40      0.40        15
-weighted avg       0.54      0.40      0.40        15
-
-
-## Usage
-
-```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import torch
-
-# Load model and tokenizer
-model_name = "rlogh/cheese-texture-classifier-distilbert"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-
-# Example prediction
-text = "Feta is a crumbly, tangy Greek cheese with a salty bite and creamy undertones."
-inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
-
-with torch.no_grad():
-    outputs = model(**inputs)
-    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
-    predicted_class = torch.argmax(predictions, dim=-1).item()
-
-class_names = ["hard", "semi-hard", "semi-soft", "soft"]
-print(f"Predicted texture: {class_names[predicted_class]}")
-```
-
-## Class Definitions
-
-- **Hard**: Firm, aged cheeses that are dense and can be grated (e.g., Parmesan, Cheddar)
-- **Semi-hard**: Moderately firm cheeses with some flexibility (e.g., Gouda, Swiss)
-- **Semi-soft**: Cheeses with some give but maintain shape (e.g., Mozzarella, Blue cheese)
-- **Soft**: Creamy, spreadable cheeses (e.g., Brie, Camembert, Cottage cheese)
-
-## Limitations and Ethics
-
-### Limitations
-- **Small Dataset**: Trained on only 100 samples, limiting generalization
-- **Text Quality**: Performance depends on description quality and consistency
-- **Subjective Labels**: Texture classification has inherent subjectivity
-- **Domain Specific**: Only applicable to cheese texture classification
-- **Language**: English-only model
-
-### Ethical Considerations
-- **Bias**: Model may reflect biases in the original dataset
-- **Cultural Context**: Cheese descriptions may be culturally specific
-- **Commercial Use**: Not intended for commercial cheese production decisions
-- **Accuracy**: Should not be used for critical food safety applications
-
-### Recommendations
-- Use for educational/research purposes only
-- Validate predictions with domain experts
-- Consider cultural context when applying to different regions
-- Retrain with larger, more diverse datasets for production use
-
-## AI Usage Disclosure
-
-This model was developed using:
-- **Base Model**: DistilBERT (distilbert-base-uncased)
-- **Training Framework**: Hugging Face Transformers
-- **Fine-tuning**: Standard BERT fine-tuning techniques
-- **No Additional AI**: No other AI systems were used in development
-
-## Citation
-
-**Model Citation:**
-```bibtex
-@model{rlogh/cheese-texture-classifier-distilbert,
-  title={Cheese Texture Classifier (DistilBERT)},
-  author={Rumi Loghmani},
-  year={2024},
-  url={https://huggingface.co/rlogh/cheese-texture-classifier-distilbert}
-}
-```
-
-**Dataset Citation:**
-```bibtex
-@dataset{aslan-ng/cheese-text,
-  title={Cheese Text Dataset},
-  author={Aslan Noorghasemi},
-  year={2024},
-  url={https://huggingface.co/datasets/aslan-ng/cheese-text}
-}
-```
-
-## License
-
-MIT License - See LICENSE file for details.
+---
+license: mit
+tags:
+- text-classification
+- cheese
+- texture
+- distilbert
+- transformers
+- fine-tuned
+datasets:
+- aslan-ng/cheese-text
+metrics:
+- accuracy
+model-index:
+- name: Cheese Texture Classifier (DistilBERT)
+  results:
+  - task:
+      type: text-classification
+      name: Cheese Texture Classification
+    dataset:
+      type: aslan-ng/cheese-text
+      name: Cheese Text Dataset
+    metrics:
+    - type: accuracy
+      value: 0.400
+      name: Test Accuracy
+---
+
+# Cheese Texture Classifier (DistilBERT)
+
+**Model Creator**: Rumi Loghmani (@rlogh)  
+**Original Dataset**: aslan-ng/cheese-text (by Aslan Noorghasemi)
+
+This model performs 4-class texture classification on cheese descriptions using fine-tuned DistilBERT.
+
+## Model Description
+
+- **Architecture**: DistilBERT-base-uncased fine-tuned for sequence classification
+- **Task**: 4-class texture classification (hard, semi-hard, semi-soft, soft)
+- **Input**: Cheese description text (up to 512 tokens)
+- **Output**: 4-class probability distribution
+
+## Training Details
+
+### Data
+- **Dataset**: [aslan-ng/cheese-text](https://huggingface.co/datasets/aslan-ng/cheese-text) (original split: 100 samples)
+- **Train/Val/Test Split**: 70/15/15 (stratified)
+- **Text Source**: Cheese descriptions from the dataset
+- **Labels**: Texture categories (hard, semi-hard, semi-soft, soft)
+
+### Preprocessing
+- **Tokenization**: DistilBERT tokenizer with 512 max length
+- **Padding**: Max length padding
+- **Truncation**: Long descriptions truncated to 512 tokens
+
+### Training Setup
+- **Model**: distilbert-base-uncased
+- **Epochs**: 10
+- **Batch Size**: 8 (train/val)
+- **Learning Rate**: 2e-5
+- **Warmup Steps**: 10
+- **Weight Decay**: 0.01
+- **Optimizer**: AdamW
+- **Scheduler**: Linear warmup + linear decay
+- **Mixed Precision**: FP16 (if GPU available)
+- **Seed**: 42 (for reproducibility)
+
+### Hardware/Compute
+- **Training Device**: CPU
+- **Training Time**: ~5-10 minutes on GPU
+- **Model Size**: ~67M parameters
+- **Memory Usage**: ~2-4GB GPU memory
+
+## Performance
+
+- **Test Accuracy**: 0.400
+- **Test Loss**: 1.290
+
+### Class-wise Performance
+              precision    recall  f1-score   support
+
+        hard       0.50      0.33      0.40         3
+   semi-hard       0.29      0.50      0.36         4
+   semi-soft       0.40      0.50      0.44         4
+        soft       1.00      0.25      0.40         4
+
+    accuracy                           0.40        15
+   macro avg       0.55      0.40      0.40        15
+weighted avg       0.55      0.40      0.40        15
+
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+model_name = "rlogh/cheese-texture-classifier-distilbert"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Example prediction
+text = "Feta is a crumbly, tangy Greek cheese with a salty bite and creamy undertones."
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_class = torch.argmax(predictions, dim=-1).item()
+
+class_names = ["hard", "semi-hard", "semi-soft", "soft"]
+print(f"Predicted texture: {class_names[predicted_class]}")
+```
+
+## Class Definitions
+
+- **Hard**: Firm, aged cheeses that are dense and can be grated (e.g., Parmesan, Cheddar)
+- **Semi-hard**: Moderately firm cheeses with some flexibility (e.g., Gouda, Swiss)
+- **Semi-soft**: Cheeses with some give but maintain shape (e.g., Mozzarella, Blue cheese)
+- **Soft**: Creamy, spreadable cheeses (e.g., Brie, Camembert, Cottage cheese)
+
+## Limitations and Ethics
+
+### Limitations
+- **Small Dataset**: Trained on only 100 samples, limiting generalization
+- **Text Quality**: Performance depends on description quality and consistency
+- **Subjective Labels**: Texture classification has inherent subjectivity
+- **Domain Specific**: Only applicable to cheese texture classification
+- **Language**: English-only model
+
+### Ethical Considerations
+- **Bias**: Model may reflect biases in the original dataset
+- **Cultural Context**: Cheese descriptions may be culturally specific
+- **Commercial Use**: Not intended for commercial cheese production decisions
+- **Accuracy**: Should not be used for critical food safety applications
+
+### Recommendations
+- Use for educational/research purposes only
+- Validate predictions with domain experts
+- Consider cultural context when applying to different regions
+- Retrain with larger, more diverse datasets for production use
+
+## AI Usage Disclosure
+
+This model was developed using:
+- **Base Model**: DistilBERT (distilbert-base-uncased)
+- **Training Framework**: Hugging Face Transformers
+- **Fine-tuning**: Standard BERT fine-tuning techniques
+- **No Additional AI**: No other AI systems were used in development
+
+## Citation
+
+**Model Citation:**
+```bibtex
+@model{rlogh/cheese-texture-classifier-distilbert,
+  title={Cheese Texture Classifier (DistilBERT)},
+  author={Rumi Loghmani},
+  year={2024},
+  url={https://huggingface.co/rlogh/cheese-texture-classifier-distilbert}
+}
+```
+
+**Dataset Citation:**
+```bibtex
+@dataset{aslan-ng/cheese-text,
+  title={Cheese Text Dataset},
+  author={Aslan Noorghasemi},
+  year={2024},
+  url={https://huggingface.co/datasets/aslan-ng/cheese-text}
+}
+```
+
+## License
+
+MIT License - See LICENSE file for details.

checkpoint-18/config.json

@@ -1,36 +1,36 @@
-{
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "dtype": "float32",
-  "hidden_dim": 3072,
-  "id2label": {
-    "0": "hard",
-    "1": "semi-hard",
-    "2": "semi-soft",
-    "3": "soft"
-  },
-  "initializer_range": 0.02,
-  "label2id": {
-    "hard": 0,
-    "semi-hard": 1,
-    "semi-soft": 2,
-    "soft": 3
-  },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "transformers_version": "4.56.1",
-  "vocab_size": 30522
-}
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "hard",
+    "1": "semi-hard",
+    "2": "semi-soft",
+    "3": "soft"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hard": 0,
+    "semi-hard": 1,
+    "semi-soft": 2,
+    "soft": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

checkpoint-18/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9186fe36c00e96c7e1bcb163360a0c126b68f912e75a7b99162c4d2bb613851c
+oid sha256:11fe9e2b21185c4f2954811e3a55e84e135c56e516110a0c1fa796bedc5fac7e
 size 267838720

checkpoint-18/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764865d51baf2ef3802c555c974821b44033f32c9711af3cc57760694e04f01a
-size 535740043
+oid sha256:a6c4c757ffaa0a421a500e295e32ff062d66229a9454efbaf7e87273b3f3b4f2
+size 535737163

checkpoint-18/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128fd6789dbecdaa703802c84141d4eeb7956a1f3aa57027a4a20d800b5b22e4
-size 14645
+oid sha256:af011acd911ebca2868ec2c14dc0310b255271ca08299aad8c829637dbba9d41
+size 14455

checkpoint-18/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5cb1142c9841e543151dfa10e04da4d1ddc82e8206c217979304fd6bbdcf000
+oid sha256:9e2c385954a605c7e89276ade36d44efa2f1e4d36d1ad3f35c3db6322f80f00a
 size 1465

checkpoint-18/special_tokens_map.json

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

checkpoint-18/tokenizer_config.json

@@ -1,58 +1,58 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-18/trainer_state.json

@@ -1,73 +1,73 @@
-{
-  "best_global_step": 9,
-  "best_metric": 0.4,
-  "best_model_checkpoint": "./cheese-text-classifier\\checkpoint-9",
-  "epoch": 2.0,
-  "eval_steps": 500,
-  "global_step": 18,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.5555555555555556,
-      "grad_norm": 2.3992674350738525,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 1.3393,
-      "step": 5
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3667316436767578,
-      "eval_runtime": 0.1993,
-      "eval_samples_per_second": 75.254,
-      "eval_steps_per_second": 10.034,
-      "step": 9
-    },
-    {
-      "epoch": 1.1111111111111112,
-      "grad_norm": 3.988067865371704,
-      "learning_rate": 1.8e-05,
-      "loss": 1.334,
-      "step": 10
-    },
-    {
-      "epoch": 1.6666666666666665,
-      "grad_norm": 3.5621254444122314,
-      "learning_rate": 1.9e-05,
-      "loss": 1.3276,
-      "step": 15
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.351041555404663,
-      "eval_runtime": 0.1866,
-      "eval_samples_per_second": 80.391,
-      "eval_steps_per_second": 10.719,
-      "step": 18
-    }
-  ],
-  "logging_steps": 5,
-  "max_steps": 90,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "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": 18546097274880.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}
+{
+  "best_global_step": 9,
+  "best_metric": 0.26666666666666666,
+  "best_model_checkpoint": "./cheese-text-classifier/checkpoint-9",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 2.245687246322632,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3897,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3788894414901733,
+      "eval_runtime": 15.3581,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.13,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 3.2673349380493164,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3742,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7203733921051025,
+      "learning_rate": 1.9e-05,
+      "loss": 1.376,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3665523529052734,
+      "eval_runtime": 11.7383,
+      "eval_samples_per_second": 1.278,
+      "eval_steps_per_second": 0.17,
+      "step": 18
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 18546097274880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e09a73f1acd70625a9205129f2e812d36048a9c26a346e45f2c59de8cf03c1d
+oid sha256:601f05c65c90d8f98b95428e2f3212dc00f04a7ec1ca04f350f1094719f63609
 size 5713

checkpoint-27/config.json

@@ -1,36 +1,36 @@
-{
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "dtype": "float32",
-  "hidden_dim": 3072,
-  "id2label": {
-    "0": "hard",
-    "1": "semi-hard",
-    "2": "semi-soft",
-    "3": "soft"
-  },
-  "initializer_range": 0.02,
-  "label2id": {
-    "hard": 0,
-    "semi-hard": 1,
-    "semi-soft": 2,
-    "soft": 3
-  },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "transformers_version": "4.56.1",
-  "vocab_size": 30522
-}
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "hard",
+    "1": "semi-hard",
+    "2": "semi-soft",
+    "3": "soft"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hard": 0,
+    "semi-hard": 1,
+    "semi-soft": 2,
+    "soft": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

checkpoint-27/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b4ae0a98e84722b94644c4c957706abff999d48271c524f0fbcc939eef3fb4
+oid sha256:d4888eeca7da0a0b10e6b5a3fb079da48820c2f9fdd6e89feffcf85bd2a0d0ef
 size 267838720

checkpoint-27/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43ef309428ff39308802dfcd91f6e2e108ced7d58eee8b2a0454b509db0c9e7
-size 535740043
+oid sha256:6fae6998da3a0801252042a7e3bfc3dc0ce8d6c774b40c1093e349b6ab71b28b
+size 535737163

checkpoint-27/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c9ded891071528d1d7d37f98c82a4150c15973ace82e86232ed82afc455292
-size 14645
+oid sha256:554a6f518e4416ac9e811b97c1541ed8428693dee1381b601f6162a53b82547e
+size 14455

checkpoint-27/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261ab7bb7f2dd6da966c1a5d536f05b09c8e99cc5b65e2e3c3057a488f68aed4
+oid sha256:095e33bc11ef1e7d68d549fbfb34695fddb25a664a3a948781f0a9761c641095
 size 1465

checkpoint-27/special_tokens_map.json

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

checkpoint-27/tokenizer_config.json

@@ -1,58 +1,58 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-27/trainer_state.json

@@ -1,96 +1,96 @@
-{
-  "best_global_step": 9,
-  "best_metric": 0.4,
-  "best_model_checkpoint": "./cheese-text-classifier\\checkpoint-9",
-  "epoch": 3.0,
-  "eval_steps": 500,
-  "global_step": 27,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.5555555555555556,
-      "grad_norm": 2.3992674350738525,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 1.3393,
-      "step": 5
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3667316436767578,
-      "eval_runtime": 0.1993,
-      "eval_samples_per_second": 75.254,
-      "eval_steps_per_second": 10.034,
-      "step": 9
-    },
-    {
-      "epoch": 1.1111111111111112,
-      "grad_norm": 3.988067865371704,
-      "learning_rate": 1.8e-05,
-      "loss": 1.334,
-      "step": 10
-    },
-    {
-      "epoch": 1.6666666666666665,
-      "grad_norm": 3.5621254444122314,
-      "learning_rate": 1.9e-05,
-      "loss": 1.3276,
-      "step": 15
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.351041555404663,
-      "eval_runtime": 0.1866,
-      "eval_samples_per_second": 80.391,
-      "eval_steps_per_second": 10.719,
-      "step": 18
-    },
-    {
-      "epoch": 2.2222222222222223,
-      "grad_norm": 3.5041863918304443,
-      "learning_rate": 1.775e-05,
-      "loss": 1.3127,
-      "step": 20
-    },
-    {
-      "epoch": 2.7777777777777777,
-      "grad_norm": 3.1173243522644043,
-      "learning_rate": 1.65e-05,
-      "loss": 1.2905,
-      "step": 25
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3322917222976685,
-      "eval_runtime": 0.187,
-      "eval_samples_per_second": 80.199,
-      "eval_steps_per_second": 10.693,
-      "step": 27
-    }
-  ],
-  "logging_steps": 5,
-  "max_steps": 90,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "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": 27819145912320.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}
+{
+  "best_global_step": 27,
+  "best_metric": 0.4,
+  "best_model_checkpoint": "./cheese-text-classifier/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 2.245687246322632,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3897,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3788894414901733,
+      "eval_runtime": 15.3581,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.13,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 3.2673349380493164,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3742,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7203733921051025,
+      "learning_rate": 1.9e-05,
+      "loss": 1.376,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3665523529052734,
+      "eval_runtime": 11.7383,
+      "eval_samples_per_second": 1.278,
+      "eval_steps_per_second": 0.17,
+      "step": 18
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.6290931701660156,
+      "learning_rate": 1.775e-05,
+      "loss": 1.3642,
+      "step": 20
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 2.063326358795166,
+      "learning_rate": 1.65e-05,
+      "loss": 1.3545,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4,
+      "eval_loss": 1.3509334325790405,
+      "eval_runtime": 11.9563,
+      "eval_samples_per_second": 1.255,
+      "eval_steps_per_second": 0.167,
+      "step": 27
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 27819145912320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-27/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e09a73f1acd70625a9205129f2e812d36048a9c26a346e45f2c59de8cf03c1d
+oid sha256:601f05c65c90d8f98b95428e2f3212dc00f04a7ec1ca04f350f1094719f63609
 size 5713

checkpoint-36/config.json

@@ -1,36 +1,36 @@
-{
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "dtype": "float32",
-  "hidden_dim": 3072,
-  "id2label": {
-    "0": "hard",
-    "1": "semi-hard",
-    "2": "semi-soft",
-    "3": "soft"
-  },
-  "initializer_range": 0.02,
-  "label2id": {
-    "hard": 0,
-    "semi-hard": 1,
-    "semi-soft": 2,
-    "soft": 3
-  },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "transformers_version": "4.56.1",
-  "vocab_size": 30522
-}
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "hard",
+    "1": "semi-hard",
+    "2": "semi-soft",
+    "3": "soft"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hard": 0,
+    "semi-hard": 1,
+    "semi-soft": 2,
+    "soft": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

checkpoint-36/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9103761626f348ad8ca62f8ef15453e3af535e38f46e03550cf0d68cfff73a
+oid sha256:29b812f914923941dbe98fce4ff58906f5d0eae634ad2df4198c356581fc654c
 size 267838720

checkpoint-36/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cedb5646f450b04e186c4c25cbb1dca1a8f0c7dd82ac5ae174215f95f7ea0834
-size 535740043
+oid sha256:8690a3e03e5a439a76615bbee3420038fe419e65b4be94ff4e685f69f12804fd
+size 535737163

checkpoint-36/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1e78dd4b5227c2191e07b09d8fa38a94689402f68cf150e526371b1a4a54c5
-size 14645
+oid sha256:10c93fff6674ca3522c6a4ae993b108084f886b364f5e3ff427c4e294456a47d
+size 14455

checkpoint-36/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df566675e03ea54508b1a61983473558080c554f19f4207d0ed860743b01bbbf
+oid sha256:ea88c3b0d587a8a75030aaac449e3d64407849d75a8c69dcf18ed1c9863f7914
 size 1465

checkpoint-36/special_tokens_map.json

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

checkpoint-36/tokenizer_config.json

@@ -1,58 +1,58 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-36/trainer_state.json

@@ -1,119 +1,119 @@
-{
-  "best_global_step": 9,
-  "best_metric": 0.4,
-  "best_model_checkpoint": "./cheese-text-classifier\\checkpoint-9",
-  "epoch": 4.0,
-  "eval_steps": 500,
-  "global_step": 36,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.5555555555555556,
-      "grad_norm": 2.3992674350738525,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 1.3393,
-      "step": 5
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3667316436767578,
-      "eval_runtime": 0.1993,
-      "eval_samples_per_second": 75.254,
-      "eval_steps_per_second": 10.034,
-      "step": 9
-    },
-    {
-      "epoch": 1.1111111111111112,
-      "grad_norm": 3.988067865371704,
-      "learning_rate": 1.8e-05,
-      "loss": 1.334,
-      "step": 10
-    },
-    {
-      "epoch": 1.6666666666666665,
-      "grad_norm": 3.5621254444122314,
-      "learning_rate": 1.9e-05,
-      "loss": 1.3276,
-      "step": 15
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.351041555404663,
-      "eval_runtime": 0.1866,
-      "eval_samples_per_second": 80.391,
-      "eval_steps_per_second": 10.719,
-      "step": 18
-    },
-    {
-      "epoch": 2.2222222222222223,
-      "grad_norm": 3.5041863918304443,
-      "learning_rate": 1.775e-05,
-      "loss": 1.3127,
-      "step": 20
-    },
-    {
-      "epoch": 2.7777777777777777,
-      "grad_norm": 3.1173243522644043,
-      "learning_rate": 1.65e-05,
-      "loss": 1.2905,
-      "step": 25
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3322917222976685,
-      "eval_runtime": 0.187,
-      "eval_samples_per_second": 80.199,
-      "eval_steps_per_second": 10.693,
-      "step": 27
-    },
-    {
-      "epoch": 3.3333333333333335,
-      "grad_norm": 5.531054973602295,
-      "learning_rate": 1.525e-05,
-      "loss": 1.2266,
-      "step": 30
-    },
-    {
-      "epoch": 3.888888888888889,
-      "grad_norm": 3.253871440887451,
-      "learning_rate": 1.4e-05,
-      "loss": 1.1597,
-      "step": 35
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.316666841506958,
-      "eval_runtime": 0.156,
-      "eval_samples_per_second": 96.134,
-      "eval_steps_per_second": 12.818,
-      "step": 36
-    }
-  ],
-  "logging_steps": 5,
-  "max_steps": 90,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "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": 37092194549760.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}
+{
+  "best_global_step": 36,
+  "best_metric": 0.4666666666666667,
+  "best_model_checkpoint": "./cheese-text-classifier/checkpoint-36",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 2.245687246322632,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3897,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3788894414901733,
+      "eval_runtime": 15.3581,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.13,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 3.2673349380493164,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3742,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7203733921051025,
+      "learning_rate": 1.9e-05,
+      "loss": 1.376,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3665523529052734,
+      "eval_runtime": 11.7383,
+      "eval_samples_per_second": 1.278,
+      "eval_steps_per_second": 0.17,
+      "step": 18
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.6290931701660156,
+      "learning_rate": 1.775e-05,
+      "loss": 1.3642,
+      "step": 20
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 2.063326358795166,
+      "learning_rate": 1.65e-05,
+      "loss": 1.3545,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4,
+      "eval_loss": 1.3509334325790405,
+      "eval_runtime": 11.9563,
+      "eval_samples_per_second": 1.255,
+      "eval_steps_per_second": 0.167,
+      "step": 27
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.2415618896484375,
+      "learning_rate": 1.525e-05,
+      "loss": 1.3202,
+      "step": 30
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 2.6389851570129395,
+      "learning_rate": 1.4e-05,
+      "loss": 1.2773,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4666666666666667,
+      "eval_loss": 1.3365625143051147,
+      "eval_runtime": 16.0326,
+      "eval_samples_per_second": 0.936,
+      "eval_steps_per_second": 0.125,
+      "step": 36
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 37092194549760.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-36/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e09a73f1acd70625a9205129f2e812d36048a9c26a346e45f2c59de8cf03c1d
+oid sha256:601f05c65c90d8f98b95428e2f3212dc00f04a7ec1ca04f350f1094719f63609
 size 5713

checkpoint-45/config.json

@@ -1,36 +1,36 @@
-{
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "dtype": "float32",
-  "hidden_dim": 3072,
-  "id2label": {
-    "0": "hard",
-    "1": "semi-hard",
-    "2": "semi-soft",
-    "3": "soft"
-  },
-  "initializer_range": 0.02,
-  "label2id": {
-    "hard": 0,
-    "semi-hard": 1,
-    "semi-soft": 2,
-    "soft": 3
-  },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "transformers_version": "4.56.1",
-  "vocab_size": 30522
-}
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "hard",
+    "1": "semi-hard",
+    "2": "semi-soft",
+    "3": "soft"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hard": 0,
+    "semi-hard": 1,
+    "semi-soft": 2,
+    "soft": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

checkpoint-45/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de112e603b7ce6bea67f3c24b99fafac7bf34253d9bdf5ff989b09ac2b83ca4a
+oid sha256:881e3ee05fb017ce1e24d8350e287da798aabc02cafb046a9aaa2420b7ba77f3
 size 267838720

checkpoint-45/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a00865eaa9f97851e56a88891b92d080ddf724e23e3f3cfcdf1ccfa7f9ec5e
-size 535740043
+oid sha256:3aee79bdea1f103631c54ca9a61e674818b2052f820821825012f7f18df6e5fd
+size 535737163

checkpoint-45/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cbb01837febe7919f0932a54877b346f17063c101f3fe1e012d2f57b20df246
-size 14645
+oid sha256:dfd0ad23828b8751d20859a2c2db516e48d99722a8d6c22df92cd57e959ce4aa
+size 14455

checkpoint-45/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb288caf5a3a28e45dd5cedb94250ec50410cd795dd5578017e9d2d2319ad46d
+oid sha256:7ab1da70076c3717ffc71289d6363e31a50dc677989fbcd4dc39336f5515d6d4
 size 1465

checkpoint-45/special_tokens_map.json

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

checkpoint-45/tokenizer_config.json

@@ -1,58 +1,58 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-45/trainer_state.json

@@ -1,142 +1,142 @@
-{
-  "best_global_step": 9,
-  "best_metric": 0.4,
-  "best_model_checkpoint": "./cheese-text-classifier\\checkpoint-9",
-  "epoch": 5.0,
-  "eval_steps": 500,
-  "global_step": 45,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.5555555555555556,
-      "grad_norm": 2.3992674350738525,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 1.3393,
-      "step": 5
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3667316436767578,
-      "eval_runtime": 0.1993,
-      "eval_samples_per_second": 75.254,
-      "eval_steps_per_second": 10.034,
-      "step": 9
-    },
-    {
-      "epoch": 1.1111111111111112,
-      "grad_norm": 3.988067865371704,
-      "learning_rate": 1.8e-05,
-      "loss": 1.334,
-      "step": 10
-    },
-    {
-      "epoch": 1.6666666666666665,
-      "grad_norm": 3.5621254444122314,
-      "learning_rate": 1.9e-05,
-      "loss": 1.3276,
-      "step": 15
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.351041555404663,
-      "eval_runtime": 0.1866,
-      "eval_samples_per_second": 80.391,
-      "eval_steps_per_second": 10.719,
-      "step": 18
-    },
-    {
-      "epoch": 2.2222222222222223,
-      "grad_norm": 3.5041863918304443,
-      "learning_rate": 1.775e-05,
-      "loss": 1.3127,
-      "step": 20
-    },
-    {
-      "epoch": 2.7777777777777777,
-      "grad_norm": 3.1173243522644043,
-      "learning_rate": 1.65e-05,
-      "loss": 1.2905,
-      "step": 25
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3322917222976685,
-      "eval_runtime": 0.187,
-      "eval_samples_per_second": 80.199,
-      "eval_steps_per_second": 10.693,
-      "step": 27
-    },
-    {
-      "epoch": 3.3333333333333335,
-      "grad_norm": 5.531054973602295,
-      "learning_rate": 1.525e-05,
-      "loss": 1.2266,
-      "step": 30
-    },
-    {
-      "epoch": 3.888888888888889,
-      "grad_norm": 3.253871440887451,
-      "learning_rate": 1.4e-05,
-      "loss": 1.1597,
-      "step": 35
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.316666841506958,
-      "eval_runtime": 0.156,
-      "eval_samples_per_second": 96.134,
-      "eval_steps_per_second": 12.818,
-      "step": 36
-    },
-    {
-      "epoch": 4.444444444444445,
-      "grad_norm": 5.929306507110596,
-      "learning_rate": 1.275e-05,
-      "loss": 1.1161,
-      "step": 40
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 4.499341011047363,
-      "learning_rate": 1.15e-05,
-      "loss": 1.1096,
-      "step": 45
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.304785132408142,
-      "eval_runtime": 0.1465,
-      "eval_samples_per_second": 102.38,
-      "eval_steps_per_second": 13.651,
-      "step": 45
-    }
-  ],
-  "logging_steps": 5,
-  "max_steps": 90,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "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": 46365243187200.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}
+{
+  "best_global_step": 36,
+  "best_metric": 0.4666666666666667,
+  "best_model_checkpoint": "./cheese-text-classifier/checkpoint-36",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 2.245687246322632,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3897,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3788894414901733,
+      "eval_runtime": 15.3581,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.13,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 3.2673349380493164,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3742,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7203733921051025,
+      "learning_rate": 1.9e-05,
+      "loss": 1.376,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3665523529052734,
+      "eval_runtime": 11.7383,
+      "eval_samples_per_second": 1.278,
+      "eval_steps_per_second": 0.17,
+      "step": 18
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.6290931701660156,
+      "learning_rate": 1.775e-05,
+      "loss": 1.3642,
+      "step": 20
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 2.063326358795166,
+      "learning_rate": 1.65e-05,
+      "loss": 1.3545,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4,
+      "eval_loss": 1.3509334325790405,
+      "eval_runtime": 11.9563,
+      "eval_samples_per_second": 1.255,
+      "eval_steps_per_second": 0.167,
+      "step": 27
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.2415618896484375,
+      "learning_rate": 1.525e-05,
+      "loss": 1.3202,
+      "step": 30
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 2.6389851570129395,
+      "learning_rate": 1.4e-05,
+      "loss": 1.2773,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4666666666666667,
+      "eval_loss": 1.3365625143051147,
+      "eval_runtime": 16.0326,
+      "eval_samples_per_second": 0.936,
+      "eval_steps_per_second": 0.125,
+      "step": 36
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 4.96947717666626,
+      "learning_rate": 1.275e-05,
+      "loss": 1.2581,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.3252763748168945,
+      "learning_rate": 1.15e-05,
+      "loss": 1.2385,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4,
+      "eval_loss": 1.3152297735214233,
+      "eval_runtime": 11.4967,
+      "eval_samples_per_second": 1.305,
+      "eval_steps_per_second": 0.174,
+      "step": 45
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 46365243187200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-45/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e09a73f1acd70625a9205129f2e812d36048a9c26a346e45f2c59de8cf03c1d
+oid sha256:601f05c65c90d8f98b95428e2f3212dc00f04a7ec1ca04f350f1094719f63609
 size 5713

checkpoint-54/config.json

@@ -1,36 +1,36 @@
-{
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "dtype": "float32",
-  "hidden_dim": 3072,
-  "id2label": {
-    "0": "hard",
-    "1": "semi-hard",
-    "2": "semi-soft",
-    "3": "soft"
-  },
-  "initializer_range": 0.02,
-  "label2id": {
-    "hard": 0,
-    "semi-hard": 1,
-    "semi-soft": 2,
-    "soft": 3
-  },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "transformers_version": "4.56.1",
-  "vocab_size": 30522
-}
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "hard",
+    "1": "semi-hard",
+    "2": "semi-soft",
+    "3": "soft"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hard": 0,
+    "semi-hard": 1,
+    "semi-soft": 2,
+    "soft": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa846c5c226056cf5ce5353619db80041460988d55162b17a591cffe149a800
+oid sha256:c67f13c61deeb6b7adef2ccee9818a40ccb3f8d91726396efcfe5f63186e2597
 size 267838720

checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1eb8fea032ede5f8effc13bef01b07d87685d4ecd7c665082c802a5915b57d1
-size 535740043
+oid sha256:668a302afd21ca03554c15ff8c56e7f2e9f8439d40c5666355f63c4c20b84194
+size 535737163

checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067a193dac0906a35e128e6d201f4390897d736a9c9e8d5a2830394c21b775c0
-size 14645
+oid sha256:1ee8d2e9a02430c78237891f53745435230af59814a0e2823c3b4c7c861b7824
+size 14455

checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4671a75c3a48b181d2f951bb250e6d670ab787e12764f4c7021663e9d714a63d
+oid sha256:413360cb5e557f5ecf080a401c6b3faae1a8f1d812b7d0c52a9cc6ff59355c54
 size 1465

checkpoint-54/special_tokens_map.json

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

checkpoint-54/tokenizer_config.json

@@ -1,58 +1,58 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-54/trainer_state.json

@@ -1,158 +1,158 @@
-{
-  "best_global_step": 54,
-  "best_metric": 0.4666666666666667,
-  "best_model_checkpoint": "./cheese-text-classifier\\checkpoint-54",
-  "epoch": 6.0,
-  "eval_steps": 500,
-  "global_step": 54,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.5555555555555556,
-      "grad_norm": 2.3992674350738525,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 1.3393,
-      "step": 5
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3667316436767578,
-      "eval_runtime": 0.1993,
-      "eval_samples_per_second": 75.254,
-      "eval_steps_per_second": 10.034,
-      "step": 9
-    },
-    {
-      "epoch": 1.1111111111111112,
-      "grad_norm": 3.988067865371704,
-      "learning_rate": 1.8e-05,
-      "loss": 1.334,
-      "step": 10
-    },
-    {
-      "epoch": 1.6666666666666665,
-      "grad_norm": 3.5621254444122314,
-      "learning_rate": 1.9e-05,
-      "loss": 1.3276,
-      "step": 15
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.351041555404663,
-      "eval_runtime": 0.1866,
-      "eval_samples_per_second": 80.391,
-      "eval_steps_per_second": 10.719,
-      "step": 18
-    },
-    {
-      "epoch": 2.2222222222222223,
-      "grad_norm": 3.5041863918304443,
-      "learning_rate": 1.775e-05,
-      "loss": 1.3127,
-      "step": 20
-    },
-    {
-      "epoch": 2.7777777777777777,
-      "grad_norm": 3.1173243522644043,
-      "learning_rate": 1.65e-05,
-      "loss": 1.2905,
-      "step": 25
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.3322917222976685,
-      "eval_runtime": 0.187,
-      "eval_samples_per_second": 80.199,
-      "eval_steps_per_second": 10.693,
-      "step": 27
-    },
-    {
-      "epoch": 3.3333333333333335,
-      "grad_norm": 5.531054973602295,
-      "learning_rate": 1.525e-05,
-      "loss": 1.2266,
-      "step": 30
-    },
-    {
-      "epoch": 3.888888888888889,
-      "grad_norm": 3.253871440887451,
-      "learning_rate": 1.4e-05,
-      "loss": 1.1597,
-      "step": 35
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.316666841506958,
-      "eval_runtime": 0.156,
-      "eval_samples_per_second": 96.134,
-      "eval_steps_per_second": 12.818,
-      "step": 36
-    },
-    {
-      "epoch": 4.444444444444445,
-      "grad_norm": 5.929306507110596,
-      "learning_rate": 1.275e-05,
-      "loss": 1.1161,
-      "step": 40
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 4.499341011047363,
-      "learning_rate": 1.15e-05,
-      "loss": 1.1096,
-      "step": 45
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 1.304785132408142,
-      "eval_runtime": 0.1465,
-      "eval_samples_per_second": 102.38,
-      "eval_steps_per_second": 13.651,
-      "step": 45
-    },
-    {
-      "epoch": 5.555555555555555,
-      "grad_norm": 4.16509485244751,
-      "learning_rate": 1.025e-05,
-      "loss": 0.9954,
-      "step": 50
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.4666666666666667,
-      "eval_loss": 1.3045247793197632,
-      "eval_runtime": 0.1861,
-      "eval_samples_per_second": 80.608,
-      "eval_steps_per_second": 10.748,
-      "step": 54
-    }
-  ],
-  "logging_steps": 5,
-  "max_steps": 90,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "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": 55638291824640.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}
+{
+  "best_global_step": 36,
+  "best_metric": 0.4666666666666667,
+  "best_model_checkpoint": "./cheese-text-classifier/checkpoint-36",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 2.245687246322632,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3897,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3788894414901733,
+      "eval_runtime": 15.3581,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.13,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 3.2673349380493164,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3742,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7203733921051025,
+      "learning_rate": 1.9e-05,
+      "loss": 1.376,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26666666666666666,
+      "eval_loss": 1.3665523529052734,
+      "eval_runtime": 11.7383,
+      "eval_samples_per_second": 1.278,
+      "eval_steps_per_second": 0.17,
+      "step": 18
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.6290931701660156,
+      "learning_rate": 1.775e-05,
+      "loss": 1.3642,
+      "step": 20
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 2.063326358795166,
+      "learning_rate": 1.65e-05,
+      "loss": 1.3545,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4,
+      "eval_loss": 1.3509334325790405,
+      "eval_runtime": 11.9563,
+      "eval_samples_per_second": 1.255,
+      "eval_steps_per_second": 0.167,
+      "step": 27
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.2415618896484375,
+      "learning_rate": 1.525e-05,
+      "loss": 1.3202,
+      "step": 30
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 2.6389851570129395,
+      "learning_rate": 1.4e-05,
+      "loss": 1.2773,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4666666666666667,
+      "eval_loss": 1.3365625143051147,
+      "eval_runtime": 16.0326,
+      "eval_samples_per_second": 0.936,
+      "eval_steps_per_second": 0.125,
+      "step": 36
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 4.96947717666626,
+      "learning_rate": 1.275e-05,
+      "loss": 1.2581,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.3252763748168945,
+      "learning_rate": 1.15e-05,
+      "loss": 1.2385,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4,
+      "eval_loss": 1.3152297735214233,
+      "eval_runtime": 11.4967,
+      "eval_samples_per_second": 1.305,
+      "eval_steps_per_second": 0.174,
+      "step": 45
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 3.6944730281829834,
+      "learning_rate": 1.025e-05,
+      "loss": 1.1673,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4666666666666667,
+      "eval_loss": 1.3012595176696777,
+      "eval_runtime": 11.6907,
+      "eval_samples_per_second": 1.283,
+      "eval_steps_per_second": 0.171,
+      "step": 54
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 55638291824640.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e09a73f1acd70625a9205129f2e812d36048a9c26a346e45f2c59de8cf03c1d
+oid sha256:601f05c65c90d8f98b95428e2f3212dc00f04a7ec1ca04f350f1094719f63609
 size 5713