Initial model push after training

README.md

@@ -0,0 +1,91 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-large-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: math_question_grade_detection_Bert_databalanced
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# math_question_grade_detection_Bert_databalanced
+
+This model is a fine-tuned version of [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6880
+- Accuracy: 0.7603
+- Precision: 0.7651
+- Recall: 0.7603
+- F1: 0.7588
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 0.2817 | 50   | 2.1003          | 0.2349   | 0.3799    | 0.2349 | 0.2106 |
+| No log        | 0.5634 | 100  | 1.9607          | 0.2762   | 0.3337    | 0.2762 | 0.2498 |
+| No log        | 0.8451 | 150  | 1.5031          | 0.4778   | 0.4633    | 0.4778 | 0.4591 |
+| No log        | 1.1268 | 200  | 1.2546          | 0.5460   | 0.5596    | 0.5460 | 0.5176 |
+| No log        | 1.4085 | 250  | 1.0941          | 0.5746   | 0.5804    | 0.5746 | 0.5675 |
+| No log        | 1.6901 | 300  | 0.9381          | 0.6730   | 0.6943    | 0.6730 | 0.6721 |
+| No log        | 1.9718 | 350  | 0.8974          | 0.6619   | 0.6822    | 0.6619 | 0.6570 |
+| No log        | 2.2535 | 400  | 0.8243          | 0.6889   | 0.6913    | 0.6889 | 0.6856 |
+| No log        | 2.5352 | 450  | 0.8219          | 0.6937   | 0.7131    | 0.6937 | 0.6881 |
+| 1.2537        | 2.8169 | 500  | 0.7642          | 0.7159   | 0.7239    | 0.7159 | 0.7121 |
+| 1.2537        | 3.0986 | 550  | 0.7580          | 0.7175   | 0.7197    | 0.7175 | 0.7068 |
+| 1.2537        | 3.3803 | 600  | 0.7310          | 0.7397   | 0.7523    | 0.7397 | 0.7387 |
+| 1.2537        | 3.6620 | 650  | 0.7562          | 0.7413   | 0.7466    | 0.7413 | 0.7349 |
+| 1.2537        | 3.9437 | 700  | 0.6512          | 0.7730   | 0.7792    | 0.7730 | 0.7726 |
+| 1.2537        | 4.2254 | 750  | 0.6941          | 0.7476   | 0.7484    | 0.7476 | 0.7447 |
+| 1.2537        | 4.5070 | 800  | 0.6866          | 0.7571   | 0.7607    | 0.7571 | 0.7550 |
+| 1.2537        | 4.7887 | 850  | 0.6942          | 0.7603   | 0.7644    | 0.7603 | 0.7588 |
+| 1.2537        | 5.0704 | 900  | 0.7230          | 0.7683   | 0.7821    | 0.7683 | 0.7656 |
+| 1.2537        | 5.3521 | 950  | 0.7123          | 0.7603   | 0.7669    | 0.7603 | 0.7588 |
+| 0.321         | 5.6338 | 1000 | 0.6939          | 0.7667   | 0.7725    | 0.7667 | 0.7652 |
+| 0.321         | 5.9155 | 1050 | 0.6884          | 0.7667   | 0.7723    | 0.7667 | 0.7657 |
+| 0.321         | 6.1972 | 1100 | 0.6880          | 0.7603   | 0.7651    | 0.7603 | 0.7588 |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "google-bert/bert-large-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb68c6a05e7f573c6920f8408b1ccb59d2b55da2d7d9a2c2455d83af9e48a71
+size 1340651460

runs/Dec18_06-34-11_7ad37ae5c0da/events.out.tfevents.1734503668.7ad37ae5c0da.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d45618e893e7ac2c1b4d8778e2e058a797f68d4429192aea0ed610830325229
+size 16553

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:102d320489a0e837ad9fe51107424878f419ca3e4ee69030ef9545aec5a66d92
+size 5304