Model save

README.md

@@ -1,27 +1,27 @@
 ---
 library_name: transformers
-license: mit
-base_model: FacebookAI/roberta-large
+license: apache-2.0
+base_model: google-bert/bert-large-uncased
 tags:
 - generated_from_trainer
 metrics:
 - accuracy
 - f1
 model-index:
-- name: roberta-large-csb
+- name: bert-large-csb
   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. -->
 
-# roberta-large-csb
+# bert-large-csb
 
-This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on an unknown dataset.
+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: 0.4928
-- Accuracy: 0.8703
-- F1: 0.8701
+- Loss: 0.5239
+- Accuracy: 0.8637
+- F1: 0.8638
 
 ## Model description
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.4257        | 1.0   | 455  | 0.4663          | 0.7956   | 0.7887 |
-| 0.3337        | 2.0   | 910  | 0.3817          | 0.8549   | 0.8549 |
-| 0.3542        | 3.0   | 1365 | 0.4928          | 0.8703   | 0.8701 |
-| 0.2674        | 4.0   | 1820 | 0.6630          | 0.8615   | 0.8616 |
-| 0.0791        | 5.0   | 2275 | 0.8964          | 0.8615   | 0.8612 |
-| 0.0331        | 6.0   | 2730 | 1.1715          | 0.8352   | 0.8327 |
-| 0.0427        | 7.0   | 3185 | 1.1071          | 0.8637   | 0.8638 |
-| 0.0002        | 8.0   | 3640 | 1.1752          | 0.8615   | 0.8616 |
-| 0.0001        | 9.0   | 4095 | 1.2017          | 0.8637   | 0.8637 |
-| 0.037         | 10.0  | 4550 | 1.2238          | 0.8637   | 0.8637 |
+| 0.4506        | 1.0   | 455  | 0.4215          | 0.7890   | 0.7831 |
+| 0.2919        | 2.0   | 910  | 0.4337          | 0.8505   | 0.8505 |
+| 0.3034        | 3.0   | 1365 | 0.5239          | 0.8637   | 0.8638 |
+| 0.2416        | 4.0   | 1820 | 0.5891          | 0.8527   | 0.8527 |
+| 0.0793        | 5.0   | 2275 | 0.8805          | 0.8374   | 0.8371 |
+| 0.0385        | 6.0   | 2730 | 1.1213          | 0.8396   | 0.8384 |
+| 0.0215        | 7.0   | 3185 | 1.1417          | 0.8440   | 0.8437 |
+| 0.0001        | 8.0   | 3640 | 1.3328          | 0.8484   | 0.8482 |
+| 0.0001        | 9.0   | 4095 | 1.3534          | 0.8418   | 0.8416 |
+| 0.0165        | 10.0  | 4550 | 1.4137          | 0.8418   | 0.8415 |
 
 
 ### Framework versions

bert-large-uncased_best/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Rejected",
+    "1": "Accepted"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Accepted": 1,
+    "Rejected": 0
+  },
+  "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",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

bert-large-uncased_best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426c4e9a0a2490149e1fc026871b3f1e54946f71fa41f6edc6b397c626139b00
+size 1340622760

bert-large-uncased_best/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

bert-large-uncased_best/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

bert-large-uncased_best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553e61d724fc0884b0f9eb7c628a2a275cb4f93f4def704b76307450f074c4ef
+size 5432

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634f22e086d642b6ccbed9363ec7e29841eb80abf1bf4b38a10a840daa9567a0
+oid sha256:426c4e9a0a2490149e1fc026871b3f1e54946f71fa41f6edc6b397c626139b00
 size 1340622760