End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: distilbert/distilbert-base-uncased
+license: mit
+base_model: roberta-large
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # f1_score_model
 
-This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6515
-- Accuracy: 0.6429
-- F1: 0.5562
-- Precision: 0.5129
-- Recall: 0.6429
+- Loss: 0.6087
+- Accuracy: 0.7016
+- F1: 0.6217
+- Precision: 0.5813
+- Recall: 0.7016
 
 ## Model description
 
@@ -45,18 +45,19 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 16
-- eval_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.6062        | 2.49  | 500  | 0.6515          | 0.6429   | 0.5562 | 0.5129    | 0.6429 |
-| 0.42          | 4.98  | 1000 | 0.7364          | 0.6454   | 0.5587 | 0.5154    | 0.6454 |
+| 0.4236        | 4.98  | 1000 | 0.6087          | 0.7016   | 0.6217 | 0.5813    | 0.7016 |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,15 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "roberta-large",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
     "0": "llama",
     "1": "mistral",
@@ -15,23 +17,24 @@
     "3": "gpt4"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "gpt3.5": 2,
     "gpt4": 3,
     "llama": 0,
     "mistral": 1
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aeda606cbc083a7b8c15b9d7d98f6585eaf906c6157bbfa4f4cccccecec01e5
-size 267838720
+oid sha256:739d1b4afbd730134024c130a2a4330cb9775e4ee043144eff1c6a662e38d807
+size 1421503616

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,55 +1,57 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a51b1767cd7ffb46b2e1b3e2baf9699e32ad86700fb8ef64dc480bf2fdeb38f
-size 4920
+oid sha256:554a9ec1e94ad4ac4478dfe8245f5a5868283988276526e76d924e932aed756e
+size 4856