reevan/roberta_rom

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: bert-base-uncased
+license: mit
+base_model: FacebookAI/roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7059
-- Precision: 0.7644
-- Recall: 0.7468
-- F1: 0.7509
-- Accuracy: 0.7471
+- Loss: 0.6917
+- Precision: 0.7168
+- Recall: 0.7053
+- F1: 0.7088
+- Accuracy: 0.726
 
 ## Model description
 
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 238  | 0.9040          | 0.5971    | 0.5675 | 0.5718 | 0.5670   |
-| No log        | 2.0   | 476  | 0.7639          | 0.6792    | 0.6517 | 0.6549 | 0.6513   |
-| 0.8758        | 3.0   | 714  | 0.6876          | 0.7305    | 0.7120 | 0.7162 | 0.7126   |
-| 0.8758        | 4.0   | 952  | 0.6862          | 0.7599    | 0.7507 | 0.7532 | 0.7510   |
-| 0.4678        | 5.0   | 1190 | 0.7059          | 0.7644    | 0.7468 | 0.7509 | 0.7471   |
+| 0.9791        | 1.0   | 1489 | 0.8084          | 0.6198    | 0.6089 | 0.6093 | 0.6385   |
+| 0.8129        | 2.0   | 2978 | 0.7380          | 0.6635    | 0.6500 | 0.6531 | 0.6735   |
+| 0.6937        | 3.0   | 4467 | 0.7328          | 0.6826    | 0.6716 | 0.6745 | 0.691    |
+| 0.6002        | 4.0   | 5956 | 0.6901          | 0.7110    | 0.6951 | 0.6973 | 0.7205   |
+| 0.5362        | 5.0   | 7445 | 0.6917          | 0.7168    | 0.7053 | 0.7088 | 0.726    |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.40.0
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.0
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "FacebookAI/roberta-base",
   "architectures": [
-    "BertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -21,17 +22,17 @@
     "Neutral": 2,
     "Positive": 1
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8819237d080e3d579869decf7fc3728b8ecb673d3b5c7066ebb0612dc6c6e9eb
-size 437961724
+oid sha256:b297ca6257d8293120303e5db9f107f590fbf16009373f1bddb3437f9573a11d
+size 498615900

runs/Apr23_07-26-18_74091af1fdb5/events.out.tfevents.1713857181.74091af1fdb5.150.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b82c53d417fcdfe302ccf92eb83e815120121a003aec2af224df9b04c9a616
+size 10477

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": "BertTokenizer",
-  "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:b8b01a2373714dfdee7b3ca03a642f36acdec62f3b0b2995732a8c57e54860dd
-size 4856
+oid sha256:05c9f34d2e758e42177de593150ac6a6ad2b34ecadcc9a3212d42805b637784b
+size 4984