RajuEEE/RewardModelSmallerQuestionWithTwoLabelsLengthJustified

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: bert-base-uncased
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # RewardModelSmallerQuestionWithTwoLabelsLengthJustified
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5852
-- F1: 0.6898
-- Roc Auc: 0.6909
-- Accuracy: 0.6836
+- Loss: 0.5034
+- F1: 0.7627
+- Roc Auc: 0.7617
+- Accuracy: 0.7576
 
 ## Model description
 
@@ -46,17 +46,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| 0.6905        | 1.0   | 145  | 0.6891          | 0.5293 | 0.5764  | 0.4727   |
-| 0.6889        | 2.0   | 290  | 0.6676          | 0.5502 | 0.5600  | 0.5382   |
-| 0.6488        | 3.0   | 435  | 0.6286          | 0.6410 | 0.6436  | 0.6364   |
-| 0.57          | 4.0   | 580  | 0.5852          | 0.6898 | 0.6909  | 0.6836   |
-| 0.3953        | 5.0   | 725  | 0.6550          | 0.6679 | 0.6691  | 0.6655   |
+| 0.6097        | 1.0   | 200  | 0.5931          | 0.6923 | 0.6915  | 0.6887   |
+| 0.5183        | 2.0   | 400  | 0.5034          | 0.7627 | 0.7617  | 0.7576   |
 
 
 ### Framework versions

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "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,
@@ -19,17 +20,17 @@
     "Bad": 0,
     "Good": 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": "multi_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "type_vocab_size": 2,
+  "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:a9e606e99c754ac907f667f52890bc7ea67349b34dbacbd6fca107eb259cc325
-size 437958648
+oid sha256:7e16b2a144ba2502bce72a170fc0d50840b4a16866383f444c23109f21c20042
+size 498612824

runs/Nov17_18-08-14_dd165b2cc716/events.out.tfevents.1700244504.dd165b2cc716.273.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2dcaf1f6911b0d16f12d88cea22395cae85290716b1f6248cc08862b96c101
+size 6292

runs/Nov17_18-08-14_dd165b2cc716/events.out.tfevents.1700244844.dd165b2cc716.273.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6575b284e094c86653fce8af2068936743a2883f8a2567cc9a4eb0a7b0e24d1c
+size 508

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:c36bbcbfb2a04f90cceacb3917a0cb86128cfe73adaf0aca488abf0539b0cf02
+oid sha256:293f8c28cb090a85251ec32d986d28051c33dfce8a097433d6e34488cc3fa045
 size 4664