RajuEEE/RewardModel_RobertaBase

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.5009
-- F1: 0.7738
-- Roc Auc: 0.7738
-- Accuracy: 0.7698
+- Loss: 0.6783
+- F1: 0.7879
+- Roc Auc: 0.825
+- Accuracy: 0.65
 
 ## Model description
 
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| No log        | 1.0   | 93   | 0.5440          | 0.7331 | 0.7341  | 0.7302   |
-| 0.648         | 2.0   | 186  | 0.5009          | 0.7738 | 0.7738  | 0.7698   |
-| 0.5515        | 3.0   | 279  | 0.4938          | 0.7545 | 0.7560  | 0.75     |
+| No log        | 1.0   | 10   | 0.6885          | 0.2222 | 0.5625  | 0.125    |
+| No log        | 2.0   | 20   | 0.6844          | 0.6207 | 0.725   | 0.45     |
+| No log        | 3.0   | 30   | 0.6783          | 0.7879 | 0.825   | 0.65     |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -29,7 +29,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "multi_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.41.2",
   "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 sha256:200b568f995f4af36f1f9a85868aad308152273cdb4dccc2ebc7639668f90e44
+oid sha256:3798861170f9d71666f8d027e4a6f165c954832666ab1753fa9a011fa88be543
 size 498612824

runs/Jun15_04-45-17_cebb3ca22ba1/events.out.tfevents.1718426719.cebb3ca22ba1.153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131b8ae102cb5b54c337b612295d391a505bb4954ce88d56555f82007426ae72
+size 6564

runs/Jun15_04-45-17_cebb3ca22ba1/events.out.tfevents.1718426833.cebb3ca22ba1.153.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda870c223de85e72b993b626fc10ceceb906fa2966ac3b4dc1313d5c6bb931c
+size 500

tokenizer.json

@@ -83,6 +83,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64fec19fc11b6813a2221bf67cba94d70e32d46a788c7adaaded5acbb329d0ab
-size 4600
+oid sha256:0f703e3b72ae27ef4f5e9a269353350f65f2c64b4d9943155ecf0cc2a7cb531d
+size 5112