SudhaBhattacharjee/Classifier3_e5-small-v2

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: microsoft/deberta-v3-base
+base_model: intfloat/e5-small-v2
 tags:
 - generated_from_trainer
 metrics:
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # RewardModel_deberta-v3-large
 
-This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
+This model is a fine-tuned version of [intfloat/e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1138
+- Loss: 0.5170
 - Accuracy: 1.0
 - F1: 1.0
 - Roc Auc: 1.0
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Roc Auc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:-------:|
-| No log        | 1.0   | 20   | 0.6241          | 0.98     | 0.9800 | 0.98    |
-| No log        | 2.0   | 40   | 0.1138          | 1.0      | 1.0    | 1.0     |
-| No log        | 3.0   | 60   | 0.0122          | 1.0      | 1.0    | 1.0     |
-| No log        | 4.0   | 80   | 0.0050          | 1.0      | 1.0    | 1.0     |
-| 0.2382        | 5.0   | 100  | 0.0040          | 1.0      | 1.0    | 1.0     |
+| No log        | 1.0   | 20   | 0.6583          | 0.56     | 0.4544 | 0.56    |
+| No log        | 2.0   | 40   | 0.5170          | 1.0      | 1.0    | 1.0     |
+| No log        | 3.0   | 60   | 0.3450          | 1.0      | 1.0    | 1.0     |
+| No log        | 4.0   | 80   | 0.2474          | 1.0      | 1.0    | 1.0     |
+| 0.4644        | 5.0   | 100  | 0.2256          | 1.0      | 1.0    | 1.0     |
 
 
 ### Framework versions

config.json

@@ -1,44 +1,33 @@
 {
   "architectures": [
-    "DebertaV2ForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "id2label": {
     "0": "Bad",
     "1": "Good"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "label2id": {
     "Bad": 0,
     "Good": 1
   },
-  "layer_norm_eps": 1e-07,
-  "legacy": true,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 768,
-  "pos_att_type": [
-    "p2c",
-    "c2p"
-  ],
-  "position_biased_input": false,
-  "position_buckets": 256,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "relative_attention": true,
-  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.54.0",
-  "type_vocab_size": 0,
-  "vocab_size": 128100
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242046661cd54cbe7e61ad5bdfdcfd9d83793dcfc65c845de9bc7b23b12e944a
-size 737719272
+oid sha256:d8c44723ee2b81c0cbc199e001934cad195f42b2a21fa5105b5a207c86279c41
+size 133466376

runs/Aug04_06-55-51_5cb435fcb73d/events.out.tfevents.1754290556.5cb435fcb73d.3700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f640cdbcfb88d4791372c21fc12cb42a4fef36f7ed1838cca980ccca7db0c2ef
+size 5143

runs/Aug04_06-57-41_5cb435fcb73d/events.out.tfevents.1754290674.5cb435fcb73d.3700.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b289a6a447875a270ad9b9b45ddfeae23ee95a13504fafc804be18c24c4e4b
+size 7723

runs/Aug04_06-57-41_5cb435fcb73d/events.out.tfevents.1754290733.5cb435fcb73d.3700.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1878e6fca5489fca1e0d5fed97d203ee57529d1699f37f4060dc3dfe259587ce
+size 500

special_tokens_map.json

@@ -1,14 +1,36 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[CLS]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "[SEP]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128000": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,19 +41,16 @@
       "special": true
     }
   },
-  "bos_token": "[CLS]",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
+  "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b5c2d9bcaca06399ffdcb75b743d48d0f7948a93af8ddd83314295f263e813
+oid sha256:87e5d2bfd2ef78bc63e8c86d7c383e55c75bb9f5104cea78c9960b448c6ecabb
 size 5368