Training complete

README.md

@@ -1,7 +1,6 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: bert-base-uncased
+base_model: mrm8488/electricidad-base-discriminator
 tags:
 - classification
 - generated_from_trainer
@@ -17,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # chat-prompts
 
-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 [mrm8488/electricidad-base-discriminator](https://huggingface.co/mrm8488/electricidad-base-discriminator) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.1966
-- Accuracy: 0.4471
+- Loss: 4.8844
+- Accuracy: 0.1647
 
 ## Model description
 
@@ -51,21 +50,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 22   | 5.1516          | 0.0059   |
-| No log        | 2.0   | 44   | 4.9859          | 0.0235   |
-| No log        | 3.0   | 66   | 4.8969          | 0.0235   |
-| No log        | 4.0   | 88   | 4.7226          | 0.1118   |
-| No log        | 5.0   | 110  | 4.5940          | 0.1235   |
-| No log        | 6.0   | 132  | 4.4824          | 0.2176   |
-| No log        | 7.0   | 154  | 4.3730          | 0.2824   |
-| No log        | 8.0   | 176  | 4.2695          | 0.3824   |
-| No log        | 9.0   | 198  | 4.2165          | 0.4353   |
-| No log        | 10.0  | 220  | 4.1966          | 0.4471   |
+| No log        | 1.0   | 22   | 5.1285          | 0.0059   |
+| No log        | 2.0   | 44   | 5.1238          | 0.0118   |
+| No log        | 3.0   | 66   | 5.1159          | 0.0118   |
+| No log        | 4.0   | 88   | 5.0894          | 0.0118   |
+| No log        | 5.0   | 110  | 5.0602          | 0.0176   |
+| No log        | 6.0   | 132  | 5.0048          | 0.0294   |
+| No log        | 7.0   | 154  | 4.9572          | 0.0706   |
+| No log        | 8.0   | 176  | 4.9201          | 0.0941   |
+| No log        | 9.0   | 198  | 4.8930          | 0.1294   |
+| No log        | 10.0  | 220  | 4.8844          | 0.1647   |
 
 
 ### Framework versions
 
 - Transformers 4.47.0
-- Pytorch 2.5.1+cu121
+- Pytorch 2.5.1+cu124
 - Datasets 3.2.0
 - Tokenizers 0.21.0

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "mrm8488/electricidad-base-discriminator",
   "architectures": [
-    "BertForSequenceClassification"
+    "ElectraForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "embedding_size": 768,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -355,15 +355,19 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "electra",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 31002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9940cb5c93dceebd52cdc4da91a0904950bfe226ed2779d003cab3218d8bc717
-size 438472340
+oid sha256:aa9983a57965077200b57c2d0a75fcb4fa0d40108fee763e82bb370ec76b9c7d
+size 439947500

tokenizer_config.json

@@ -1,39 +1,39 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "4": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "5": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,16 +41,18 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "ElectraTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb93df72fdc84ca6dcf11cedf6471d14c0f1f43e26a31bace1b83a0ae3578bf
+oid sha256:66bfc2d5202dfd51fdfc4df0477042812da0d71dd6d659b8a772fc0cb4222b0e
 size 5304