jarvisss

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert/distilbert-base-uncased
+base_model: google-bert/bert-base-cased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
 
 ## Model description
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 18   | 3.0936          | 0.3333   |
+| No log        | 1.0   | 18   | 3.2827          | 0.0      |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "google-bert/bert-base-cased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "28",
     "1": "Audi",
@@ -32,6 +33,7 @@
     "20": "iPhone"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "28": 0,
     "Audi": 1,
@@ -55,17 +57,17 @@
     "Zak 'The Man' Rowton": 19,
     "iPhone": 20
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a61f587e95108babe0709e23e9371ded6e82210f553dc6e7d00d6eefff01aa7
-size 267891012
+oid sha256:f64908e63038e6177bf4f61724303ae3a3b6b259b330a28cb8733c33c5e842be
+size 433329212

runs/Apr24_15-29-29_ZaksMSI/events.out.tfevents.1713990571.ZaksMSI.4012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bb896c6cfed330fea238a54d07e24651ea48cd57704e357014f66b13a98520
+size 6277

tokenizer_config.json

@@ -43,13 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec0df6e43cdbce213b3df1be91eb19494728cc7b123e6dee802e7f09444cc3c
+oid sha256:4e7275ea9852247fc5e165e4a324391e9a8403083432d196e7175dff959b16a1
 size 4920