Training in progress, epoch 1

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "prajjwal1/bert-tiny",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
   "id2label": {
     "0": "O",
     "1": "JOB",
@@ -25,6 +25,7 @@
     "13": "REVIEW"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 512,
   "label2id": {
     "ADDRESS": 10,
     "CITY": 7,
@@ -41,17 +42,17 @@
     "STATE": 6,
     "SUMMARY": 12
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
   "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": "4.26.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8809f9fa4d7a1a38b7d74c2527a5ea15e6001c4c189da9cddc26dea05131ac
-size 267892397
+oid sha256:9a9974b932afb6aa9e8743c2918859c0a7b1bf4792454028d07c7f950b9e2f65
+size 17568751

runs/Feb14_16-21-45_elytum-X670-AORUS-ELITE-AX/1676388109.3431861/events.out.tfevents.1676388109.elytum-X670-AORUS-ELITE-AX.1310810.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8a41d8d7b3878a2aa7ad7f5e519f43ad6dff1f475b5d48cfe3cdc1dbafa30a
+size 5708

runs/Feb14_16-21-45_elytum-X670-AORUS-ELITE-AX/events.out.tfevents.1676388109.elytum-X670-AORUS-ELITE-AX.1310810.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b457b66d06bfbb343bf885f1adf2b7e580379ce3ec50bba03cdcb10667ba881f
+size 5417

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,14 +1,16 @@
 {
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "distilbert-base-uncased",
+  "name_or_path": "prajjwal1/bert-tiny",
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,
   "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 sha256:4ab093afd426bd1f108d4dec91ee2ab41dc541cc09467165eb4da47c3aae9c7d
+oid sha256:9c21a6fb6bdfc66d6e22a3dbb0aa4ee0e99c4caad0267bb25f9130f2c826810b
 size 3515