Training in progress, epoch 1

config.json

@@ -1,69 +1,36 @@
 {
-  "_name_or_path": "shubhamgantayat/my_pii_model_gpt_2",
-  "activation_function": "gelu_new",
+  "_name_or_path": "google-bert/bert-large-uncased",
   "architectures": [
-    "GPT2ForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
-    "0": "I-STREET_ADDRESS",
-    "1": "I-ID_NUM",
-    "2": "I-NAME_STUDENT",
-    "3": "B-PHONE_NUM",
-    "4": "B-USERNAME",
-    "5": "B-EMAIL",
-    "6": "I-PHONE_NUM",
-    "7": "O",
-    "8": "B-STREET_ADDRESS",
-    "9": "B-URL_PERSONAL",
-    "10": "I-URL_PERSONAL",
-    "11": "B-ID_NUM",
-    "12": "B-NAME_STUDENT"
+    "0": "O",
+    "1": "B-CHEMICAL",
+    "2": "I-CHEMICAL"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
-    "B-EMAIL": 5,
-    "B-ID_NUM": 11,
-    "B-NAME_STUDENT": 12,
-    "B-PHONE_NUM": 3,
-    "B-STREET_ADDRESS": 8,
-    "B-URL_PERSONAL": 9,
-    "B-USERNAME": 4,
-    "I-ID_NUM": 1,
-    "I-NAME_STUDENT": 2,
-    "I-PHONE_NUM": 6,
-    "I-STREET_ADDRESS": 0,
-    "I-URL_PERSONAL": 10,
-    "O": 7
-  },
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
+    "B-CHEMICAL": 1,
+    "I-CHEMICAL": 2,
+    "O": 0
   },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78365c6438b0395b4edae75cba9944facdc62dc0ccfa3deef0a73c1d87edd617
-size 497814348
+oid sha256:75367bea95c9fae99b164ae6613353b33561e75fcb27a8e816194e43c47ed2d8
+size 1336428268

runs/Apr15_07-08-01_49dea0775c7f/events.out.tfevents.1713164882.49dea0775c7f.185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227adc7f10d11bf1bfa836318585575f66e1e89c7abd800eb55b3fa8c533016b
+size 4785

runs/Apr15_07-08-21_49dea0775c7f/events.out.tfevents.1713164901.49dea0775c7f.185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73510e640f2f058dca711a809fd1e22914fce4cfa4394b2c7d09e9a27a4064a
+size 5267

special_tokens_map.json

@@ -1,18 +1,6 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
   "pad_token": {
     "content": "[PAD]",
     "lstrip": false,
@@ -20,11 +8,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,16 +1,39 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50257": {
-      "content": "[PAD]",
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -18,15 +41,15 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "max_length": 1024,
-  "model_max_length": 1024,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
   "pad_token": "[PAD]",
-  "stride": 0,
-  "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<|endoftext|>"
+  "sep_token": "[SEP]",
+  "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 sha256:833730114593cda1e55abb055be521a2e929a3cb3c37a4ee4ef59b9b09ddf58e
+oid sha256:1084e7de888274ddc87d31bd540978e580582d484e5c94bfefc690032859c32e
 size 4984