Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "shubhamgantayat/my_pii_model_gpt_2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForTokenClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d20f958ab17d762e9be59207ae78e685dff5ea74d5d5470c270fd7e014a998
+size 497814348

runs/Apr04_05-15-13_fc2af777fbcd/events.out.tfevents.1712207715.fc2af777fbcd.356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22175c2c01fe999fc08c7cd491a4e16bee5aff70c0d9f7167453cef11edf4bde
+size 7323

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": 1024,
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833730114593cda1e55abb055be521a2e929a3cb3c37a4ee4ef59b9b09ddf58e
+size 4984