Training in progress, epoch 1

config.json

@@ -5,9 +5,9 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 13,
+  "bos_token_id": 103,
   "embd_pdrop": 0.1,
-  "eos_token_id": 14,
+  "eos_token_id": 104,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -17,7 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 15,
+  "pad_token_id": 105,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -34,7 +34,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 16
+  "vocab_size": 109
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8192b65d651ae379d926ab2ac5689f2b700f0349201837692f97c7a5ac3166
-size 343433856
+oid sha256:c611a34d822851c990b4056427b66d5d320373b4208f3001fa3ed40f385719fb
+size 343719552

tokenizer.json

@@ -0,0 +1,226 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 103,
+      "content": "[BOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 104,
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 105,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "[BOS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[EOS]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "[BOS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[EOS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[EOS]",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[BOS]": {
+        "id": "[BOS]",
+        "ids": [
+          103
+        ],
+        "tokens": [
+          "[BOS]"
+        ]
+      },
+      "[EOS]": {
+        "id": "[EOS]",
+        "ids": [
+          104
+        ],
+        "tokens": [
+          "[EOS]"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "0": 0,
+      "1": 1,
+      "2": 2,
+      "3": 3,
+      "4": 4,
+      "5": 5,
+      "6": 6,
+      "7": 7,
+      "8": 8,
+      "9": 9,
+      "10": 10,
+      "11": 11,
+      "12": 12,
+      "13": 13,
+      "14": 14,
+      "15": 15,
+      "16": 16,
+      "17": 17,
+      "18": 18,
+      "19": 19,
+      "20": 20,
+      "21": 21,
+      "22": 22,
+      "23": 23,
+      "24": 24,
+      "25": 25,
+      "26": 26,
+      "27": 27,
+      "28": 28,
+      "29": 29,
+      "30": 30,
+      "31": 31,
+      "32": 32,
+      "33": 33,
+      "34": 34,
+      "35": 35,
+      "36": 36,
+      "37": 37,
+      "38": 38,
+      "39": 39,
+      "40": 40,
+      "41": 41,
+      "42": 42,
+      "43": 43,
+      "44": 44,
+      "45": 45,
+      "46": 46,
+      "47": 47,
+      "48": 48,
+      "49": 49,
+      "50": 50,
+      "51": 51,
+      "52": 52,
+      "53": 53,
+      "54": 54,
+      "55": 55,
+      "56": 56,
+      "57": 57,
+      "58": 58,
+      "59": 59,
+      "60": 60,
+      "61": 61,
+      "62": 62,
+      "63": 63,
+      "64": 64,
+      "65": 65,
+      "66": 66,
+      "67": 67,
+      "68": 68,
+      "69": 69,
+      "70": 70,
+      "71": 71,
+      "72": 72,
+      "73": 73,
+      "74": 74,
+      "75": 75,
+      "76": 76,
+      "77": 77,
+      "78": 78,
+      "79": 79,
+      "80": 80,
+      "81": 81,
+      "82": 82,
+      "83": 83,
+      "84": 84,
+      "85": 85,
+      "86": 86,
+      "87": 87,
+      "88": 88,
+      "89": 89,
+      "90": 90,
+      "91": 91,
+      "92": 92,
+      "93": 93,
+      "94": 94,
+      "95": 95,
+      "96": 96,
+      "97": 97,
+      "98": 98,
+      "99": 99,
+      "+": 100,
+      "*": 101,
+      "=": 102,
+      "[BOS]": 103,
+      "[EOS]": 104,
+      "[PAD]": 105
+    },
+    "unk_token": "[UNK]"
+  }
+}

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "13": {
+    "103": {
       "content": "[BOS]",
       "lstrip": false,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "14": {
+    "104": {
       "content": "[EOS]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "15": {
+    "105": {
       "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
@@ -28,7 +28,7 @@
   "bos_token": "[BOS]",
   "clean_up_tokenization_spaces": true,
   "eos_token": "[EOS]",
-  "model_max_length": 64,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "tokenizer_class": "CharacterTokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d001b64fce175c741ad3c4f6c7c67a4d2e67bbc43d57fcbb8c9eec926b19f8
-size 4527
+oid sha256:83e1798f23cb48ad2a135c1f84e94622430ecc4956d0bafaf20524754cabd041
+size 4655