Training in progress, step 240

config.json

@@ -3,6 +3,7 @@
     "EncoderDecoderModel"
   ],
   "decoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "",
     "add_cross_attention": true,
     "architectures": null,
@@ -78,10 +79,11 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 53
+    "vocab_size": 52
   },
   "decoder_start_token_id": 2,
   "encoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "",
     "add_cross_attention": false,
     "architectures": null,
@@ -157,13 +159,13 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 53
+    "vocab_size": 52
   },
   "eos_token_id": 0,
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
   "pad_token_id": 3,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.48.3",
   "unk_token_id": null
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d9c024e1e3d7d9a5df926e8039a15c4bd48836b296e195124e53acefbe0cdb
-size 31207604
+oid sha256:b03dd9866b16e1489cafed293ba084665b8b1265bce390aca66bcbf89c4a9e18
+size 31205552

runs/Mar03_20-16-38_8d7670e5dd92/events.out.tfevents.1741032999.8d7670e5dd92.554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:222a6d199bb099581572501f0e2ea2fc213d84a59f2a30e38c05fce03befb4c2
+size 9132

runs/Mar03_20-17-28_8d7670e5dd92/events.out.tfevents.1741033049.8d7670e5dd92.554.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac091c7296f21a778a638ad702c2e0183ac4c578b17d5da027c1faeb9f0aef3
+size 9132

runs/Mar03_20-28-52_8d7670e5dd92/events.out.tfevents.1741033733.8d7670e5dd92.554.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27be49082bfed6bb918edc34e3f44496da5b43396b8c9b1fd423817cf8a0310d
+size 27952

tokenizer.json

@@ -95,6 +95,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "[EOS]": 0,
       "[UNK]": 1,
@@ -112,81 +113,188 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "=": 16,
+      "10": 16,
       "99": 17,
-      "10": 18,
-      "98": 19,
-      "11": 20,
+      "98": 18,
+      "11": 19,
+      "97": 20,
       "12": 21,
-      "97": 22,
+      "96": 22,
       "13": 23,
-      "96": 24,
+      "14": 24,
       "95": 25,
-      "14": 26,
+      "15": 26,
       "94": 27,
-      "15": 28,
+      "93": 28,
       "16": 29,
-      "93": 30,
-      "17": 31,
-      "92": 32,
-      "91": 33,
-      "18": 34,
-      "19": 35,
-      "90": 36,
+      "17": 30,
+      "92": 31,
+      "91": 32,
+      "18": 33,
+      "19": 34,
+      "90": 35,
+      "89": 36,
       "20": 37,
-      "89": 38,
+      "88": 38,
       "21": 39,
-      "88": 40,
-      "22": 41,
-      "87": 42,
+      "22": 40,
+      "87": 41,
+      "86": 42,
       "23": 43,
-      "86": 44,
-      "24": 45,
-      "85": 46,
+      "24": 44,
+      "85": 45,
+      "84": 46,
       "25": 47,
-      "84": 48,
-      "26": 49,
-      "83": 50,
-      "27": 51,
-      "82": 52
+      "26": 48,
+      "83": 49,
+      "27": 50,
+      "82": 51
     },
     "merges": [
-      "9 9",
-      "1 0",
-      "9 8",
-      "1 1",
-      "1 2",
-      "9 7",
-      "1 3",
-      "9 6",
-      "9 5",
-      "1 4",
-      "9 4",
-      "1 5",
-      "1 6",
-      "9 3",
-      "1 7",
-      "9 2",
-      "9 1",
-      "1 8",
-      "1 9",
-      "9 0",
-      "2 0",
-      "8 9",
-      "2 1",
-      "8 8",
-      "2 2",
-      "8 7",
-      "2 3",
-      "8 6",
-      "2 4",
-      "8 5",
-      "2 5",
-      "8 4",
-      "2 6",
-      "8 3",
-      "2 7",
-      "8 2"
+      [
+        "1",
+        "0"
+      ],
+      [
+        "9",
+        "9"
+      ],
+      [
+        "9",
+        "8"
+      ],
+      [
+        "1",
+        "1"
+      ],
+      [
+        "9",
+        "7"
+      ],
+      [
+        "1",
+        "2"
+      ],
+      [
+        "9",
+        "6"
+      ],
+      [
+        "1",
+        "3"
+      ],
+      [
+        "1",
+        "4"
+      ],
+      [
+        "9",
+        "5"
+      ],
+      [
+        "1",
+        "5"
+      ],
+      [
+        "9",
+        "4"
+      ],
+      [
+        "9",
+        "3"
+      ],
+      [
+        "1",
+        "6"
+      ],
+      [
+        "1",
+        "7"
+      ],
+      [
+        "9",
+        "2"
+      ],
+      [
+        "9",
+        "1"
+      ],
+      [
+        "1",
+        "8"
+      ],
+      [
+        "1",
+        "9"
+      ],
+      [
+        "9",
+        "0"
+      ],
+      [
+        "8",
+        "9"
+      ],
+      [
+        "2",
+        "0"
+      ],
+      [
+        "8",
+        "8"
+      ],
+      [
+        "2",
+        "1"
+      ],
+      [
+        "2",
+        "2"
+      ],
+      [
+        "8",
+        "7"
+      ],
+      [
+        "8",
+        "6"
+      ],
+      [
+        "2",
+        "3"
+      ],
+      [
+        "2",
+        "4"
+      ],
+      [
+        "8",
+        "5"
+      ],
+      [
+        "8",
+        "4"
+      ],
+      [
+        "2",
+        "5"
+      ],
+      [
+        "2",
+        "6"
+      ],
+      [
+        "8",
+        "3"
+      ],
+      [
+        "2",
+        "7"
+      ],
+      [
+        "8",
+        "2"
+      ]
     ]
   }
 }

tokenizer_config.json

@@ -33,9 +33,10 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "eos_token": "[EOS]",
+  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "tokenizer_class": "PreTrainedTokenizerFast"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f63b88acd55144274e10cea203015237b824f2edc459fa6207a536b4ed9983
-size 5112
+oid sha256:5608d1a93fb9374e9f46c3ce223d0542685ffcc484bd6cb7ef470ec61f58bb2f
+size 5496