Training in progress, step 240

config.json

@@ -0,0 +1,94 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "dtype": null,
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "bert",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "return_dict": true,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 2,
+    "use_cache": true,
+    "vocab_size": 51
+  },
+  "decoder_start_token_id": 2,
+  "dtype": "float32",
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "dtype": null,
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "bert",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "return_dict": true,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 2,
+    "use_cache": true,
+    "vocab_size": 51
+  },
+  "eos_token_id": 0,
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 3,
+  "transformers_version": "5.0.0",
+  "unk_token_id": null,
+  "use_cache": false
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 2,
+  "eos_token_id": [
+    0
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7897ffc6ce406484645e6c18881784dc1a1481d36d75e5b4369f53b83905a1ea
+size 31203500

tokenizer.json

@@ -0,0 +1,295 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[EOS]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[EOS]": {
+        "id": "[EOS]",
+        "ids": [
+          0
+        ],
+        "tokens": [
+          "[EOS]"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "[EOS]": 0,
+      "[UNK]": 1,
+      "[CLS]": 2,
+      "[PAD]": 3,
+      "+": 4,
+      "-": 5,
+      "0": 6,
+      "1": 7,
+      "2": 8,
+      "3": 9,
+      "4": 10,
+      "5": 11,
+      "6": 12,
+      "7": 13,
+      "8": 14,
+      "9": 15,
+      "10": 16,
+      "99": 17,
+      "11": 18,
+      "98": 19,
+      "97": 20,
+      "12": 21,
+      "13": 22,
+      "96": 23,
+      "14": 24,
+      "95": 25,
+      "15": 26,
+      "94": 27,
+      "16": 28,
+      "93": 29,
+      "92": 30,
+      "17": 31,
+      "18": 32,
+      "91": 33,
+      "90": 34,
+      "19": 35,
+      "89": 36,
+      "20": 37,
+      "21": 38,
+      "88": 39,
+      "22": 40,
+      "87": 41,
+      "23": 42,
+      "86": 43,
+      "24": 44,
+      "85": 45,
+      "25": 46,
+      "84": 47,
+      "83": 48,
+      "26": 49,
+      "82": 50
+    },
+    "merges": [
+      [
+        "1",
+        "0"
+      ],
+      [
+        "9",
+        "9"
+      ],
+      [
+        "1",
+        "1"
+      ],
+      [
+        "9",
+        "8"
+      ],
+      [
+        "9",
+        "7"
+      ],
+      [
+        "1",
+        "2"
+      ],
+      [
+        "1",
+        "3"
+      ],
+      [
+        "9",
+        "6"
+      ],
+      [
+        "1",
+        "4"
+      ],
+      [
+        "9",
+        "5"
+      ],
+      [
+        "1",
+        "5"
+      ],
+      [
+        "9",
+        "4"
+      ],
+      [
+        "1",
+        "6"
+      ],
+      [
+        "9",
+        "3"
+      ],
+      [
+        "9",
+        "2"
+      ],
+      [
+        "1",
+        "7"
+      ],
+      [
+        "1",
+        "8"
+      ],
+      [
+        "9",
+        "1"
+      ],
+      [
+        "9",
+        "0"
+      ],
+      [
+        "1",
+        "9"
+      ],
+      [
+        "8",
+        "9"
+      ],
+      [
+        "2",
+        "0"
+      ],
+      [
+        "2",
+        "1"
+      ],
+      [
+        "8",
+        "8"
+      ],
+      [
+        "2",
+        "2"
+      ],
+      [
+        "8",
+        "7"
+      ],
+      [
+        "2",
+        "3"
+      ],
+      [
+        "8",
+        "6"
+      ],
+      [
+        "2",
+        "4"
+      ],
+      [
+        "8",
+        "5"
+      ],
+      [
+        "2",
+        "5"
+      ],
+      [
+        "8",
+        "4"
+      ],
+      [
+        "8",
+        "3"
+      ],
+      [
+        "2",
+        "6"
+      ],
+      [
+        "8",
+        "2"
+      ]
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bcefde39caa530aaefe67d3bc305c31a9c028a2737bc061d1dd86faa7e72c9d
+size 5329