Training in progress, step 240

config.json

@@ -0,0 +1,169 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_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,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 53
+  },
+  "decoder_start_token_id": 2,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_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,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 53
+  },
+  "eos_token_id": 0,
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "unk_token_id": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac7c4b030af2311d8f91d63fb8aeb6877b2633a699fb5997a6e6aec690a9698
+size 31207604

runs/Mar03_18-23-14_17f3732c0d2a/events.out.tfevents.1741026195.17f3732c0d2a.294.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245d061942cc1fd0a8f6cd20e2bf1087ee325b832ed792548b4c2d1e07e639d4
+size 9132

runs/Mar03_18-27-25_17f3732c0d2a/events.out.tfevents.1741026447.17f3732c0d2a.294.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe81013f9d7b9969d4fcb3566a9c62d5f8ac13ea89961dced1db2f6e3f2d2a5
+size 9133

runs/Mar03_18-28-39_17f3732c0d2a/events.out.tfevents.1741026520.17f3732c0d2a.294.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b7a1e58847b185c80eba356ff43fb4bc74b110e044ac34ce7d281b9ce6ab07
+size 8280

runs/Mar03_18-28-53_17f3732c0d2a/events.out.tfevents.1741026534.17f3732c0d2a.294.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363c75503798c4a3f26b904b2cc2fe516d2af4c5fcf38c860318fce9734e5056
+size 8280

runs/Mar03_18-31-06_17f3732c0d2a/events.out.tfevents.1741026671.17f3732c0d2a.5309.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ba8cd761e21be5ade66154d078a762e3af30030ae9736be04b42803b35a949
+size 27756

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,301 @@
+{
+  "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,
+      "=": 16,
+      "10": 17,
+      "99": 18,
+      "11": 19,
+      "98": 20,
+      "97": 21,
+      "12": 22,
+      "96": 23,
+      "13": 24,
+      "95": 25,
+      "14": 26,
+      "15": 27,
+      "94": 28,
+      "93": 29,
+      "16": 30,
+      "92": 31,
+      "17": 32,
+      "91": 33,
+      "18": 34,
+      "90": 35,
+      "19": 36,
+      "20": 37,
+      "89": 38,
+      "88": 39,
+      "21": 40,
+      "22": 41,
+      "87": 42,
+      "86": 43,
+      "23": 44,
+      "85": 45,
+      "24": 46,
+      "84": 47,
+      "25": 48,
+      "26": 49,
+      "83": 50,
+      "27": 51,
+      "82": 52
+    },
+    "merges": [
+      [
+        "1",
+        "0"
+      ],
+      [
+        "9",
+        "9"
+      ],
+      [
+        "1",
+        "1"
+      ],
+      [
+        "9",
+        "8"
+      ],
+      [
+        "9",
+        "7"
+      ],
+      [
+        "1",
+        "2"
+      ],
+      [
+        "9",
+        "6"
+      ],
+      [
+        "1",
+        "3"
+      ],
+      [
+        "9",
+        "5"
+      ],
+      [
+        "1",
+        "4"
+      ],
+      [
+        "1",
+        "5"
+      ],
+      [
+        "9",
+        "4"
+      ],
+      [
+        "9",
+        "3"
+      ],
+      [
+        "1",
+        "6"
+      ],
+      [
+        "9",
+        "2"
+      ],
+      [
+        "1",
+        "7"
+      ],
+      [
+        "9",
+        "1"
+      ],
+      [
+        "1",
+        "8"
+      ],
+      [
+        "9",
+        "0"
+      ],
+      [
+        "1",
+        "9"
+      ],
+      [
+        "2",
+        "0"
+      ],
+      [
+        "8",
+        "9"
+      ],
+      [
+        "8",
+        "8"
+      ],
+      [
+        "2",
+        "1"
+      ],
+      [
+        "2",
+        "2"
+      ],
+      [
+        "8",
+        "7"
+      ],
+      [
+        "8",
+        "6"
+      ],
+      [
+        "2",
+        "3"
+      ],
+      [
+        "8",
+        "5"
+      ],
+      [
+        "2",
+        "4"
+      ],
+      [
+        "8",
+        "4"
+      ],
+      [
+        "2",
+        "5"
+      ],
+      [
+        "2",
+        "6"
+      ],
+      [
+        "8",
+        "3"
+      ],
+      [
+        "2",
+        "7"
+      ],
+      [
+        "8",
+        "2"
+      ]
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cacb53e0478c7ce91f9c87fb0a4a7c183ec75c1fbcbc30e1ce6f482d290340e5
+size 5432