Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+vocab.txt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,104 @@
+{
+  "_name_or_path": "imvladikon/alephbertgimmel-base-512",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "S-ANG",
+    "1": "B-ANG",
+    "2": "I-ANG",
+    "3": "E-ANG",
+    "4": "S-DUC",
+    "5": "B-DUC",
+    "6": "I-DUC",
+    "7": "E-DUC",
+    "8": "B-EVE",
+    "9": "E-EVE",
+    "10": "S-EVE",
+    "11": "I-EVE",
+    "12": "S-FAC",
+    "13": "B-FAC",
+    "14": "E-FAC",
+    "15": "I-FAC",
+    "16": "S-GPE",
+    "17": "B-GPE",
+    "18": "E-GPE",
+    "19": "I-GPE",
+    "20": "S-LOC",
+    "21": "B-LOC",
+    "22": "E-LOC",
+    "23": "I-LOC",
+    "24": "O",
+    "25": "S-ORG",
+    "26": "B-ORG",
+    "27": "E-ORG",
+    "28": "I-ORG",
+    "29": "B-PER",
+    "30": "I-PER",
+    "31": "E-PER",
+    "32": "S-PER",
+    "33": "B-WOA",
+    "34": "E-WOA",
+    "35": "I-WOA",
+    "36": "S-WOA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANG": 1,
+    "B-DUC": 5,
+    "B-EVE": 8,
+    "B-FAC": 13,
+    "B-GPE": 17,
+    "B-LOC": 21,
+    "B-ORG": 26,
+    "B-PER": 29,
+    "B-WOA": 33,
+    "E-ANG": 3,
+    "E-DUC": 7,
+    "E-EVE": 9,
+    "E-FAC": 14,
+    "E-GPE": 18,
+    "E-LOC": 22,
+    "E-ORG": 27,
+    "E-PER": 31,
+    "E-WOA": 34,
+    "I-ANG": 2,
+    "I-DUC": 6,
+    "I-EVE": 11,
+    "I-FAC": 15,
+    "I-GPE": 19,
+    "I-LOC": 23,
+    "I-ORG": 28,
+    "I-PER": 30,
+    "I-WOA": 35,
+    "O": 24,
+    "S-ANG": 0,
+    "S-DUC": 4,
+    "S-EVE": 10,
+    "S-FAC": 12,
+    "S-GPE": 16,
+    "S-LOC": 20,
+    "S-ORG": 25,
+    "S-PER": 32,
+    "S-WOA": 36
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb86da5ffcc942843ccc468ce11124260c7f715cbf1bfd678ee180d4f1b57e8
+size 735156180

runs/Dec25_09-19-38_soc-5CG223442L/events.out.tfevents.1703488779.soc-5CG223442L

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0c75c752e4859aded141e998085e1c675e7495bd5ab0a36b1b78cde592e7de
+size 6218

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "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
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a696052564d3c4456753011632228b5bb8947ce2ecb0cf750b90b14be422f72b
+size 4155

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8eb3d9f7ef0b8f036227785d1dbdc90926ba6816d3899736832d912ccd52e2
+size 1296919