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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-abb",
+    "1": "B-adj",
+    "2": "B-adv",
+    "3": "B-conj",
+    "4": "B-fw",
+    "5": "B-int",
+    "6": "B-n",
+    "7": "B-num",
+    "8": "B-part",
+    "9": "B-ppm",
+    "10": "B-pron",
+    "11": "B-punc",
+    "12": "B-sb",
+    "13": "B-tn",
+    "14": "B-v",
+    "15": "I-abb",
+    "16": "I-adj",
+    "17": "I-adv",
+    "18": "I-conj",
+    "19": "I-fw",
+    "20": "I-int",
+    "21": "I-n",
+    "22": "I-num",
+    "23": "I-part",
+    "24": "I-ppm",
+    "25": "I-pron",
+    "26": "I-punc",
+    "27": "I-tn",
+    "28": "I-v"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-abb": 0,
+    "B-adj": 1,
+    "B-adv": 2,
+    "B-conj": 3,
+    "B-fw": 4,
+    "B-int": 5,
+    "B-n": 6,
+    "B-num": 7,
+    "B-part": 8,
+    "B-ppm": 9,
+    "B-pron": 10,
+    "B-punc": 11,
+    "B-sb": 12,
+    "B-tn": 13,
+    "B-v": 14,
+    "I-abb": 15,
+    "I-adj": 16,
+    "I-adv": 17,
+    "I-conj": 18,
+    "I-fw": 19,
+    "I-int": 20,
+    "I-n": 21,
+    "I-num": 22,
+    "I-part": 23,
+    "I-ppm": 24,
+    "I-pron": 25,
+    "I-punc": 26,
+    "I-tn": 27,
+    "I-v": 28
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4917c49683382c9a1ec5ab01fdded2bcd02997f4eec985f2e0ec0e6539b84dc
+size 1109925476

runs/Dec24_15-33-22_194344975db9/events.out.tfevents.1766590406.194344975db9.2899.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9479683bbe1066247ff6e6024910ffbaafc202c4d9387bc9149fe6544a31ea
+size 4184

runs/Dec24_15-35-58_194344975db9/events.out.tfevents.1766590562.194344975db9.4104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a809df26745587cc29aa778fb06df6469392ef789962ff9b35c0b9ed1320655d
+size 6338

runs/Dec24_15-37-37_194344975db9/events.out.tfevents.1766590660.194344975db9.4823.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5750080968d5c9f858cb4640a98af89153873b1d489f82319b703f5d19bef11
+size 7834

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208374f3822b73c2c46f34b6c47b43a6e79e6740e27f3e6f30087ad9d8139d2d
+size 5841