Training in progress, step 500

.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 +1,202 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-ah",
+    "2": "I-ah",
+    "3": "B-at",
+    "4": "I-at",
+    "5": "B-az",
+    "6": "I-az",
+    "7": "B-g_",
+    "8": "I-g_",
+    "9": "B-gc",
+    "10": "I-gc",
+    "11": "B-gh",
+    "12": "I-gh",
+    "13": "B-gl",
+    "14": "I-gl",
+    "15": "B-gp",
+    "16": "I-gp",
+    "17": "B-gq",
+    "18": "I-gq",
+    "19": "B-gr",
+    "20": "I-gr",
+    "21": "B-gs",
+    "22": "I-gs",
+    "23": "B-gt",
+    "24": "I-gt",
+    "25": "B-gu",
+    "26": "I-gu",
+    "27": "B-i_",
+    "28": "I-i_",
+    "29": "B-ia",
+    "30": "I-ia",
+    "31": "B-ic",
+    "32": "I-ic",
+    "33": "B-if",
+    "34": "I-if",
+    "35": "B-io",
+    "36": "I-io",
+    "37": "B-mn",
+    "38": "I-mn",
+    "39": "B-mt",
+    "40": "I-mt",
+    "41": "B-mr",
+    "42": "I-mr",
+    "43": "B-o_",
+    "44": "I-o_",
+    "45": "B-oa",
+    "46": "I-oa",
+    "47": "B-oc",
+    "48": "I-oc",
+    "49": "B-oe",
+    "50": "I-oe",
+    "51": "B-om",
+    "52": "I-om",
+    "53": "B-op",
+    "54": "I-op",
+    "55": "B-or",
+    "56": "I-or",
+    "57": "B-p_",
+    "58": "I-p_",
+    "59": "B-pb",
+    "60": "I-pb",
+    "61": "B-pc",
+    "62": "I-pc",
+    "63": "B-pd",
+    "64": "I-pd",
+    "65": "B-pf",
+    "66": "I-pf",
+    "67": "B-pm",
+    "68": "I-pm",
+    "69": "B-pp",
+    "70": "I-pp",
+    "71": "B-ps",
+    "72": "I-ps",
+    "73": "B-td",
+    "74": "I-td",
+    "75": "B-tf",
+    "76": "I-tf",
+    "77": "B-th",
+    "78": "I-th",
+    "79": "B-ti",
+    "80": "I-ti",
+    "81": "B-tm",
+    "82": "I-tm",
+    "83": "B-ty",
+    "84": "I-ty"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-ah": 1,
+    "B-at": 3,
+    "B-az": 5,
+    "B-g_": 7,
+    "B-gc": 9,
+    "B-gh": 11,
+    "B-gl": 13,
+    "B-gp": 15,
+    "B-gq": 17,
+    "B-gr": 19,
+    "B-gs": 21,
+    "B-gt": 23,
+    "B-gu": 25,
+    "B-i_": 27,
+    "B-ia": 29,
+    "B-ic": 31,
+    "B-if": 33,
+    "B-io": 35,
+    "B-mn": 37,
+    "B-mr": 41,
+    "B-mt": 39,
+    "B-o_": 43,
+    "B-oa": 45,
+    "B-oc": 47,
+    "B-oe": 49,
+    "B-om": 51,
+    "B-op": 53,
+    "B-or": 55,
+    "B-p_": 57,
+    "B-pb": 59,
+    "B-pc": 61,
+    "B-pd": 63,
+    "B-pf": 65,
+    "B-pm": 67,
+    "B-pp": 69,
+    "B-ps": 71,
+    "B-td": 73,
+    "B-tf": 75,
+    "B-th": 77,
+    "B-ti": 79,
+    "B-tm": 81,
+    "B-ty": 83,
+    "I-ah": 2,
+    "I-at": 4,
+    "I-az": 6,
+    "I-g_": 8,
+    "I-gc": 10,
+    "I-gh": 12,
+    "I-gl": 14,
+    "I-gp": 16,
+    "I-gq": 18,
+    "I-gr": 20,
+    "I-gs": 22,
+    "I-gt": 24,
+    "I-gu": 26,
+    "I-i_": 28,
+    "I-ia": 30,
+    "I-ic": 32,
+    "I-if": 34,
+    "I-io": 36,
+    "I-mn": 38,
+    "I-mr": 42,
+    "I-mt": 40,
+    "I-o_": 44,
+    "I-oa": 46,
+    "I-oc": 48,
+    "I-oe": 50,
+    "I-om": 52,
+    "I-op": 54,
+    "I-or": 56,
+    "I-p_": 58,
+    "I-pb": 60,
+    "I-pc": 62,
+    "I-pd": 64,
+    "I-pf": 66,
+    "I-pm": 68,
+    "I-pp": 70,
+    "I-ps": 72,
+    "I-td": 74,
+    "I-tf": 76,
+    "I-th": 78,
+    "I-ti": 80,
+    "I-tm": 82,
+    "I-ty": 84,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "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 sha256:8e9cb4f7f1e90679b89a884583e876590aef239160b14de0d9961b6f0205e5ff
+size 2235760364

runs/Mar04_00-21-19_n21/events.out.tfevents.1709508081.n21.1060809.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad274b0bf1bb99c54cb7f3fec26452cb1d5f27a14429b5f99a164234dde53fda
+size 7291

runs/Mar04_23-10-18_g11/events.out.tfevents.1709590223.g11.840720.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:231961c6b25dbab6499c7f02ef60b1b43edc5cb2fec7e0a291020571b0147797
+size 7919

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa291bfa97d66d7fb8430f5288946c29885347653dc5902c0f31eba8bd89df6
+size 4728