Training in progress, epoch 1

config.json

@@ -0,0 +1,97 @@
+{
+  "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-PERSON",
+    "1": "I-PERSON",
+    "2": "O",
+    "3": "B-ORGANIZATION",
+    "4": "B-LOCATION",
+    "5": "I-ORGANIZATION",
+    "6": "I-LOCATION",
+    "7": "B-DATE",
+    "8": "I-DATE",
+    "9": "B-TIME",
+    "10": "I-TIME",
+    "11": "B-MONEY",
+    "12": "I-MONEY",
+    "13": "B-FACILITY",
+    "14": "I-FACILITY",
+    "15": "B-URL",
+    "16": "I-URL",
+    "17": "B-PERCENT",
+    "18": "I-PERCENT",
+    "19": "B-LEN",
+    "20": "I-LEN",
+    "21": "B-AGO",
+    "22": "I-AGO",
+    "23": "B-LAW",
+    "24": "I-LAW",
+    "25": "B-PHONE",
+    "26": "I-PHONE",
+    "27": "B-EMAIL",
+    "28": "I-EMAIL",
+    "29": "B-ZIP",
+    "30": "B-TEMPERATURE",
+    "31": "I-TEMPERATURE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGO": 21,
+    "B-DATE": 7,
+    "B-EMAIL": 27,
+    "B-FACILITY": 13,
+    "B-LAW": 23,
+    "B-LEN": 19,
+    "B-LOCATION": 4,
+    "B-MONEY": 11,
+    "B-ORGANIZATION": 3,
+    "B-PERCENT": 17,
+    "B-PERSON": 0,
+    "B-PHONE": 25,
+    "B-TEMPERATURE": 30,
+    "B-TIME": 9,
+    "B-URL": 15,
+    "B-ZIP": 29,
+    "I-AGO": 22,
+    "I-DATE": 8,
+    "I-EMAIL": 28,
+    "I-FACILITY": 14,
+    "I-LAW": 24,
+    "I-LEN": 20,
+    "I-LOCATION": 6,
+    "I-MONEY": 12,
+    "I-ORGANIZATION": 5,
+    "I-PERCENT": 18,
+    "I-PERSON": 1,
+    "I-PHONE": 26,
+    "I-TEMPERATURE": 31,
+    "I-TIME": 10,
+    "I-URL": 16,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c8ca5c0d444769d99e4b552dd4d18297494adf3a636f118e1f5c401df50492
+size 418737632

runs/Feb12_08-31-50_6761f8d55dac/events.out.tfevents.1739349111.6761f8d55dac.18798.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bc4ce3bd767426fcae1117f4765aeefbab2668464487ceb8bca0d218825763
+size 6559

runs/Feb12_08-32-01_6761f8d55dac/events.out.tfevents.1739349122.6761f8d55dac.18798.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c11d033887ca494bc89d41eb316605069e676044978e00e433981c2f7c4913
+size 7032

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "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_config.json

@@ -0,0 +1,85 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "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>NOTUSED",
+      "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
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881e08502357b869e9d756dee875d592aa1a0f44ce77721dcee4e103464d8b51
+size 5432