Training in progress, step 10000

config.json

@@ -1,15 +1,13 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "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": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "O",
     "1": "B-PER",
@@ -22,7 +20,6 @@
     "8": "I-MISC"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "B-LOC": 5,
     "B-MISC": 7,
@@ -34,17 +31,17 @@
     "I-PER": 2,
     "O": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.18.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3415408c8d9e6981ef5affbf6933a97dca8ab6d4ced017f7f887a335f52091dc
-size 1109910961
+oid sha256:4f3304db88e2bf718b2902b17662bdc4fa1d752a33a0858bd306d1c204559720
+size 538997621

runs/Apr11_15-35-13_28d6c324a863/events.out.tfevents.1649691563.28d6c324a863.71.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17aca851283e59357429f8df09d4e044631481600185d24e31654def1e33645
-size 7362
+oid sha256:a44f7fc73ed379a86219938b962bc798bf4bca0dc1cb388758449209881ed627
+size 8187

runs/Apr11_15-35-13_28d6c324a863/events.out.tfevents.1649696458.28d6c324a863.71.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98957104ecde07f5cc68f505266cec815c324d05891f19cb481906d7f1b36a59
+size 512

runs/Apr11_17-28-37_28d6c324a863/1649698251.5724418/events.out.tfevents.1649698251.28d6c324a863.71.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c1c3222194dbe4f6b25d782bbd5d502297456b6257a7512df684134ca52e7b
+size 4870

runs/Apr11_17-28-37_28d6c324a863/events.out.tfevents.1649698251.28d6c324a863.71.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce7e5fe5eccc2084590408e4395f042442f7f57c0cca8e4a0207abef7db01df
+size 7242

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
-size 17082758
+oid sha256:7d76a4d25ebe8f217654f1039bd991bfc96e7c2cd36e6d28aff941783ed1e9c8
+size 2919460

tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-multilingual-cased", "tokenizer_class": "DistilBertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243e049b8ea7367eaa819cd5094aa8cdcf7f98e227a478166514886f2ad97c57
+oid sha256:cc6527dce732338800a5aba65d776a1e2b082902d2a82fb3d97485dbd77129ba
 size 3055