Training in progress, step 500

config.json

@@ -1,17 +1,14 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "AlbertForTokenClassification"
+    "RobertaForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
+  "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,
   "id2label": {
     "0": "LABEL_0",
@@ -25,7 +22,6 @@
     "8": "LABEL_8"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
@@ -38,18 +34,16 @@
     "LABEL_7": 7,
     "LABEL_8": 8
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.28.0",
-  "type_vocab_size": 2,
-  "vocab_size": 30000
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ae1b1febc782c62ab739bdeb44050368b9ecaccb89081715304e90c9237a03
-size 44412735
+oid sha256:3bee80f7b10084f11b186506458832d29c10f917e8382a387f29810f5b8969e7
+size 496320557

runs/Jun07_15-01-02_155-248-204-220/1686153293.7186553/events.out.tfevents.1686153293.155-248-204-220.323755.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9db27f63fb8d2ff9b43c4db4dfd832481662e22cb348f4f56f5554ffd93978
+size 5924

runs/Jun07_15-01-02_155-248-204-220/events.out.tfevents.1686153293.155-248-204-220.323755.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd7073377656677cb3c94713cb484cae26a1ea0266e267c8814f512ae1896b4
+size 4591

special_tokens_map.json

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

tokenizer_config.json

@@ -1,22 +1,15 @@
 {
-  "bos_token": "[CLS]",
+  "add_prefix_space": true,
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "[SEP]",
-  "tokenizer_class": "AlbertTokenizer",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
   "unk_token": "<unk>"
 }