Training in progress, step 1000

config.json

@@ -1,17 +1,14 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "AlbertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "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",
@@ -19,26 +16,23 @@
     "2": "LABEL_2"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "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",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.33.1",
-  "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:c21ab1261cc2da5dfa1dbe434378f9c4be2c630231d1b417d5a6c96a8fe1fa5e
-size 46752834
+oid sha256:a6c1c68f69e6dcc655d04cc88ffe94b373b08a55c53d7bed8daf03526443ef04
+size 498660721

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_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97de83b93a21c9eb1e67303907907d55c3586b7c62c56f544803aecd024d36f2
+oid sha256:fd92e51bb6eb524f4c2bce64cb9f25df39a9a066ac3fb865d08cd42ed22ff177
 size 4027