Training in progress, step 500

config.json

@@ -1,54 +1,38 @@
 {
-  "_name_or_path": "xlnet-base-cased",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "XLNetForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attn_type": "bi",
-  "bi_data": false,
-  "bos_token_id": 1,
-  "clamp_len": -1,
-  "d_head": 64,
-  "d_inner": 3072,
-  "d_model": 768,
-  "dropout": 0.1,
-  "end_n_top": 5,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
   "eos_token_id": 2,
-  "ff_activation": "gelu",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "layer_norm_eps": 1e-12,
-  "mem_len": null,
-  "model_type": "xlnet",
-  "n_head": 12,
-  "n_layer": 12,
-  "pad_token_id": 5,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "reuse_len": null,
-  "same_length": false,
-  "start_n_top": 5,
-  "summary_activation": "tanh",
-  "summary_last_dropout": 0.1,
-  "summary_type": "last",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 250
-    }
-  },
   "torch_dtype": "float32",
   "transformers_version": "4.33.1",
-  "untie_r": true,
-  "use_mems_eval": true,
-  "use_mems_train": false,
-  "vocab_size": 32000
+  "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 sha256:09d465da522c264f04a378cead1f54e549654758db707986000b4712deddee81
-size 469314837
+oid sha256:099c756076f456f0ab55d79e15dbd995e4ef9f7f984211ebc9e25acdaed004ee
+size 498660721

special_tokens_map.json

@@ -1,10 +1,6 @@
 {
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
   "bos_token": "<s>",
-  "cls_token": "<cls>",
+  "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
@@ -14,6 +10,6 @@
     "single_word": false
   },
   "pad_token": "<pad>",
-  "sep_token": "<sep>",
+  "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,26 +1,15 @@
 {
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
+  "add_prefix_space": false,
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<cls>",
-  "do_lower_case": false,
+  "cls_token": "<s>",
   "eos_token": "</s>",
-  "keep_accents": false,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1000000000000000019884624838656,
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
   "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "<sep>",
-  "tokenizer_class": "XLNetTokenizer",
+  "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 sha256:88b2ac8961f7acda4816774e5fc33d921c3d97f744301b54bf56cd040ab15726
+oid sha256:3cffcd3161fffc785550ff274dccb1c0c2f31f322352e66f83016438600c1754
 size 4027