Training in progress, step 500

config.json

@@ -1,19 +1,13 @@
 {
-  "_name_or_path": "xlnet-base-cased",
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
   "architectures": [
-    "XLNetForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attn_type": "bi",
-  "bi_data": false,
-  "bos_token_id": 1,
-  "clamp_len": -1,
-  "d_head": 64,
-  "d_inner": 3072,
-  "d_model": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
   "dropout": 0.1,
-  "end_n_top": 5,
-  "eos_token_id": 2,
-  "ff_activation": "gelu",
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -25,30 +19,18 @@
     "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,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
   "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
-    }
-  },
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.32.1",
-  "untie_r": true,
-  "use_mems_eval": true,
-  "use_mems_train": false,
-  "vocab_size": 32000
+  "vocab_size": 28996
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:075b5c93fc9caed306724030c3626126af94ba22f85fa60eab95ca43eb10ed1c
-size 469314837
+oid sha256:05d5c28df2ba29cc64eea07864cf56a7d58398c1a189d41f16f26ba83bcad960
+size 263170733

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
-  "bos_token": "<s>",
-  "cls_token": "<cls>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "<sep>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,26 +1,13 @@
 {
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<cls>",
+  "cls_token": "[CLS]",
   "do_lower_case": false,
-  "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,
-  "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "<sep>",
-  "tokenizer_class": "XLNetTokenizer",
-  "unk_token": "<unk>"
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf61bd262c3e7d9fdad073252c780e128dcb04e9870d2bb79bee4b85f2085176
+oid sha256:fd763c5c57928a2b881a7ab45ee833f9c844c61dd2264fc9369c71d123ce57d5
 size 4027