Training in progress, epoch 1

config.json

@@ -1,33 +1,43 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "xlnet-base-cased",
   "architectures": [
-    "AlbertForMultipleChoice"
+    "XLNetForMultipleChoice"
   ],
-  "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,
-  "hidden_size": 768,
+  "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,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
-  "num_attention_heads": 12,
-  "num_hidden_groups": 1,
-  "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "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": "4.35.2",
-  "type_vocab_size": 2,
-  "vocab_size": 30000
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf830371517cb4a6d2ff79e461d7f3f88ee36650b9335c9b6eb30ed5010c824
-size 46740836
+oid sha256:6c1b9ee163760affe035163efc6f5b26caf1c816d24e1e1cd7b7a2a5dd678e44
+size 469261516

runs/Feb16_08-49-28_d4b2fc9666a9/events.out.tfevents.1708073368.d4b2fc9666a9.1740.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab3f89c68edc680308187f3b405601f367c1070fc06c770ecaf938a11a1e363
+size 4789

special_tokens_map.json

@@ -1,15 +1,19 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "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": "<sep>",
   "unk_token": "<unk>"
 }

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
-size 760289
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<unk>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[CLS]",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "[SEP]",
+      "content": "<cls>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -33,25 +33,61 @@
       "special": true
     },
     "4": {
-      "content": "[MASK]",
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<mask>",
       "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
   "keep_accents": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "remove_space": true,
-  "sep_token": "[SEP]",
-  "tokenizer_class": "AlbertTokenizer",
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b67130a2936ed29beedda03caa6540451db145709ab96b7745c990be82ec28
+oid sha256:98f47c57ae5cc92f7d64c29c70f956ea39ed9b66ba48eb71c82db75d920bc4a6
 size 4600