Training in progress, epoch 1

config.json

@@ -1,49 +1,39 @@
 {
-  "_name_or_path": "xlnet-base-cased",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "XLNetForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "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",
+  "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,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0
   },
   "layer_norm_eps": 1e-12,
-  "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
-    }
-  },
+  "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",
   "torch_dtype": "float32",
   "transformers_version": "4.28.1",
-  "untie_r": true,
-  "use_mems_eval": true,
-  "use_mems_train": false,
-  "vocab_size": 32000
+  "type_vocab_size": 2,
+  "vocab_size": 30000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feeaedc7e2b6a3a7f2f57a477c2929e63e12ffb973185072f3bebef04f2f5e7a
-size 469308693
+oid sha256:b070efeff6a53d1599928e8351b16fb54f9339ceb238b7568e1806919d735b6b
+size 46751109

runs/Apr19_06-46-24_8ca3a47d7845/events.out.tfevents.1681886862.8ca3a47d7845.184.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d5dedfe9229769a9bb0721665d7f9d05a7129a73478ec77c14ff3c9cd01f84
-size 4784
+oid sha256:29346d68bc927356d0f7d77dcbf623db9ac6652e4dd648ff3e79fc6353fe6adf
+size 5404

runs/Apr19_06-52-20_8ca3a47d7845/1681887147.638673/events.out.tfevents.1681887147.8ca3a47d7845.184.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a557b20c96c91435f6790ba17d6f37264e48660327ae9848343f6b9312b87b0
+size 5884

runs/Apr19_06-52-20_8ca3a47d7845/events.out.tfevents.1681887147.8ca3a47d7845.184.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5db388c197497208e96b632a8429082a472fdb64662fd276f0a5dc70940c65
+size 4694

special_tokens_map.json

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

tokenizer_config.json

@@ -1,26 +1,22 @@
 {
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<cls>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
   "keep_accents": false,
   "mask_token": {
     "__type": "AddedToken",
-    "content": "<mask>",
+    "content": "[MASK]",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "remove_space": true,
-  "sep_token": "<sep>",
-  "tokenizer_class": "XLNetTokenizer",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640e45a7b467a7d09097662efac250c1b1df865d229047a9458256384f7336c7
+oid sha256:6cadfe0d02938efc90bf055ca76313bd3ed0b2f5b66ba16e760ff03a2990318d
 size 3579