Training in progress, epoch 1

config.json

@@ -1,33 +1,42 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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": "negative",
     "1": "positive"
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
   "label2id": {
     "negative": 0,
     "positive": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "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",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "vocab_size": 30000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5142bdb3e74d6b190081946ae938103df6bf2b1b136e518e54fb7ec7ed7c81a1
-size 267855533
+oid sha256:4d356bf00903dcab8436dfc5bc69f0dca9bacb416be91b8ff618b8f155254460
+size 46754181

runs/Oct31_22-21-11_1f2824fc2b55/events.out.tfevents.1698790959.1f2824fc2b55.32.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2245f065605c35adaed999f2d8049fed9ffc1daf34b4ecd9a16ea17e8a2cab19
+size 5377

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tokenizer_config.json

@@ -1,13 +1,23 @@
 {
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 512,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
+  "remove_space": true,
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9290f980afef6fe8daf08257addfc2392149cccf4e5d7170ae8afbaa705e1d3
+oid sha256:5d2e1a058b6bd89e0e5aca85d6506626e746209c574ba5c031e84163bfaae57b
 size 4027