Training in progress, step 500

config.json

@@ -1,20 +1,25 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "albert/albert-base-v2",
   "_num_labels": 2,
   "architectures": [
-    "BertForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "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": "neg",
     "1": "pos"
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "neg": 0,
@@ -22,15 +27,17 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "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",
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
   "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a1e6b1b0d76961cc52379bd34d07e19761ae8fe00987b0b752a071c9ce6b24
-size 437958648
+oid sha256:fd7ab504282f661dccf06ea77ce1b282fa42145947eb2d99f5b39c9cb53cb018
+size 46743912

runs/Jul19_15-20-36_7cbd3327a802/events.out.tfevents.1721402479.7cbd3327a802.319991.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8384d3c87048c20180b7b6b4b67d9902bd047b02c3fddeafc8ff6fd8c9bd251a
+size 5377

runs/Jul19_15-35-23_7cbd3327a802/events.out.tfevents.1721403385.7cbd3327a802.322287.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f00b2d6412f6d768383de8415b0924c3544b6720c65a30afdb495cb7ba0c16
+size 6014

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

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,24 +32,26 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
   "mask_token": "[MASK]",
   "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": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93284c6abc48f1e3ef270ed1c7634d2b3e4148c0ce72a040701207e3a4fa0b21
+oid sha256:39a0f144c81632d12f1eb633617e23737c247dc20b8fe6386358c321bacc9d94
 size 4792