Training in progress, epoch 1

config.json

@@ -1,13 +1,17 @@
 {
-  "_name_or_path": "google-bert/bert-base-cased",
+  "_name_or_path": "albert/albert-base-v2",
   "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": {
     "MAV_CMD_NAV_ALTITUDE_WAIT (83 )": 0,
@@ -41,6 +45,7 @@
     "MAV_CMD_NAV_WAYPOINT (16 )": 28
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "0": "MAV_CMD_NAV_ALTITUDE_WAIT (83 )",
@@ -75,15 +80,17 @@
   },
   "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": "4.42.3",
   "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d017740b4270fe61d57625d9bff8380137e5d8bd43a1dbfd43fd51f0a10f1241
-size 433353820
+oid sha256:4c37936f682607d272ab8dff595f2a9c6ca997ce7fe47e4dc412d1b15a2b767f
+size 46826964

runs/Jul19_06-46-07_7fa17642f4f4/events.out.tfevents.1721371568.7fa17642f4f4.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b836609d5145eeb871538b93eca63c4c3779292db0db6b26bc5a71c5f2447943
-size 12128
+oid sha256:47cc273890952aa9583a51bbaf1f1edb8286f2addba73a0f84ebed0159d65562
+size 12954

runs/Jul19_07-08-57_7fa17642f4f4/events.out.tfevents.1721372938.7fa17642f4f4.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c8e22dd8f8fae27d814bc0d7b955c1aa56517731f060593a3e2475f3a43828
+size 8089

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": false,
+  "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 sha256:590ff2cb07b051d9a90c15cd068ca99dad76b01ebaed7015e0e9175994e4d30a
+oid sha256:62e5eb7359e125aabb9249e275fb5026c174a4d40b332e088cec427ebf97ba7e
 size 5112