Training in progress, epoch 1

config.json

@@ -1,13 +1,15 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "google/mobilebert-uncased",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "MobileBertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
   "id2label": {
     "0": "O",
     "1": "TOOL",
@@ -15,22 +17,29 @@
     "3": "TARGET"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
   "label2id": {
     "HEADING": 2,
     "O": 0,
     "TARGET": 3,
     "TOOL": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa0589b842f180ee7d375f059f753930eabb61625b23d09c225e3b9ed68aa77
-size 265476168
+oid sha256:6c9010de7d0f4861c33cdaac251d7f7329942f3570788c0ed2a91f6e553754f3
+size 98474224

runs/May24_08-28-16_instance-358/events.out.tfevents.1716539317.instance-358

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af091a5f05aa45f08de27e8db5aa6ed2fe1407db6028e3f63af0d17f1bb7afde
+size 5002

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -45,11 +45,11 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "MobileBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8003f1ecb9e624318dae2ffd323fd07c44783441bc45119a4f5e48fe9458e4
+oid sha256:d3393b74354a0acd7ce2185ce2923fc242b00c1fa1a6ddc694d3b69a4a799bdb
 size 4539