Training in progress, epoch 1

config.json

@@ -1,12 +1,14 @@
 {
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "MobileBertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": true,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
   "id2label": {
     "0": "sadness",
     "1": "joy",
@@ -16,6 +18,9 @@
     "5": "surprise"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
   "label2id": {
     "anger": 3,
     "fear": 4,
@@ -24,17 +29,22 @@
     "sadness": 0,
     "surprise": 5
   },
+  "layer_norm_eps": 1e-12,
   "max_length": 128,
   "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,
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
+  "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 sha256:42f0eb594fd3e11aa2d878eb96a2c1f4ac0e03fb1573f99347d08dc085abb503
-size 267844872
+oid sha256:07ed248e3e3488549af736a163f3f604df5dd273b50088da9a56eccaafe6234a
+size 99529152

runs/Apr26_10-01-20_58a95f8b215f/events.out.tfevents.1714125681.58a95f8b215f.47.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae848e43e2eb6ee30550458f5ec64c444f095b0ae4a96501d1ca6c4b670769b
+size 5255

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:c02ea553ff2173014ac892d52f5aff43e830dac5bed2f7d16c1c1be7fb76d254
+oid sha256:9e6fcef131e7aaa57e5438e3ad675f2df95f008602518b504dc9830b169f517f
 size 4219