Training in progress, epoch 1

config.json

@@ -1,14 +1,12 @@
 {
+  "activation": "gelu",
   "architectures": [
-    "MobileBertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "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,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "sadness",
     "1": "joy",
@@ -18,9 +16,6 @@
     "5": "surprise"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 512,
-  "intra_bottleneck_size": 128,
-  "key_query_shared_bottleneck": true,
   "label2id": {
     "anger": 3,
     "fear": 4,
@@ -29,22 +24,17 @@
     "sadness": 0,
     "surprise": 5
   },
-  "layer_norm_eps": 1e-12,
   "max_length": 128,
   "max_position_embeddings": 512,
-  "model_type": "mobilebert",
-  "normalization_type": "no_norm",
-  "num_attention_heads": 4,
-  "num_feedforward_networks": 4,
-  "num_hidden_layers": 24,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "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 sha256:6aa5c6e1309d1bf2ce93c3d485ca048c7dabb534ed527c68df09587f213b122e
-size 99529152
+oid sha256:96fb699bb898c8f6dcfa1f10c016837b1cb82c30d0d97a90ef18b47e26d9322a
+size 267844872

runs/Apr12_09-54-38_08520d36c435/events.out.tfevents.1712915679.08520d36c435.1080.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2330e2d27d0f4c6c43e687cf0d7c8ee4a33eb6d2acd0b3ae630b137c46e25a9
+size 4184

runs/Apr12_09-55-14_08520d36c435/events.out.tfevents.1712915715.08520d36c435.1599.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d40009a8479390e575ff22d34faf97f9e317104ba9a35a385e334aa3b96f645
+size 4558

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858cd512df8268d101697545488e8d97f8d869b2348d59fa2761e4a569f168d1
+oid sha256:8cdee18864975ec6468210af89e0016ca17971cd2b0cc0353c3553d663803b70
 size 4155