Training in progress, epoch 1

config.json

@@ -1,37 +1,35 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e443e4515f8e39b8a6a4f858dcc547b1134931722297320ce60a12c85d11e2c
-size 437961724
+oid sha256:ce551aab616ffa79afaeed573fbf134ce2d57d810bfa7e3d89b91a72265cd2f3
+size 267835644

runs/Nov23_18-16-40_148d266fc63b/events.out.tfevents.1700763410.148d266fc63b.2595.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83080bcb38f46cf855ae7d63391a2d2611c14e3f3c7309fdc9861c81a0d87fd7
+size 4297

runs/Nov23_18-17-44_148d266fc63b/events.out.tfevents.1700763466.148d266fc63b.2595.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da3b677b313f5ce41f6aab06a694780a0a24d90211b4370079783d320ea1619
+size 4346

runs/Nov23_18-18-57_148d266fc63b/events.out.tfevents.1700763540.148d266fc63b.2595.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25fc9db4b86c279a9f457d93428ff401403b74258ac2909c2d165e26a2448d8
+size 5290

tokenizer_config.json

@@ -50,6 +50,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:500c4f4847b7ccddcc3a40db638f8db5ca68d8ae0e482d62ce6c18971b7c7fd0
+oid sha256:db30db7f9e71bc6b2cdd49a70f693e8fff56fe4d5b5e19858ae76a502d0ed293
 size 4600