Training in progress, epoch 1

config.json

@@ -1,26 +1,25 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
   "architectures": [
-    "BertForQuestionAnswering"
+    "DistilBertForQuestionAnswering"
   ],
-  "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,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "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,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53594c3474d005da5d14ffbe11e8bd76e9735eaeabe693162c62fef80c8d2f51
-size 430908208
+oid sha256:10b021fbdef7ef8bbee7ac4cf7d343513d8fbe239ba6ecdb765d86c136cceaa1
+size 260782152

runs/Jun11_11-07-09_1badb48aac2f/events.out.tfevents.1718104074.1badb48aac2f.9207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12dd46180303141461927660edf2c81df5f22d67b413e12f5da8c37d512a0091
+size 4184

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:ae14836a2fe08f020ae5e019fcc6049a09c5a36b00948cb512f1fd87acca0293
+oid sha256:366e92bc7fccc81818f8b4fbf7c633875b4a188b2fefb68e6e1eaafb0169055a
 size 5112