Training in progress, epoch 1

config.json

@@ -1,31 +1,27 @@
 {
   "_name_or_path": "distilroberta-base",
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "RobertaForQuestionAnswering"
   ],
-  "attention_dropout": 0.1,
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
-  "dim": 768,
-  "dropout": 0.1,
+  "classifier_dropout": null,
   "eos_token_id": 2,
   "hidden_act": "gelu",
-  "hidden_dim": 3072,
   "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.33.2",
   "type_vocab_size": 1,
+  "use_cache": true,
   "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ab41780b7c3bdad9a392144adc4733c845950fb47db59f95ede84ba5e43d76
-size 326149157
+oid sha256:33ff2811884c603c0c944f8839670aab5658fce8576d8f5d066dee4c397041e2
+size 326152425

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8cc553397307d9f4c79c0b47a9319d009173937a1ad1c633aa29574b67c774e
+oid sha256:3db9916b535b2c8135de7b4620b7fee8b879e2d88bd74e594eb0086ddbafc72e
 size 4027