Training in progress, epoch 1

config.json

@@ -1,25 +1,28 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "FacebookAI/roberta-base",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "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": "4.42.4",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e752486258c32531b880ee02d62cf644958a66f8bdfabd686da316179077d663
-size 267832560
+oid sha256:920f3d121b18a54bdacd07927c1235afb646bc825e859acebe9432058fc20a2e
+size 498612824

runs/Aug27_10-31-32_647c6ef99f2b/events.out.tfevents.1724754698.647c6ef99f2b.624.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d167a67b7f7d8ac2d149732dc429a18a01ed190fdd8f8466f7ef3be82ef13b5c
+size 4910

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f49bffbbd3863dce2c1ec6a43caeae5cde37652c00943eb1d0bd1fc0a74b838
+oid sha256:eae2060579d40be566187d52cc19be0cc42dedf1ca8272fad244f40cad637614
 size 5176