Training in progress, epoch 1

config.json

@@ -1,33 +1,37 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "xlm-roberta-large",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
-  "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": 1024,
   "id2label": {
     "0": "BAD",
     "1": "GOOD"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "BAD": 0,
     "GOOD": 1
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "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": "4.30.2",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0828046a188ba498155d349e5687759a2405ee658811f74ef4f7aebc13d3aaf5
-size 267855533
+oid sha256:7ea01eed074d82accb8c67313d2267372727e97843ce0d25d8b6795c2b586417
+size 2239709941

runs/Jun30_14-08-18_684dc99c19bd/events.out.tfevents.1688134179.684dc99c19bd.211.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7573b57b9c5c0b6a30ef5efd76641cbc0978f7735a26d539c09b0e6d5b36b201
+size 88

runs/Jun30_14-11-15_684dc99c19bd/events.out.tfevents.1688134278.684dc99c19bd.211.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c314d27d6187ffd1a22e059784f5c6d759f77f1810a292324d0ca562dd614e4e
+size 4184

runs/Jun30_14-12-30_684dc99c19bd/events.out.tfevents.1688134357.684dc99c19bd.4121.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8285054a64a8a0c71a3e9b51cacf0a8f46d4e6f6c228fed95e1bfaeef13defc7
+size 4318

runs/Jun30_14-19-33_684dc99c19bd/events.out.tfevents.1688134779.684dc99c19bd.5725.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceaeaeb0ae340b5ee97a7aadf8c23210f98e8f1f688a301c895bb5547878804c
+size 4955

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51a7a3951dea200289a2738a5e70263786405bb28e5fc3e4399ce97e1c3a389
+oid sha256:cfc20f4cf1b6be883581ceacbf98951394659e259a03ebe7df54e8f7f9930949
 size 3963