Training in progress, step 500

config.json

@@ -1,43 +1,25 @@
 {
-  "_name_or_path": "xlm-mlm-en-2048",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "XLMForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "asm": false,
   "attention_dropout": 0.1,
-  "bos_index": 0,
-  "bos_token_id": 0,
-  "causal": false,
+  "dim": 768,
   "dropout": 0.1,
-  "emb_dim": 2048,
-  "embed_init_std": 0.02209708691207961,
-  "end_n_top": 5,
-  "eos_index": 1,
-  "gelu_activation": true,
-  "init_std": 0.02,
-  "is_encoder": true,
-  "lang_id": 0,
-  "layer_norm_eps": 1e-12,
-  "mask_index": 5,
-  "mask_token_id": 0,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
   "max_position_embeddings": 512,
-  "model_type": "xlm",
-  "n_heads": 16,
-  "n_langs": 1,
-  "n_layers": 12,
-  "pad_index": 2,
-  "pad_token_id": 2,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
-  "sinusoidal_embeddings": false,
-  "start_n_top": 5,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "first",
-  "summary_use_proj": true,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
-  "unk_index": 3,
-  "use_lang_emb": true,
-  "vocab_size": 30145
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16070134ce86f981c937d1f6cbe760d0072ed51172c8ac4c704d44ade16dfedb
-size 2668441385
+oid sha256:214fcaa9793e73e854f157a6fb274360d8f51df361112b97512a638881926b36
+size 267855533

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70d1d5a3569f2888e26d84c8a67fa1ce02392f1212ee94deefe67e3dd5e59b9
-size 3515
+oid sha256:60a499f41e066f276bad9a8b768d53ca8d9a8006451f73a2038f00269f91d7d7
+size 3579