Training in progress, step 58

config.json

@@ -1,25 +1,43 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "xlm-mlm-en-2048",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "XLMForSequenceClassification"
   ],
+  "asm": false,
   "attention_dropout": 0.1,
-  "dim": 768,
+  "bos_index": 0,
+  "bos_token_id": 0,
+  "causal": false,
   "dropout": 0.1,
-  "hidden_dim": 3072,
-  "initializer_range": 0.02,
+  "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,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "model_type": "xlm",
+  "n_heads": 16,
+  "n_langs": 1,
+  "n_layers": 12,
+  "pad_index": 2,
+  "pad_token_id": 2,
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "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,
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
-  "vocab_size": 30522
+  "unk_index": 3,
+  "use_lang_emb": true,
+  "vocab_size": 30145
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb13a6304e6b16e475034e0a1633480239c0c070eafa5f5302081843707c52f
-size 267855533
+oid sha256:16070134ce86f981c937d1f6cbe760d0072ed51172c8ac4c704d44ade16dfedb
+size 2668441385

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f6b758158fb3b681be9d8741c4c7d8ed8f38d76016cbf75fad88df34466838
+oid sha256:d70d1d5a3569f2888e26d84c8a67fa1ce02392f1212ee94deefe67e3dd5e59b9
 size 3515