XTREME_panx_best_checkpoint

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "do_sample": false,
+  "eos_token_id": 2,
+  "eos_token_ids": 0,
+  "finetuning_task": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_beams": 1,
+  "num_hidden_layers": 24,
+  "num_labels": 7,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pruned_heads": {},
+  "repetition_penalty": 1.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "type_vocab_size": 1,
+  "use_bfloat16": false,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0834f1980621e52cc8d5b24d6e9dba4725ab8f81f2b0e5c42a81bc69c1c9b251
+size 2239759488

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4ec09e9cf88a6379bf28473b42f77dacd5d6c5a48be7710029367a2df89a4a
+size 2095