Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 250001,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "facebook/xlm-roberta-xl",
+  "architectures": [
+    "XLMRobertaXLForQuestionAnswering"
+  ],
+  "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": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta-xl",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250880
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498d635d319ca1ff8b53fe3c488a69195a2822dc66c91d7649b0227e3f69c4c1
+size 27807981087

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e235059a5dc9b9fe9c99f9f184fb786ba6335a09b869500f526dd8dd72f7bc65
+size 9917581377

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29bf2506201fba71226a2b3623dcff1c0b79093b02636ce0a88567748629da33
+size 3986371908

pytorch_model.bin.index.json

@@ -0,0 +1,590 @@
+{
+  "metadata": {
+    "total_size": 13903738888
+  },
+  "weight_map": {
+    "qa_outputs.bias": "pytorch_model-00002-of-00002.bin",
+    "qa_outputs.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.embeddings.token_type_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.0.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.10.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.11.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.12.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.13.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.14.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.15.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.16.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.17.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.18.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.19.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.20.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.21.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.22.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.23.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.23.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.23.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.23.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.23.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.23.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.24.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.25.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.26.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.27.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.28.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.29.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.3.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.3.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.30.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.30.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.31.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.32.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.33.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.34.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.attention.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.35.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "roberta.encoder.layer.4.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.4.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.5.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.6.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.7.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.8.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.attention.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.output.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "roberta.encoder.layer.9.output.dense.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2073d35c9b5656528a20fc26ecb7b09a9131c4ed037fd14a0ddbeaac2554f9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaeaba621451ae7dc2e90f2788243c11cdd8a56cb8472983118c8d24714a8b1b
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7386849913e8e0052c3cc1774cb96e0fa11ef5997e59bd07e41331e4e387f95
+size 17082756

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9999310225901017,
+  "eval_steps": 500,
+  "global_step": 14497,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9771431199411332e-05,
+      "loss": 3.0982,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9541482707873437e-05,
+      "loss": 1.5591,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9311534216335545e-05,
+      "loss": 1.1593,
+      "step": 1500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9081585724797646e-05,
+      "loss": 0.979,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8851637233259754e-05,
+      "loss": 0.9437,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8621688741721855e-05,
+      "loss": 0.8984,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8392200147167038e-05,
+      "loss": 0.8578,
+      "step": 3500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.816225165562914e-05,
+      "loss": 0.8538,
+      "step": 4000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7932303164091244e-05,
+      "loss": 0.824,
+      "step": 4500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.770235467255335e-05,
+      "loss": 0.7844,
+      "step": 5000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7472406181015452e-05,
+      "loss": 0.7969,
+      "step": 5500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7242917586460636e-05,
+      "loss": 0.7902,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.7012969094922737e-05,
+      "loss": 0.7709,
+      "step": 6500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6783020603384845e-05,
+      "loss": 0.7573,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1905351877212524,
+      "eval_runtime": 298.8537,
+      "eval_samples_per_second": 39.782,
+      "eval_steps_per_second": 13.261,
+      "step": 7248
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.655307211184695e-05,
+      "loss": 0.603,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.632312362030905e-05,
+      "loss": 0.4874,
+      "step": 8000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.6093175128771158e-05,
+      "loss": 0.4762,
+      "step": 8500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.586322663723326e-05,
+      "loss": 0.496,
+      "step": 9000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.5633738042678443e-05,
+      "loss": 0.4922,
+      "step": 9500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.5403789551140547e-05,
+      "loss": 0.4737,
+      "step": 10000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.517384105960265e-05,
+      "loss": 0.481,
+      "step": 10500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.4943892568064754e-05,
+      "loss": 0.485,
+      "step": 11000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.4713944076526859e-05,
+      "loss": 0.4892,
+      "step": 11500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.448445548197204e-05,
+      "loss": 0.4775,
+      "step": 12000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.4254966887417219e-05,
+      "loss": 0.4676,
+      "step": 12500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.4025018395879325e-05,
+      "loss": 0.4688,
+      "step": 13000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.379506990434143e-05,
+      "loss": 0.4785,
+      "step": 13500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.3565121412803532e-05,
+      "loss": 0.4734,
+      "step": 14000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.368137240409851,
+      "eval_runtime": 299.2167,
+      "eval_samples_per_second": 39.734,
+      "eval_steps_per_second": 13.245,
+      "step": 14497
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 43488,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1.135274382017962e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8dd56b004b8339f7f6edf148f3298dedd4c92a4ac8af82dd32296d82abf986
+size 4536