added model

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6bf2cc3928d9ca469a78d91f61eceebeed47aeabed2292e34e39da4c25344b
+size 2224483448

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733b215d6b80bfe6e1af01f6fb81b3dea97a4caedc0c21fd397f3acb91b0e4cc
+size 1112269335

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bead7310380d2f06e87716435e408d7cfe331bfd8d7c6364b87ceba30e0387f
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae59b6a5b3b3b0fd9d285b7cce4acf79bc8b62aa976f03772764daa5bc0594ab
+size 623

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 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base"}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.5536774704373721,
+  "best_model_checkpoint": "R2-OUTPUT/xlm-roberta-base/ContextIncluded_IdiomExcluded/4/checkpoint-185",
+  "epoch": 5.0,
+  "global_step": 185,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5641025900840759,
+      "eval_f1": 0.4068936527952921,
+      "eval_loss": 0.6858616471290588,
+      "eval_runtime": 0.8041,
+      "eval_samples_per_second": 339.518,
+      "eval_steps_per_second": 43.528,
+      "step": 37
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5641025900840759,
+      "eval_f1": 0.4068936527952921,
+      "eval_loss": 0.7174506187438965,
+      "eval_runtime": 0.8048,
+      "eval_samples_per_second": 339.219,
+      "eval_steps_per_second": 43.49,
+      "step": 74
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5641025900840759,
+      "eval_f1": 0.4068936527952921,
+      "eval_loss": 0.8625497817993164,
+      "eval_runtime": 0.804,
+      "eval_samples_per_second": 339.572,
+      "eval_steps_per_second": 43.535,
+      "step": 111
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5274725556373596,
+      "eval_f1": 0.5077237216898057,
+      "eval_loss": 0.8788116574287415,
+      "eval_runtime": 0.8029,
+      "eval_samples_per_second": 340.023,
+      "eval_steps_per_second": 43.593,
+      "step": 148
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5604395866394043,
+      "eval_f1": 0.5536774704373721,
+      "eval_loss": 1.1304702758789062,
+      "eval_runtime": 0.8023,
+      "eval_samples_per_second": 340.278,
+      "eval_steps_per_second": 43.625,
+      "step": 185
+    }
+  ],
+  "max_steps": 333,
+  "num_train_epochs": 9,
+  "total_flos": 1242795250575360.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192168a0c83cdce7dd45ada2c698f12df1515c8fef44dc34d64f30f594d66e7d
+size 2543