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 sha256:8c4f9a3a807823b9888d787477749cb970967cbdd4acd440993b4128321ec586
+size 2224483646

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af518e58b9a73726225036da1b023dc0b16dcdd4be2fe2d7d5ed9a79d948f71
+size 1112269338

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b527df58000efc40c6e33fbef76cb84effe946531e10eee7563a3dd0a31651
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334ce08fc14633a84062a29c73b0461cb681367f63e1814af2f1619e71afe324
+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 +1,96 @@
+{
+  "best_metric": 0.7140781182094741,
+  "best_model_checkpoint": "OUTPUT/xlm-roberta-base/FalseTrue-0/0/checkpoint-296",
+  "epoch": 8.0,
+  "global_step": 296,
+  "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": 0.6925989985466003,
+      "eval_runtime": 0.8159,
+      "eval_samples_per_second": 334.599,
+      "eval_steps_per_second": 42.897,
+      "step": 37
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5641025900840759,
+      "eval_f1": 0.4068936527952921,
+      "eval_loss": 0.7125938534736633,
+      "eval_runtime": 0.8146,
+      "eval_samples_per_second": 335.145,
+      "eval_steps_per_second": 42.967,
+      "step": 74
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5604395866394043,
+      "eval_f1": 0.4052004333694475,
+      "eval_loss": 0.7705000042915344,
+      "eval_runtime": 0.8132,
+      "eval_samples_per_second": 335.709,
+      "eval_steps_per_second": 43.04,
+      "step": 111
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7142857313156128,
+      "eval_f1": 0.7028323699421966,
+      "eval_loss": 0.8162457346916199,
+      "eval_runtime": 0.814,
+      "eval_samples_per_second": 335.389,
+      "eval_steps_per_second": 42.999,
+      "step": 148
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7069597244262695,
+      "eval_f1": 0.6908952629291613,
+      "eval_loss": 1.4020615816116333,
+      "eval_runtime": 0.8166,
+      "eval_samples_per_second": 334.305,
+      "eval_steps_per_second": 42.86,
+      "step": 185
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.721611738204956,
+      "eval_f1": 0.7063504997827033,
+      "eval_loss": 1.4205191135406494,
+      "eval_runtime": 0.8137,
+      "eval_samples_per_second": 335.499,
+      "eval_steps_per_second": 43.013,
+      "step": 222
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7252747416496277,
+      "eval_f1": 0.7118124041200964,
+      "eval_loss": 1.5443077087402344,
+      "eval_runtime": 0.8137,
+      "eval_samples_per_second": 335.506,
+      "eval_steps_per_second": 43.014,
+      "step": 259
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7289377450942993,
+      "eval_f1": 0.7140781182094741,
+      "eval_loss": 1.6495815515518188,
+      "eval_runtime": 0.8093,
+      "eval_samples_per_second": 337.346,
+      "eval_steps_per_second": 43.249,
+      "step": 296
+    }
+  ],
+  "max_steps": 333,
+  "num_train_epochs": 9,
+  "total_flos": 1988472400920576.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991a8ddd81bd9450a86b7363c9662ba3f3708d540d4076fcfd9a0b2d0272a145
+size 2479