Baseline-RU-EN

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<IN>": 250003,
+  "<OOD>": 250002
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250004
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53091f41fce233d25966d29369a0509d53808016e411f175a3eb8b9d6430d795
+size 4351493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba375a1fb4edea24b0bd69af3271393442a9cd88fbb616194adf452c19c8d459
+size 2239714037

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142c47ef1813b3e4df3e447ee4169f993eeec218c3e044070403c64706132c0f
+size 14639

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ef38c4eb2a94ad35bdbe041f09d2b687493eed3af4f367c14bddaf9c13162c
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bb1bc9253dfb0d5bb20df6e1d9e2b3093e3f6835335654599e077017c8d867
+size 627

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-large",
+  "normalization": true,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.055517952889204025,
+  "best_model_checkpoint": "XLM_RU_EN_WMT2021_WO_LF_100/checkpoint-500",
+  "epoch": 2.2831050228310503,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.94337899543379e-06,
+      "loss": 0.0826,
+      "step": 500
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 0.055517952889204025,
+      "eval_mse": 0.05551794916391373,
+      "eval_pearson_correlation": 0.4512787180760665,
+      "eval_rmse": 0.23562246561050415,
+      "eval_runtime": 9.8163,
+      "eval_samples_per_second": 101.871,
+      "eval_spearman_corr": 0.3608326915950213,
+      "eval_steps_per_second": 3.26,
+      "learning_rate": 4.94337899543379e-06,
+      "step": 500
+    }
+  ],
+  "max_steps": 43800,
+  "num_train_epochs": 200,
+  "total_flos": 2767652060607936.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd35932a44862649ee76cdd4ffd03c7d53dc4bba745491ee0c595b541fd2de01
+size 3387