EN-ZH-Baseline

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": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb335d9e288d9c54cded6b93d138a07425fdd3ec6cb68cf7bd47872f73472ec8
+size 4351493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50556ba76f953bf1a3a85bdd934b2905ac0d09fc4c7216c276e15adeb3b8bb35
+size 2239705845

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8eefe3fedb78406eb9d383560f3a104132ff24bed4370c0d0b2c685192c2f7
+size 14639

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e38461da3bbefd681e30510d4a9d0b183360fe991c0db05bcffbc534512fa18
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01511cf89ef840d91162ce4b810a2c0e0e17b9b45e1a139b26927c953686115
+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 +1,92 @@
+{
+  "best_metric": 0.08194395899772644,
+  "best_model_checkpoint": "EN-ZH_1/checkpoint-2000",
+  "epoch": 9.132420091324201,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.943264840182649e-06,
+      "loss": 0.0782,
+      "step": 500
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 0.09038791805505753,
+      "eval_mse": 0.09038791805505753,
+      "eval_pearson_correlation": 0.27106565217061607,
+      "eval_rmse": 0.3006458282470703,
+      "eval_runtime": 2.5621,
+      "eval_samples_per_second": 390.302,
+      "eval_spearman_corr": 0.2775738204162434,
+      "eval_steps_per_second": 12.49,
+      "learning_rate": 4.943264840182649e-06,
+      "step": 500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 4.886187214611872e-06,
+      "loss": 0.0652,
+      "step": 1000
+    },
+    {
+      "epoch": 4.57,
+      "eval_loss": 0.13348764181137085,
+      "eval_mse": 0.13348764181137085,
+      "eval_pearson_correlation": 0.2843881419278993,
+      "eval_rmse": 0.3653596043586731,
+      "eval_runtime": 2.5338,
+      "eval_samples_per_second": 394.661,
+      "eval_spearman_corr": 0.28295941028055765,
+      "eval_steps_per_second": 12.629,
+      "learning_rate": 4.886187214611872e-06,
+      "step": 1000
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 4.829109589041096e-06,
+      "loss": 0.0535,
+      "step": 1500
+    },
+    {
+      "epoch": 6.85,
+      "eval_loss": 0.0903298631310463,
+      "eval_mse": 0.0903298631310463,
+      "eval_pearson_correlation": 0.2694354241445327,
+      "eval_rmse": 0.3005492687225342,
+      "eval_runtime": 2.5266,
+      "eval_samples_per_second": 395.797,
+      "eval_spearman_corr": 0.2616406362679335,
+      "eval_steps_per_second": 12.665,
+      "learning_rate": 4.829109589041096e-06,
+      "step": 1500
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 4.77203196347032e-06,
+      "loss": 0.0433,
+      "step": 2000
+    },
+    {
+      "epoch": 9.13,
+      "eval_loss": 0.08194395899772644,
+      "eval_mse": 0.08194395899772644,
+      "eval_pearson_correlation": 0.2779026135189634,
+      "eval_rmse": 0.2862585484981537,
+      "eval_runtime": 2.5257,
+      "eval_samples_per_second": 395.931,
+      "eval_spearman_corr": 0.2617183191390256,
+      "eval_steps_per_second": 12.67,
+      "learning_rate": 4.77203196347032e-06,
+      "step": 2000
+    }
+  ],
+  "max_steps": 43800,
+  "num_train_epochs": 200,
+  "total_flos": 1.74539961616248e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1343eb1c002f0b5a5ad1a5e66d419df5fb84b0c1484ba16c32ccce92637105e
+size 3387