EN-DE-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 sha256:4ac0225dfa9ea23a010ce9b40f59b97191d2b7134f6a9dbcc9dc414a6bdd9b26
+size 4351493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0d586b6547932530b595e34f1e763f2eff9ffbf4175545364a92bd640089b8
+size 2239705845

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35255d3111066f58c447cd2773a5fb996d0d70e7e3d28aa4f9e7aec7cbb9b68
+size 14639

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744edeac403c147f5dc5b2897b00b69b566de03e2f55bb626632624516e0090b
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0292cde3db6e94d4a0c937f3bd24bef512e7a5ea0776810f5616d42bb6735e
+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 +1,168 @@
+{
+  "best_metric": 0.030037986114621162,
+  "best_model_checkpoint": "EN-DE_1/checkpoint-4000",
+  "epoch": 18.264840182648403,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.943150684931507e-06,
+      "loss": 0.0458,
+      "step": 500
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 0.0317346565425396,
+      "eval_mse": 0.0317346565425396,
+      "eval_pearson_correlation": 0.46990232914177965,
+      "eval_rmse": 0.1781422346830368,
+      "eval_runtime": 2.578,
+      "eval_samples_per_second": 387.905,
+      "eval_spearman_corr": 0.4789856726431624,
+      "eval_steps_per_second": 12.413,
+      "learning_rate": 4.943150684931507e-06,
+      "step": 500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 4.8860730593607305e-06,
+      "loss": 0.0363,
+      "step": 1000
+    },
+    {
+      "epoch": 4.57,
+      "eval_loss": 0.031161895021796227,
+      "eval_mse": 0.031161896884441376,
+      "eval_pearson_correlation": 0.4681432735823584,
+      "eval_rmse": 0.17652732133865356,
+      "eval_runtime": 2.5825,
+      "eval_samples_per_second": 387.218,
+      "eval_spearman_corr": 0.5022684527295919,
+      "eval_steps_per_second": 12.391,
+      "learning_rate": 4.8860730593607305e-06,
+      "step": 1000
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 4.829109589041096e-06,
+      "loss": 0.03,
+      "step": 1500
+    },
+    {
+      "epoch": 6.85,
+      "eval_loss": 0.03813818097114563,
+      "eval_mse": 0.03813818469643593,
+      "eval_pearson_correlation": 0.47614034267336836,
+      "eval_rmse": 0.1952899992465973,
+      "eval_runtime": 2.586,
+      "eval_samples_per_second": 386.701,
+      "eval_spearman_corr": 0.5117927401539177,
+      "eval_steps_per_second": 12.374,
+      "learning_rate": 4.829109589041096e-06,
+      "step": 1500
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 4.77203196347032e-06,
+      "loss": 0.0235,
+      "step": 2000
+    },
+    {
+      "epoch": 9.13,
+      "eval_loss": 0.03011469729244709,
+      "eval_mse": 0.03011469729244709,
+      "eval_pearson_correlation": 0.5004122369046293,
+      "eval_rmse": 0.17353586852550507,
+      "eval_runtime": 2.5817,
+      "eval_samples_per_second": 387.347,
+      "eval_spearman_corr": 0.5088055517612488,
+      "eval_steps_per_second": 12.395,
+      "learning_rate": 4.77203196347032e-06,
+      "step": 2000
+    },
+    {
+      "epoch": 11.42,
+      "learning_rate": 4.7149543378995435e-06,
+      "loss": 0.0196,
+      "step": 2500
+    },
+    {
+      "epoch": 11.42,
+      "eval_loss": 0.040484823286533356,
+      "eval_mse": 0.040484823286533356,
+      "eval_pearson_correlation": 0.4791417607023304,
+      "eval_rmse": 0.20120841264724731,
+      "eval_runtime": 2.5689,
+      "eval_samples_per_second": 389.264,
+      "eval_spearman_corr": 0.49223680640020745,
+      "eval_steps_per_second": 12.456,
+      "learning_rate": 4.7149543378995435e-06,
+      "step": 2500
+    },
+    {
+      "epoch": 13.7,
+      "learning_rate": 4.6578767123287675e-06,
+      "loss": 0.0169,
+      "step": 3000
+    },
+    {
+      "epoch": 13.7,
+      "eval_loss": 0.03211166337132454,
+      "eval_mse": 0.03211166337132454,
+      "eval_pearson_correlation": 0.509159843974805,
+      "eval_rmse": 0.1791972815990448,
+      "eval_runtime": 2.5988,
+      "eval_samples_per_second": 384.8,
+      "eval_spearman_corr": 0.4970874031697612,
+      "eval_steps_per_second": 12.314,
+      "learning_rate": 4.6578767123287675e-06,
+      "step": 3000
+    },
+    {
+      "epoch": 15.98,
+      "learning_rate": 4.600799086757991e-06,
+      "loss": 0.0144,
+      "step": 3500
+    },
+    {
+      "epoch": 15.98,
+      "eval_loss": 0.03915296494960785,
+      "eval_mse": 0.03915296494960785,
+      "eval_pearson_correlation": 0.49790449972703843,
+      "eval_rmse": 0.19787108898162842,
+      "eval_runtime": 2.5896,
+      "eval_samples_per_second": 386.156,
+      "eval_spearman_corr": 0.4949469011494366,
+      "eval_steps_per_second": 12.357,
+      "learning_rate": 4.600799086757991e-06,
+      "step": 3500
+    },
+    {
+      "epoch": 18.26,
+      "learning_rate": 4.543721461187215e-06,
+      "loss": 0.0124,
+      "step": 4000
+    },
+    {
+      "epoch": 18.26,
+      "eval_loss": 0.030037986114621162,
+      "eval_mse": 0.030037986114621162,
+      "eval_pearson_correlation": 0.5246180486388605,
+      "eval_rmse": 0.17331470549106598,
+      "eval_runtime": 2.5739,
+      "eval_samples_per_second": 388.513,
+      "eval_spearman_corr": 0.5060582469818566,
+      "eval_steps_per_second": 12.432,
+      "learning_rate": 4.543721461187215e-06,
+      "step": 4000
+    }
+  ],
+  "max_steps": 43800,
+  "num_train_epochs": 200,
+  "total_flos": 3.49079923232496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26026ec284da0b45a59d9900ab9ae6d8bd6928a13271be2bfe4c80a8a9762aeb
+size 3387