Model

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "ixa-ehu/berteus-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "stsb",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 3,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50099
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5c752db733fff267d87c1ac388efa0678ad2a65bd93654551864a43890e2ae
+size 498145397

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tb/events.out.tfevents.1688906412.asier-pc.14041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b649312dcc1398ebe935318af31177e4e24e574fa08a19b47982fae4b8d1109d
+size 10334

test_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_combined_score": 0.9103811678023414,
+    "eval_loss": 0.34662991762161255,
+    "eval_pearson": 0.9178814188008078,
+    "eval_runtime": 10.2029,
+    "eval_samples_per_second": 85.466,
+    "eval_spearmanr": 0.9028809168038749,
+    "eval_steps_per_second": 10.683,
+    "test_samples_stsb": 872
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.9135991932046025,
+  "best_model_checkpoint": "../models/eusts/checkpoint-2180",
+  "epoch": 10.0,
+  "global_step": 2180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.8726207906295755e-05,
+      "loss": 1.4053,
+      "step": 218
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.8498445305588846,
+      "eval_loss": 0.5913795232772827,
+      "eval_pearson": 0.8576485507627736,
+      "eval_runtime": 10.4654,
+      "eval_samples_per_second": 83.227,
+      "eval_spearmanr": 0.8420405103549957,
+      "eval_steps_per_second": 10.415,
+      "step": 218
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.553440702781845e-05,
+      "loss": 0.3881,
+      "step": 436
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.887035736675172,
+      "eval_loss": 0.447421669960022,
+      "eval_pearson": 0.8917341241804541,
+      "eval_runtime": 10.5067,
+      "eval_samples_per_second": 82.899,
+      "eval_spearmanr": 0.8823373491698899,
+      "eval_steps_per_second": 10.374,
+      "step": 436
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.2342606149341143e-05,
+      "loss": 0.2083,
+      "step": 654
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.8970108216951012,
+      "eval_loss": 0.4096603989601135,
+      "eval_pearson": 0.9016467997316473,
+      "eval_runtime": 10.4817,
+      "eval_samples_per_second": 83.097,
+      "eval_spearmanr": 0.8923748436585551,
+      "eval_steps_per_second": 10.399,
+      "step": 654
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.9150805270863837e-05,
+      "loss": 0.1393,
+      "step": 872
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.9009673665742599,
+      "eval_loss": 0.3968064486980438,
+      "eval_pearson": 0.9046095606853766,
+      "eval_runtime": 10.448,
+      "eval_samples_per_second": 83.366,
+      "eval_spearmanr": 0.8973251724631434,
+      "eval_steps_per_second": 10.433,
+      "step": 872
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.595900439238653e-05,
+      "loss": 0.1023,
+      "step": 1090
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.906389648678596,
+      "eval_loss": 0.38093939423561096,
+      "eval_pearson": 0.9095917410726173,
+      "eval_runtime": 10.7338,
+      "eval_samples_per_second": 81.146,
+      "eval_spearmanr": 0.9031875562845746,
+      "eval_steps_per_second": 10.155,
+      "step": 1090
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.2767203513909225e-05,
+      "loss": 0.0841,
+      "step": 1308
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.9098955778506463,
+      "eval_loss": 0.37849491834640503,
+      "eval_pearson": 0.9139073667065271,
+      "eval_runtime": 10.6077,
+      "eval_samples_per_second": 82.11,
+      "eval_spearmanr": 0.9058837889947655,
+      "eval_steps_per_second": 10.276,
+      "step": 1308
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 9.575402635431918e-06,
+      "loss": 0.0664,
+      "step": 1526
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.9111955743924036,
+      "eval_loss": 0.35929641127586365,
+      "eval_pearson": 0.9148956072886006,
+      "eval_runtime": 10.7134,
+      "eval_samples_per_second": 81.3,
+      "eval_spearmanr": 0.9074955414962067,
+      "eval_steps_per_second": 10.174,
+      "step": 1526
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 6.383601756954612e-06,
+      "loss": 0.057,
+      "step": 1744
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.9122781067251765,
+      "eval_loss": 0.3573194146156311,
+      "eval_pearson": 0.9160432969800479,
+      "eval_runtime": 10.694,
+      "eval_samples_per_second": 81.448,
+      "eval_spearmanr": 0.9085129164703051,
+      "eval_steps_per_second": 10.193,
+      "step": 1744
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3.191800878477306e-06,
+      "loss": 0.0485,
+      "step": 1962
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.9128873266818468,
+      "eval_loss": 0.3531445860862732,
+      "eval_pearson": 0.9165594039106797,
+      "eval_runtime": 10.7576,
+      "eval_samples_per_second": 80.966,
+      "eval_spearmanr": 0.9092152494530139,
+      "eval_steps_per_second": 10.132,
+      "step": 1962
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0449,
+      "step": 2180
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": 0.9135991932046025,
+      "eval_loss": 0.3487534821033478,
+      "eval_pearson": 0.917271052630473,
+      "eval_runtime": 10.8295,
+      "eval_samples_per_second": 80.428,
+      "eval_spearmanr": 0.9099273337787319,
+      "eval_steps_per_second": 10.065,
+      "step": 2180
+    },
+    {
+      "epoch": 10.0,
+      "step": 2180,
+      "total_flos": 1.834393807540224e+16,
+      "train_loss": 0.2544048738042149,
+      "train_runtime": 2592.0512,
+      "train_samples_per_second": 26.898,
+      "train_steps_per_second": 0.841
+    }
+  ],
+  "max_steps": 2180,
+  "num_train_epochs": 10,
+  "total_flos": 1.834393807540224e+16,
+  "trial_name": null,
+  "trial_params": null
+}

valid_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_combined_score": 0.9135991932046025,
+    "eval_loss": 0.3487534821033478,
+    "eval_pearson": 0.917271052630473,
+    "eval_runtime": 10.5874,
+    "eval_samples": 871,
+    "eval_samples_per_second": 82.268,
+    "eval_spearmanr": 0.9099273337787319,
+    "eval_steps_per_second": 10.295
+}