Upload best checkpoint for bert-base-multilingual-cased_fold_0

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f963744a06d8b7a89075a7b8e398b8cdf981063e17592a6a1bdb3b999b4870
+size 711443456

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5822def57cb0340641066c098c392c360ae610616546c11d4daaf99d339747b0
+size 1423007994

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a630957004990b03073ef5a2ebff93ab40f6ddc5a17eac2a3226d4270647db90
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a0a03af3366488145de520c0bd02bcbfb45eb12a4fc5c0fcf3a9b2753cd7c0
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_global_step": 1244,
+  "best_metric": 0.8507081171349183,
+  "best_model_checkpoint": "./results-PR/bert-base-multilingual-cased_fold_0/checkpoint-1244",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1244,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8038585209003215,
+      "grad_norm": 7.114378929138184,
+      "learning_rate": 2.0056270096463023e-05,
+      "loss": 0.5627,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6967015285599356,
+      "eval_f1": 0.7010085418034284,
+      "eval_loss": 0.598173975944519,
+      "eval_precision": 0.8246874487091888,
+      "eval_recall": 0.6967015285599356,
+      "eval_runtime": 5.247,
+      "eval_samples_per_second": 236.898,
+      "eval_steps_per_second": 29.731,
+      "step": 622
+    },
+    {
+      "epoch": 1.607717041800643,
+      "grad_norm": 5.695389747619629,
+      "learning_rate": 4.0152733118971066e-05,
+      "loss": 0.5187,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8487530168946098,
+      "eval_f1": 0.8507081171349183,
+      "eval_loss": 0.5054676532745361,
+      "eval_precision": 0.8555064529752252,
+      "eval_recall": 0.8487530168946098,
+      "eval_runtime": 5.797,
+      "eval_samples_per_second": 214.42,
+      "eval_steps_per_second": 26.91,
+      "step": 1244
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2615323890278400.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fad7626a268a86fcd2af8bc76723535bc22b99c7271a56102bf0229f504399
+size 5368