Upload 11 files

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.36.2",
+  "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 sha256:9c767dfad3e29b518a057bf3ddd2b28b799a2aa05f35665604b6de4f57f96c57
+size 709083980

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412a82c2234920070b300ca21df1bfafcf0180706e661425ae0bf65d4fbf7c92
+size 1418282106

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bdea52281fced67da539f1a74b02436bd3710b220c686fd0178a16ebee67528
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68dbb6dc288a6449e49b997de05c3510a00e08d8853d3539d8e9d035a845a35a
+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 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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 +1,123 @@
+{
+  "best_metric": 0.1812099814414978,
+  "best_model_checkpoint": "/content/drive/MyDrive/BERT/np_model_es/checkpoint-486",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1701,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9390050468637346,
+      "eval_f1": 0.7960042060988434,
+      "eval_loss": 0.19681523740291595,
+      "eval_precision": 0.7577577577577578,
+      "eval_recall": 0.8383167220376523,
+      "eval_runtime": 5.2116,
+      "eval_samples_per_second": 46.435,
+      "eval_steps_per_second": 11.705,
+      "step": 243
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.949098774333093,
+      "eval_f1": 0.8397027600849256,
+      "eval_loss": 0.1812099814414978,
+      "eval_precision": 0.8063200815494393,
+      "eval_recall": 0.875968992248062,
+      "eval_runtime": 5.4915,
+      "eval_samples_per_second": 44.069,
+      "eval_steps_per_second": 11.108,
+      "step": 486
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 7.94238683127572e-06,
+      "loss": 0.2577,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9495313626532084,
+      "eval_f1": 0.8511326860841423,
+      "eval_loss": 0.19488638639450073,
+      "eval_precision": 0.8296529968454258,
+      "eval_recall": 0.8737541528239202,
+      "eval_runtime": 5.0485,
+      "eval_samples_per_second": 47.935,
+      "eval_steps_per_second": 12.083,
+      "step": 729
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.950396539293439,
+      "eval_f1": 0.8493297587131368,
+      "eval_loss": 0.21376554667949677,
+      "eval_precision": 0.8232848232848233,
+      "eval_recall": 0.8770764119601329,
+      "eval_runtime": 4.8302,
+      "eval_samples_per_second": 50.101,
+      "eval_steps_per_second": 12.629,
+      "step": 972
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 5.884773662551441e-06,
+      "loss": 0.1112,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9499639509733238,
+      "eval_f1": 0.8502732240437159,
+      "eval_loss": 0.24179881811141968,
+      "eval_precision": 0.8392664509169363,
+      "eval_recall": 0.8615725359911407,
+      "eval_runtime": 4.8298,
+      "eval_samples_per_second": 50.106,
+      "eval_steps_per_second": 12.63,
+      "step": 1215
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9492429704397981,
+      "eval_f1": 0.8493449781659388,
+      "eval_loss": 0.24828843772411346,
+      "eval_precision": 0.83745963401507,
+      "eval_recall": 0.8615725359911407,
+      "eval_runtime": 5.5749,
+      "eval_samples_per_second": 43.409,
+      "eval_steps_per_second": 10.942,
+      "step": 1458
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 3.827160493827161e-06,
+      "loss": 0.0661,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.949098774333093,
+      "eval_f1": 0.8526200873362445,
+      "eval_loss": 0.2728496193885803,
+      "eval_precision": 0.8406889128094726,
+      "eval_recall": 0.8648947951273532,
+      "eval_runtime": 4.9946,
+      "eval_samples_per_second": 48.452,
+      "eval_steps_per_second": 12.213,
+      "step": 1701
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2430,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 224033373641160.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e87a3ed6a162fca7747f429127ee0fc9f8ed2b3f94362a617fb2466891f27e
+size 4728