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:fd6630922940d7868f4f53f826382c5b261b55ab11b226eaa9f3141d47026eee
+size 709083980

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a253f8fec005df252510d973ec40f57b5611256a2839f292d626e35a9d45505
+size 1418282106

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaef4d03c58d19510a1abb4fa24723119d6f0c53100d7d8c61cbc7083b7b5be7
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3249cb33f83bf8719a679cd7df8b5a8e47ef0927c1fb5a2621ae16e84771d7c5
+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 +1,129 @@
+{
+  "best_metric": 0.3673701882362366,
+  "best_model_checkpoint": "/content/drive/MyDrive/BERT/np_model_en/checkpoint-1281",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 5124,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.60967993754879e-06,
+      "loss": 0.017,
+      "step": 500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.2193598750975805e-06,
+      "loss": 0.0185,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9556333917104495,
+      "eval_f1": 0.8681155105686216,
+      "eval_loss": 0.3673701882362366,
+      "eval_precision": 0.8556338028169014,
+      "eval_recall": 0.8809667673716012,
+      "eval_runtime": 12.6723,
+      "eval_samples_per_second": 50.583,
+      "eval_steps_per_second": 25.331,
+      "step": 1281
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.82903981264637e-06,
+      "loss": 0.0171,
+      "step": 1500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.43871975019516e-06,
+      "loss": 0.026,
+      "step": 2000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.04839968774395e-06,
+      "loss": 0.0147,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9529334500875657,
+      "eval_f1": 0.8568033273915627,
+      "eval_loss": 0.3900972008705139,
+      "eval_precision": 0.842781998831093,
+      "eval_recall": 0.8712990936555891,
+      "eval_runtime": 12.7155,
+      "eval_samples_per_second": 50.411,
+      "eval_steps_per_second": 25.245,
+      "step": 2562
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 3.6580796252927404e-06,
+      "loss": 0.0165,
+      "step": 3000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.26775956284153e-06,
+      "loss": 0.0157,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9541009924109749,
+      "eval_f1": 0.8641901931649331,
+      "eval_loss": 0.39443621039390564,
+      "eval_precision": 0.8502923976608188,
+      "eval_recall": 0.8785498489425981,
+      "eval_runtime": 12.2687,
+      "eval_samples_per_second": 52.247,
+      "eval_steps_per_second": 26.164,
+      "step": 3843
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 2.8774395003903203e-06,
+      "loss": 0.0099,
+      "step": 4000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.48711943793911e-06,
+      "loss": 0.0088,
+      "step": 4500
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 2.0967993754879002e-06,
+      "loss": 0.0137,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9572387624051372,
+      "eval_f1": 0.8727598566308244,
+      "eval_loss": 0.37448590993881226,
+      "eval_precision": 0.8629651506202008,
+      "eval_recall": 0.8827794561933535,
+      "eval_runtime": 13.0619,
+      "eval_samples_per_second": 49.074,
+      "eval_steps_per_second": 24.575,
+      "step": 5124
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7686,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 193986016343568.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2d413ba8c2d368b5338bfb9ad46ab10c411780a5bf4b09dcb6958b981906f2
+size 4728