Upload 11 files

config.json

@@ -0,0 +1,135 @@
+{
+  "_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": "O",
+    "1": "r0:arg0",
+    "2": "r0:arg1",
+    "3": "r0:arg2",
+    "4": "r0:root",
+    "5": "r10:arg0",
+    "6": "r10:arg1",
+    "7": "r10:root",
+    "8": "r11:arg0",
+    "9": "r11:root",
+    "10": "r12:arg1",
+    "11": "r12:root",
+    "12": "r13:arg1",
+    "13": "r13:root",
+    "14": "r1:arg0",
+    "15": "r1:arg1",
+    "16": "r1:arg2",
+    "17": "r1:root",
+    "18": "r2:arg0",
+    "19": "r2:arg1",
+    "20": "r2:arg2",
+    "21": "r2:root",
+    "22": "r3:arg0",
+    "23": "r3:arg1",
+    "24": "r3:arg2",
+    "25": "r3:root",
+    "26": "r4:arg0",
+    "27": "r4:arg1",
+    "28": "r4:arg2",
+    "29": "r4:root",
+    "30": "r5:arg0",
+    "31": "r5:arg1",
+    "32": "r5:arg2",
+    "33": "r5:root",
+    "34": "r6:arg0",
+    "35": "r6:arg1",
+    "36": "r6:arg2",
+    "37": "r6:root",
+    "38": "r7:arg0",
+    "39": "r7:arg1",
+    "40": "r7:arg2",
+    "41": "r7:root",
+    "42": "r8:arg0",
+    "43": "r8:arg1",
+    "44": "r8:arg2",
+    "45": "r8:root",
+    "46": "r9:arg0",
+    "47": "r9:arg1",
+    "48": "r9:arg2",
+    "49": "r9:root"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "r0:arg0": 1,
+    "r0:arg1": 2,
+    "r0:arg2": 3,
+    "r0:root": 4,
+    "r10:arg0": 5,
+    "r10:arg1": 6,
+    "r10:root": 7,
+    "r11:arg0": 8,
+    "r11:root": 9,
+    "r12:arg1": 10,
+    "r12:root": 11,
+    "r13:arg1": 12,
+    "r13:root": 13,
+    "r1:arg0": 14,
+    "r1:arg1": 15,
+    "r1:arg2": 16,
+    "r1:root": 17,
+    "r2:arg0": 18,
+    "r2:arg1": 19,
+    "r2:arg2": 20,
+    "r2:root": 21,
+    "r3:arg0": 22,
+    "r3:arg1": 23,
+    "r3:arg2": 24,
+    "r3:root": 25,
+    "r4:arg0": 26,
+    "r4:arg1": 27,
+    "r4:arg2": 28,
+    "r4:root": 29,
+    "r5:arg0": 30,
+    "r5:arg1": 31,
+    "r5:arg2": 32,
+    "r5:root": 33,
+    "r6:arg0": 34,
+    "r6:arg1": 35,
+    "r6:arg2": 36,
+    "r6:root": 37,
+    "r7:arg0": 38,
+    "r7:arg1": 39,
+    "r7:arg2": 40,
+    "r7:root": 41,
+    "r8:arg0": 42,
+    "r8:arg1": 43,
+    "r8:arg2": 44,
+    "r8:root": 45,
+    "r9:arg0": 46,
+    "r9:arg1": 47,
+    "r9:arg2": 48,
+    "r9:root": 49
+  },
+  "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": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0126b545fe0240a13b963ec94f4d0f15c7a1b8e8ad181dd91e838ad195eb0f82
+size 1418525797

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2715586e0486b8314a7ca5722d32049169ef63a5d1eddd9400301bc55949880d
+size 709275633

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28238529fef29fb763aa58326402157c5346334cabb7c711b05d5a3f1e020c9e
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14881f8352737c801b7e15ff2544419ace05937680ded1c03cfe4be45005e78
+size 623

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 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.32368871569633484,
+  "best_model_checkpoint": "gal_mBERT/checkpoint-1250",
+  "epoch": 6.0,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8816548086359176,
+      "eval_f1": 0.5462899150011488,
+      "eval_loss": 0.42043304443359375,
+      "eval_precision": 0.5816076960704386,
+      "eval_recall": 0.5150158821830783,
+      "eval_runtime": 5.2868,
+      "eval_samples_per_second": 188.582,
+      "eval_steps_per_second": 11.916,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.5392,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8960377821393523,
+      "eval_f1": 0.6141933543827995,
+      "eval_loss": 0.35990580916404724,
+      "eval_precision": 0.6406838143036386,
+      "eval_recall": 0.5898065261334103,
+      "eval_runtime": 5.3036,
+      "eval_samples_per_second": 187.984,
+      "eval_steps_per_second": 11.879,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9000245338567223,
+      "eval_f1": 0.6498169529709941,
+      "eval_loss": 0.3427206575870514,
+      "eval_precision": 0.6341027754877714,
+      "eval_recall": 0.6663297718740976,
+      "eval_runtime": 5.3775,
+      "eval_samples_per_second": 185.401,
+      "eval_steps_per_second": 11.715,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.2739,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.907262021589794,
+      "eval_f1": 0.6595900439238652,
+      "eval_loss": 0.3309294283390045,
+      "eval_precision": 0.668993168993169,
+      "eval_recall": 0.6504475887958417,
+      "eval_runtime": 5.2835,
+      "eval_samples_per_second": 188.7,
+      "eval_steps_per_second": 11.924,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9131194798822375,
+      "eval_f1": 0.6891636363636363,
+      "eval_loss": 0.32368871569633484,
+      "eval_precision": 0.6943141852286049,
+      "eval_recall": 0.6840889402252383,
+      "eval_runtime": 5.2998,
+      "eval_samples_per_second": 188.119,
+      "eval_steps_per_second": 11.887,
+      "step": 1250
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.88e-05,
+      "loss": 0.1948,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9126288027477919,
+      "eval_f1": 0.69868810833686,
+      "eval_loss": 0.3336099088191986,
+      "eval_precision": 0.6829840044125759,
+      "eval_recall": 0.7151313889691019,
+      "eval_runtime": 5.4071,
+      "eval_samples_per_second": 184.388,
+      "eval_steps_per_second": 11.651,
+      "step": 1500
+    }
+  ],
+  "max_steps": 25000,
+  "num_train_epochs": 100,
+  "total_flos": 934904811170400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6250f2149d4dc6cb98df45879dd43456bab54a87bd001bb8146be4d8981913
+size 3503