Upload 11 files

config.json

@@ -0,0 +1,135 @@
+{
+  "_name_or_path": "mbruton/spa_mBERT",
+  "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 sha256:00c3456259bd016acb0ba94114f64bd95a3805dca1d2041d0867185ea2aa02a7
+size 1418525797

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8ff3193a40e457469f08975787d5619a0bdd0769dc365e0e902e18668d9dd2
+size 709275633

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478142f0fbeb50d21dde010322218069e75aaefea35c551e692fea734dd91394
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6ea3f39845052ca758a3db1bba68813da22478b6e8fddd3de91aa8d2da7249
+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 +1,76 @@
+{
+  "best_metric": 0.3174082040786743,
+  "best_model_checkpoint": "gal_sp_mBERT/checkpoint-750",
+  "epoch": 4.0,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8976631501472031,
+      "eval_f1": 0.6289719626168223,
+      "eval_loss": 0.36869561672210693,
+      "eval_precision": 0.682786608048698,
+      "eval_recall": 0.5830205024545192,
+      "eval_runtime": 5.5033,
+      "eval_samples_per_second": 181.163,
+      "eval_steps_per_second": 11.448,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.4367,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.914622178606477,
+      "eval_f1": 0.7035446539049421,
+      "eval_loss": 0.3205152750015259,
+      "eval_precision": 0.7093791281373845,
+      "eval_recall": 0.6978053710655501,
+      "eval_runtime": 5.8377,
+      "eval_samples_per_second": 170.785,
+      "eval_steps_per_second": 10.792,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9163702158979392,
+      "eval_f1": 0.7188652482269503,
+      "eval_loss": 0.3174082040786743,
+      "eval_precision": 0.7064399219403401,
+      "eval_recall": 0.7317354894600058,
+      "eval_runtime": 5.6206,
+      "eval_samples_per_second": 177.384,
+      "eval_steps_per_second": 11.209,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.2325,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9164315505397449,
+      "eval_f1": 0.709383145091225,
+      "eval_loss": 0.32722988724708557,
+      "eval_precision": 0.7114435085681092,
+      "eval_recall": 0.7073346809125036,
+      "eval_runtime": 5.4618,
+      "eval_samples_per_second": 182.541,
+      "eval_steps_per_second": 11.535,
+      "step": 1000
+    }
+  ],
+  "max_steps": 25000,
+  "num_train_epochs": 100,
+  "total_flos": 623488737039000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91208781d779f9188be4792bdcaa4c3a23be443f8f16c38d0acc8e70be49af12
+size 3503