Upload 11 files

config.json

@@ -0,0 +1,135 @@
+{
+  "_name_or_path": "liaad/srl-en_mbert-base",
+  "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:c5d8973f363cfc6d8de8d44368d7778f6dbe6e2b079346fcea0c455397c2576e
+size 1418525797

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40bb8048ab950c5b3507fcdf9863a438f3268ec23662eafe8a9be7dfab0d872
+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 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--liaad--srl-en_mbert-base/snapshots/0c963b783ca3a81aafce1c53c0bb17715a7f0903/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.3187411427497864,
+  "best_model_checkpoint": "gal_en_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": 0.8779133954857704,
+      "eval_f1": 0.5262912258867455,
+      "eval_loss": 0.44472846388816833,
+      "eval_precision": 0.5704890387858348,
+      "eval_recall": 0.4884493213976321,
+      "eval_runtime": 5.3275,
+      "eval_samples_per_second": 187.141,
+      "eval_steps_per_second": 11.825,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.5654,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.897479146221786,
+      "eval_f1": 0.6228456315750205,
+      "eval_loss": 0.36001163721084595,
+      "eval_precision": 0.6444341516134012,
+      "eval_recall": 0.6026566560785446,
+      "eval_runtime": 5.2617,
+      "eval_samples_per_second": 189.481,
+      "eval_steps_per_second": 11.973,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9003312070657508,
+      "eval_f1": 0.6522937725312786,
+      "eval_loss": 0.3470691740512848,
+      "eval_precision": 0.6389696717906107,
+      "eval_recall": 0.666185388391568,
+      "eval_runtime": 5.3516,
+      "eval_samples_per_second": 186.3,
+      "eval_steps_per_second": 11.772,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.2726,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9087953876349362,
+      "eval_f1": 0.6704950207167261,
+      "eval_loss": 0.32999733090400696,
+      "eval_precision": 0.6751573708095447,
+      "eval_recall": 0.6658966214265089,
+      "eval_runtime": 5.2725,
+      "eval_samples_per_second": 189.094,
+      "eval_steps_per_second": 11.949,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.914407507360157,
+      "eval_f1": 0.6932259245697546,
+      "eval_loss": 0.3187411427497864,
+      "eval_precision": 0.7033734581661465,
+      "eval_recall": 0.6833670228125902,
+      "eval_runtime": 5.3299,
+      "eval_samples_per_second": 187.056,
+      "eval_steps_per_second": 11.82,
+      "step": 1250
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.88e-05,
+      "loss": 0.1882,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9141008341511285,
+      "eval_f1": 0.7037852425253888,
+      "eval_loss": 0.33032578229904175,
+      "eval_precision": 0.6925227113906359,
+      "eval_recall": 0.7154201559341611,
+      "eval_runtime": 5.4015,
+      "eval_samples_per_second": 184.577,
+      "eval_steps_per_second": 11.663,
+      "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 sha256:999e47d0e57ea1a36c9092deb6b1fe05b1351f5189bf370df1e0c1d68c5798a6
+size 3503