Upload with huggingface_hub

README.md

@@ -0,0 +1,15 @@
+---
+license: apache-2.0
+tags:
+- canine
+- pretrained-on-english-language
+---
+
+### How to use
+
+Here is how to use this model:
+
+```python
+from transformers import CanineModel
+model = CanineModel.from_pretrained('mushfiqur11/<repo name>')
+```

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 36.0,
+    "eval_las": 82.59496169943931,
+    "eval_loss": 1.4142358303070068,
+    "eval_runtime": 3.6817,
+    "eval_samples": 500,
+    "eval_samples_per_second": 135.809,
+    "eval_steps_per_second": 17.112,
+    "eval_uas": 86.22759219774146,
+    "test_las": 84.14085914085913,
+    "test_loss": 1.319367527961731,
+    "test_runtime": 3.6296,
+    "test_samples": 500,
+    "test_samples_per_second": 137.755,
+    "test_steps_per_second": 17.357,
+    "test_uas": 87.56243756243757,
+    "train_loss": 0.1895591730541653,
+    "train_runtime": 2603.8023,
+    "train_samples": 3997,
+    "train_samples_per_second": 184.346,
+    "train_steps_per_second": 5.761
+}

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForBiaffineParsing"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "_",
+    "1": "acl",
+    "2": "advcl",
+    "3": "advmod",
+    "4": "amod",
+    "5": "appos",
+    "6": "aux",
+    "7": "case",
+    "8": "cc",
+    "9": "ccomp",
+    "10": "clf",
+    "11": "compound",
+    "12": "conj",
+    "13": "cop",
+    "14": "csubj",
+    "15": "dep",
+    "16": "det",
+    "17": "discourse",
+    "18": "dislocated",
+    "19": "expl",
+    "20": "fixed",
+    "21": "flat",
+    "22": "goeswith",
+    "23": "iobj",
+    "24": "list",
+    "25": "mark",
+    "26": "nmod",
+    "27": "nsubj",
+    "28": "nummod",
+    "29": "obj",
+    "30": "obl",
+    "31": "orphan",
+    "32": "parataxis",
+    "33": "punct",
+    "34": "reparandum",
+    "35": "root",
+    "36": "vocative",
+    "37": "xcomp"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_": 0,
+    "acl": 1,
+    "advcl": 2,
+    "advmod": 3,
+    "amod": 4,
+    "appos": 5,
+    "aux": 6,
+    "case": 7,
+    "cc": 8,
+    "ccomp": 9,
+    "clf": 10,
+    "compound": 11,
+    "conj": 12,
+    "cop": 13,
+    "csubj": 14,
+    "dep": 15,
+    "det": 16,
+    "discourse": 17,
+    "dislocated": 18,
+    "expl": 19,
+    "fixed": 20,
+    "flat": 21,
+    "goeswith": 22,
+    "iobj": 23,
+    "list": 24,
+    "mark": 25,
+    "nmod": 26,
+    "nsubj": 27,
+    "nummod": 28,
+    "obj": 29,
+    "obl": 30,
+    "orphan": 31,
+    "parataxis": 32,
+    "punct": 33,
+    "reparandum": 34,
+    "root": 35,
+    "vocative": 36,
+    "xcomp": 37
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": -100,
+  "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": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2172417277d665da3b7c00a0019481153224adf04091cd30eca480d0b489a5e7
+size 803749941

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,385 @@
+{
+  "best_metric": 82.59496169943931,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/bert-base-finetuned-parsing-ud-Chinese-GSD/checkpoint-2000",
+  "epoch": 36.0,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.840000000000001e-05,
+      "loss": 3.3926,
+      "step": 100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 7.947919463087248e-05,
+      "loss": 1.027,
+      "step": 200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.894228187919463e-05,
+      "loss": 0.6817,
+      "step": 300
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 7.840536912751678e-05,
+      "loss": 0.5063,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.786845637583893e-05,
+      "loss": 0.367,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_las": 81.48148148148148,
+      "eval_loss": 0.8465050458908081,
+      "eval_runtime": 3.7622,
+      "eval_samples_per_second": 132.902,
+      "eval_steps_per_second": 16.746,
+      "eval_uas": 85.58003632630499,
+      "step": 500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 7.733154362416108e-05,
+      "loss": 0.259,
+      "step": 600
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 7.679463087248322e-05,
+      "loss": 0.2121,
+      "step": 700
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 7.625771812080537e-05,
+      "loss": 0.1829,
+      "step": 800
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 7.572080536912752e-05,
+      "loss": 0.1592,
+      "step": 900
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 7.518389261744967e-05,
+      "loss": 0.135,
+      "step": 1000
+    },
+    {
+      "epoch": 8.0,
+      "eval_las": 82.23959567243149,
+      "eval_loss": 1.149000883102417,
+      "eval_runtime": 3.7521,
+      "eval_samples_per_second": 133.26,
+      "eval_steps_per_second": 16.791,
+      "eval_uas": 86.01437258153676,
+      "step": 1000
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 7.464697986577182e-05,
+      "loss": 0.1142,
+      "step": 1100
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 7.411006711409397e-05,
+      "loss": 0.1008,
+      "step": 1200
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 7.357315436241611e-05,
+      "loss": 0.0923,
+      "step": 1300
+    },
+    {
+      "epoch": 11.2,
+      "learning_rate": 7.303624161073826e-05,
+      "loss": 0.0833,
+      "step": 1400
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 7.249932885906041e-05,
+      "loss": 0.0804,
+      "step": 1500
+    },
+    {
+      "epoch": 12.0,
+      "eval_las": 81.89212666824606,
+      "eval_loss": 1.3434501886367798,
+      "eval_runtime": 3.7531,
+      "eval_samples_per_second": 133.225,
+      "eval_steps_per_second": 16.786,
+      "eval_uas": 85.7458738055753,
+      "step": 1500
+    },
+    {
+      "epoch": 12.8,
+      "learning_rate": 7.196241610738256e-05,
+      "loss": 0.0703,
+      "step": 1600
+    },
+    {
+      "epoch": 13.6,
+      "learning_rate": 7.142550335570471e-05,
+      "loss": 0.0663,
+      "step": 1700
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 7.088859060402686e-05,
+      "loss": 0.0638,
+      "step": 1800
+    },
+    {
+      "epoch": 15.2,
+      "learning_rate": 7.0351677852349e-05,
+      "loss": 0.0564,
+      "step": 1900
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 6.981476510067114e-05,
+      "loss": 0.0593,
+      "step": 2000
+    },
+    {
+      "epoch": 16.0,
+      "eval_las": 82.59496169943931,
+      "eval_loss": 1.4142358303070068,
+      "eval_runtime": 3.7723,
+      "eval_samples_per_second": 132.545,
+      "eval_steps_per_second": 16.701,
+      "eval_uas": 86.22759219774146,
+      "step": 2000
+    },
+    {
+      "epoch": 16.8,
+      "learning_rate": 6.927785234899329e-05,
+      "loss": 0.0506,
+      "step": 2100
+    },
+    {
+      "epoch": 17.6,
+      "learning_rate": 6.874093959731543e-05,
+      "loss": 0.0486,
+      "step": 2200
+    },
+    {
+      "epoch": 18.4,
+      "learning_rate": 6.820402684563758e-05,
+      "loss": 0.0481,
+      "step": 2300
+    },
+    {
+      "epoch": 19.2,
+      "learning_rate": 6.766711409395973e-05,
+      "loss": 0.0433,
+      "step": 2400
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 6.713020134228188e-05,
+      "loss": 0.0425,
+      "step": 2500
+    },
+    {
+      "epoch": 20.0,
+      "eval_las": 81.96319987364762,
+      "eval_loss": 1.5313485860824585,
+      "eval_runtime": 3.7514,
+      "eval_samples_per_second": 133.284,
+      "eval_steps_per_second": 16.794,
+      "eval_uas": 85.66690357735133,
+      "step": 2500
+    },
+    {
+      "epoch": 20.8,
+      "learning_rate": 6.659328859060403e-05,
+      "loss": 0.0427,
+      "step": 2600
+    },
+    {
+      "epoch": 21.6,
+      "learning_rate": 6.605637583892618e-05,
+      "loss": 0.0386,
+      "step": 2700
+    },
+    {
+      "epoch": 22.4,
+      "learning_rate": 6.551946308724832e-05,
+      "loss": 0.0384,
+      "step": 2800
+    },
+    {
+      "epoch": 23.2,
+      "learning_rate": 6.498255033557047e-05,
+      "loss": 0.0329,
+      "step": 2900
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 6.444563758389262e-05,
+      "loss": 0.0367,
+      "step": 3000
+    },
+    {
+      "epoch": 24.0,
+      "eval_las": 82.53178551686014,
+      "eval_loss": 1.592229962348938,
+      "eval_runtime": 3.6848,
+      "eval_samples_per_second": 135.693,
+      "eval_steps_per_second": 17.097,
+      "eval_uas": 86.06965174129353,
+      "step": 3000
+    },
+    {
+      "epoch": 24.8,
+      "learning_rate": 6.390872483221477e-05,
+      "loss": 0.0318,
+      "step": 3100
+    },
+    {
+      "epoch": 25.6,
+      "learning_rate": 6.337181208053692e-05,
+      "loss": 0.0335,
+      "step": 3200
+    },
+    {
+      "epoch": 26.4,
+      "learning_rate": 6.283489932885907e-05,
+      "loss": 0.033,
+      "step": 3300
+    },
+    {
+      "epoch": 27.2,
+      "learning_rate": 6.229798657718121e-05,
+      "loss": 0.0305,
+      "step": 3400
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 6.176107382550336e-05,
+      "loss": 0.0286,
+      "step": 3500
+    },
+    {
+      "epoch": 28.0,
+      "eval_las": 82.16852246702993,
+      "eval_loss": 1.742520809173584,
+      "eval_runtime": 3.6834,
+      "eval_samples_per_second": 135.745,
+      "eval_steps_per_second": 17.104,
+      "eval_uas": 85.96699044460239,
+      "step": 3500
+    },
+    {
+      "epoch": 28.8,
+      "learning_rate": 6.122416107382551e-05,
+      "loss": 0.0269,
+      "step": 3600
+    },
+    {
+      "epoch": 29.6,
+      "learning_rate": 6.068724832214766e-05,
+      "loss": 0.0242,
+      "step": 3700
+    },
+    {
+      "epoch": 30.4,
+      "learning_rate": 6.015033557046981e-05,
+      "loss": 0.0273,
+      "step": 3800
+    },
+    {
+      "epoch": 31.2,
+      "learning_rate": 5.9613422818791955e-05,
+      "loss": 0.0244,
+      "step": 3900
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 5.90765100671141e-05,
+      "loss": 0.0254,
+      "step": 4000
+    },
+    {
+      "epoch": 32.0,
+      "eval_las": 81.81315644002211,
+      "eval_loss": 1.792807698249817,
+      "eval_runtime": 3.6847,
+      "eval_samples_per_second": 135.698,
+      "eval_steps_per_second": 17.098,
+      "eval_uas": 85.65110953170655,
+      "step": 4000
+    },
+    {
+      "epoch": 32.8,
+      "learning_rate": 5.853959731543625e-05,
+      "loss": 0.0234,
+      "step": 4100
+    },
+    {
+      "epoch": 33.6,
+      "learning_rate": 5.80026845637584e-05,
+      "loss": 0.0228,
+      "step": 4200
+    },
+    {
+      "epoch": 34.4,
+      "learning_rate": 5.7465771812080534e-05,
+      "loss": 0.0219,
+      "step": 4300
+    },
+    {
+      "epoch": 35.2,
+      "learning_rate": 5.692885906040268e-05,
+      "loss": 0.0204,
+      "step": 4400
+    },
+    {
+      "epoch": 36.0,
+      "learning_rate": 5.639194630872483e-05,
+      "loss": 0.0238,
+      "step": 4500
+    },
+    {
+      "epoch": 36.0,
+      "eval_las": 81.94740582800284,
+      "eval_loss": 1.849847435951233,
+      "eval_runtime": 3.6813,
+      "eval_samples_per_second": 135.822,
+      "eval_steps_per_second": 17.114,
+      "eval_uas": 85.52475716654821,
+      "step": 4500
+    },
+    {
+      "epoch": 36.0,
+      "step": 4500,
+      "total_flos": 2.4026636277633024e+16,
+      "train_loss": 0.1895591730541653,
+      "train_runtime": 2603.8023,
+      "train_samples_per_second": 184.346,
+      "train_steps_per_second": 5.761
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 120,
+  "total_flos": 2.4026636277633024e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97f5552e990ed9d250f561a0571df811aa54ebbd952b190635ea73abdbe325d
+size 3387