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": 28.99,
+    "eval_las": 29.294196353905335,
+    "eval_loss": 3.0349910259246826,
+    "eval_runtime": 6.1778,
+    "eval_samples": 950,
+    "eval_samples_per_second": 153.776,
+    "eval_steps_per_second": 19.262,
+    "eval_uas": 47.00618832580699,
+    "test_las": 30.110473580542944,
+    "test_loss": 2.873572587966919,
+    "test_runtime": 6.3685,
+    "test_samples": 989,
+    "test_samples_per_second": 155.297,
+    "test_steps_per_second": 19.471,
+    "test_uas": 48.87385458593817,
+    "train_loss": 2.234064235687256,
+    "train_runtime": 2087.3588,
+    "train_samples": 4400,
+    "train_samples_per_second": 229.956,
+    "train_steps_per_second": 7.186
+}

config.json

@@ -0,0 +1,106 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForBiaffineParsing"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a563970c986ca0f12e1cccbc6e1d7ff8a926399c131ef52c977205ca5e0b3b
+size 525577269

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-cased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,345 @@
+{
+  "best_metric": 29.294196353905335,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Korean-GSD/checkpoint-1500",
+  "epoch": 28.985507246376812,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.52e-05,
+      "loss": 4.639,
+      "step": 100
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 7.949530201342283e-05,
+      "loss": 3.2377,
+      "step": 200
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 7.895838926174497e-05,
+      "loss": 3.0918,
+      "step": 300
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 7.842147651006712e-05,
+      "loss": 2.9885,
+      "step": 400
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 7.788456375838927e-05,
+      "loss": 2.9165,
+      "step": 500
+    },
+    {
+      "epoch": 3.62,
+      "eval_las": 27.86419133634387,
+      "eval_loss": 2.9203531742095947,
+      "eval_runtime": 6.1866,
+      "eval_samples_per_second": 153.558,
+      "eval_steps_per_second": 19.235,
+      "eval_uas": 44.94062552266265,
+      "step": 500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 7.734765100671142e-05,
+      "loss": 2.8823,
+      "step": 600
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 7.681073825503357e-05,
+      "loss": 2.8323,
+      "step": 700
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 7.627382550335572e-05,
+      "loss": 2.7932,
+      "step": 800
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 7.573691275167786e-05,
+      "loss": 2.753,
+      "step": 900
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 7.52e-05,
+      "loss": 2.7026,
+      "step": 1000
+    },
+    {
+      "epoch": 7.25,
+      "eval_las": 29.118581702625857,
+      "eval_loss": 2.91562819480896,
+      "eval_runtime": 6.1737,
+      "eval_samples_per_second": 153.878,
+      "eval_steps_per_second": 19.275,
+      "eval_uas": 46.52115738417796,
+      "step": 1000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 7.466308724832215e-05,
+      "loss": 2.6742,
+      "step": 1100
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 7.41261744966443e-05,
+      "loss": 2.5757,
+      "step": 1200
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 7.358926174496644e-05,
+      "loss": 2.5635,
+      "step": 1300
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 7.305234899328859e-05,
+      "loss": 2.5617,
+      "step": 1400
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 7.251543624161074e-05,
+      "loss": 2.4701,
+      "step": 1500
+    },
+    {
+      "epoch": 10.87,
+      "eval_las": 29.294196353905335,
+      "eval_loss": 3.0349910259246826,
+      "eval_runtime": 6.1916,
+      "eval_samples_per_second": 153.433,
+      "eval_steps_per_second": 19.219,
+      "eval_uas": 47.00618832580699,
+      "step": 1500
+    },
+    {
+      "epoch": 11.59,
+      "learning_rate": 7.197852348993289e-05,
+      "loss": 2.3668,
+      "step": 1600
+    },
+    {
+      "epoch": 12.32,
+      "learning_rate": 7.144161073825504e-05,
+      "loss": 2.3771,
+      "step": 1700
+    },
+    {
+      "epoch": 13.04,
+      "learning_rate": 7.090469798657718e-05,
+      "loss": 2.3208,
+      "step": 1800
+    },
+    {
+      "epoch": 13.77,
+      "learning_rate": 7.036778523489933e-05,
+      "loss": 2.2402,
+      "step": 1900
+    },
+    {
+      "epoch": 14.49,
+      "learning_rate": 6.983087248322148e-05,
+      "loss": 2.1529,
+      "step": 2000
+    },
+    {
+      "epoch": 14.49,
+      "eval_las": 29.0600434855327,
+      "eval_loss": 3.292515277862549,
+      "eval_runtime": 6.1874,
+      "eval_samples_per_second": 153.538,
+      "eval_steps_per_second": 19.233,
+      "eval_uas": 47.09817695266767,
+      "step": 2000
+    },
+    {
+      "epoch": 15.22,
+      "learning_rate": 6.929395973154363e-05,
+      "loss": 2.1538,
+      "step": 2100
+    },
+    {
+      "epoch": 15.94,
+      "learning_rate": 6.875704697986578e-05,
+      "loss": 2.0934,
+      "step": 2200
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 6.822013422818793e-05,
+      "loss": 1.9925,
+      "step": 2300
+    },
+    {
+      "epoch": 17.39,
+      "learning_rate": 6.768322147651007e-05,
+      "loss": 1.9471,
+      "step": 2400
+    },
+    {
+      "epoch": 18.12,
+      "learning_rate": 6.714630872483222e-05,
+      "loss": 1.9399,
+      "step": 2500
+    },
+    {
+      "epoch": 18.12,
+      "eval_las": 28.85934102692758,
+      "eval_loss": 3.839879274368286,
+      "eval_runtime": 6.1995,
+      "eval_samples_per_second": 153.237,
+      "eval_steps_per_second": 19.195,
+      "eval_uas": 46.28700451580532,
+      "step": 2500
+    },
+    {
+      "epoch": 18.84,
+      "learning_rate": 6.660939597315437e-05,
+      "loss": 1.8651,
+      "step": 2600
+    },
+    {
+      "epoch": 19.57,
+      "learning_rate": 6.607248322147652e-05,
+      "loss": 1.7929,
+      "step": 2700
+    },
+    {
+      "epoch": 20.29,
+      "learning_rate": 6.553557046979867e-05,
+      "loss": 1.7378,
+      "step": 2800
+    },
+    {
+      "epoch": 21.01,
+      "learning_rate": 6.499865771812081e-05,
+      "loss": 1.7862,
+      "step": 2900
+    },
+    {
+      "epoch": 21.74,
+      "learning_rate": 6.446174496644296e-05,
+      "loss": 1.6585,
+      "step": 3000
+    },
+    {
+      "epoch": 21.74,
+      "eval_las": 28.349222277972906,
+      "eval_loss": 4.253769397735596,
+      "eval_runtime": 6.1742,
+      "eval_samples_per_second": 153.865,
+      "eval_steps_per_second": 19.274,
+      "eval_uas": 45.63472152533868,
+      "step": 3000
+    },
+    {
+      "epoch": 22.46,
+      "learning_rate": 6.392483221476511e-05,
+      "loss": 1.6568,
+      "step": 3100
+    },
+    {
+      "epoch": 23.19,
+      "learning_rate": 6.338791946308726e-05,
+      "loss": 1.625,
+      "step": 3200
+    },
+    {
+      "epoch": 23.91,
+      "learning_rate": 6.28510067114094e-05,
+      "loss": 1.628,
+      "step": 3300
+    },
+    {
+      "epoch": 24.64,
+      "learning_rate": 6.231409395973154e-05,
+      "loss": 1.5299,
+      "step": 3400
+    },
+    {
+      "epoch": 25.36,
+      "learning_rate": 6.177718120805369e-05,
+      "loss": 1.5284,
+      "step": 3500
+    },
+    {
+      "epoch": 25.36,
+      "eval_las": 28.6001003512293,
+      "eval_loss": 4.6269941329956055,
+      "eval_runtime": 6.1796,
+      "eval_samples_per_second": 153.733,
+      "eval_steps_per_second": 19.257,
+      "eval_uas": 45.37548084964041,
+      "step": 3500
+    },
+    {
+      "epoch": 26.09,
+      "learning_rate": 6.124026845637584e-05,
+      "loss": 1.5192,
+      "step": 3600
+    },
+    {
+      "epoch": 26.81,
+      "learning_rate": 6.070335570469799e-05,
+      "loss": 1.4848,
+      "step": 3700
+    },
+    {
+      "epoch": 27.54,
+      "learning_rate": 6.0166442953020136e-05,
+      "loss": 1.4342,
+      "step": 3800
+    },
+    {
+      "epoch": 28.26,
+      "learning_rate": 5.962953020134229e-05,
+      "loss": 1.418,
+      "step": 3900
+    },
+    {
+      "epoch": 28.99,
+      "learning_rate": 5.909261744966444e-05,
+      "loss": 1.4311,
+      "step": 4000
+    },
+    {
+      "epoch": 28.99,
+      "eval_las": 28.299046663321626,
+      "eval_loss": 4.774014472961426,
+      "eval_runtime": 6.1783,
+      "eval_samples_per_second": 153.765,
+      "eval_steps_per_second": 19.261,
+      "eval_uas": 45.16641578859341,
+      "step": 4000
+    },
+    {
+      "epoch": 28.99,
+      "step": 4000,
+      "total_flos": 2.1298234165100544e+16,
+      "train_loss": 2.234064235687256,
+      "train_runtime": 2087.3588,
+      "train_samples_per_second": 229.956,
+      "train_steps_per_second": 7.186
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 109,
+  "total_flos": 2.1298234165100544e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8b845c9911c1d4335a76e4d288d4dcad253b59902b2d6654f5f08019455c5b
+size 3387