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": 29.41,
+    "eval_las": 76.59314722877838,
+    "eval_loss": 2.0029706954956055,
+    "eval_runtime": 3.6676,
+    "eval_samples": 507,
+    "eval_samples_per_second": 138.239,
+    "eval_steps_per_second": 17.45,
+    "eval_uas": 80.7682916904045,
+    "test_las": 73.48473223876016,
+    "test_loss": 2.3923442363739014,
+    "test_runtime": 3.9112,
+    "test_samples": 543,
+    "test_samples_per_second": 138.834,
+    "test_steps_per_second": 17.386,
+    "test_uas": 78.47168942765076,
+    "train_loss": 0.30513293038881745,
+    "train_runtime": 3575.6323,
+    "train_samples": 7050,
+    "train_samples_per_second": 134.242,
+    "train_steps_per_second": 4.195
+}

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 sha256:6ef1f98b6a7e0b609fd38158310ff47c036224faf9db35c7eb27e40ed6b8563c
+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 +1,545 @@
+{
+  "best_metric": 76.59314722877838,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Japanese-GSD/checkpoint-4000",
+  "epoch": 29.41176470588235,
+  "global_step": 6500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.52e-05,
+      "loss": 3.6592,
+      "step": 100
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.949530201342283e-05,
+      "loss": 1.457,
+      "step": 200
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 7.895838926174497e-05,
+      "loss": 1.1567,
+      "step": 300
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.842147651006712e-05,
+      "loss": 1.0594,
+      "step": 400
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 7.788456375838927e-05,
+      "loss": 0.9461,
+      "step": 500
+    },
+    {
+      "epoch": 2.26,
+      "eval_las": 72.71913404411167,
+      "eval_loss": 0.9768415689468384,
+      "eval_runtime": 3.6781,
+      "eval_samples_per_second": 137.841,
+      "eval_steps_per_second": 17.4,
+      "eval_uas": 77.79767233661593,
+      "step": 500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 7.734765100671142e-05,
+      "loss": 0.8798,
+      "step": 600
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 7.681073825503357e-05,
+      "loss": 0.8167,
+      "step": 700
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 7.627382550335572e-05,
+      "loss": 0.7486,
+      "step": 800
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 7.573691275167786e-05,
+      "loss": 0.7195,
+      "step": 900
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 7.52e-05,
+      "loss": 0.6067,
+      "step": 1000
+    },
+    {
+      "epoch": 4.52,
+      "eval_las": 75.72230813054448,
+      "eval_loss": 0.9424547553062439,
+      "eval_runtime": 3.6759,
+      "eval_samples_per_second": 137.927,
+      "eval_steps_per_second": 17.411,
+      "eval_uas": 80.39391226499552,
+      "step": 1000
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 7.466308724832215e-05,
+      "loss": 0.6358,
+      "step": 1100
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 7.41261744966443e-05,
+      "loss": 0.4864,
+      "step": 1200
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 7.358926174496644e-05,
+      "loss": 0.5311,
+      "step": 1300
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 7.305234899328859e-05,
+      "loss": 0.4331,
+      "step": 1400
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 7.251543624161074e-05,
+      "loss": 0.4255,
+      "step": 1500
+    },
+    {
+      "epoch": 6.79,
+      "eval_las": 75.43745421990722,
+      "eval_loss": 1.1136951446533203,
+      "eval_runtime": 3.6925,
+      "eval_samples_per_second": 137.307,
+      "eval_steps_per_second": 17.333,
+      "eval_uas": 80.19044518596891,
+      "step": 1500
+    },
+    {
+      "epoch": 7.24,
+      "learning_rate": 7.197852348993289e-05,
+      "loss": 0.3744,
+      "step": 1600
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 7.144161073825504e-05,
+      "loss": 0.3474,
+      "step": 1700
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 7.090469798657718e-05,
+      "loss": 0.3244,
+      "step": 1800
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 7.036778523489933e-05,
+      "loss": 0.2716,
+      "step": 1900
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 6.983087248322148e-05,
+      "loss": 0.2877,
+      "step": 2000
+    },
+    {
+      "epoch": 9.05,
+      "eval_las": 75.58395051680637,
+      "eval_loss": 1.3644814491271973,
+      "eval_runtime": 3.6735,
+      "eval_samples_per_second": 138.014,
+      "eval_steps_per_second": 17.422,
+      "eval_uas": 80.19858386912998,
+      "step": 2000
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 6.929395973154363e-05,
+      "loss": 0.2162,
+      "step": 2100
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 6.875704697986578e-05,
+      "loss": 0.2386,
+      "step": 2200
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 6.822013422818793e-05,
+      "loss": 0.1861,
+      "step": 2300
+    },
+    {
+      "epoch": 10.86,
+      "learning_rate": 6.768322147651007e-05,
+      "loss": 0.1989,
+      "step": 2400
+    },
+    {
+      "epoch": 11.31,
+      "learning_rate": 6.714630872483222e-05,
+      "loss": 0.1631,
+      "step": 2500
+    },
+    {
+      "epoch": 11.31,
+      "eval_las": 75.29095792300807,
+      "eval_loss": 1.5608779191970825,
+      "eval_runtime": 3.672,
+      "eval_samples_per_second": 138.07,
+      "eval_steps_per_second": 17.429,
+      "eval_uas": 80.17416781964678,
+      "step": 2500
+    },
+    {
+      "epoch": 11.76,
+      "learning_rate": 6.660939597315437e-05,
+      "loss": 0.1637,
+      "step": 2600
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 6.607248322147652e-05,
+      "loss": 0.1513,
+      "step": 2700
+    },
+    {
+      "epoch": 12.67,
+      "learning_rate": 6.553557046979867e-05,
+      "loss": 0.1318,
+      "step": 2800
+    },
+    {
+      "epoch": 13.12,
+      "learning_rate": 6.499865771812081e-05,
+      "loss": 0.1326,
+      "step": 2900
+    },
+    {
+      "epoch": 13.57,
+      "learning_rate": 6.446174496644296e-05,
+      "loss": 0.1156,
+      "step": 3000
+    },
+    {
+      "epoch": 13.57,
+      "eval_las": 75.71416944738341,
+      "eval_loss": 1.6040022373199463,
+      "eval_runtime": 3.6712,
+      "eval_samples_per_second": 138.103,
+      "eval_steps_per_second": 17.433,
+      "eval_uas": 80.20672255229104,
+      "step": 3000
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 6.392483221476511e-05,
+      "loss": 0.117,
+      "step": 3100
+    },
+    {
+      "epoch": 14.48,
+      "learning_rate": 6.338791946308726e-05,
+      "loss": 0.0966,
+      "step": 3200
+    },
+    {
+      "epoch": 14.93,
+      "learning_rate": 6.28510067114094e-05,
+      "loss": 0.1057,
+      "step": 3300
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 6.231409395973154e-05,
+      "loss": 0.091,
+      "step": 3400
+    },
+    {
+      "epoch": 15.84,
+      "learning_rate": 6.177718120805369e-05,
+      "loss": 0.09,
+      "step": 3500
+    },
+    {
+      "epoch": 15.84,
+      "eval_las": 75.79555627899406,
+      "eval_loss": 1.8544515371322632,
+      "eval_runtime": 3.6721,
+      "eval_samples_per_second": 138.068,
+      "eval_steps_per_second": 17.429,
+      "eval_uas": 80.03581020590869,
+      "step": 3500
+    },
+    {
+      "epoch": 16.29,
+      "learning_rate": 6.124026845637584e-05,
+      "loss": 0.0816,
+      "step": 3600
+    },
+    {
+      "epoch": 16.74,
+      "learning_rate": 6.070335570469799e-05,
+      "loss": 0.0809,
+      "step": 3700
+    },
+    {
+      "epoch": 17.19,
+      "learning_rate": 6.0166442953020136e-05,
+      "loss": 0.0753,
+      "step": 3800
+    },
+    {
+      "epoch": 17.65,
+      "learning_rate": 5.962953020134229e-05,
+      "loss": 0.073,
+      "step": 3900
+    },
+    {
+      "epoch": 18.1,
+      "learning_rate": 5.909261744966444e-05,
+      "loss": 0.07,
+      "step": 4000
+    },
+    {
+      "epoch": 18.1,
+      "eval_las": 76.59314722877838,
+      "eval_loss": 2.0029706954956055,
+      "eval_runtime": 3.6667,
+      "eval_samples_per_second": 138.273,
+      "eval_steps_per_second": 17.455,
+      "eval_uas": 80.7682916904045,
+      "step": 4000
+    },
+    {
+      "epoch": 18.55,
+      "learning_rate": 5.855570469798659e-05,
+      "loss": 0.0641,
+      "step": 4100
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 5.8018791946308735e-05,
+      "loss": 0.0687,
+      "step": 4200
+    },
+    {
+      "epoch": 19.46,
+      "learning_rate": 5.7481879194630884e-05,
+      "loss": 0.0548,
+      "step": 4300
+    },
+    {
+      "epoch": 19.91,
+      "learning_rate": 5.694496644295303e-05,
+      "loss": 0.0608,
+      "step": 4400
+    },
+    {
+      "epoch": 20.36,
+      "learning_rate": 5.6408053691275166e-05,
+      "loss": 0.0526,
+      "step": 4500
+    },
+    {
+      "epoch": 20.36,
+      "eval_las": 75.82811101163833,
+      "eval_loss": 2.0474750995635986,
+      "eval_runtime": 3.6759,
+      "eval_samples_per_second": 137.925,
+      "eval_steps_per_second": 17.411,
+      "eval_uas": 80.42646699763978,
+      "step": 4500
+    },
+    {
+      "epoch": 20.81,
+      "learning_rate": 5.5871140939597315e-05,
+      "loss": 0.0574,
+      "step": 4600
+    },
+    {
+      "epoch": 21.27,
+      "learning_rate": 5.533422818791946e-05,
+      "loss": 0.0506,
+      "step": 4700
+    },
+    {
+      "epoch": 21.72,
+      "learning_rate": 5.479731543624161e-05,
+      "loss": 0.0506,
+      "step": 4800
+    },
+    {
+      "epoch": 22.17,
+      "learning_rate": 5.426040268456376e-05,
+      "loss": 0.0478,
+      "step": 4900
+    },
+    {
+      "epoch": 22.62,
+      "learning_rate": 5.372348993288591e-05,
+      "loss": 0.0455,
+      "step": 5000
+    },
+    {
+      "epoch": 22.62,
+      "eval_las": 75.73044681370554,
+      "eval_loss": 2.1534557342529297,
+      "eval_runtime": 3.6739,
+      "eval_samples_per_second": 138.001,
+      "eval_steps_per_second": 17.42,
+      "eval_uas": 80.47529909660616,
+      "step": 5000
+    },
+    {
+      "epoch": 23.08,
+      "learning_rate": 5.3186577181208056e-05,
+      "loss": 0.0446,
+      "step": 5100
+    },
+    {
+      "epoch": 23.53,
+      "learning_rate": 5.2649664429530204e-05,
+      "loss": 0.0409,
+      "step": 5200
+    },
+    {
+      "epoch": 23.98,
+      "learning_rate": 5.211275167785235e-05,
+      "loss": 0.0448,
+      "step": 5300
+    },
+    {
+      "epoch": 24.43,
+      "learning_rate": 5.15758389261745e-05,
+      "loss": 0.0379,
+      "step": 5400
+    },
+    {
+      "epoch": 24.89,
+      "learning_rate": 5.1038926174496656e-05,
+      "loss": 0.0416,
+      "step": 5500
+    },
+    {
+      "epoch": 24.89,
+      "eval_las": 76.22690648653048,
+      "eval_loss": 2.1511826515197754,
+      "eval_runtime": 3.6773,
+      "eval_samples_per_second": 137.872,
+      "eval_steps_per_second": 17.404,
+      "eval_uas": 80.80898510620982,
+      "step": 5500
+    },
+    {
+      "epoch": 25.34,
+      "learning_rate": 5.050201342281879e-05,
+      "loss": 0.0352,
+      "step": 5600
+    },
+    {
+      "epoch": 25.79,
+      "learning_rate": 4.996510067114094e-05,
+      "loss": 0.0369,
+      "step": 5700
+    },
+    {
+      "epoch": 26.24,
+      "learning_rate": 4.942818791946309e-05,
+      "loss": 0.0354,
+      "step": 5800
+    },
+    {
+      "epoch": 26.7,
+      "learning_rate": 4.8891275167785235e-05,
+      "loss": 0.0342,
+      "step": 5900
+    },
+    {
+      "epoch": 27.15,
+      "learning_rate": 4.835436241610738e-05,
+      "loss": 0.0342,
+      "step": 6000
+    },
+    {
+      "epoch": 27.15,
+      "eval_las": 75.9908846748596,
+      "eval_loss": 2.3812143802642822,
+      "eval_runtime": 3.6674,
+      "eval_samples_per_second": 138.245,
+      "eval_steps_per_second": 17.451,
+      "eval_uas": 80.6299340766664,
+      "step": 6000
+    },
+    {
+      "epoch": 27.6,
+      "learning_rate": 4.781744966442953e-05,
+      "loss": 0.0296,
+      "step": 6100
+    },
+    {
+      "epoch": 28.05,
+      "learning_rate": 4.728053691275168e-05,
+      "loss": 0.0304,
+      "step": 6200
+    },
+    {
+      "epoch": 28.51,
+      "learning_rate": 4.674362416107383e-05,
+      "loss": 0.0304,
+      "step": 6300
+    },
+    {
+      "epoch": 28.96,
+      "learning_rate": 4.6206711409395976e-05,
+      "loss": 0.0319,
+      "step": 6400
+    },
+    {
+      "epoch": 29.41,
+      "learning_rate": 4.5669798657718125e-05,
+      "loss": 0.0264,
+      "step": 6500
+    },
+    {
+      "epoch": 29.41,
+      "eval_las": 75.8769431106047,
+      "eval_loss": 2.4017791748046875,
+      "eval_runtime": 3.6647,
+      "eval_samples_per_second": 138.347,
+      "eval_steps_per_second": 17.464,
+      "eval_uas": 80.4671604134451,
+      "step": 6500
+    },
+    {
+      "epoch": 29.41,
+      "step": 6500,
+      "total_flos": 3.4624658436900864e+16,
+      "train_loss": 0.30513293038881745,
+      "train_runtime": 3575.6323,
+      "train_samples_per_second": 134.242,
+      "train_steps_per_second": 4.195
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 68,
+  "total_flos": 3.4624658436900864e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec296e36cf98d0966a00f70014d3b1668d53c15b1d0910a0869130066db47b9a
+size 3387