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": 76.92,
+    "eval_las": 14.889152449594015,
+    "eval_loss": 4.103353500366211,
+    "eval_runtime": 2.9637,
+    "eval_samples": 381,
+    "eval_samples_per_second": 128.557,
+    "eval_steps_per_second": 16.196,
+    "eval_uas": 31.748928017516647,
+    "test_las": 13.477296828304253,
+    "test_loss": 4.127927780151367,
+    "test_runtime": 3.0193,
+    "test_samples": 403,
+    "test_samples_per_second": 133.474,
+    "test_steps_per_second": 16.891,
+    "test_uas": 30.52154632218259,
+    "train_loss": 2.0616751454671225,
+    "train_runtime": 1642.7036,
+    "train_samples": 1227,
+    "train_samples_per_second": 292.201,
+    "train_steps_per_second": 9.131
+}

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 sha256:9be2f320a2241bd643f97d790786c84ecc682538b141a27340986fa5068f14bb
+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 +1,265 @@
+{
+  "best_metric": 14.889152449594015,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Coptic-Scriptorium/checkpoint-500",
+  "epoch": 76.92307692307692,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.6e-05,
+      "loss": 5.3836,
+      "step": 100
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 7.948993288590604e-05,
+      "loss": 4.1364,
+      "step": 200
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 7.895302013422819e-05,
+      "loss": 3.8943,
+      "step": 300
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 7.841610738255034e-05,
+      "loss": 3.7384,
+      "step": 400
+    },
+    {
+      "epoch": 12.82,
+      "learning_rate": 7.787919463087249e-05,
+      "loss": 3.5767,
+      "step": 500
+    },
+    {
+      "epoch": 12.82,
+      "eval_las": 14.889152449594015,
+      "eval_loss": 4.103353500366211,
+      "eval_runtime": 2.9493,
+      "eval_samples_per_second": 129.182,
+      "eval_steps_per_second": 16.275,
+      "eval_uas": 31.748928017516647,
+      "step": 500
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 7.734228187919463e-05,
+      "loss": 3.4084,
+      "step": 600
+    },
+    {
+      "epoch": 17.95,
+      "learning_rate": 7.680536912751678e-05,
+      "loss": 3.2001,
+      "step": 700
+    },
+    {
+      "epoch": 20.51,
+      "learning_rate": 7.626845637583893e-05,
+      "loss": 2.9538,
+      "step": 800
+    },
+    {
+      "epoch": 23.08,
+      "learning_rate": 7.573154362416108e-05,
+      "loss": 2.7223,
+      "step": 900
+    },
+    {
+      "epoch": 25.64,
+      "learning_rate": 7.519463087248323e-05,
+      "loss": 2.4472,
+      "step": 1000
+    },
+    {
+      "epoch": 25.64,
+      "eval_las": 11.248973633792538,
+      "eval_loss": 5.691993713378906,
+      "eval_runtime": 2.9489,
+      "eval_samples_per_second": 129.203,
+      "eval_steps_per_second": 16.278,
+      "eval_uas": 27.926284098166228,
+      "step": 1000
+    },
+    {
+      "epoch": 28.21,
+      "learning_rate": 7.465771812080537e-05,
+      "loss": 2.2519,
+      "step": 1100
+    },
+    {
+      "epoch": 30.77,
+      "learning_rate": 7.412080536912752e-05,
+      "loss": 2.0317,
+      "step": 1200
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 7.358389261744967e-05,
+      "loss": 1.8544,
+      "step": 1300
+    },
+    {
+      "epoch": 35.9,
+      "learning_rate": 7.304697986577182e-05,
+      "loss": 1.7134,
+      "step": 1400
+    },
+    {
+      "epoch": 38.46,
+      "learning_rate": 7.251006711409397e-05,
+      "loss": 1.5671,
+      "step": 1500
+    },
+    {
+      "epoch": 38.46,
+      "eval_las": 9.871362101997994,
+      "eval_loss": 7.934547424316406,
+      "eval_runtime": 2.9464,
+      "eval_samples_per_second": 129.311,
+      "eval_steps_per_second": 16.291,
+      "eval_uas": 25.444758689900553,
+      "step": 1500
+    },
+    {
+      "epoch": 41.03,
+      "learning_rate": 7.197315436241612e-05,
+      "loss": 1.4647,
+      "step": 1600
+    },
+    {
+      "epoch": 43.59,
+      "learning_rate": 7.143624161073826e-05,
+      "loss": 1.3584,
+      "step": 1700
+    },
+    {
+      "epoch": 46.15,
+      "learning_rate": 7.089932885906041e-05,
+      "loss": 1.2918,
+      "step": 1800
+    },
+    {
+      "epoch": 48.72,
+      "learning_rate": 7.036241610738256e-05,
+      "loss": 1.2333,
+      "step": 1900
+    },
+    {
+      "epoch": 51.28,
+      "learning_rate": 6.982550335570471e-05,
+      "loss": 1.2108,
+      "step": 2000
+    },
+    {
+      "epoch": 51.28,
+      "eval_las": 9.570294681142231,
+      "eval_loss": 10.208051681518555,
+      "eval_runtime": 2.9507,
+      "eval_samples_per_second": 129.123,
+      "eval_steps_per_second": 16.267,
+      "eval_uas": 24.58717270322051,
+      "step": 2000
+    },
+    {
+      "epoch": 53.85,
+      "learning_rate": 6.928859060402686e-05,
+      "loss": 1.1363,
+      "step": 2100
+    },
+    {
+      "epoch": 56.41,
+      "learning_rate": 6.8751677852349e-05,
+      "loss": 1.1452,
+      "step": 2200
+    },
+    {
+      "epoch": 58.97,
+      "learning_rate": 6.821476510067115e-05,
+      "loss": 1.0937,
+      "step": 2300
+    },
+    {
+      "epoch": 61.54,
+      "learning_rate": 6.76778523489933e-05,
+      "loss": 1.0555,
+      "step": 2400
+    },
+    {
+      "epoch": 64.1,
+      "learning_rate": 6.714093959731544e-05,
+      "loss": 1.0311,
+      "step": 2500
+    },
+    {
+      "epoch": 64.1,
+      "eval_las": 9.707143508803942,
+      "eval_loss": 11.06482219696045,
+      "eval_runtime": 2.9481,
+      "eval_samples_per_second": 129.236,
+      "eval_steps_per_second": 16.282,
+      "eval_uas": 24.368214578961776,
+      "step": 2500
+    },
+    {
+      "epoch": 66.67,
+      "learning_rate": 6.660402684563758e-05,
+      "loss": 1.0068,
+      "step": 2600
+    },
+    {
+      "epoch": 69.23,
+      "learning_rate": 6.606711409395973e-05,
+      "loss": 1.0095,
+      "step": 2700
+    },
+    {
+      "epoch": 71.79,
+      "learning_rate": 6.553020134228188e-05,
+      "loss": 0.9792,
+      "step": 2800
+    },
+    {
+      "epoch": 74.36,
+      "learning_rate": 6.499328859060403e-05,
+      "loss": 0.988,
+      "step": 2900
+    },
+    {
+      "epoch": 76.92,
+      "learning_rate": 6.445637583892618e-05,
+      "loss": 0.9661,
+      "step": 3000
+    },
+    {
+      "epoch": 76.92,
+      "eval_las": 9.670650488094152,
+      "eval_loss": 10.523516654968262,
+      "eval_runtime": 2.9465,
+      "eval_samples_per_second": 129.304,
+      "eval_steps_per_second": 16.29,
+      "eval_uas": 24.41383085484901,
+      "step": 3000
+    },
+    {
+      "epoch": 76.92,
+      "step": 3000,
+      "total_flos": 1.5763284763250688e+16,
+      "train_loss": 2.0616751454671225,
+      "train_runtime": 1642.7036,
+      "train_samples_per_second": 292.201,
+      "train_steps_per_second": 9.131
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 385,
+  "total_flos": 1.5763284763250688e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701914dbbae9ea7861ef042c289ea84b860792a3e4b4dfaa6b5b186739676f8e
+size 3451