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": 24.0,
+    "eval_las": 27.560609650161886,
+    "eval_loss": 3.2153432369232178,
+    "eval_runtime": 3.9651,
+    "eval_samples": 500,
+    "eval_samples_per_second": 126.1,
+    "eval_steps_per_second": 15.889,
+    "eval_uas": 38.72699992102977,
+    "test_las": 29.312354312354312,
+    "test_loss": 3.145913600921631,
+    "test_runtime": 3.7359,
+    "test_samples": 500,
+    "test_samples_per_second": 133.836,
+    "test_steps_per_second": 16.863,
+    "test_uas": 40.36796536796537,
+    "train_loss": 1.6239593226114908,
+    "train_runtime": 1696.2446,
+    "train_samples": 3997,
+    "train_samples_per_second": 282.978,
+    "train_steps_per_second": 8.843
+}

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:f8a45d1d45dc6b2261bb1b78957b0f1c6b8fdad5a8afbb1ba0ef07a8b770f79b
+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": 27.560609650161886,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Chinese-GSD/checkpoint-500",
+  "epoch": 24.0,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.52e-05,
+      "loss": 5.1119,
+      "step": 100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 7.949530201342283e-05,
+      "loss": 3.5502,
+      "step": 200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.895838926174497e-05,
+      "loss": 3.2732,
+      "step": 300
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 7.842147651006712e-05,
+      "loss": 3.1436,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.788456375838927e-05,
+      "loss": 2.9782,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_las": 27.560609650161886,
+      "eval_loss": 3.2153432369232178,
+      "eval_runtime": 3.7874,
+      "eval_samples_per_second": 132.018,
+      "eval_steps_per_second": 16.634,
+      "eval_uas": 38.72699992102977,
+      "step": 500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 7.734765100671142e-05,
+      "loss": 2.7713,
+      "step": 600
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 7.681073825503357e-05,
+      "loss": 2.596,
+      "step": 700
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 7.627382550335572e-05,
+      "loss": 2.4727,
+      "step": 800
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 7.573691275167786e-05,
+      "loss": 2.2636,
+      "step": 900
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 7.52e-05,
+      "loss": 2.1577,
+      "step": 1000
+    },
+    {
+      "epoch": 8.0,
+      "eval_las": 27.24472873726605,
+      "eval_loss": 3.5974676609039307,
+      "eval_runtime": 3.7904,
+      "eval_samples_per_second": 131.911,
+      "eval_steps_per_second": 16.621,
+      "eval_uas": 37.81094527363184,
+      "step": 1000
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 7.466308724832215e-05,
+      "loss": 1.9002,
+      "step": 1100
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 7.41261744966443e-05,
+      "loss": 1.7571,
+      "step": 1200
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 7.358926174496644e-05,
+      "loss": 1.6221,
+      "step": 1300
+    },
+    {
+      "epoch": 11.2,
+      "learning_rate": 7.305234899328859e-05,
+      "loss": 1.4755,
+      "step": 1400
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 7.251543624161074e-05,
+      "loss": 1.3676,
+      "step": 1500
+    },
+    {
+      "epoch": 12.0,
+      "eval_las": 26.139145542130613,
+      "eval_loss": 4.466611385345459,
+      "eval_runtime": 3.7901,
+      "eval_samples_per_second": 131.922,
+      "eval_steps_per_second": 16.622,
+      "eval_uas": 37.3055358129985,
+      "step": 1500
+    },
+    {
+      "epoch": 12.8,
+      "learning_rate": 7.197852348993289e-05,
+      "loss": 1.1862,
+      "step": 1600
+    },
+    {
+      "epoch": 13.6,
+      "learning_rate": 7.144161073825504e-05,
+      "loss": 1.0804,
+      "step": 1700
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 7.090469798657718e-05,
+      "loss": 1.0108,
+      "step": 1800
+    },
+    {
+      "epoch": 15.2,
+      "learning_rate": 7.036778523489933e-05,
+      "loss": 0.9181,
+      "step": 1900
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 6.983087248322148e-05,
+      "loss": 0.8486,
+      "step": 2000
+    },
+    {
+      "epoch": 16.0,
+      "eval_las": 25.70480928689884,
+      "eval_loss": 5.577605247497559,
+      "eval_runtime": 3.7894,
+      "eval_samples_per_second": 131.945,
+      "eval_steps_per_second": 16.625,
+      "eval_uas": 36.713259101318805,
+      "step": 2000
+    },
+    {
+      "epoch": 16.8,
+      "learning_rate": 6.929395973154363e-05,
+      "loss": 0.7407,
+      "step": 2100
+    },
+    {
+      "epoch": 17.6,
+      "learning_rate": 6.875704697986578e-05,
+      "loss": 0.682,
+      "step": 2200
+    },
+    {
+      "epoch": 18.4,
+      "learning_rate": 6.822013422818793e-05,
+      "loss": 0.6301,
+      "step": 2300
+    },
+    {
+      "epoch": 19.2,
+      "learning_rate": 6.768322147651007e-05,
+      "loss": 0.5779,
+      "step": 2400
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 6.714630872483222e-05,
+      "loss": 0.5466,
+      "step": 2500
+    },
+    {
+      "epoch": 20.0,
+      "eval_las": 26.09966042801864,
+      "eval_loss": 6.376339912414551,
+      "eval_runtime": 3.7911,
+      "eval_samples_per_second": 131.889,
+      "eval_steps_per_second": 16.618,
+      "eval_uas": 37.08441917397141,
+      "step": 2500
+    },
+    {
+      "epoch": 20.8,
+      "learning_rate": 6.660939597315437e-05,
+      "loss": 0.4749,
+      "step": 2600
+    },
+    {
+      "epoch": 21.6,
+      "learning_rate": 6.607248322147652e-05,
+      "loss": 0.4391,
+      "step": 2700
+    },
+    {
+      "epoch": 22.4,
+      "learning_rate": 6.553557046979867e-05,
+      "loss": 0.4082,
+      "step": 2800
+    },
+    {
+      "epoch": 23.2,
+      "learning_rate": 6.499865771812081e-05,
+      "loss": 0.3809,
+      "step": 2900
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 6.446174496644296e-05,
+      "loss": 0.3536,
+      "step": 3000
+    },
+    {
+      "epoch": 24.0,
+      "eval_las": 26.060175313906658,
+      "eval_loss": 7.119637489318848,
+      "eval_runtime": 3.7886,
+      "eval_samples_per_second": 131.973,
+      "eval_steps_per_second": 16.629,
+      "eval_uas": 37.37660901840007,
+      "step": 3000
+    },
+    {
+      "epoch": 24.0,
+      "step": 3000,
+      "total_flos": 1.6017757518422016e+16,
+      "train_loss": 1.6239593226114908,
+      "train_runtime": 1696.2446,
+      "train_samples_per_second": 282.978,
+      "train_steps_per_second": 8.843
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 120,
+  "total_flos": 1.6017757518422016e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087378b4f0d17aa974e0a6ddae8a00b6afcd6b0e89c5a4aa9b3a3e5fb75b775b
+size 3387