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 +1,20 @@
+{
+    "epoch": 21.74,
+    "eval_accuracy": 0.9572671015219937,
+    "eval_loss": 0.18942660093307495,
+    "eval_runtime": 4.9097,
+    "eval_samples": 950,
+    "eval_samples_per_second": 193.495,
+    "eval_steps_per_second": 24.238,
+    "test_accuracy": 0.9579515286460564,
+    "test_loss": 0.16365599632263184,
+    "test_runtime": 5.1039,
+    "test_samples": 989,
+    "test_samples_per_second": 193.772,
+    "test_steps_per_second": 24.295,
+    "train_loss": 0.0700680200457573,
+    "train_runtime": 844.3355,
+    "train_samples": 4400,
+    "train_samples_per_second": 568.494,
+    "train_steps_per_second": 17.765
+}

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "CCONJ",
+    "5": "DET",
+    "6": "INTJ",
+    "7": "NOUN",
+    "8": "NUM",
+    "9": "PART",
+    "10": "PRON",
+    "11": "PROPN",
+    "12": "PUNCT",
+    "13": "SCONJ",
+    "14": "SYM",
+    "15": "VERB",
+    "16": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "CCONJ": 4,
+    "DET": 5,
+    "INTJ": 6,
+    "NOUN": 7,
+    "NUM": 8,
+    "PART": 9,
+    "PRON": 10,
+    "PROPN": 11,
+    "PUNCT": 12,
+    "SCONJ": 13,
+    "SYM": 14,
+    "VERB": 15,
+    "X": 16
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "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:e331687114de3df42ec40ff21d00616df2422f72707626ef1367965842522638
+size 709189741

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 +1,259 @@
+{
+  "best_metric": 0.9572671015219937,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-pos-ud-Korean-GSD/checkpoint-500",
+  "epoch": 21.73913043478261,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.840000000000001e-05,
+      "loss": 0.9879,
+      "step": 100
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 7.947382550335571e-05,
+      "loss": 0.2181,
+      "step": 200
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 7.893691275167786e-05,
+      "loss": 0.1495,
+      "step": 300
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 7.840000000000001e-05,
+      "loss": 0.1132,
+      "step": 400
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 7.786308724832216e-05,
+      "loss": 0.0799,
+      "step": 500
+    },
+    {
+      "epoch": 3.62,
+      "eval_accuracy": 0.9572671015219937,
+      "eval_loss": 0.18942660093307495,
+      "eval_runtime": 4.8972,
+      "eval_samples_per_second": 193.989,
+      "eval_steps_per_second": 24.3,
+      "step": 500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 7.73261744966443e-05,
+      "loss": 0.0661,
+      "step": 600
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 7.678926174496645e-05,
+      "loss": 0.0532,
+      "step": 700
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 7.62523489932886e-05,
+      "loss": 0.0401,
+      "step": 800
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 7.571543624161075e-05,
+      "loss": 0.0368,
+      "step": 900
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 7.51785234899329e-05,
+      "loss": 0.0331,
+      "step": 1000
+    },
+    {
+      "epoch": 7.25,
+      "eval_accuracy": 0.9542565646429169,
+      "eval_loss": 0.23469237983226776,
+      "eval_runtime": 4.9192,
+      "eval_samples_per_second": 193.122,
+      "eval_steps_per_second": 24.191,
+      "step": 1000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 7.464161073825505e-05,
+      "loss": 0.0279,
+      "step": 1100
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 7.410469798657718e-05,
+      "loss": 0.0276,
+      "step": 1200
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 7.356778523489933e-05,
+      "loss": 0.0239,
+      "step": 1300
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 7.303087248322148e-05,
+      "loss": 0.0211,
+      "step": 1400
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 7.249395973154363e-05,
+      "loss": 0.019,
+      "step": 1500
+    },
+    {
+      "epoch": 10.87,
+      "eval_accuracy": 0.9547583207894297,
+      "eval_loss": 0.2637677788734436,
+      "eval_runtime": 4.9181,
+      "eval_samples_per_second": 193.163,
+      "eval_steps_per_second": 24.196,
+      "step": 1500
+    },
+    {
+      "epoch": 11.59,
+      "learning_rate": 7.195704697986577e-05,
+      "loss": 0.0174,
+      "step": 1600
+    },
+    {
+      "epoch": 12.32,
+      "learning_rate": 7.142013422818792e-05,
+      "loss": 0.0178,
+      "step": 1700
+    },
+    {
+      "epoch": 13.04,
+      "learning_rate": 7.088322147651007e-05,
+      "loss": 0.0181,
+      "step": 1800
+    },
+    {
+      "epoch": 13.77,
+      "learning_rate": 7.034630872483222e-05,
+      "loss": 0.014,
+      "step": 1900
+    },
+    {
+      "epoch": 14.49,
+      "learning_rate": 6.980939597315437e-05,
+      "loss": 0.0144,
+      "step": 2000
+    },
+    {
+      "epoch": 14.49,
+      "eval_accuracy": 0.9535875564475664,
+      "eval_loss": 0.2897445857524872,
+      "eval_runtime": 4.9125,
+      "eval_samples_per_second": 193.386,
+      "eval_steps_per_second": 24.224,
+      "step": 2000
+    },
+    {
+      "epoch": 15.22,
+      "learning_rate": 6.927248322147651e-05,
+      "loss": 0.0154,
+      "step": 2100
+    },
+    {
+      "epoch": 15.94,
+      "learning_rate": 6.873557046979866e-05,
+      "loss": 0.0133,
+      "step": 2200
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 6.819865771812081e-05,
+      "loss": 0.0142,
+      "step": 2300
+    },
+    {
+      "epoch": 17.39,
+      "learning_rate": 6.766174496644296e-05,
+      "loss": 0.0132,
+      "step": 2400
+    },
+    {
+      "epoch": 18.12,
+      "learning_rate": 6.712483221476511e-05,
+      "loss": 0.013,
+      "step": 2500
+    },
+    {
+      "epoch": 18.12,
+      "eval_accuracy": 0.9560127111557116,
+      "eval_loss": 0.2839347720146179,
+      "eval_runtime": 4.9076,
+      "eval_samples_per_second": 193.578,
+      "eval_steps_per_second": 24.248,
+      "step": 2500
+    },
+    {
+      "epoch": 18.84,
+      "learning_rate": 6.658791946308726e-05,
+      "loss": 0.0114,
+      "step": 2600
+    },
+    {
+      "epoch": 19.57,
+      "learning_rate": 6.60510067114094e-05,
+      "loss": 0.0106,
+      "step": 2700
+    },
+    {
+      "epoch": 20.29,
+      "learning_rate": 6.551409395973155e-05,
+      "loss": 0.0103,
+      "step": 2800
+    },
+    {
+      "epoch": 21.01,
+      "learning_rate": 6.49771812080537e-05,
+      "loss": 0.0123,
+      "step": 2900
+    },
+    {
+      "epoch": 21.74,
+      "learning_rate": 6.444026845637585e-05,
+      "loss": 0.0093,
+      "step": 3000
+    },
+    {
+      "epoch": 21.74,
+      "eval_accuracy": 0.9540056865696604,
+      "eval_loss": 0.2998155355453491,
+      "eval_runtime": 4.8962,
+      "eval_samples_per_second": 194.026,
+      "eval_steps_per_second": 24.304,
+      "step": 3000
+    },
+    {
+      "epoch": 21.74,
+      "step": 3000,
+      "total_flos": 1.2500041419988992e+16,
+      "train_loss": 0.0700680200457573,
+      "train_runtime": 844.3355,
+      "train_samples_per_second": 568.494,
+      "train_steps_per_second": 17.765
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 109,
+  "total_flos": 1.2500041419988992e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27347fc50f0511ac0230f4d9971ba6ebef9670e19ad2d76a2fc5269a36e2f431
+size 3387