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": 76.92,
+    "eval_accuracy": 0.2892984216768543,
+    "eval_loss": 1.9470784664154053,
+    "eval_runtime": 1.9293,
+    "eval_samples": 381,
+    "eval_samples_per_second": 197.482,
+    "eval_steps_per_second": 24.88,
+    "test_accuracy": 0.2644365178829654,
+    "test_loss": 2.0118589401245117,
+    "test_runtime": 2.0343,
+    "test_samples": 403,
+    "test_samples_per_second": 198.105,
+    "test_steps_per_second": 25.07,
+    "train_loss": 1.4148986282348632,
+    "train_runtime": 758.2535,
+    "train_samples": 1227,
+    "train_samples_per_second": 633.034,
+    "train_steps_per_second": 19.782
+}

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "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,
+  "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:b77137a5b8f9a3f517d4f416823a3e27d12feea48463f0656ed37f95e08661e8
+size 431017069

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 +1,259 @@
+{
+  "best_metric": 0.2892984216768543,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-pos-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": 5e-05,
+      "loss": 2.1362,
+      "step": 100
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 4.966442953020135e-05,
+      "loss": 1.9133,
+      "step": 200
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 4.932885906040269e-05,
+      "loss": 1.8901,
+      "step": 300
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 4.8993288590604034e-05,
+      "loss": 1.8743,
+      "step": 400
+    },
+    {
+      "epoch": 12.82,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 1.8572,
+      "step": 500
+    },
+    {
+      "epoch": 12.82,
+      "eval_accuracy": 0.2892984216768543,
+      "eval_loss": 1.9470784664154053,
+      "eval_runtime": 1.9235,
+      "eval_samples_per_second": 198.078,
+      "eval_steps_per_second": 24.955,
+      "step": 500
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 4.832214765100672e-05,
+      "loss": 1.8448,
+      "step": 600
+    },
+    {
+      "epoch": 17.95,
+      "learning_rate": 4.798657718120805e-05,
+      "loss": 1.8263,
+      "step": 700
+    },
+    {
+      "epoch": 20.51,
+      "learning_rate": 4.76510067114094e-05,
+      "loss": 1.7988,
+      "step": 800
+    },
+    {
+      "epoch": 23.08,
+      "learning_rate": 4.731543624161074e-05,
+      "loss": 1.7733,
+      "step": 900
+    },
+    {
+      "epoch": 25.64,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 1.7321,
+      "step": 1000
+    },
+    {
+      "epoch": 25.64,
+      "eval_accuracy": 0.27597846911778123,
+      "eval_loss": 2.090031147003174,
+      "eval_runtime": 1.9389,
+      "eval_samples_per_second": 196.498,
+      "eval_steps_per_second": 24.756,
+      "step": 1000
+    },
+    {
+      "epoch": 28.21,
+      "learning_rate": 4.664429530201342e-05,
+      "loss": 1.6957,
+      "step": 1100
+    },
+    {
+      "epoch": 30.77,
+      "learning_rate": 4.630872483221477e-05,
+      "loss": 1.6365,
+      "step": 1200
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 4.597315436241611e-05,
+      "loss": 1.5917,
+      "step": 1300
+    },
+    {
+      "epoch": 35.9,
+      "learning_rate": 4.5637583892617453e-05,
+      "loss": 1.5378,
+      "step": 1400
+    },
+    {
+      "epoch": 38.46,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 1.4759,
+      "step": 1500
+    },
+    {
+      "epoch": 38.46,
+      "eval_accuracy": 0.2506158197244777,
+      "eval_loss": 2.431821584701538,
+      "eval_runtime": 1.933,
+      "eval_samples_per_second": 197.107,
+      "eval_steps_per_second": 24.832,
+      "step": 1500
+    },
+    {
+      "epoch": 41.03,
+      "learning_rate": 4.496644295302014e-05,
+      "loss": 1.4153,
+      "step": 1600
+    },
+    {
+      "epoch": 43.59,
+      "learning_rate": 4.463087248322148e-05,
+      "loss": 1.354,
+      "step": 1700
+    },
+    {
+      "epoch": 46.15,
+      "learning_rate": 4.4295302013422824e-05,
+      "loss": 1.2879,
+      "step": 1800
+    },
+    {
+      "epoch": 48.72,
+      "learning_rate": 4.395973154362416e-05,
+      "loss": 1.2279,
+      "step": 1900
+    },
+    {
+      "epoch": 51.28,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 1.1962,
+      "step": 2000
+    },
+    {
+      "epoch": 51.28,
+      "eval_accuracy": 0.2390292856491196,
+      "eval_loss": 2.9406466484069824,
+      "eval_runtime": 1.9342,
+      "eval_samples_per_second": 196.977,
+      "eval_steps_per_second": 24.816,
+      "step": 2000
+    },
+    {
+      "epoch": 53.85,
+      "learning_rate": 4.328859060402685e-05,
+      "loss": 1.1217,
+      "step": 2100
+    },
+    {
+      "epoch": 56.41,
+      "learning_rate": 4.295302013422819e-05,
+      "loss": 1.0833,
+      "step": 2200
+    },
+    {
+      "epoch": 58.97,
+      "learning_rate": 4.2617449664429534e-05,
+      "loss": 1.0293,
+      "step": 2300
+    },
+    {
+      "epoch": 61.54,
+      "learning_rate": 4.228187919463087e-05,
+      "loss": 0.9821,
+      "step": 2400
+    },
+    {
+      "epoch": 64.1,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.9384,
+      "step": 2500
+    },
+    {
+      "epoch": 64.1,
+      "eval_accuracy": 0.22935863516102545,
+      "eval_loss": 3.6179699897766113,
+      "eval_runtime": 1.942,
+      "eval_samples_per_second": 196.187,
+      "eval_steps_per_second": 24.716,
+      "step": 2500
+    },
+    {
+      "epoch": 66.67,
+      "learning_rate": 4.161073825503356e-05,
+      "loss": 0.8994,
+      "step": 2600
+    },
+    {
+      "epoch": 69.23,
+      "learning_rate": 4.1275167785234905e-05,
+      "loss": 0.8775,
+      "step": 2700
+    },
+    {
+      "epoch": 71.79,
+      "learning_rate": 4.0942953020134226e-05,
+      "loss": 0.8304,
+      "step": 2800
+    },
+    {
+      "epoch": 74.36,
+      "learning_rate": 4.060738255033557e-05,
+      "loss": 0.8287,
+      "step": 2900
+    },
+    {
+      "epoch": 76.92,
+      "learning_rate": 4.027181208053691e-05,
+      "loss": 0.7909,
+      "step": 3000
+    },
+    {
+      "epoch": 76.92,
+      "eval_accuracy": 0.23273423957668096,
+      "eval_loss": 4.074990749359131,
+      "eval_runtime": 1.9336,
+      "eval_samples_per_second": 197.047,
+      "eval_steps_per_second": 24.825,
+      "step": 3000
+    },
+    {
+      "epoch": 76.92,
+      "step": 3000,
+      "total_flos": 1.2335402138867712e+16,
+      "train_loss": 1.4148986282348632,
+      "train_runtime": 758.2535,
+      "train_samples_per_second": 633.034,
+      "train_steps_per_second": 19.782
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 385,
+  "total_flos": 1.2335402138867712e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c137655c5413a4683eb16e207fbc627682320e0cdf1d87521522f2abd6af2b
+size 3387