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 +1,26 @@
+{
+    "epoch": 74.29,
+    "eval_accuracy_score": 0.9790609137055838,
+    "eval_f1": 0.8868703550784476,
+    "eval_loss": 0.14278778433799744,
+    "eval_precision": 0.8788870703764321,
+    "eval_recall": 0.895,
+    "eval_runtime": 4.4475,
+    "eval_samples": 320,
+    "eval_samples_per_second": 71.951,
+    "eval_steps_per_second": 8.994,
+    "test_accuracy_score": 0.9701858442071966,
+    "test_f1": 0.8364700961940611,
+    "test_loss": 0.2297782301902771,
+    "test_precision": 0.8250825082508251,
+    "test_recall": 0.8481764206955047,
+    "test_runtime": 8.8463,
+    "test_samples": 638,
+    "test_samples_per_second": 72.12,
+    "test_steps_per_second": 9.043,
+    "train_loss": 0.01710937021443477,
+    "train_runtime": 8154.5313,
+    "train_samples": 2235,
+    "train_samples_per_second": 58.863,
+    "train_steps_per_second": 1.839
+}

config.json

@@ -0,0 +1,53 @@
+{
+  "_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": "O",
+    "1": "B-DATE",
+    "2": "I-DATE",
+    "3": "B-PER",
+    "4": "I-PER",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-LOC",
+    "8": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 1,
+    "B-LOC": 7,
+    "B-ORG": 5,
+    "B-PER": 3,
+    "I-DATE": 2,
+    "I-LOC": 8,
+    "I-ORG": 6,
+    "I-PER": 4,
+    "O": 0
+  },
+  "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 sha256:2dc1314ac689ae3e31e105ab6c619d587e3f763b799509f449cbabb4bece2153
+size 709165101

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 +1,397 @@
+{
+  "best_metric": 0.8868703550784476,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-ibo/checkpoint-3000",
+  "epoch": 74.28571428571429,
+  "global_step": 5200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.86,
+      "eval_accuracy_score": 0.9765228426395939,
+      "eval_f1": 0.8673300165837479,
+      "eval_loss": 0.08876766264438629,
+      "eval_precision": 0.863036303630363,
+      "eval_recall": 0.8716666666666667,
+      "eval_runtime": 4.4473,
+      "eval_samples_per_second": 71.954,
+      "eval_steps_per_second": 8.994,
+      "step": 200
+    },
+    {
+      "epoch": 5.71,
+      "eval_accuracy_score": 0.9741434010152284,
+      "eval_f1": 0.8617886178861788,
+      "eval_loss": 0.11480691283941269,
+      "eval_precision": 0.8412698412698413,
+      "eval_recall": 0.8833333333333333,
+      "eval_runtime": 4.4462,
+      "eval_samples_per_second": 71.972,
+      "eval_steps_per_second": 8.997,
+      "step": 400
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1451,
+      "step": 500
+    },
+    {
+      "epoch": 8.57,
+      "eval_accuracy_score": 0.9781091370558376,
+      "eval_f1": 0.874074074074074,
+      "eval_loss": 0.10442519187927246,
+      "eval_precision": 0.8634146341463415,
+      "eval_recall": 0.885,
+      "eval_runtime": 4.449,
+      "eval_samples_per_second": 71.926,
+      "eval_steps_per_second": 8.991,
+      "step": 600
+    },
+    {
+      "epoch": 11.43,
+      "eval_accuracy_score": 0.9766814720812182,
+      "eval_f1": 0.8705688375927452,
+      "eval_loss": 0.11804218590259552,
+      "eval_precision": 0.8613376835236541,
+      "eval_recall": 0.88,
+      "eval_runtime": 4.4511,
+      "eval_samples_per_second": 71.893,
+      "eval_steps_per_second": 8.987,
+      "step": 800
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0084,
+      "step": 1000
+    },
+    {
+      "epoch": 14.29,
+      "eval_accuracy_score": 0.9746192893401016,
+      "eval_f1": 0.8457047539616346,
+      "eval_loss": 0.1311611831188202,
+      "eval_precision": 0.8464106844741235,
+      "eval_recall": 0.845,
+      "eval_runtime": 4.4345,
+      "eval_samples_per_second": 72.162,
+      "eval_steps_per_second": 9.02,
+      "step": 1000
+    },
+    {
+      "epoch": 17.14,
+      "eval_accuracy_score": 0.9763642131979695,
+      "eval_f1": 0.8714168714168715,
+      "eval_loss": 0.134602889418602,
+      "eval_precision": 0.856682769726248,
+      "eval_recall": 0.8866666666666667,
+      "eval_runtime": 4.4493,
+      "eval_samples_per_second": 71.921,
+      "eval_steps_per_second": 8.99,
+      "step": 1200
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy_score": 0.9803299492385786,
+      "eval_f1": 0.8872180451127819,
+      "eval_loss": 0.1307426393032074,
+      "eval_precision": 0.8894472361809045,
+      "eval_recall": 0.885,
+      "eval_runtime": 4.442,
+      "eval_samples_per_second": 72.039,
+      "eval_steps_per_second": 9.005,
+      "step": 1400
+    },
+    {
+      "epoch": 21.43,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.005,
+      "step": 1500
+    },
+    {
+      "epoch": 22.86,
+      "eval_accuracy_score": 0.9771573604060914,
+      "eval_f1": 0.8767576509511993,
+      "eval_loss": 0.14564308524131775,
+      "eval_precision": 0.8702791461412152,
+      "eval_recall": 0.8833333333333333,
+      "eval_runtime": 4.4473,
+      "eval_samples_per_second": 71.954,
+      "eval_steps_per_second": 8.994,
+      "step": 1600
+    },
+    {
+      "epoch": 25.71,
+      "eval_accuracy_score": 0.9771573604060914,
+      "eval_f1": 0.8782104391052196,
+      "eval_loss": 0.13427743315696716,
+      "eval_precision": 0.8731466227347611,
+      "eval_recall": 0.8833333333333333,
+      "eval_runtime": 4.443,
+      "eval_samples_per_second": 72.023,
+      "eval_steps_per_second": 9.003,
+      "step": 1800
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0039,
+      "step": 2000
+    },
+    {
+      "epoch": 28.57,
+      "eval_accuracy_score": 0.9762055837563451,
+      "eval_f1": 0.8687707641196013,
+      "eval_loss": 0.15129442512989044,
+      "eval_precision": 0.8658940397350994,
+      "eval_recall": 0.8716666666666667,
+      "eval_runtime": 4.4359,
+      "eval_samples_per_second": 72.139,
+      "eval_steps_per_second": 9.017,
+      "step": 2000
+    },
+    {
+      "epoch": 31.43,
+      "eval_accuracy_score": 0.9750951776649747,
+      "eval_f1": 0.8700754400670577,
+      "eval_loss": 0.16774575412273407,
+      "eval_precision": 0.8752107925801011,
+      "eval_recall": 0.865,
+      "eval_runtime": 4.4409,
+      "eval_samples_per_second": 72.057,
+      "eval_steps_per_second": 9.007,
+      "step": 2200
+    },
+    {
+      "epoch": 34.29,
+      "eval_accuracy_score": 0.9749365482233503,
+      "eval_f1": 0.8601973684210527,
+      "eval_loss": 0.1633668839931488,
+      "eval_precision": 0.849025974025974,
+      "eval_recall": 0.8716666666666667,
+      "eval_runtime": 4.4452,
+      "eval_samples_per_second": 71.988,
+      "eval_steps_per_second": 8.998,
+      "step": 2400
+    },
+    {
+      "epoch": 35.71,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0036,
+      "step": 2500
+    },
+    {
+      "epoch": 37.14,
+      "eval_accuracy_score": 0.9766814720812182,
+      "eval_f1": 0.8782104391052196,
+      "eval_loss": 0.16212213039398193,
+      "eval_precision": 0.8731466227347611,
+      "eval_recall": 0.8833333333333333,
+      "eval_runtime": 4.4427,
+      "eval_samples_per_second": 72.028,
+      "eval_steps_per_second": 9.004,
+      "step": 2600
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy_score": 0.9763642131979695,
+      "eval_f1": 0.8719665271966527,
+      "eval_loss": 0.16754868626594543,
+      "eval_precision": 0.8756302521008403,
+      "eval_recall": 0.8683333333333333,
+      "eval_runtime": 4.4401,
+      "eval_samples_per_second": 72.07,
+      "eval_steps_per_second": 9.009,
+      "step": 2800
+    },
+    {
+      "epoch": 42.86,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0023,
+      "step": 3000
+    },
+    {
+      "epoch": 42.86,
+      "eval_accuracy_score": 0.9790609137055838,
+      "eval_f1": 0.8868703550784476,
+      "eval_loss": 0.14278778433799744,
+      "eval_precision": 0.8788870703764321,
+      "eval_recall": 0.895,
+      "eval_runtime": 4.4323,
+      "eval_samples_per_second": 72.197,
+      "eval_steps_per_second": 9.025,
+      "step": 3000
+    },
+    {
+      "epoch": 45.71,
+      "eval_accuracy_score": 0.9782677664974619,
+      "eval_f1": 0.8855721393034827,
+      "eval_loss": 0.14296667277812958,
+      "eval_precision": 0.8811881188118812,
+      "eval_recall": 0.89,
+      "eval_runtime": 4.4374,
+      "eval_samples_per_second": 72.114,
+      "eval_steps_per_second": 9.014,
+      "step": 3200
+    },
+    {
+      "epoch": 48.57,
+      "eval_accuracy_score": 0.9781091370558376,
+      "eval_f1": 0.8870703764320785,
+      "eval_loss": 0.14033867418766022,
+      "eval_precision": 0.8713826366559485,
+      "eval_recall": 0.9033333333333333,
+      "eval_runtime": 4.4359,
+      "eval_samples_per_second": 72.138,
+      "eval_steps_per_second": 9.017,
+      "step": 3400
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0026,
+      "step": 3500
+    },
+    {
+      "epoch": 51.43,
+      "eval_accuracy_score": 0.9749365482233503,
+      "eval_f1": 0.8693467336683417,
+      "eval_loss": 0.18670859932899475,
+      "eval_precision": 0.8737373737373737,
+      "eval_recall": 0.865,
+      "eval_runtime": 4.4362,
+      "eval_samples_per_second": 72.133,
+      "eval_steps_per_second": 9.017,
+      "step": 3600
+    },
+    {
+      "epoch": 54.29,
+      "eval_accuracy_score": 0.9803299492385786,
+      "eval_f1": 0.8937908496732027,
+      "eval_loss": 0.1545487940311432,
+      "eval_precision": 0.8766025641025641,
+      "eval_recall": 0.9116666666666666,
+      "eval_runtime": 4.4428,
+      "eval_samples_per_second": 72.027,
+      "eval_steps_per_second": 9.003,
+      "step": 3800
+    },
+    {
+      "epoch": 57.14,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0021,
+      "step": 4000
+    },
+    {
+      "epoch": 57.14,
+      "eval_accuracy_score": 0.975253807106599,
+      "eval_f1": 0.8647302904564315,
+      "eval_loss": 0.1578870564699173,
+      "eval_precision": 0.8611570247933884,
+      "eval_recall": 0.8683333333333333,
+      "eval_runtime": 4.4357,
+      "eval_samples_per_second": 72.143,
+      "eval_steps_per_second": 9.018,
+      "step": 4000
+    },
+    {
+      "epoch": 60.0,
+      "eval_accuracy_score": 0.9792195431472082,
+      "eval_f1": 0.8872305140961857,
+      "eval_loss": 0.14871039986610413,
+      "eval_precision": 0.8828382838283828,
+      "eval_recall": 0.8916666666666667,
+      "eval_runtime": 4.4317,
+      "eval_samples_per_second": 72.207,
+      "eval_steps_per_second": 9.026,
+      "step": 4200
+    },
+    {
+      "epoch": 62.86,
+      "eval_accuracy_score": 0.9758883248730964,
+      "eval_f1": 0.865546218487395,
+      "eval_loss": 0.16632404923439026,
+      "eval_precision": 0.8728813559322034,
+      "eval_recall": 0.8583333333333333,
+      "eval_runtime": 4.4414,
+      "eval_samples_per_second": 72.05,
+      "eval_steps_per_second": 9.006,
+      "step": 4400
+    },
+    {
+      "epoch": 64.29,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0026,
+      "step": 4500
+    },
+    {
+      "epoch": 65.71,
+      "eval_accuracy_score": 0.9747779187817259,
+      "eval_f1": 0.865721434528774,
+      "eval_loss": 0.15900883078575134,
+      "eval_precision": 0.8664440734557596,
+      "eval_recall": 0.865,
+      "eval_runtime": 4.441,
+      "eval_samples_per_second": 72.055,
+      "eval_steps_per_second": 9.007,
+      "step": 4600
+    },
+    {
+      "epoch": 68.57,
+      "eval_accuracy_score": 0.9789022842639594,
+      "eval_f1": 0.8827470686767169,
+      "eval_loss": 0.16089987754821777,
+      "eval_precision": 0.8872053872053872,
+      "eval_recall": 0.8783333333333333,
+      "eval_runtime": 4.4442,
+      "eval_samples_per_second": 72.004,
+      "eval_steps_per_second": 9.001,
+      "step": 4800
+    },
+    {
+      "epoch": 71.43,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0017,
+      "step": 5000
+    },
+    {
+      "epoch": 71.43,
+      "eval_accuracy_score": 0.9750951776649747,
+      "eval_f1": 0.8611339359079703,
+      "eval_loss": 0.1948554664850235,
+      "eval_precision": 0.8492706645056726,
+      "eval_recall": 0.8733333333333333,
+      "eval_runtime": 12.3435,
+      "eval_samples_per_second": 25.925,
+      "eval_steps_per_second": 3.241,
+      "step": 5000
+    },
+    {
+      "epoch": 74.29,
+      "eval_accuracy_score": 0.9777918781725888,
+      "eval_f1": 0.886158886158886,
+      "eval_loss": 0.15537256002426147,
+      "eval_precision": 0.8711755233494364,
+      "eval_recall": 0.9016666666666666,
+      "eval_runtime": 4.4385,
+      "eval_samples_per_second": 72.096,
+      "eval_steps_per_second": 9.012,
+      "step": 5200
+    },
+    {
+      "epoch": 74.29,
+      "step": 5200,
+      "total_flos": 2.169292304429568e+16,
+      "train_loss": 0.01710937021443477,
+      "train_runtime": 8154.5313,
+      "train_samples_per_second": 58.863,
+      "train_steps_per_second": 1.839
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 215,
+  "total_flos": 2.169292304429568e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d581ce018ce8735151aa6240b9420cd5144ecf76e88ae256f5c03662ddfc8efe
+size 3259