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": 3.41,
+    "eval_accuracy_score": 0.9919806855769333,
+    "eval_f1": 0.946596004891969,
+    "eval_loss": 0.033798202872276306,
+    "eval_precision": 0.9340305711987128,
+    "eval_recall": 0.959504132231405,
+    "eval_runtime": 24.1129,
+    "eval_samples": 1721,
+    "eval_samples_per_second": 71.372,
+    "eval_steps_per_second": 8.958,
+    "test_accuracy_score": 0.9877443750167609,
+    "test_f1": 0.8561260803253686,
+    "test_loss": 0.049406249076128006,
+    "test_precision": 0.8279252704031466,
+    "test_recall": 0.8863157894736842,
+    "test_runtime": 24.045,
+    "test_samples": 1721,
+    "test_samples_per_second": 71.574,
+    "test_steps_per_second": 8.983,
+    "train_loss": 0.03252722313006719,
+    "train_runtime": 5922.6834,
+    "train_samples": 45057,
+    "train_samples_per_second": 81.044,
+    "train_steps_per_second": 2.533
+}

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 sha256:26d4bf6c51bf811af54a89c0e2aafdd251505dadb4b71836f75d005dbdeeb1c2
+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 +1,367 @@
+{
+  "best_metric": 0.946596004891969,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-zh/checkpoint-3000",
+  "epoch": 3.4066713981547196,
+  "global_step": 4800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "eval_accuracy_score": 0.9769949905874095,
+      "eval_f1": 0.8151797603195738,
+      "eval_loss": 0.06385169178247452,
+      "eval_precision": 0.7889175257731958,
+      "eval_recall": 0.8432506887052341,
+      "eval_runtime": 24.1345,
+      "eval_samples_per_second": 71.309,
+      "eval_steps_per_second": 8.95,
+      "step": 200
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy_score": 0.9891728619593079,
+      "eval_f1": 0.9067463010723497,
+      "eval_loss": 0.03630797192454338,
+      "eval_precision": 0.8937650521808937,
+      "eval_recall": 0.9201101928374655,
+      "eval_runtime": 24.1366,
+      "eval_samples_per_second": 71.302,
+      "eval_steps_per_second": 8.949,
+      "step": 400
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1392,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy_score": 0.9874924220669411,
+      "eval_f1": 0.9033054450692636,
+      "eval_loss": 0.03671281412243843,
+      "eval_precision": 0.8994810161158153,
+      "eval_recall": 0.9071625344352617,
+      "eval_runtime": 24.1358,
+      "eval_samples_per_second": 71.305,
+      "eval_steps_per_second": 8.949,
+      "step": 600
+    },
+    {
+      "epoch": 0.57,
+      "eval_accuracy_score": 0.9906405879412484,
+      "eval_f1": 0.9202271498107085,
+      "eval_loss": 0.030743952840566635,
+      "eval_precision": 0.903611258629846,
+      "eval_recall": 0.937465564738292,
+      "eval_runtime": 24.1206,
+      "eval_samples_per_second": 71.35,
+      "eval_steps_per_second": 8.955,
+      "step": 800
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0391,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "eval_accuracy_score": 0.987524329153505,
+      "eval_f1": 0.9087680961485933,
+      "eval_loss": 0.03989069163799286,
+      "eval_precision": 0.9011375947995667,
+      "eval_recall": 0.9165289256198347,
+      "eval_runtime": 24.1074,
+      "eval_samples_per_second": 71.389,
+      "eval_steps_per_second": 8.96,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy_score": 0.9905555023770779,
+      "eval_f1": 0.926657645466847,
+      "eval_loss": 0.032413773238658905,
+      "eval_precision": 0.9106382978723404,
+      "eval_recall": 0.9432506887052342,
+      "eval_runtime": 24.1368,
+      "eval_samples_per_second": 71.302,
+      "eval_steps_per_second": 8.949,
+      "step": 1200
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy_score": 0.989800367995065,
+      "eval_f1": 0.9251387572762962,
+      "eval_loss": 0.036592062562704086,
+      "eval_precision": 0.9095022624434389,
+      "eval_recall": 0.9413223140495868,
+      "eval_runtime": 24.1374,
+      "eval_samples_per_second": 71.3,
+      "eval_steps_per_second": 8.949,
+      "step": 1400
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0319,
+      "step": 1500
+    },
+    {
+      "epoch": 1.14,
+      "eval_accuracy_score": 0.9906724950278123,
+      "eval_f1": 0.9408690869086909,
+      "eval_loss": 0.03387833759188652,
+      "eval_precision": 0.9393190554640307,
+      "eval_recall": 0.9424242424242424,
+      "eval_runtime": 24.1207,
+      "eval_samples_per_second": 71.35,
+      "eval_steps_per_second": 8.955,
+      "step": 1600
+    },
+    {
+      "epoch": 1.28,
+      "eval_accuracy_score": 0.9921508567052743,
+      "eval_f1": 0.9472521402927369,
+      "eval_loss": 0.031188521534204483,
+      "eval_precision": 0.9496124031007752,
+      "eval_recall": 0.9449035812672176,
+      "eval_runtime": 24.0966,
+      "eval_samples_per_second": 71.421,
+      "eval_steps_per_second": 8.964,
+      "step": 1800
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0215,
+      "step": 2000
+    },
+    {
+      "epoch": 1.42,
+      "eval_accuracy_score": 0.9917041574933793,
+      "eval_f1": 0.9353570944572435,
+      "eval_loss": 0.028981657698750496,
+      "eval_precision": 0.920512136569752,
+      "eval_recall": 0.9506887052341598,
+      "eval_runtime": 24.134,
+      "eval_samples_per_second": 71.31,
+      "eval_steps_per_second": 8.95,
+      "step": 2000
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy_score": 0.991278729672527,
+      "eval_f1": 0.9291854277527629,
+      "eval_loss": 0.027085134759545326,
+      "eval_precision": 0.9205190592051906,
+      "eval_recall": 0.9380165289256198,
+      "eval_runtime": 24.1322,
+      "eval_samples_per_second": 71.316,
+      "eval_steps_per_second": 8.951,
+      "step": 2200
+    },
+    {
+      "epoch": 1.7,
+      "eval_accuracy_score": 0.9881624708847835,
+      "eval_f1": 0.9310910582444627,
+      "eval_loss": 0.04595605656504631,
+      "eval_precision": 0.9242671009771987,
+      "eval_recall": 0.9380165289256198,
+      "eval_runtime": 24.1249,
+      "eval_samples_per_second": 71.337,
+      "eval_steps_per_second": 8.953,
+      "step": 2400
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0212,
+      "step": 2500
+    },
+    {
+      "epoch": 1.85,
+      "eval_accuracy_score": 0.9916509790157727,
+      "eval_f1": 0.9383054565396216,
+      "eval_loss": 0.02704950049519539,
+      "eval_precision": 0.9339519650655022,
+      "eval_recall": 0.9426997245179063,
+      "eval_runtime": 24.1289,
+      "eval_samples_per_second": 71.325,
+      "eval_steps_per_second": 8.952,
+      "step": 2600
+    },
+    {
+      "epoch": 1.99,
+      "eval_accuracy_score": 0.9914701721919105,
+      "eval_f1": 0.9384028345598255,
+      "eval_loss": 0.031768567860126495,
+      "eval_precision": 0.9285329018338727,
+      "eval_recall": 0.9484848484848485,
+      "eval_runtime": 24.1114,
+      "eval_samples_per_second": 71.377,
+      "eval_steps_per_second": 8.958,
+      "step": 2800
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0183,
+      "step": 3000
+    },
+    {
+      "epoch": 2.13,
+      "eval_accuracy_score": 0.9919806855769333,
+      "eval_f1": 0.946596004891969,
+      "eval_loss": 0.033798202872276306,
+      "eval_precision": 0.9340305711987128,
+      "eval_recall": 0.959504132231405,
+      "eval_runtime": 24.1185,
+      "eval_samples_per_second": 71.356,
+      "eval_steps_per_second": 8.956,
+      "step": 3000
+    },
+    {
+      "epoch": 2.27,
+      "eval_accuracy_score": 0.9928740840007232,
+      "eval_f1": 0.9457025920873124,
+      "eval_loss": 0.02753218449652195,
+      "eval_precision": 0.9367567567567567,
+      "eval_recall": 0.9548209366391185,
+      "eval_runtime": 24.1012,
+      "eval_samples_per_second": 71.407,
+      "eval_steps_per_second": 8.962,
+      "step": 3200
+    },
+    {
+      "epoch": 2.41,
+      "eval_accuracy_score": 0.9928421769141593,
+      "eval_f1": 0.9465940054495913,
+      "eval_loss": 0.026147814467549324,
+      "eval_precision": 0.9363881401617251,
+      "eval_recall": 0.9570247933884297,
+      "eval_runtime": 24.1545,
+      "eval_samples_per_second": 71.25,
+      "eval_steps_per_second": 8.942,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0128,
+      "step": 3500
+    },
+    {
+      "epoch": 2.56,
+      "eval_accuracy_score": 0.9918105144485924,
+      "eval_f1": 0.9442399454669393,
+      "eval_loss": 0.030992617830634117,
+      "eval_precision": 0.9346828609986505,
+      "eval_recall": 0.9539944903581267,
+      "eval_runtime": 24.1093,
+      "eval_samples_per_second": 71.383,
+      "eval_steps_per_second": 8.959,
+      "step": 3600
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy_score": 0.9916828861023367,
+      "eval_f1": 0.9474550692824805,
+      "eval_loss": 0.03291752561926842,
+      "eval_precision": 0.9437004646078163,
+      "eval_recall": 0.9512396694214876,
+      "eval_runtime": 24.1311,
+      "eval_samples_per_second": 71.319,
+      "eval_steps_per_second": 8.951,
+      "step": 3800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0134,
+      "step": 4000
+    },
+    {
+      "epoch": 2.84,
+      "eval_accuracy_score": 0.9919168714038055,
+      "eval_f1": 0.9425444596443229,
+      "eval_loss": 0.029299931600689888,
+      "eval_precision": 0.936141304347826,
+      "eval_recall": 0.9490358126721763,
+      "eval_runtime": 24.0874,
+      "eval_samples_per_second": 71.448,
+      "eval_steps_per_second": 8.967,
+      "step": 4000
+    },
+    {
+      "epoch": 2.98,
+      "eval_accuracy_score": 0.9920125926634973,
+      "eval_f1": 0.9384928716904277,
+      "eval_loss": 0.03006567806005478,
+      "eval_precision": 0.9253012048192771,
+      "eval_recall": 0.9520661157024793,
+      "eval_runtime": 24.1243,
+      "eval_samples_per_second": 71.339,
+      "eval_steps_per_second": 8.954,
+      "step": 4200
+    },
+    {
+      "epoch": 3.12,
+      "eval_accuracy_score": 0.9918530572306776,
+      "eval_f1": 0.943499725726824,
+      "eval_loss": 0.03543129563331604,
+      "eval_precision": 0.9393773894046968,
+      "eval_recall": 0.9476584022038568,
+      "eval_runtime": 24.0895,
+      "eval_samples_per_second": 71.442,
+      "eval_steps_per_second": 8.967,
+      "step": 4400
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.01,
+      "step": 4500
+    },
+    {
+      "epoch": 3.26,
+      "eval_accuracy_score": 0.9917147931889005,
+      "eval_f1": 0.9457131136332558,
+      "eval_loss": 0.03731205314397812,
+      "eval_precision": 0.9389084985066521,
+      "eval_recall": 0.9526170798898072,
+      "eval_runtime": 24.1136,
+      "eval_samples_per_second": 71.371,
+      "eval_steps_per_second": 8.958,
+      "step": 4600
+    },
+    {
+      "epoch": 3.41,
+      "eval_accuracy_score": 0.9919594141858907,
+      "eval_f1": 0.9425412856557936,
+      "eval_loss": 0.034975141286849976,
+      "eval_precision": 0.9340005409791723,
+      "eval_recall": 0.9512396694214876,
+      "eval_runtime": 24.1047,
+      "eval_samples_per_second": 71.397,
+      "eval_steps_per_second": 8.961,
+      "step": 4800
+    },
+    {
+      "epoch": 3.41,
+      "step": 4800,
+      "total_flos": 2.005670985822259e+16,
+      "train_loss": 0.03252722313006719,
+      "train_runtime": 5922.6834,
+      "train_samples_per_second": 81.044,
+      "train_steps_per_second": 2.533
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 11,
+  "total_flos": 2.005670985822259e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1da4ff5769abd44d05518eb2d6723b24f3adca4dcfff92d448d3af96bf03955
+size 3259