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": 155.56,
+    "eval_accuracy_score": 0.9596923892866613,
+    "eval_f1": 0.7548387096774194,
+    "eval_loss": 0.35259804129600525,
+    "eval_precision": 0.7048192771084337,
+    "eval_recall": 0.8125,
+    "eval_runtime": 2.7613,
+    "eval_samples": 200,
+    "eval_samples_per_second": 72.431,
+    "eval_steps_per_second": 9.054,
+    "test_accuracy_score": 0.9636215831724418,
+    "test_f1": 0.7854710556186153,
+    "test_loss": 0.3192311227321625,
+    "test_precision": 0.762114537444934,
+    "test_recall": 0.810304449648712,
+    "test_runtime": 5.626,
+    "test_samples": 407,
+    "test_samples_per_second": 72.343,
+    "test_steps_per_second": 9.065,
+    "train_loss": 0.011920496485063008,
+    "train_runtime": 10148.142,
+    "train_samples": 1428,
+    "train_samples_per_second": 47.299,
+    "train_steps_per_second": 1.478
+}

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 sha256:0627e325a8bcc8f7640cc9281068e0df9877d55e6655c2d4c61a31add51c6502
+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 +1,529 @@
+{
+  "best_metric": 0.7548387096774194,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-lug/checkpoint-6000",
+  "epoch": 155.55555555555554,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.44,
+      "eval_accuracy_score": 0.949085123309467,
+      "eval_f1": 0.7053435114503817,
+      "eval_loss": 0.200306236743927,
+      "eval_precision": 0.6294277929155313,
+      "eval_recall": 0.8020833333333334,
+      "eval_runtime": 2.7824,
+      "eval_samples_per_second": 71.881,
+      "eval_steps_per_second": 8.985,
+      "step": 200
+    },
+    {
+      "epoch": 8.89,
+      "eval_accuracy_score": 0.9461681251657386,
+      "eval_f1": 0.6605783866057838,
+      "eval_loss": 0.2998030185699463,
+      "eval_precision": 0.5880758807588076,
+      "eval_recall": 0.7534722222222222,
+      "eval_runtime": 2.7782,
+      "eval_samples_per_second": 71.989,
+      "eval_steps_per_second": 8.999,
+      "step": 400
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1417,
+      "step": 500
+    },
+    {
+      "epoch": 13.33,
+      "eval_accuracy_score": 0.9543887562980642,
+      "eval_f1": 0.7278382581648523,
+      "eval_loss": 0.2749716639518738,
+      "eval_precision": 0.6591549295774648,
+      "eval_recall": 0.8125,
+      "eval_runtime": 2.7787,
+      "eval_samples_per_second": 71.975,
+      "eval_steps_per_second": 8.997,
+      "step": 600
+    },
+    {
+      "epoch": 17.78,
+      "eval_accuracy_score": 0.9517369398037656,
+      "eval_f1": 0.6957878315132605,
+      "eval_loss": 0.30419987440109253,
+      "eval_precision": 0.6317280453257791,
+      "eval_recall": 0.7743055555555556,
+      "eval_runtime": 2.7786,
+      "eval_samples_per_second": 71.978,
+      "eval_steps_per_second": 8.997,
+      "step": 800
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0049,
+      "step": 1000
+    },
+    {
+      "epoch": 22.22,
+      "eval_accuracy_score": 0.9498806682577565,
+      "eval_f1": 0.7075471698113208,
+      "eval_loss": 0.36269524693489075,
+      "eval_precision": 0.646551724137931,
+      "eval_recall": 0.78125,
+      "eval_runtime": 2.7801,
+      "eval_samples_per_second": 71.941,
+      "eval_steps_per_second": 8.993,
+      "step": 1000
+    },
+    {
+      "epoch": 26.67,
+      "eval_accuracy_score": 0.9533280297003447,
+      "eval_f1": 0.7145135566188199,
+      "eval_loss": 0.36558207869529724,
+      "eval_precision": 0.6607669616519174,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 2.7791,
+      "eval_samples_per_second": 71.966,
+      "eval_steps_per_second": 8.996,
+      "step": 1200
+    },
+    {
+      "epoch": 31.11,
+      "eval_accuracy_score": 0.9557146645452135,
+      "eval_f1": 0.7142857142857142,
+      "eval_loss": 0.2809523344039917,
+      "eval_precision": 0.6847133757961783,
+      "eval_recall": 0.7465277777777778,
+      "eval_runtime": 2.7804,
+      "eval_samples_per_second": 71.931,
+      "eval_steps_per_second": 8.991,
+      "step": 1400
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0036,
+      "step": 1500
+    },
+    {
+      "epoch": 35.56,
+      "eval_accuracy_score": 0.9517369398037656,
+      "eval_f1": 0.6644951140065147,
+      "eval_loss": 0.32650795578956604,
+      "eval_precision": 0.6257668711656442,
+      "eval_recall": 0.7083333333333334,
+      "eval_runtime": 2.7784,
+      "eval_samples_per_second": 71.985,
+      "eval_steps_per_second": 8.998,
+      "step": 1600
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy_score": 0.952797666401485,
+      "eval_f1": 0.6910828025477705,
+      "eval_loss": 0.3485059440135956,
+      "eval_precision": 0.638235294117647,
+      "eval_recall": 0.7534722222222222,
+      "eval_runtime": 2.7769,
+      "eval_samples_per_second": 72.023,
+      "eval_steps_per_second": 9.003,
+      "step": 1800
+    },
+    {
+      "epoch": 44.44,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0028,
+      "step": 2000
+    },
+    {
+      "epoch": 44.44,
+      "eval_accuracy_score": 0.9512065765049058,
+      "eval_f1": 0.6754530477759474,
+      "eval_loss": 0.3388746678829193,
+      "eval_precision": 0.6426332288401254,
+      "eval_recall": 0.7118055555555556,
+      "eval_runtime": 2.7758,
+      "eval_samples_per_second": 72.052,
+      "eval_steps_per_second": 9.007,
+      "step": 2000
+    },
+    {
+      "epoch": 48.89,
+      "eval_accuracy_score": 0.9549191195969239,
+      "eval_f1": 0.7112561174551387,
+      "eval_loss": 0.3353417217731476,
+      "eval_precision": 0.6707692307692308,
+      "eval_recall": 0.7569444444444444,
+      "eval_runtime": 2.7837,
+      "eval_samples_per_second": 71.847,
+      "eval_steps_per_second": 8.981,
+      "step": 2200
+    },
+    {
+      "epoch": 53.33,
+      "eval_accuracy_score": 0.9541235746486343,
+      "eval_f1": 0.701095461658842,
+      "eval_loss": 0.3772818446159363,
+      "eval_precision": 0.6381766381766382,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 2.7767,
+      "eval_samples_per_second": 72.029,
+      "eval_steps_per_second": 9.004,
+      "step": 2400
+    },
+    {
+      "epoch": 55.56,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0024,
+      "step": 2500
+    },
+    {
+      "epoch": 57.78,
+      "eval_accuracy_score": 0.9581012993900823,
+      "eval_f1": 0.7302100161550888,
+      "eval_loss": 0.3589210510253906,
+      "eval_precision": 0.6827794561933535,
+      "eval_recall": 0.7847222222222222,
+      "eval_runtime": 2.7851,
+      "eval_samples_per_second": 71.809,
+      "eval_steps_per_second": 8.976,
+      "step": 2600
+    },
+    {
+      "epoch": 62.22,
+      "eval_accuracy_score": 0.9498806682577565,
+      "eval_f1": 0.7086614173228347,
+      "eval_loss": 0.384027361869812,
+      "eval_precision": 0.6484149855907781,
+      "eval_recall": 0.78125,
+      "eval_runtime": 2.7806,
+      "eval_samples_per_second": 71.928,
+      "eval_steps_per_second": 8.991,
+      "step": 2800
+    },
+    {
+      "epoch": 66.67,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0018,
+      "step": 3000
+    },
+    {
+      "epoch": 66.67,
+      "eval_accuracy_score": 0.9533280297003447,
+      "eval_f1": 0.7140600315955765,
+      "eval_loss": 0.3608270287513733,
+      "eval_precision": 0.6550724637681159,
+      "eval_recall": 0.7847222222222222,
+      "eval_runtime": 2.7702,
+      "eval_samples_per_second": 72.197,
+      "eval_steps_per_second": 9.025,
+      "step": 3000
+    },
+    {
+      "epoch": 71.11,
+      "eval_accuracy_score": 0.9504110315566163,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.33889251947402954,
+      "eval_precision": 0.6091954022988506,
+      "eval_recall": 0.7361111111111112,
+      "eval_runtime": 2.7756,
+      "eval_samples_per_second": 72.058,
+      "eval_steps_per_second": 9.007,
+      "step": 3200
+    },
+    {
+      "epoch": 75.56,
+      "eval_accuracy_score": 0.9559798461946434,
+      "eval_f1": 0.7193548387096774,
+      "eval_loss": 0.325101763010025,
+      "eval_precision": 0.6716867469879518,
+      "eval_recall": 0.7743055555555556,
+      "eval_runtime": 2.7793,
+      "eval_samples_per_second": 71.96,
+      "eval_steps_per_second": 8.995,
+      "step": 3400
+    },
+    {
+      "epoch": 77.78,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0017,
+      "step": 3500
+    },
+    {
+      "epoch": 80.0,
+      "eval_accuracy_score": 0.9543887562980642,
+      "eval_f1": 0.7051070840197693,
+      "eval_loss": 0.3474235534667969,
+      "eval_precision": 0.670846394984326,
+      "eval_recall": 0.7430555555555556,
+      "eval_runtime": 2.7778,
+      "eval_samples_per_second": 72.0,
+      "eval_steps_per_second": 9.0,
+      "step": 3600
+    },
+    {
+      "epoch": 84.44,
+      "eval_accuracy_score": 0.9554494828957836,
+      "eval_f1": 0.7081339712918661,
+      "eval_loss": 0.3440423309803009,
+      "eval_precision": 0.6548672566371682,
+      "eval_recall": 0.7708333333333334,
+      "eval_runtime": 2.7746,
+      "eval_samples_per_second": 72.083,
+      "eval_steps_per_second": 9.01,
+      "step": 3800
+    },
+    {
+      "epoch": 88.89,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.001,
+      "step": 4000
+    },
+    {
+      "epoch": 88.89,
+      "eval_accuracy_score": 0.9562450278440732,
+      "eval_f1": 0.7081967213114755,
+      "eval_loss": 0.34857451915740967,
+      "eval_precision": 0.6708074534161491,
+      "eval_recall": 0.75,
+      "eval_runtime": 2.7573,
+      "eval_samples_per_second": 72.535,
+      "eval_steps_per_second": 9.067,
+      "step": 4000
+    },
+    {
+      "epoch": 93.33,
+      "eval_accuracy_score": 0.9573057544417927,
+      "eval_f1": 0.7246376811594203,
+      "eval_loss": 0.3356036841869354,
+      "eval_precision": 0.6756756756756757,
+      "eval_recall": 0.78125,
+      "eval_runtime": 2.7694,
+      "eval_samples_per_second": 72.219,
+      "eval_steps_per_second": 9.027,
+      "step": 4200
+    },
+    {
+      "epoch": 97.78,
+      "eval_accuracy_score": 0.9530628480509149,
+      "eval_f1": 0.7017543859649124,
+      "eval_loss": 0.37629222869873047,
+      "eval_precision": 0.6489675516224189,
+      "eval_recall": 0.7638888888888888,
+      "eval_runtime": 2.7682,
+      "eval_samples_per_second": 72.25,
+      "eval_steps_per_second": 9.031,
+      "step": 4400
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0015,
+      "step": 4500
+    },
+    {
+      "epoch": 102.22,
+      "eval_accuracy_score": 0.9496154866083267,
+      "eval_f1": 0.673170731707317,
+      "eval_loss": 0.3837837874889374,
+      "eval_precision": 0.6330275229357798,
+      "eval_recall": 0.71875,
+      "eval_runtime": 2.7764,
+      "eval_samples_per_second": 72.036,
+      "eval_steps_per_second": 9.004,
+      "step": 4600
+    },
+    {
+      "epoch": 106.67,
+      "eval_accuracy_score": 0.9551843012463538,
+      "eval_f1": 0.7251655629139072,
+      "eval_loss": 0.35345935821533203,
+      "eval_precision": 0.6930379746835443,
+      "eval_recall": 0.7604166666666666,
+      "eval_runtime": 2.7673,
+      "eval_samples_per_second": 72.271,
+      "eval_steps_per_second": 9.034,
+      "step": 4800
+    },
+    {
+      "epoch": 111.11,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0017,
+      "step": 5000
+    },
+    {
+      "epoch": 111.11,
+      "eval_accuracy_score": 0.9588968443383717,
+      "eval_f1": 0.7311072056239015,
+      "eval_loss": 0.3115241229534149,
+      "eval_precision": 0.7402135231316725,
+      "eval_recall": 0.7222222222222222,
+      "eval_runtime": 2.7806,
+      "eval_samples_per_second": 71.926,
+      "eval_steps_per_second": 8.991,
+      "step": 5000
+    },
+    {
+      "epoch": 115.56,
+      "eval_accuracy_score": 0.9599575709360912,
+      "eval_f1": 0.7281879194630871,
+      "eval_loss": 0.29021960496902466,
+      "eval_precision": 0.7045454545454546,
+      "eval_recall": 0.7534722222222222,
+      "eval_runtime": 2.7637,
+      "eval_samples_per_second": 72.368,
+      "eval_steps_per_second": 9.046,
+      "step": 5200
+    },
+    {
+      "epoch": 120.0,
+      "eval_accuracy_score": 0.9554494828957836,
+      "eval_f1": 0.7348242811501597,
+      "eval_loss": 0.37681084871292114,
+      "eval_precision": 0.6804733727810651,
+      "eval_recall": 0.7986111111111112,
+      "eval_runtime": 2.7807,
+      "eval_samples_per_second": 71.925,
+      "eval_steps_per_second": 8.991,
+      "step": 5400
+    },
+    {
+      "epoch": 122.22,
+      "learning_rate": 3.1879194630872485e-05,
+      "loss": 0.0013,
+      "step": 5500
+    },
+    {
+      "epoch": 124.44,
+      "eval_accuracy_score": 0.958631662688942,
+      "eval_f1": 0.745928338762215,
+      "eval_loss": 0.33346712589263916,
+      "eval_precision": 0.7024539877300614,
+      "eval_recall": 0.7951388888888888,
+      "eval_runtime": 2.7673,
+      "eval_samples_per_second": 72.273,
+      "eval_steps_per_second": 9.034,
+      "step": 5600
+    },
+    {
+      "epoch": 128.89,
+      "eval_accuracy_score": 0.9565102094935031,
+      "eval_f1": 0.7249190938511326,
+      "eval_loss": 0.33011287450790405,
+      "eval_precision": 0.6787878787878788,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 2.7709,
+      "eval_samples_per_second": 72.178,
+      "eval_steps_per_second": 9.022,
+      "step": 5800
+    },
+    {
+      "epoch": 133.33,
+      "learning_rate": 3.02013422818792e-05,
+      "loss": 0.0009,
+      "step": 6000
+    },
+    {
+      "epoch": 133.33,
+      "eval_accuracy_score": 0.9596923892866613,
+      "eval_f1": 0.7548387096774194,
+      "eval_loss": 0.35259804129600525,
+      "eval_precision": 0.7048192771084337,
+      "eval_recall": 0.8125,
+      "eval_runtime": 2.7569,
+      "eval_samples_per_second": 72.544,
+      "eval_steps_per_second": 9.068,
+      "step": 6000
+    },
+    {
+      "epoch": 137.78,
+      "eval_accuracy_score": 0.954653937947494,
+      "eval_f1": 0.6905537459283388,
+      "eval_loss": 0.3407050371170044,
+      "eval_precision": 0.6503067484662577,
+      "eval_recall": 0.7361111111111112,
+      "eval_runtime": 2.7686,
+      "eval_samples_per_second": 72.24,
+      "eval_steps_per_second": 9.03,
+      "step": 6200
+    },
+    {
+      "epoch": 142.22,
+      "eval_accuracy_score": 0.9578361177406524,
+      "eval_f1": 0.7337662337662337,
+      "eval_loss": 0.3645722270011902,
+      "eval_precision": 0.6890243902439024,
+      "eval_recall": 0.7847222222222222,
+      "eval_runtime": 2.7671,
+      "eval_samples_per_second": 72.277,
+      "eval_steps_per_second": 9.035,
+      "step": 6400
+    },
+    {
+      "epoch": 144.44,
+      "learning_rate": 2.8523489932885905e-05,
+      "loss": 0.0012,
+      "step": 6500
+    },
+    {
+      "epoch": 146.67,
+      "eval_accuracy_score": 0.9567753911429329,
+      "eval_f1": 0.7427652733118972,
+      "eval_loss": 0.3477034866809845,
+      "eval_precision": 0.6916167664670658,
+      "eval_recall": 0.8020833333333334,
+      "eval_runtime": 2.7617,
+      "eval_samples_per_second": 72.419,
+      "eval_steps_per_second": 9.052,
+      "step": 6600
+    },
+    {
+      "epoch": 151.11,
+      "eval_accuracy_score": 0.9549191195969239,
+      "eval_f1": 0.7156862745098039,
+      "eval_loss": 0.3507363796234131,
+      "eval_precision": 0.6759259259259259,
+      "eval_recall": 0.7604166666666666,
+      "eval_runtime": 2.7711,
+      "eval_samples_per_second": 72.173,
+      "eval_steps_per_second": 9.022,
+      "step": 6800
+    },
+    {
+      "epoch": 155.56,
+      "learning_rate": 2.6845637583892618e-05,
+      "loss": 0.0004,
+      "step": 7000
+    },
+    {
+      "epoch": 155.56,
+      "eval_accuracy_score": 0.9557146645452135,
+      "eval_f1": 0.7368421052631579,
+      "eval_loss": 0.40961742401123047,
+      "eval_precision": 0.6814159292035398,
+      "eval_recall": 0.8020833333333334,
+      "eval_runtime": 2.7599,
+      "eval_samples_per_second": 72.467,
+      "eval_steps_per_second": 9.058,
+      "step": 7000
+    },
+    {
+      "epoch": 155.56,
+      "step": 7000,
+      "total_flos": 2.902406748816384e+16,
+      "train_loss": 0.011920496485063008,
+      "train_runtime": 10148.142,
+      "train_samples_per_second": 47.299,
+      "train_steps_per_second": 1.478
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 334,
+  "total_flos": 2.902406748816384e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd36baab522a4b93c201cf39efa567c8bde4b8e17e8c0680cb43ac1699018e1
+size 3259