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": 73.53,
+    "eval_accuracy_score": 0.9665495432185524,
+    "eval_f1": 0.7928669410150893,
+    "eval_loss": 0.291377454996109,
+    "eval_precision": 0.7831978319783198,
+    "eval_recall": 0.8027777777777778,
+    "eval_runtime": 4.2304,
+    "eval_samples": 305,
+    "eval_samples_per_second": 72.097,
+    "eval_steps_per_second": 9.219,
+    "test_accuracy_score": 0.9614495375954966,
+    "test_f1": 0.775235531628533,
+    "test_loss": 0.3572275936603546,
+    "test_precision": 0.7883211678832117,
+    "test_recall": 0.7625772285966461,
+    "test_runtime": 8.9266,
+    "test_samples": 645,
+    "test_samples_per_second": 72.256,
+    "test_steps_per_second": 9.074,
+    "train_loss": 0.014607224118709565,
+    "train_runtime": 5667.0091,
+    "train_samples": 2171,
+    "train_samples_per_second": 84.701,
+    "train_steps_per_second": 2.647
+}

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:b0bae34f3d96cbe791cd848f36c9f69d689a445b2d0d15f8af45239a64ca4390
+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 +1,385 @@
+{
+  "best_metric": 0.7928669410150893,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-yor/checkpoint-4000",
+  "epoch": 73.52941176470588,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.94,
+      "eval_accuracy_score": 0.9617709065354884,
+      "eval_f1": 0.7467362924281985,
+      "eval_loss": 0.16836212575435638,
+      "eval_precision": 0.7044334975369458,
+      "eval_recall": 0.7944444444444444,
+      "eval_runtime": 4.2439,
+      "eval_samples_per_second": 71.868,
+      "eval_steps_per_second": 9.19,
+      "step": 200
+    },
+    {
+      "epoch": 5.88,
+      "eval_accuracy_score": 0.9564300773014758,
+      "eval_f1": 0.7172774869109947,
+      "eval_loss": 0.20965266227722168,
+      "eval_precision": 0.6782178217821783,
+      "eval_recall": 0.7611111111111111,
+      "eval_runtime": 4.2334,
+      "eval_samples_per_second": 72.046,
+      "eval_steps_per_second": 9.212,
+      "step": 400
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1207,
+      "step": 500
+    },
+    {
+      "epoch": 8.82,
+      "eval_accuracy_score": 0.9651440618411806,
+      "eval_f1": 0.7470198675496688,
+      "eval_loss": 0.19184653460979462,
+      "eval_precision": 0.7139240506329114,
+      "eval_recall": 0.7833333333333333,
+      "eval_runtime": 4.2345,
+      "eval_samples_per_second": 72.028,
+      "eval_steps_per_second": 9.21,
+      "step": 600
+    },
+    {
+      "epoch": 11.76,
+      "eval_accuracy_score": 0.9675333801827126,
+      "eval_f1": 0.7758389261744967,
+      "eval_loss": 0.20845761895179749,
+      "eval_precision": 0.7506493506493507,
+      "eval_recall": 0.8027777777777778,
+      "eval_runtime": 4.2327,
+      "eval_samples_per_second": 72.058,
+      "eval_steps_per_second": 9.214,
+      "step": 800
+    },
+    {
+      "epoch": 14.71,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0064,
+      "step": 1000
+    },
+    {
+      "epoch": 14.71,
+      "eval_accuracy_score": 0.9676739283204497,
+      "eval_f1": 0.768,
+      "eval_loss": 0.20797914266586304,
+      "eval_precision": 0.7384615384615385,
+      "eval_recall": 0.8,
+      "eval_runtime": 4.225,
+      "eval_samples_per_second": 72.189,
+      "eval_steps_per_second": 9.231,
+      "step": 1000
+    },
+    {
+      "epoch": 17.65,
+      "eval_accuracy_score": 0.9612087139845397,
+      "eval_f1": 0.7708609271523178,
+      "eval_loss": 0.2564171552658081,
+      "eval_precision": 0.7367088607594937,
+      "eval_recall": 0.8083333333333333,
+      "eval_runtime": 4.2295,
+      "eval_samples_per_second": 72.112,
+      "eval_steps_per_second": 9.221,
+      "step": 1200
+    },
+    {
+      "epoch": 20.59,
+      "eval_accuracy_score": 0.967111735769501,
+      "eval_f1": 0.7891156462585034,
+      "eval_loss": 0.2191239595413208,
+      "eval_precision": 0.7733333333333333,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.2308,
+      "eval_samples_per_second": 72.09,
+      "eval_steps_per_second": 9.218,
+      "step": 1400
+    },
+    {
+      "epoch": 22.06,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0037,
+      "step": 1500
+    },
+    {
+      "epoch": 23.53,
+      "eval_accuracy_score": 0.9680955727336613,
+      "eval_f1": 0.7924016282225237,
+      "eval_loss": 0.213937446475029,
+      "eval_precision": 0.7745358090185677,
+      "eval_recall": 0.8111111111111111,
+      "eval_runtime": 4.2289,
+      "eval_samples_per_second": 72.122,
+      "eval_steps_per_second": 9.222,
+      "step": 1600
+    },
+    {
+      "epoch": 26.47,
+      "eval_accuracy_score": 0.9631763879128602,
+      "eval_f1": 0.7652645861601086,
+      "eval_loss": 0.2679533362388611,
+      "eval_precision": 0.7480106100795756,
+      "eval_recall": 0.7833333333333333,
+      "eval_runtime": 4.2299,
+      "eval_samples_per_second": 72.106,
+      "eval_steps_per_second": 9.22,
+      "step": 1800
+    },
+    {
+      "epoch": 29.41,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0033,
+      "step": 2000
+    },
+    {
+      "epoch": 29.41,
+      "eval_accuracy_score": 0.9633169360505973,
+      "eval_f1": 0.7709190672153635,
+      "eval_loss": 0.2611113488674164,
+      "eval_precision": 0.7615176151761518,
+      "eval_recall": 0.7805555555555556,
+      "eval_runtime": 4.2112,
+      "eval_samples_per_second": 72.426,
+      "eval_steps_per_second": 9.261,
+      "step": 2000
+    },
+    {
+      "epoch": 32.35,
+      "eval_accuracy_score": 0.9657062543921293,
+      "eval_f1": 0.7735099337748345,
+      "eval_loss": 0.2416420429944992,
+      "eval_precision": 0.739240506329114,
+      "eval_recall": 0.8111111111111111,
+      "eval_runtime": 4.2178,
+      "eval_samples_per_second": 72.312,
+      "eval_steps_per_second": 9.246,
+      "step": 2200
+    },
+    {
+      "epoch": 35.29,
+      "eval_accuracy_score": 0.9575544624033732,
+      "eval_f1": 0.7470198675496688,
+      "eval_loss": 0.26062682271003723,
+      "eval_precision": 0.7139240506329114,
+      "eval_recall": 0.7833333333333333,
+      "eval_runtime": 4.2283,
+      "eval_samples_per_second": 72.134,
+      "eval_steps_per_second": 9.224,
+      "step": 2400
+    },
+    {
+      "epoch": 36.76,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0033,
+      "step": 2500
+    },
+    {
+      "epoch": 38.24,
+      "eval_accuracy_score": 0.9621925509486999,
+      "eval_f1": 0.7560321715817695,
+      "eval_loss": 0.2517440915107727,
+      "eval_precision": 0.7305699481865285,
+      "eval_recall": 0.7833333333333333,
+      "eval_runtime": 4.221,
+      "eval_samples_per_second": 72.257,
+      "eval_steps_per_second": 9.239,
+      "step": 2600
+    },
+    {
+      "epoch": 41.18,
+      "eval_accuracy_score": 0.9619114546732256,
+      "eval_f1": 0.7779273216689098,
+      "eval_loss": 0.25837406516075134,
+      "eval_precision": 0.7545691906005222,
+      "eval_recall": 0.8027777777777778,
+      "eval_runtime": 4.2231,
+      "eval_samples_per_second": 72.221,
+      "eval_steps_per_second": 9.235,
+      "step": 2800
+    },
+    {
+      "epoch": 44.12,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0021,
+      "step": 3000
+    },
+    {
+      "epoch": 44.12,
+      "eval_accuracy_score": 0.9619114546732256,
+      "eval_f1": 0.7852257181942545,
+      "eval_loss": 0.2560689449310303,
+      "eval_precision": 0.7735849056603774,
+      "eval_recall": 0.7972222222222223,
+      "eval_runtime": 4.2232,
+      "eval_samples_per_second": 72.22,
+      "eval_steps_per_second": 9.235,
+      "step": 3000
+    },
+    {
+      "epoch": 47.06,
+      "eval_accuracy_score": 0.9631763879128602,
+      "eval_f1": 0.757123473541384,
+      "eval_loss": 0.24956972897052765,
+      "eval_precision": 0.7400530503978779,
+      "eval_recall": 0.775,
+      "eval_runtime": 4.2237,
+      "eval_samples_per_second": 72.212,
+      "eval_steps_per_second": 9.234,
+      "step": 3200
+    },
+    {
+      "epoch": 50.0,
+      "eval_accuracy_score": 0.9655657062543921,
+      "eval_f1": 0.7722222222222223,
+      "eval_loss": 0.28158125281333923,
+      "eval_precision": 0.7722222222222223,
+      "eval_recall": 0.7722222222222223,
+      "eval_runtime": 4.2211,
+      "eval_samples_per_second": 72.256,
+      "eval_steps_per_second": 9.239,
+      "step": 3400
+    },
+    {
+      "epoch": 51.47,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.002,
+      "step": 3500
+    },
+    {
+      "epoch": 52.94,
+      "eval_accuracy_score": 0.9645818692902319,
+      "eval_f1": 0.772117962466488,
+      "eval_loss": 0.24671129882335663,
+      "eval_precision": 0.7461139896373057,
+      "eval_recall": 0.8,
+      "eval_runtime": 4.2219,
+      "eval_samples_per_second": 72.243,
+      "eval_steps_per_second": 9.238,
+      "step": 3600
+    },
+    {
+      "epoch": 55.88,
+      "eval_accuracy_score": 0.9659873506676037,
+      "eval_f1": 0.7923497267759563,
+      "eval_loss": 0.2602536678314209,
+      "eval_precision": 0.7795698924731183,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.2241,
+      "eval_samples_per_second": 72.205,
+      "eval_steps_per_second": 9.233,
+      "step": 3800
+    },
+    {
+      "epoch": 58.82,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0013,
+      "step": 4000
+    },
+    {
+      "epoch": 58.82,
+      "eval_accuracy_score": 0.9665495432185524,
+      "eval_f1": 0.7928669410150893,
+      "eval_loss": 0.291377454996109,
+      "eval_precision": 0.7831978319783198,
+      "eval_recall": 0.8027777777777778,
+      "eval_runtime": 4.2136,
+      "eval_samples_per_second": 72.384,
+      "eval_steps_per_second": 9.256,
+      "step": 4000
+    },
+    {
+      "epoch": 61.76,
+      "eval_accuracy_score": 0.9658468025298664,
+      "eval_f1": 0.7842605156037992,
+      "eval_loss": 0.280934602022171,
+      "eval_precision": 0.76657824933687,
+      "eval_recall": 0.8027777777777778,
+      "eval_runtime": 4.2253,
+      "eval_samples_per_second": 72.183,
+      "eval_steps_per_second": 9.23,
+      "step": 4200
+    },
+    {
+      "epoch": 64.71,
+      "eval_accuracy_score": 0.9621925509486999,
+      "eval_f1": 0.7779273216689098,
+      "eval_loss": 0.3064756691455841,
+      "eval_precision": 0.7545691906005222,
+      "eval_recall": 0.8027777777777778,
+      "eval_runtime": 4.2222,
+      "eval_samples_per_second": 72.237,
+      "eval_steps_per_second": 9.237,
+      "step": 4400
+    },
+    {
+      "epoch": 66.18,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0021,
+      "step": 4500
+    },
+    {
+      "epoch": 67.65,
+      "eval_accuracy_score": 0.9673928320449754,
+      "eval_f1": 0.7667121418826739,
+      "eval_loss": 0.2502681016921997,
+      "eval_precision": 0.7533512064343163,
+      "eval_recall": 0.7805555555555556,
+      "eval_runtime": 4.2225,
+      "eval_samples_per_second": 72.232,
+      "eval_steps_per_second": 9.236,
+      "step": 4600
+    },
+    {
+      "epoch": 70.59,
+      "eval_accuracy_score": 0.9641602248770204,
+      "eval_f1": 0.7788331071913162,
+      "eval_loss": 0.2737264335155487,
+      "eval_precision": 0.7612732095490716,
+      "eval_recall": 0.7972222222222223,
+      "eval_runtime": 4.2229,
+      "eval_samples_per_second": 72.225,
+      "eval_steps_per_second": 9.235,
+      "step": 4800
+    },
+    {
+      "epoch": 73.53,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0013,
+      "step": 5000
+    },
+    {
+      "epoch": 73.53,
+      "eval_accuracy_score": 0.963879128601546,
+      "eval_f1": 0.7750677506775068,
+      "eval_loss": 0.2737545967102051,
+      "eval_precision": 0.7566137566137566,
+      "eval_recall": 0.7944444444444444,
+      "eval_runtime": 4.2199,
+      "eval_samples_per_second": 72.277,
+      "eval_steps_per_second": 9.242,
+      "step": 5000
+    },
+    {
+      "epoch": 73.53,
+      "step": 5000,
+      "total_flos": 2.085737378893056e+16,
+      "train_loss": 0.014607224118709565,
+      "train_runtime": 5667.0091,
+      "train_samples_per_second": 84.701,
+      "train_steps_per_second": 2.647
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 221,
+  "total_flos": 2.085737378893056e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88807b0dc9c59c63f2667c1a34e5cd9d39b3a45d23b642bedc26c34c80914d9d
+size 3259