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": 6.83,
+    "eval_accuracy_score": 0.9931272146723259,
+    "eval_f1": 0.9597055019401054,
+    "eval_loss": 0.03970629721879959,
+    "eval_precision": 0.958656330749354,
+    "eval_recall": 0.9607569721115538,
+    "eval_runtime": 45.0783,
+    "eval_samples": 3250,
+    "eval_samples_per_second": 72.097,
+    "eval_steps_per_second": 9.029,
+    "test_accuracy_score": 0.9848174868095186,
+    "test_f1": 0.9193890967937696,
+    "test_loss": 0.10671531409025192,
+    "test_precision": 0.9198542805100182,
+    "test_recall": 0.9189243833400728,
+    "test_runtime": 47.9545,
+    "test_samples": 3453,
+    "test_samples_per_second": 72.006,
+    "test_steps_per_second": 9.009,
+    "train_loss": 0.03388593363761902,
+    "train_runtime": 6160.4656,
+    "train_samples": 14042,
+    "train_samples_per_second": 77.916,
+    "train_steps_per_second": 2.435
+}

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:b2951705498971e78581089cb931b8623b4758fe569e3b776079b05b0cfaacf3
+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 +1,241 @@
+{
+  "best_metric": 0.9597055019401054,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-conll_2003_en/checkpoint-2000",
+  "epoch": 6.83371298405467,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.46,
+      "eval_accuracy_score": 0.9880261672053269,
+      "eval_f1": 0.9325536848472628,
+      "eval_loss": 0.05282844603061676,
+      "eval_precision": 0.9440702184119208,
+      "eval_recall": 0.9213147410358565,
+      "eval_runtime": 45.1558,
+      "eval_samples_per_second": 71.973,
+      "eval_steps_per_second": 9.013,
+      "step": 200
+    },
+    {
+      "epoch": 0.91,
+      "eval_accuracy_score": 0.9911218410498034,
+      "eval_f1": 0.9478570017776022,
+      "eval_loss": 0.03281404450535774,
+      "eval_precision": 0.9398746572659616,
+      "eval_recall": 0.9559760956175298,
+      "eval_runtime": 45.2247,
+      "eval_samples_per_second": 71.863,
+      "eval_steps_per_second": 9.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1432,
+      "step": 500
+    },
+    {
+      "epoch": 1.37,
+      "eval_accuracy_score": 0.9911607803434446,
+      "eval_f1": 0.9469395866454691,
+      "eval_loss": 0.03454526141285896,
+      "eval_precision": 0.9446867565424266,
+      "eval_recall": 0.9492031872509961,
+      "eval_runtime": 45.0931,
+      "eval_samples_per_second": 72.073,
+      "eval_steps_per_second": 9.026,
+      "step": 600
+    },
+    {
+      "epoch": 1.82,
+      "eval_accuracy_score": 0.9924457770336046,
+      "eval_f1": 0.9525887720690339,
+      "eval_loss": 0.03193691000342369,
+      "eval_precision": 0.9486369024101146,
+      "eval_recall": 0.9565737051792829,
+      "eval_runtime": 45.1422,
+      "eval_samples_per_second": 71.995,
+      "eval_steps_per_second": 9.016,
+      "step": 800
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0248,
+      "step": 1000
+    },
+    {
+      "epoch": 2.28,
+      "eval_accuracy_score": 0.9919979751567306,
+      "eval_f1": 0.9510281116519319,
+      "eval_loss": 0.03897447884082794,
+      "eval_precision": 0.9484842480681593,
+      "eval_recall": 0.9535856573705179,
+      "eval_runtime": 45.33,
+      "eval_samples_per_second": 71.696,
+      "eval_steps_per_second": 8.979,
+      "step": 1000
+    },
+    {
+      "epoch": 2.73,
+      "eval_accuracy_score": 0.9928741092636579,
+      "eval_f1": 0.955820895522388,
+      "eval_loss": 0.03231716528534889,
+      "eval_precision": 0.9548707753479125,
+      "eval_recall": 0.9567729083665338,
+      "eval_runtime": 45.1734,
+      "eval_samples_per_second": 71.945,
+      "eval_steps_per_second": 9.01,
+      "step": 1200
+    },
+    {
+      "epoch": 3.19,
+      "eval_accuracy_score": 0.9924068377399634,
+      "eval_f1": 0.9529388403494836,
+      "eval_loss": 0.03496513515710831,
+      "eval_precision": 0.9499208234362628,
+      "eval_recall": 0.9559760956175298,
+      "eval_runtime": 45.4093,
+      "eval_samples_per_second": 71.571,
+      "eval_steps_per_second": 8.963,
+      "step": 1400
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0137,
+      "step": 1500
+    },
+    {
+      "epoch": 3.64,
+      "eval_accuracy_score": 0.9919395662162689,
+      "eval_f1": 0.9535965172652617,
+      "eval_loss": 0.035889387130737305,
+      "eval_precision": 0.9473166896009436,
+      "eval_recall": 0.9599601593625497,
+      "eval_runtime": 45.1155,
+      "eval_samples_per_second": 72.037,
+      "eval_steps_per_second": 9.021,
+      "step": 1600
+    },
+    {
+      "epoch": 4.1,
+      "eval_accuracy_score": 0.9932245629064289,
+      "eval_f1": 0.9622116149562451,
+      "eval_loss": 0.03680919110774994,
+      "eval_precision": 0.9606830818109611,
+      "eval_recall": 0.9637450199203187,
+      "eval_runtime": 45.2409,
+      "eval_samples_per_second": 71.838,
+      "eval_steps_per_second": 8.996,
+      "step": 1800
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.009,
+      "step": 2000
+    },
+    {
+      "epoch": 4.56,
+      "eval_accuracy_score": 0.9931272146723259,
+      "eval_f1": 0.9597055019401054,
+      "eval_loss": 0.03970629721879959,
+      "eval_precision": 0.958656330749354,
+      "eval_recall": 0.9607569721115538,
+      "eval_runtime": 45.2082,
+      "eval_samples_per_second": 71.89,
+      "eval_steps_per_second": 9.003,
+      "step": 2000
+    },
+    {
+      "epoch": 5.01,
+      "eval_accuracy_score": 0.9928157003231961,
+      "eval_f1": 0.9558970265416085,
+      "eval_loss": 0.034936945885419846,
+      "eval_precision": 0.9576169532187125,
+      "eval_recall": 0.954183266932271,
+      "eval_runtime": 45.2011,
+      "eval_samples_per_second": 71.901,
+      "eval_steps_per_second": 9.004,
+      "step": 2200
+    },
+    {
+      "epoch": 5.47,
+      "eval_accuracy_score": 0.9927378217359137,
+      "eval_f1": 0.9555819948443386,
+      "eval_loss": 0.04039572924375534,
+      "eval_precision": 0.951243584682195,
+      "eval_recall": 0.9599601593625497,
+      "eval_runtime": 45.1221,
+      "eval_samples_per_second": 72.027,
+      "eval_steps_per_second": 9.02,
+      "step": 2400
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0068,
+      "step": 2500
+    },
+    {
+      "epoch": 5.92,
+      "eval_accuracy_score": 0.9922900198590398,
+      "eval_f1": 0.9525325903074933,
+      "eval_loss": 0.037243932485580444,
+      "eval_precision": 0.9516802545237621,
+      "eval_recall": 0.953386454183267,
+      "eval_runtime": 110.5281,
+      "eval_samples_per_second": 29.404,
+      "eval_steps_per_second": 3.682,
+      "step": 2600
+    },
+    {
+      "epoch": 6.38,
+      "eval_accuracy_score": 0.9928157003231961,
+      "eval_f1": 0.9561569959053231,
+      "eval_loss": 0.045760806649923325,
+      "eval_precision": 0.9587422391347887,
+      "eval_recall": 0.9535856573705179,
+      "eval_runtime": 45.0678,
+      "eval_samples_per_second": 72.114,
+      "eval_steps_per_second": 9.031,
+      "step": 2800
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0058,
+      "step": 3000
+    },
+    {
+      "epoch": 6.83,
+      "eval_accuracy_score": 0.9929909271445816,
+      "eval_f1": 0.957639788697299,
+      "eval_loss": 0.04067611321806908,
+      "eval_precision": 0.9583083981647716,
+      "eval_recall": 0.9569721115537848,
+      "eval_runtime": 45.0199,
+      "eval_samples_per_second": 72.19,
+      "eval_steps_per_second": 9.04,
+      "step": 3000
+    },
+    {
+      "epoch": 6.83,
+      "step": 3000,
+      "total_flos": 1.2538334439696384e+16,
+      "train_loss": 0.03388593363761902,
+      "train_runtime": 6160.4656,
+      "train_samples_per_second": 77.916,
+      "train_steps_per_second": 2.435
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 35,
+  "total_flos": 1.2538334439696384e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924c428b4891c16daa44da30e2c754b9c7c3bc73c716eb62b8f6a43567f12e4d
+size 3259