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": 38.81,
+    "eval_accuracy_score": 0.9640888094173745,
+    "eval_f1": 0.8271405492730209,
+    "eval_loss": 0.20800545811653137,
+    "eval_precision": 0.8258064516129032,
+    "eval_recall": 0.8284789644012945,
+    "eval_runtime": 4.1985,
+    "eval_samples": 302,
+    "eval_samples_per_second": 71.931,
+    "eval_steps_per_second": 9.051,
+    "test_accuracy_score": 0.9515356438433361,
+    "test_f1": 0.7057644110275689,
+    "test_loss": 0.284976989030838,
+    "test_precision": 0.685491723466407,
+    "test_recall": 0.7272727272727273,
+    "test_runtime": 8.4313,
+    "test_samples": 605,
+    "test_samples_per_second": 71.756,
+    "test_steps_per_second": 9.014,
+    "train_loss": 0.0309662873011369,
+    "train_runtime": 2918.4318,
+    "train_samples": 2116,
+    "train_samples_per_second": 164.472,
+    "train_steps_per_second": 5.14
+}

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 sha256:60a47a21d6eb17a25743da46b864eb59100bfbd940c57f8c8a9ba6471d5ed878
+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 +1,211 @@
+{
+  "best_metric": 0.8271405492730209,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-kin/checkpoint-1000",
+  "epoch": 38.80597014925373,
+  "global_step": 2600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.99,
+      "eval_accuracy_score": 0.9552972731336612,
+      "eval_f1": 0.8061538461538461,
+      "eval_loss": 0.14030461013317108,
+      "eval_precision": 0.7683284457478006,
+      "eval_recall": 0.8478964401294499,
+      "eval_runtime": 4.2191,
+      "eval_samples_per_second": 71.58,
+      "eval_steps_per_second": 9.007,
+      "step": 200
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy_score": 0.9608106094471762,
+      "eval_f1": 0.8109375,
+      "eval_loss": 0.17163802683353424,
+      "eval_precision": 0.783987915407855,
+      "eval_recall": 0.8398058252427184,
+      "eval_runtime": 4.2278,
+      "eval_samples_per_second": 71.432,
+      "eval_steps_per_second": 8.988,
+      "step": 400
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1428,
+      "step": 500
+    },
+    {
+      "epoch": 8.96,
+      "eval_accuracy_score": 0.9573834003874236,
+      "eval_f1": 0.7830940988835726,
+      "eval_loss": 0.2280413955450058,
+      "eval_precision": 0.7720125786163522,
+      "eval_recall": 0.7944983818770227,
+      "eval_runtime": 4.2189,
+      "eval_samples_per_second": 71.582,
+      "eval_steps_per_second": 9.007,
+      "step": 600
+    },
+    {
+      "epoch": 11.94,
+      "eval_accuracy_score": 0.9605125912680673,
+      "eval_f1": 0.8210862619808306,
+      "eval_loss": 0.22001390159130096,
+      "eval_precision": 0.8107255520504731,
+      "eval_recall": 0.8317152103559871,
+      "eval_runtime": 4.2196,
+      "eval_samples_per_second": 71.571,
+      "eval_steps_per_second": 9.006,
+      "step": 800
+    },
+    {
+      "epoch": 14.93,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0075,
+      "step": 1000
+    },
+    {
+      "epoch": 14.93,
+      "eval_accuracy_score": 0.9640888094173745,
+      "eval_f1": 0.8271405492730209,
+      "eval_loss": 0.20800545811653137,
+      "eval_precision": 0.8258064516129032,
+      "eval_recall": 0.8284789644012945,
+      "eval_runtime": 4.2152,
+      "eval_samples_per_second": 71.645,
+      "eval_steps_per_second": 9.015,
+      "step": 1000
+    },
+    {
+      "epoch": 17.91,
+      "eval_accuracy_score": 0.9643868275964834,
+      "eval_f1": 0.8350764279967821,
+      "eval_loss": 0.2207585573196411,
+      "eval_precision": 0.8304,
+      "eval_recall": 0.8398058252427184,
+      "eval_runtime": 4.214,
+      "eval_samples_per_second": 71.666,
+      "eval_steps_per_second": 9.018,
+      "step": 1200
+    },
+    {
+      "epoch": 20.9,
+      "eval_accuracy_score": 0.9567873640292058,
+      "eval_f1": 0.8034455755677369,
+      "eval_loss": 0.24622981250286102,
+      "eval_precision": 0.7784522003034902,
+      "eval_recall": 0.8300970873786407,
+      "eval_runtime": 4.2176,
+      "eval_samples_per_second": 71.605,
+      "eval_steps_per_second": 9.01,
+      "step": 1400
+    },
+    {
+      "epoch": 22.39,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.004,
+      "step": 1500
+    },
+    {
+      "epoch": 23.88,
+      "eval_accuracy_score": 0.9658769184920281,
+      "eval_f1": 0.8436763550667713,
+      "eval_loss": 0.22536174952983856,
+      "eval_precision": 0.8198473282442749,
+      "eval_recall": 0.8689320388349514,
+      "eval_runtime": 4.214,
+      "eval_samples_per_second": 71.666,
+      "eval_steps_per_second": 9.018,
+      "step": 1600
+    },
+    {
+      "epoch": 26.87,
+      "eval_accuracy_score": 0.9646848457755923,
+      "eval_f1": 0.8192,
+      "eval_loss": 0.20931068062782288,
+      "eval_precision": 0.810126582278481,
+      "eval_recall": 0.8284789644012945,
+      "eval_runtime": 4.2136,
+      "eval_samples_per_second": 71.672,
+      "eval_steps_per_second": 9.018,
+      "step": 1800
+    },
+    {
+      "epoch": 29.85,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0028,
+      "step": 2000
+    },
+    {
+      "epoch": 29.85,
+      "eval_accuracy_score": 0.9623007003427209,
+      "eval_f1": 0.822774659182037,
+      "eval_loss": 0.24018673598766327,
+      "eval_precision": 0.8155802861685215,
+      "eval_recall": 0.8300970873786407,
+      "eval_runtime": 4.2137,
+      "eval_samples_per_second": 71.671,
+      "eval_steps_per_second": 9.018,
+      "step": 2000
+    },
+    {
+      "epoch": 32.84,
+      "eval_accuracy_score": 0.9564893458500968,
+      "eval_f1": 0.8009630818619582,
+      "eval_loss": 0.26548677682876587,
+      "eval_precision": 0.7945859872611465,
+      "eval_recall": 0.8074433656957929,
+      "eval_runtime": 4.2161,
+      "eval_samples_per_second": 71.63,
+      "eval_steps_per_second": 9.013,
+      "step": 2200
+    },
+    {
+      "epoch": 35.82,
+      "eval_accuracy_score": 0.958128445835196,
+      "eval_f1": 0.8034727703235991,
+      "eval_loss": 0.2520817518234253,
+      "eval_precision": 0.7842835130970724,
+      "eval_recall": 0.8236245954692557,
+      "eval_runtime": 4.2073,
+      "eval_samples_per_second": 71.78,
+      "eval_steps_per_second": 9.032,
+      "step": 2400
+    },
+    {
+      "epoch": 37.31,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0033,
+      "step": 2500
+    },
+    {
+      "epoch": 38.81,
+      "eval_accuracy_score": 0.9637907912382655,
+      "eval_f1": 0.8270313757039421,
+      "eval_loss": 0.2613898515701294,
+      "eval_precision": 0.8224,
+      "eval_recall": 0.8317152103559871,
+      "eval_runtime": 4.201,
+      "eval_samples_per_second": 71.887,
+      "eval_steps_per_second": 9.045,
+      "step": 2600
+    },
+    {
+      "epoch": 38.81,
+      "step": 2600,
+      "total_flos": 1.0731614329737216e+16,
+      "train_loss": 0.0309662873011369,
+      "train_runtime": 2918.4318,
+      "train_samples_per_second": 164.472,
+      "train_steps_per_second": 5.14
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 224,
+  "total_flos": 1.0731614329737216e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae552f85b02ab08b3de371826d5954ae1689120a214df11380b1c4bd3598737
+size 3259