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": 111.11,
+    "eval_accuracy_score": 0.9452127659574469,
+    "eval_f1": 0.6384976525821597,
+    "eval_loss": 0.4099084436893463,
+    "eval_precision": 0.5811965811965812,
+    "eval_recall": 0.7083333333333334,
+    "eval_runtime": 1.5713,
+    "eval_samples": 200,
+    "eval_samples_per_second": 127.284,
+    "eval_steps_per_second": 15.91,
+    "test_accuracy_score": 0.9453369497183393,
+    "test_f1": 0.6607538802660754,
+    "test_loss": 0.41320958733558655,
+    "test_precision": 0.6201873048907388,
+    "test_recall": 0.7069988137603797,
+    "test_runtime": 3.1549,
+    "test_samples": 407,
+    "test_samples_per_second": 129.006,
+    "test_steps_per_second": 16.165,
+    "train_loss": 0.03932533206939697,
+    "train_runtime": 4566.7466,
+    "train_samples": 1428,
+    "train_samples_per_second": 105.108,
+    "train_steps_per_second": 3.285
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "google/canine-c",
+  "architectures": [
+    "CanineForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 57344,
+  "downsampling_rate": 4,
+  "eos_token_id": 57345,
+  "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,
+  "local_transformer_stride": 128,
+  "max_position_embeddings": 16384,
+  "model_type": "canine",
+  "num_attention_heads": 12,
+  "num_hash_buckets": 16384,
+  "num_hash_functions": 8,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 16,
+  "upsampling_kernel_size": 4,
+  "use_cache": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124cce149f2f67f2dd402ff7a4ea21ab2ed466d264629e122a966ed3dfda7372
+size 528594737

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": "/home/mrahma45/.cache/huggingface/transformers/f8be97736b4765e3e8d559b4e7d4f1f531b1621150e5344b600684a27bc84e38.ab71f530366fe02e2834427e7b90198bfd0d573bc4279bfafdb2b95fe2b46dde", "name_or_path": "google/canine-c", "tokenizer_class": "CanineTokenizer"}

trainer_state.json

@@ -0,0 +1,385 @@
+{
+  "best_metric": 0.6384976525821597,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-lug/checkpoint-4000",
+  "epoch": 111.11111111111111,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.44,
+      "eval_accuracy_score": 0.9188829787234043,
+      "eval_f1": 0.4549483013293944,
+      "eval_loss": 0.28194382786750793,
+      "eval_precision": 0.39588688946015427,
+      "eval_recall": 0.5347222222222222,
+      "eval_runtime": 1.5521,
+      "eval_samples_per_second": 128.858,
+      "eval_steps_per_second": 16.107,
+      "step": 200
+    },
+    {
+      "epoch": 8.89,
+      "eval_accuracy_score": 0.9319148936170213,
+      "eval_f1": 0.5022692889561271,
+      "eval_loss": 0.23164795339107513,
+      "eval_precision": 0.4450402144772118,
+      "eval_recall": 0.5763888888888888,
+      "eval_runtime": 1.5532,
+      "eval_samples_per_second": 128.769,
+      "eval_steps_per_second": 16.096,
+      "step": 400
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.3392,
+      "step": 500
+    },
+    {
+      "epoch": 13.33,
+      "eval_accuracy_score": 0.9404255319148936,
+      "eval_f1": 0.5803432137285492,
+      "eval_loss": 0.24918590486049652,
+      "eval_precision": 0.5269121813031161,
+      "eval_recall": 0.6458333333333334,
+      "eval_runtime": 1.554,
+      "eval_samples_per_second": 128.702,
+      "eval_steps_per_second": 16.088,
+      "step": 600
+    },
+    {
+      "epoch": 17.78,
+      "eval_accuracy_score": 0.9393617021276596,
+      "eval_f1": 0.5824345146379044,
+      "eval_loss": 0.2939892113208771,
+      "eval_precision": 0.5235457063711911,
+      "eval_recall": 0.65625,
+      "eval_runtime": 1.5535,
+      "eval_samples_per_second": 128.742,
+      "eval_steps_per_second": 16.093,
+      "step": 800
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0281,
+      "step": 1000
+    },
+    {
+      "epoch": 22.22,
+      "eval_accuracy_score": 0.938031914893617,
+      "eval_f1": 0.5736196319018405,
+      "eval_loss": 0.3271344006061554,
+      "eval_precision": 0.5137362637362637,
+      "eval_recall": 0.6493055555555556,
+      "eval_runtime": 1.5497,
+      "eval_samples_per_second": 129.061,
+      "eval_steps_per_second": 16.133,
+      "step": 1000
+    },
+    {
+      "epoch": 26.67,
+      "eval_accuracy_score": 0.9428191489361702,
+      "eval_f1": 0.6137071651090343,
+      "eval_loss": 0.33916962146759033,
+      "eval_precision": 0.556497175141243,
+      "eval_recall": 0.6840277777777778,
+      "eval_runtime": 1.5523,
+      "eval_samples_per_second": 128.842,
+      "eval_steps_per_second": 16.105,
+      "step": 1200
+    },
+    {
+      "epoch": 31.11,
+      "eval_accuracy_score": 0.9417553191489362,
+      "eval_f1": 0.6140089418777943,
+      "eval_loss": 0.35398396849632263,
+      "eval_precision": 0.5378590078328982,
+      "eval_recall": 0.7152777777777778,
+      "eval_runtime": 1.5487,
+      "eval_samples_per_second": 129.144,
+      "eval_steps_per_second": 16.143,
+      "step": 1400
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0079,
+      "step": 1500
+    },
+    {
+      "epoch": 35.56,
+      "eval_accuracy_score": 0.936968085106383,
+      "eval_f1": 0.5443425076452598,
+      "eval_loss": 0.3693486750125885,
+      "eval_precision": 0.48633879781420764,
+      "eval_recall": 0.6180555555555556,
+      "eval_runtime": 1.5536,
+      "eval_samples_per_second": 128.737,
+      "eval_steps_per_second": 16.092,
+      "step": 1600
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy_score": 0.9388297872340425,
+      "eval_f1": 0.5816485225505443,
+      "eval_loss": 0.37097564339637756,
+      "eval_precision": 0.5267605633802817,
+      "eval_recall": 0.6493055555555556,
+      "eval_runtime": 1.5551,
+      "eval_samples_per_second": 128.607,
+      "eval_steps_per_second": 16.076,
+      "step": 1800
+    },
+    {
+      "epoch": 44.44,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0044,
+      "step": 2000
+    },
+    {
+      "epoch": 44.44,
+      "eval_accuracy_score": 0.9438829787234042,
+      "eval_f1": 0.6108527131782945,
+      "eval_loss": 0.3714268207550049,
+      "eval_precision": 0.5518207282913166,
+      "eval_recall": 0.6840277777777778,
+      "eval_runtime": 1.5499,
+      "eval_samples_per_second": 129.039,
+      "eval_steps_per_second": 16.13,
+      "step": 2000
+    },
+    {
+      "epoch": 48.89,
+      "eval_accuracy_score": 0.9417553191489362,
+      "eval_f1": 0.5919003115264797,
+      "eval_loss": 0.39195337891578674,
+      "eval_precision": 0.536723163841808,
+      "eval_recall": 0.6597222222222222,
+      "eval_runtime": 1.5549,
+      "eval_samples_per_second": 128.623,
+      "eval_steps_per_second": 16.078,
+      "step": 2200
+    },
+    {
+      "epoch": 53.33,
+      "eval_accuracy_score": 0.9430851063829787,
+      "eval_f1": 0.6217457886676876,
+      "eval_loss": 0.3815304636955261,
+      "eval_precision": 0.5561643835616439,
+      "eval_recall": 0.7048611111111112,
+      "eval_runtime": 1.5558,
+      "eval_samples_per_second": 128.549,
+      "eval_steps_per_second": 16.069,
+      "step": 2400
+    },
+    {
+      "epoch": 55.56,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0035,
+      "step": 2500
+    },
+    {
+      "epoch": 57.78,
+      "eval_accuracy_score": 0.9409574468085107,
+      "eval_f1": 0.6037151702786376,
+      "eval_loss": 0.393964946269989,
+      "eval_precision": 0.5446927374301676,
+      "eval_recall": 0.6770833333333334,
+      "eval_runtime": 1.5537,
+      "eval_samples_per_second": 128.722,
+      "eval_steps_per_second": 16.09,
+      "step": 2600
+    },
+    {
+      "epoch": 62.22,
+      "eval_accuracy_score": 0.9438829787234042,
+      "eval_f1": 0.6151419558359622,
+      "eval_loss": 0.40122151374816895,
+      "eval_precision": 0.5635838150289018,
+      "eval_recall": 0.6770833333333334,
+      "eval_runtime": 1.554,
+      "eval_samples_per_second": 128.699,
+      "eval_steps_per_second": 16.087,
+      "step": 2800
+    },
+    {
+      "epoch": 66.67,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0027,
+      "step": 3000
+    },
+    {
+      "epoch": 66.67,
+      "eval_accuracy_score": 0.9457446808510638,
+      "eval_f1": 0.6283048211508553,
+      "eval_loss": 0.38126349449157715,
+      "eval_precision": 0.5690140845070423,
+      "eval_recall": 0.7013888888888888,
+      "eval_runtime": 1.5565,
+      "eval_samples_per_second": 128.492,
+      "eval_steps_per_second": 16.062,
+      "step": 3000
+    },
+    {
+      "epoch": 71.11,
+      "eval_accuracy_score": 0.9468085106382979,
+      "eval_f1": 0.6286594761171033,
+      "eval_loss": 0.3913482427597046,
+      "eval_precision": 0.5650969529085873,
+      "eval_recall": 0.7083333333333334,
+      "eval_runtime": 1.5517,
+      "eval_samples_per_second": 128.887,
+      "eval_steps_per_second": 16.111,
+      "step": 3200
+    },
+    {
+      "epoch": 75.56,
+      "eval_accuracy_score": 0.9441489361702128,
+      "eval_f1": 0.6101694915254237,
+      "eval_loss": 0.3978583514690399,
+      "eval_precision": 0.5484764542936288,
+      "eval_recall": 0.6875,
+      "eval_runtime": 1.5532,
+      "eval_samples_per_second": 128.765,
+      "eval_steps_per_second": 16.096,
+      "step": 3400
+    },
+    {
+      "epoch": 77.78,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.002,
+      "step": 3500
+    },
+    {
+      "epoch": 80.0,
+      "eval_accuracy_score": 0.9438829787234042,
+      "eval_f1": 0.6124999999999999,
+      "eval_loss": 0.4034854769706726,
+      "eval_precision": 0.5568181818181818,
+      "eval_recall": 0.6805555555555556,
+      "eval_runtime": 1.5526,
+      "eval_samples_per_second": 128.817,
+      "eval_steps_per_second": 16.102,
+      "step": 3600
+    },
+    {
+      "epoch": 84.44,
+      "eval_accuracy_score": 0.9406914893617021,
+      "eval_f1": 0.5878693623639192,
+      "eval_loss": 0.4116753339767456,
+      "eval_precision": 0.532394366197183,
+      "eval_recall": 0.65625,
+      "eval_runtime": 1.553,
+      "eval_samples_per_second": 128.782,
+      "eval_steps_per_second": 16.098,
+      "step": 3800
+    },
+    {
+      "epoch": 88.89,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0019,
+      "step": 4000
+    },
+    {
+      "epoch": 88.89,
+      "eval_accuracy_score": 0.9452127659574469,
+      "eval_f1": 0.6384976525821597,
+      "eval_loss": 0.4099084436893463,
+      "eval_precision": 0.5811965811965812,
+      "eval_recall": 0.7083333333333334,
+      "eval_runtime": 1.5503,
+      "eval_samples_per_second": 129.007,
+      "eval_steps_per_second": 16.126,
+      "step": 4000
+    },
+    {
+      "epoch": 93.33,
+      "eval_accuracy_score": 0.9430851063829787,
+      "eval_f1": 0.6128048780487805,
+      "eval_loss": 0.40775445103645325,
+      "eval_precision": 0.5461956521739131,
+      "eval_recall": 0.6979166666666666,
+      "eval_runtime": 1.5487,
+      "eval_samples_per_second": 129.145,
+      "eval_steps_per_second": 16.143,
+      "step": 4200
+    },
+    {
+      "epoch": 97.78,
+      "eval_accuracy_score": 0.9382978723404255,
+      "eval_f1": 0.5794392523364487,
+      "eval_loss": 0.4453897178173065,
+      "eval_precision": 0.5254237288135594,
+      "eval_recall": 0.6458333333333334,
+      "eval_runtime": 1.5505,
+      "eval_samples_per_second": 128.991,
+      "eval_steps_per_second": 16.124,
+      "step": 4400
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0019,
+      "step": 4500
+    },
+    {
+      "epoch": 102.22,
+      "eval_accuracy_score": 0.9382978723404255,
+      "eval_f1": 0.5775075987841946,
+      "eval_loss": 0.4396846294403076,
+      "eval_precision": 0.5135135135135135,
+      "eval_recall": 0.6597222222222222,
+      "eval_runtime": 1.5553,
+      "eval_samples_per_second": 128.593,
+      "eval_steps_per_second": 16.074,
+      "step": 4600
+    },
+    {
+      "epoch": 106.67,
+      "eval_accuracy_score": 0.9414893617021277,
+      "eval_f1": 0.5940902021772939,
+      "eval_loss": 0.4597267806529999,
+      "eval_precision": 0.5380281690140845,
+      "eval_recall": 0.6631944444444444,
+      "eval_runtime": 1.5543,
+      "eval_samples_per_second": 128.675,
+      "eval_steps_per_second": 16.084,
+      "step": 4800
+    },
+    {
+      "epoch": 111.11,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0015,
+      "step": 5000
+    },
+    {
+      "epoch": 111.11,
+      "eval_accuracy_score": 0.9412234042553191,
+      "eval_f1": 0.6172465960665658,
+      "eval_loss": 0.45369622111320496,
+      "eval_precision": 0.546916890080429,
+      "eval_recall": 0.7083333333333334,
+      "eval_runtime": 1.5477,
+      "eval_samples_per_second": 129.225,
+      "eval_steps_per_second": 16.153,
+      "step": 5000
+    },
+    {
+      "epoch": 111.11,
+      "step": 5000,
+      "total_flos": 2.6055896102406144e+16,
+      "train_loss": 0.03932533206939697,
+      "train_runtime": 4566.7466,
+      "train_samples_per_second": 105.108,
+      "train_steps_per_second": 3.285
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 334,
+  "total_flos": 2.6055896102406144e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366d990cbb7528c5986d2bd7b72f79498179c65e2749ee5e7a2a9b4eee83c4f0
+size 3259