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": 77.14,
+    "eval_accuracy_score": 0.9460403110617362,
+    "eval_f1": 0.6930379746835443,
+    "eval_loss": 0.33534663915634155,
+    "eval_precision": 0.6596385542168675,
+    "eval_recall": 0.73,
+    "eval_runtime": 2.5054,
+    "eval_samples": 320,
+    "eval_samples_per_second": 127.724,
+    "eval_steps_per_second": 15.966,
+    "test_accuracy_score": 0.9443258204824041,
+    "test_f1": 0.6273120818575363,
+    "test_loss": 0.3519666790962219,
+    "test_precision": 0.5851688693098385,
+    "test_recall": 0.6759966072943172,
+    "test_runtime": 4.9494,
+    "test_samples": 638,
+    "test_samples_per_second": 128.905,
+    "test_steps_per_second": 16.164,
+    "train_loss": 0.041913371869811304,
+    "train_runtime": 4784.712,
+    "train_samples": 2235,
+    "train_samples_per_second": 100.32,
+    "train_steps_per_second": 3.135
+}

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:b849cb3de851298ea2a8193d13bae26398b6d304afaa466456fb55fdaa5df510
+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 +1,409 @@
+{
+  "best_metric": 0.6930379746835443,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-ibo/checkpoint-4000",
+  "epoch": 77.14285714285714,
+  "global_step": 5400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.86,
+      "eval_accuracy_score": 0.9000158704967466,
+      "eval_f1": 0.49961449498843485,
+      "eval_loss": 0.331222265958786,
+      "eval_precision": 0.4648493543758967,
+      "eval_recall": 0.54,
+      "eval_runtime": 2.4906,
+      "eval_samples_per_second": 128.481,
+      "eval_steps_per_second": 16.06,
+      "step": 200
+    },
+    {
+      "epoch": 5.71,
+      "eval_accuracy_score": 0.9298524043802571,
+      "eval_f1": 0.6056224899598394,
+      "eval_loss": 0.24286046624183655,
+      "eval_precision": 0.5844961240310077,
+      "eval_recall": 0.6283333333333333,
+      "eval_runtime": 2.4939,
+      "eval_samples_per_second": 128.313,
+      "eval_steps_per_second": 16.039,
+      "step": 400
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.3252,
+      "step": 500
+    },
+    {
+      "epoch": 8.57,
+      "eval_accuracy_score": 0.9366767179812728,
+      "eval_f1": 0.6445131375579597,
+      "eval_loss": 0.2310349941253662,
+      "eval_precision": 0.600864553314121,
+      "eval_recall": 0.695,
+      "eval_runtime": 2.4876,
+      "eval_samples_per_second": 128.637,
+      "eval_steps_per_second": 16.08,
+      "step": 600
+    },
+    {
+      "epoch": 11.43,
+      "eval_accuracy_score": 0.9381050626884622,
+      "eval_f1": 0.6501930501930501,
+      "eval_loss": 0.22948996722698212,
+      "eval_precision": 0.6057553956834533,
+      "eval_recall": 0.7016666666666667,
+      "eval_runtime": 2.4897,
+      "eval_samples_per_second": 128.529,
+      "eval_steps_per_second": 16.066,
+      "step": 800
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0722,
+      "step": 1000
+    },
+    {
+      "epoch": 14.29,
+      "eval_accuracy_score": 0.9406443421679098,
+      "eval_f1": 0.6508313539192399,
+      "eval_loss": 0.2520008981227875,
+      "eval_precision": 0.6199095022624435,
+      "eval_recall": 0.685,
+      "eval_runtime": 2.4823,
+      "eval_samples_per_second": 128.915,
+      "eval_steps_per_second": 16.114,
+      "step": 1000
+    },
+    {
+      "epoch": 17.14,
+      "eval_accuracy_score": 0.9444532613870814,
+      "eval_f1": 0.6714399363564041,
+      "eval_loss": 0.25240662693977356,
+      "eval_precision": 0.6423135464231354,
+      "eval_recall": 0.7033333333333334,
+      "eval_runtime": 2.482,
+      "eval_samples_per_second": 128.93,
+      "eval_steps_per_second": 16.116,
+      "step": 1200
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy_score": 0.9408030471353753,
+      "eval_f1": 0.6698039215686274,
+      "eval_loss": 0.2890109419822693,
+      "eval_precision": 0.6325925925925926,
+      "eval_recall": 0.7116666666666667,
+      "eval_runtime": 2.4863,
+      "eval_samples_per_second": 128.707,
+      "eval_steps_per_second": 16.088,
+      "step": 1400
+    },
+    {
+      "epoch": 21.43,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0227,
+      "step": 1500
+    },
+    {
+      "epoch": 22.86,
+      "eval_accuracy_score": 0.9430249166798921,
+      "eval_f1": 0.6810897435897436,
+      "eval_loss": 0.2938888967037201,
+      "eval_precision": 0.6558641975308642,
+      "eval_recall": 0.7083333333333334,
+      "eval_runtime": 2.4899,
+      "eval_samples_per_second": 128.52,
+      "eval_steps_per_second": 16.065,
+      "step": 1600
+    },
+    {
+      "epoch": 25.71,
+      "eval_accuracy_score": 0.9404856372004444,
+      "eval_f1": 0.665090622537431,
+      "eval_loss": 0.30078476667404175,
+      "eval_precision": 0.6307922272047832,
+      "eval_recall": 0.7033333333333334,
+      "eval_runtime": 2.4945,
+      "eval_samples_per_second": 128.281,
+      "eval_steps_per_second": 16.035,
+      "step": 1800
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0104,
+      "step": 2000
+    },
+    {
+      "epoch": 28.57,
+      "eval_accuracy_score": 0.9468338358990637,
+      "eval_f1": 0.6836813611755608,
+      "eval_loss": 0.2752661406993866,
+      "eval_precision": 0.6378066378066378,
+      "eval_recall": 0.7366666666666667,
+      "eval_runtime": 2.6818,
+      "eval_samples_per_second": 119.321,
+      "eval_steps_per_second": 14.915,
+      "step": 2000
+    },
+    {
+      "epoch": 31.43,
+      "eval_accuracy_score": 0.9441358514521504,
+      "eval_f1": 0.6817813765182186,
+      "eval_loss": 0.32004353404045105,
+      "eval_precision": 0.662992125984252,
+      "eval_recall": 0.7016666666666667,
+      "eval_runtime": 2.487,
+      "eval_samples_per_second": 128.671,
+      "eval_steps_per_second": 16.084,
+      "step": 2200
+    },
+    {
+      "epoch": 34.29,
+      "eval_accuracy_score": 0.9444532613870814,
+      "eval_f1": 0.6868525896414344,
+      "eval_loss": 0.32289382815361023,
+      "eval_precision": 0.6580152671755726,
+      "eval_recall": 0.7183333333333334,
+      "eval_runtime": 2.4893,
+      "eval_samples_per_second": 128.549,
+      "eval_steps_per_second": 16.069,
+      "step": 2400
+    },
+    {
+      "epoch": 35.71,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0065,
+      "step": 2500
+    },
+    {
+      "epoch": 37.14,
+      "eval_accuracy_score": 0.9444532613870814,
+      "eval_f1": 0.6874003189792663,
+      "eval_loss": 0.324036180973053,
+      "eval_precision": 0.6590214067278287,
+      "eval_recall": 0.7183333333333334,
+      "eval_runtime": 2.4838,
+      "eval_samples_per_second": 128.837,
+      "eval_steps_per_second": 16.105,
+      "step": 2600
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy_score": 0.9427075067449611,
+      "eval_f1": 0.669848846459825,
+      "eval_loss": 0.3424355089664459,
+      "eval_precision": 0.6407914764079148,
+      "eval_recall": 0.7016666666666667,
+      "eval_runtime": 2.489,
+      "eval_samples_per_second": 128.566,
+      "eval_steps_per_second": 16.071,
+      "step": 2800
+    },
+    {
+      "epoch": 42.86,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0042,
+      "step": 3000
+    },
+    {
+      "epoch": 42.86,
+      "eval_accuracy_score": 0.9442945564196159,
+      "eval_f1": 0.6758064516129032,
+      "eval_loss": 0.33911556005477905,
+      "eval_precision": 0.6546875,
+      "eval_recall": 0.6983333333333334,
+      "eval_runtime": 2.478,
+      "eval_samples_per_second": 129.136,
+      "eval_steps_per_second": 16.142,
+      "step": 3000
+    },
+    {
+      "epoch": 45.71,
+      "eval_accuracy_score": 0.9457229011268052,
+      "eval_f1": 0.6880877742946709,
+      "eval_loss": 0.3264969289302826,
+      "eval_precision": 0.6494082840236687,
+      "eval_recall": 0.7316666666666667,
+      "eval_runtime": 2.4815,
+      "eval_samples_per_second": 128.956,
+      "eval_steps_per_second": 16.119,
+      "step": 3200
+    },
+    {
+      "epoch": 48.57,
+      "eval_accuracy_score": 0.9422313918425647,
+      "eval_f1": 0.6761904761904762,
+      "eval_loss": 0.35728639364242554,
+      "eval_precision": 0.6454545454545455,
+      "eval_recall": 0.71,
+      "eval_runtime": 2.4775,
+      "eval_samples_per_second": 129.162,
+      "eval_steps_per_second": 16.145,
+      "step": 3400
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0033,
+      "step": 3500
+    },
+    {
+      "epoch": 51.43,
+      "eval_accuracy_score": 0.9441358514521504,
+      "eval_f1": 0.6907051282051282,
+      "eval_loss": 0.35023757815361023,
+      "eval_precision": 0.6651234567901234,
+      "eval_recall": 0.7183333333333334,
+      "eval_runtime": 2.477,
+      "eval_samples_per_second": 129.186,
+      "eval_steps_per_second": 16.148,
+      "step": 3600
+    },
+    {
+      "epoch": 54.29,
+      "eval_accuracy_score": 0.943977146484685,
+      "eval_f1": 0.6825775656324582,
+      "eval_loss": 0.3428173363208771,
+      "eval_precision": 0.6529680365296804,
+      "eval_recall": 0.715,
+      "eval_runtime": 2.4863,
+      "eval_samples_per_second": 128.705,
+      "eval_steps_per_second": 16.088,
+      "step": 3800
+    },
+    {
+      "epoch": 57.14,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0024,
+      "step": 4000
+    },
+    {
+      "epoch": 57.14,
+      "eval_accuracy_score": 0.9460403110617362,
+      "eval_f1": 0.6930379746835443,
+      "eval_loss": 0.33534663915634155,
+      "eval_precision": 0.6596385542168675,
+      "eval_recall": 0.73,
+      "eval_runtime": 2.4857,
+      "eval_samples_per_second": 128.737,
+      "eval_steps_per_second": 16.092,
+      "step": 4000
+    },
+    {
+      "epoch": 60.0,
+      "eval_accuracy_score": 0.943659736549754,
+      "eval_f1": 0.6714285714285714,
+      "eval_loss": 0.3531126081943512,
+      "eval_precision": 0.6409090909090909,
+      "eval_recall": 0.705,
+      "eval_runtime": 2.4736,
+      "eval_samples_per_second": 129.364,
+      "eval_steps_per_second": 16.171,
+      "step": 4200
+    },
+    {
+      "epoch": 62.86,
+      "eval_accuracy_score": 0.9458816060942707,
+      "eval_f1": 0.695582329317269,
+      "eval_loss": 0.36536940932273865,
+      "eval_precision": 0.6713178294573643,
+      "eval_recall": 0.7216666666666667,
+      "eval_runtime": 2.4795,
+      "eval_samples_per_second": 129.059,
+      "eval_steps_per_second": 16.132,
+      "step": 4400
+    },
+    {
+      "epoch": 64.29,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0024,
+      "step": 4500
+    },
+    {
+      "epoch": 65.71,
+      "eval_accuracy_score": 0.9435010315822885,
+      "eval_f1": 0.6821457165732587,
+      "eval_loss": 0.3702266812324524,
+      "eval_precision": 0.6563944530046225,
+      "eval_recall": 0.71,
+      "eval_runtime": 2.4782,
+      "eval_samples_per_second": 129.126,
+      "eval_steps_per_second": 16.141,
+      "step": 4600
+    },
+    {
+      "epoch": 68.57,
+      "eval_accuracy_score": 0.9425488017774957,
+      "eval_f1": 0.6838709677419355,
+      "eval_loss": 0.3876664936542511,
+      "eval_precision": 0.6625,
+      "eval_recall": 0.7066666666666667,
+      "eval_runtime": 2.4834,
+      "eval_samples_per_second": 128.858,
+      "eval_steps_per_second": 16.107,
+      "step": 4800
+    },
+    {
+      "epoch": 71.43,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0019,
+      "step": 5000
+    },
+    {
+      "epoch": 71.43,
+      "eval_accuracy_score": 0.9441358514521504,
+      "eval_f1": 0.6751188589540411,
+      "eval_loss": 0.35965150594711304,
+      "eval_precision": 0.6435045317220544,
+      "eval_recall": 0.71,
+      "eval_runtime": 2.4894,
+      "eval_samples_per_second": 128.547,
+      "eval_steps_per_second": 16.068,
+      "step": 5000
+    },
+    {
+      "epoch": 74.29,
+      "eval_accuracy_score": 0.9422313918425647,
+      "eval_f1": 0.6736334405144694,
+      "eval_loss": 0.4093686044216156,
+      "eval_precision": 0.6506211180124224,
+      "eval_recall": 0.6983333333333334,
+      "eval_runtime": 2.495,
+      "eval_samples_per_second": 128.258,
+      "eval_steps_per_second": 16.032,
+      "step": 5200
+    },
+    {
+      "epoch": 77.14,
+      "eval_accuracy_score": 0.9423900968100302,
+      "eval_f1": 0.675098814229249,
+      "eval_loss": 0.3733450174331665,
+      "eval_precision": 0.6421052631578947,
+      "eval_recall": 0.7116666666666667,
+      "eval_runtime": 2.4781,
+      "eval_samples_per_second": 129.13,
+      "eval_steps_per_second": 16.141,
+      "step": 5400
+    },
+    {
+      "epoch": 77.14,
+      "step": 5400,
+      "total_flos": 2.831337967640832e+16,
+      "train_loss": 0.041913371869811304,
+      "train_runtime": 4784.712,
+      "train_samples_per_second": 100.32,
+      "train_steps_per_second": 3.135
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 215,
+  "total_flos": 2.831337967640832e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145306e3fff8633ca66e522ba2f6f995f0c7edcfa01ee47a790edf7ea10671a6
+size 3259