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": 29.85,
+    "eval_accuracy_score": 0.9155309270630523,
+    "eval_f1": 0.5339233038348082,
+    "eval_loss": 0.3548363149166107,
+    "eval_precision": 0.489851150202977,
+    "eval_recall": 0.586709886547812,
+    "eval_runtime": 2.3816,
+    "eval_samples": 302,
+    "eval_samples_per_second": 126.805,
+    "eval_steps_per_second": 15.956,
+    "test_accuracy_score": 0.9315360056757716,
+    "test_f1": 0.5307237141556668,
+    "test_loss": 0.32899531722068787,
+    "test_precision": 0.4732142857142857,
+    "test_recall": 0.6041450777202072,
+    "test_runtime": 4.7209,
+    "test_samples": 605,
+    "test_samples_per_second": 128.153,
+    "test_steps_per_second": 16.099,
+    "train_loss": 0.10185246992111206,
+    "train_runtime": 987.1722,
+    "train_samples": 2116,
+    "train_samples_per_second": 486.237,
+    "train_steps_per_second": 15.195
+}

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:cd72fedd36bd63193f9d192bb0f30ca5e6bb37351acddf89be128237799902df
+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 +1,169 @@
+{
+  "best_metric": 0.5339233038348082,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-kin/checkpoint-1000",
+  "epoch": 29.850746268656717,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.99,
+      "eval_accuracy_score": 0.8626628725475513,
+      "eval_f1": 0.2977635782747604,
+      "eval_loss": 0.40653204917907715,
+      "eval_precision": 0.24578059071729957,
+      "eval_recall": 0.37763371150729336,
+      "eval_runtime": 2.3533,
+      "eval_samples_per_second": 128.333,
+      "eval_steps_per_second": 16.148,
+      "step": 200
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy_score": 0.8854275872397783,
+      "eval_f1": 0.3580729166666667,
+      "eval_loss": 0.36062297224998474,
+      "eval_precision": 0.2992383025027203,
+      "eval_recall": 0.44570502431118314,
+      "eval_runtime": 2.3498,
+      "eval_samples_per_second": 128.522,
+      "eval_steps_per_second": 16.172,
+      "step": 400
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.3324,
+      "step": 500
+    },
+    {
+      "epoch": 8.96,
+      "eval_accuracy_score": 0.902201587539314,
+      "eval_f1": 0.4444444444444445,
+      "eval_loss": 0.3250875771045685,
+      "eval_precision": 0.40052015604681407,
+      "eval_recall": 0.4991896272285251,
+      "eval_runtime": 2.3578,
+      "eval_samples_per_second": 128.086,
+      "eval_steps_per_second": 16.117,
+      "step": 600
+    },
+    {
+      "epoch": 11.94,
+      "eval_accuracy_score": 0.9062453197543807,
+      "eval_f1": 0.44697508896797156,
+      "eval_loss": 0.35800644755363464,
+      "eval_precision": 0.39847715736040606,
+      "eval_recall": 0.5089141004862237,
+      "eval_runtime": 2.3569,
+      "eval_samples_per_second": 128.132,
+      "eval_steps_per_second": 16.123,
+      "step": 800
+    },
+    {
+      "epoch": 14.93,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0559,
+      "step": 1000
+    },
+    {
+      "epoch": 14.93,
+      "eval_accuracy_score": 0.9155309270630523,
+      "eval_f1": 0.5339233038348082,
+      "eval_loss": 0.3548363149166107,
+      "eval_precision": 0.489851150202977,
+      "eval_recall": 0.586709886547812,
+      "eval_runtime": 2.3472,
+      "eval_samples_per_second": 128.664,
+      "eval_steps_per_second": 16.19,
+      "step": 1000
+    },
+    {
+      "epoch": 17.91,
+      "eval_accuracy_score": 0.9156806949228695,
+      "eval_f1": 0.5113221329437545,
+      "eval_loss": 0.39484161138534546,
+      "eval_precision": 0.4654255319148936,
+      "eval_recall": 0.5672609400324149,
+      "eval_runtime": 2.3511,
+      "eval_samples_per_second": 128.453,
+      "eval_steps_per_second": 16.163,
+      "step": 1200
+    },
+    {
+      "epoch": 20.9,
+      "eval_accuracy_score": 0.9123858020068893,
+      "eval_f1": 0.4756446991404012,
+      "eval_loss": 0.4212295711040497,
+      "eval_precision": 0.42618741976893454,
+      "eval_recall": 0.5380875202593193,
+      "eval_runtime": 2.351,
+      "eval_samples_per_second": 128.457,
+      "eval_steps_per_second": 16.163,
+      "step": 1400
+    },
+    {
+      "epoch": 22.39,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0133,
+      "step": 1500
+    },
+    {
+      "epoch": 23.88,
+      "eval_accuracy_score": 0.9149318556237831,
+      "eval_f1": 0.5033308660251665,
+      "eval_loss": 0.42608439922332764,
+      "eval_precision": 0.46321525885558584,
+      "eval_recall": 0.5510534846029174,
+      "eval_runtime": 2.3525,
+      "eval_samples_per_second": 128.373,
+      "eval_steps_per_second": 16.153,
+      "step": 1600
+    },
+    {
+      "epoch": 26.87,
+      "eval_accuracy_score": 0.9161299985023214,
+      "eval_f1": 0.53003003003003,
+      "eval_loss": 0.4479231536388397,
+      "eval_precision": 0.4937062937062937,
+      "eval_recall": 0.5721231766612642,
+      "eval_runtime": 2.3519,
+      "eval_samples_per_second": 128.409,
+      "eval_steps_per_second": 16.157,
+      "step": 1800
+    },
+    {
+      "epoch": 29.85,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0058,
+      "step": 2000
+    },
+    {
+      "epoch": 29.85,
+      "eval_accuracy_score": 0.918076980679946,
+      "eval_f1": 0.5291887793783169,
+      "eval_loss": 0.4661569595336914,
+      "eval_precision": 0.49715099715099714,
+      "eval_recall": 0.5656401944894651,
+      "eval_runtime": 2.349,
+      "eval_samples_per_second": 128.566,
+      "eval_steps_per_second": 16.177,
+      "step": 2000
+    },
+    {
+      "epoch": 29.85,
+      "step": 2000,
+      "total_flos": 1.0376509207394304e+16,
+      "train_loss": 0.10185246992111206,
+      "train_runtime": 987.1722,
+      "train_samples_per_second": 486.237,
+      "train_steps_per_second": 15.195
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 224,
+  "total_flos": 1.0376509207394304e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424515a6dcd4dfc2371f5d5944eeefa3fd52c968da5823ee6fb66496d8860f08
+size 3259