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": 36.36,
+    "eval_accuracy_score": 0.8425259792166268,
+    "eval_f1": 0.0,
+    "eval_loss": 0.6995488405227661,
+    "eval_precision": 0.0,
+    "eval_recall": 0.0,
+    "eval_runtime": 3.4792,
+    "eval_samples": 250,
+    "eval_samples_per_second": 71.855,
+    "eval_steps_per_second": 9.197,
+    "test_accuracy_score": 0.8633557046979866,
+    "test_f1": 0.0,
+    "test_loss": 0.6328587532043457,
+    "test_precision": 0.0,
+    "test_recall": 0.0,
+    "test_runtime": 6.9256,
+    "test_samples": 500,
+    "test_samples_per_second": 72.196,
+    "test_steps_per_second": 9.097,
+    "train_loss": 0.6987884674072266,
+    "train_runtime": 2254.7389,
+    "train_samples": 1750,
+    "train_samples_per_second": 212.885,
+    "train_steps_per_second": 6.653
+}

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:fbf4616bc91e1926c661738ad8b1547a681de22a29253bff403daf5a58937660
+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 +1,169 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-amh/checkpoint-1000",
+  "epoch": 36.36363636363637,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.64,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.7014185786247253,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.5028,
+      "eval_samples_per_second": 71.372,
+      "eval_steps_per_second": 9.136,
+      "step": 200
+    },
+    {
+      "epoch": 7.27,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6971796751022339,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4905,
+      "eval_samples_per_second": 71.623,
+      "eval_steps_per_second": 9.168,
+      "step": 400
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.7264,
+      "step": 500
+    },
+    {
+      "epoch": 10.91,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.698952853679657,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4754,
+      "eval_samples_per_second": 71.935,
+      "eval_steps_per_second": 9.208,
+      "step": 600
+    },
+    {
+      "epoch": 14.55,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.708954393863678,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4855,
+      "eval_samples_per_second": 71.726,
+      "eval_steps_per_second": 9.181,
+      "step": 800
+    },
+    {
+      "epoch": 18.18,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.6917,
+      "step": 1000
+    },
+    {
+      "epoch": 18.18,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6995488405227661,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4744,
+      "eval_samples_per_second": 71.955,
+      "eval_steps_per_second": 9.21,
+      "step": 1000
+    },
+    {
+      "epoch": 21.82,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.698596179485321,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4893,
+      "eval_samples_per_second": 71.648,
+      "eval_steps_per_second": 9.171,
+      "step": 1200
+    },
+    {
+      "epoch": 25.45,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.7002435326576233,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4772,
+      "eval_samples_per_second": 71.897,
+      "eval_steps_per_second": 9.203,
+      "step": 1400
+    },
+    {
+      "epoch": 27.27,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.6883,
+      "step": 1500
+    },
+    {
+      "epoch": 29.09,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.7004148364067078,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4851,
+      "eval_samples_per_second": 71.734,
+      "eval_steps_per_second": 9.182,
+      "step": 1600
+    },
+    {
+      "epoch": 32.73,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6990127563476562,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4756,
+      "eval_samples_per_second": 71.93,
+      "eval_steps_per_second": 9.207,
+      "step": 1800
+    },
+    {
+      "epoch": 36.36,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.6889,
+      "step": 2000
+    },
+    {
+      "epoch": 36.36,
+      "eval_accuracy_score": 0.8425259792166268,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6986844539642334,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.4585,
+      "eval_samples_per_second": 72.285,
+      "eval_steps_per_second": 9.253,
+      "step": 2000
+    },
+    {
+      "epoch": 36.36,
+      "step": 2000,
+      "total_flos": 8314988993187840.0,
+      "train_loss": 0.6987884674072266,
+      "train_runtime": 2254.7389,
+      "train_samples_per_second": 212.885,
+      "train_steps_per_second": 6.653
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 273,
+  "total_flos": 8314988993187840.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743ba82bec6ed454834a136c19322fe699c60d94a6a50f0ffb6abbf1eecd6632
+size 3259