Fine tuned BERT sequence classification model for LABR dataset

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/jupyter/hub_models/bert-labr-unbalanced",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87aabbd86414ad4d3753e19d2448ad4f5b38b9856dba6d019bc776d578cc1149
+size 2693488029

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33fd65aad1add73f6284ea034c4c7fe8f967c1e709f833c05310911d292ae683
+size 1346791341

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bb10dd217581b5de9785a605f84148982fbf3839b866bac53dffde9fb8e8ff
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4534f62a647241efea544e23d4971a2430e57b93deba518536bb98b34471dc01
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de86a348889fd6fa7fa24799376198822b7699608f3b74a7ebb25c2b794fb83
+size 1347181680

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "asafaya/bert-large-arabic", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 0.20763197541236877,
+  "best_model_checkpoint": "BERT-LABR-unbalanced/checkpoint-1000",
+  "epoch": 0.9784735812133072,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.369210697977822e-06,
+      "loss": 0.2714,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.908311910882605,
+      "eval_f1": 0.9456024402643619,
+      "eval_loss": 0.24122537672519684,
+      "eval_precision": 0.9419765591086673,
+      "eval_recall": 0.9492563429571304,
+      "eval_runtime": 109.0386,
+      "eval_samples_per_second": 74.918,
+      "eval_steps_per_second": 2.348,
+      "step": 500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.738421395955643e-06,
+      "loss": 0.2258,
+      "step": 1000
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.9215326233321092,
+      "eval_f1": 0.9538483692130463,
+      "eval_loss": 0.20763197541236877,
+      "eval_precision": 0.9421134973687953,
+      "eval_recall": 0.9658792650918635,
+      "eval_runtime": 108.4256,
+      "eval_samples_per_second": 75.342,
+      "eval_steps_per_second": 2.361,
+      "step": 1000
+    }
+  ],
+  "max_steps": 3066,
+  "num_train_epochs": 3,
+  "total_flos": 3727725453312000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9de0cb303693a02ac6331e86713810274f8cf6772a6ce97338e4749c1046b4
+size 2991