ok

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "neuralspace-reverie/indic-transformers-bn-bert",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 100000
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.21523022651672363,
+  "best_model_checkpoint": "/content/drive/MyDrive/ali/ep4/b32/80_20/w001/checkpoint-1500",
+  "epoch": 2.6041666666666665,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.553240740740741e-05,
+      "loss": 0.4087,
+      "step": 500
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.9312065972222222,
+      "eval_f1": 0.9307073943638753,
+      "eval_loss": 0.23527929186820984,
+      "eval_precision": 0.9326704506317198,
+      "eval_recall": 0.9306763702097833,
+      "eval_runtime": 71.7132,
+      "eval_samples_per_second": 64.256,
+      "eval_steps_per_second": 2.008,
+      "step": 500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.1064814814814816e-05,
+      "loss": 0.146,
+      "step": 1000
+    },
+    {
+      "epoch": 1.74,
+      "eval_accuracy": 0.9396701388888888,
+      "eval_f1": 0.9391487062975821,
+      "eval_loss": 0.2208150178194046,
+      "eval_precision": 0.9401530845672362,
+      "eval_recall": 0.9394658139649685,
+      "eval_runtime": 71.6528,
+      "eval_samples_per_second": 64.31,
+      "eval_steps_per_second": 2.01,
+      "step": 1000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 6.597222222222223e-06,
+      "loss": 0.0711,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6,
+      "eval_accuracy": 0.9479166666666666,
+      "eval_f1": 0.9477088956446189,
+      "eval_loss": 0.21523022651672363,
+      "eval_precision": 0.9478191326365425,
+      "eval_recall": 0.9477287374866772,
+      "eval_runtime": 71.6673,
+      "eval_samples_per_second": 64.297,
+      "eval_steps_per_second": 2.009,
+      "step": 1500
+    }
+  ],
+  "max_steps": 1728,
+  "num_train_epochs": 3,
+  "total_flos": 1.35574302528e+16,
+  "trial_name": null,
+  "trial_params": null
+}