Initial commit

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b02ee7c46f11b3caadd817478e93f371eb0b26a0ab4bebb284eacbd6649b67
+size 669940139

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce3a5a139f1030b2055c15911cbf85a9c2687d05fe480744f1b2b890659c7bc
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d85b543537012921b5f93927b54071421c6cf70e87c956ab69a00b22c213db
+size 623

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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased"}

trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 3.6228787899017334,
+  "best_model_checkpoint": "/content/drive/MyDrive/tanglish-offensive-train/checkpoint-600",
+  "epoch": 1.941747572815534,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49,
+      "eval_loss": 4.307383060455322,
+      "eval_runtime": 47.3223,
+      "eval_samples_per_second": 104.369,
+      "eval_steps_per_second": 13.059,
+      "step": 150
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 3.9359772205352783,
+      "eval_runtime": 47.0618,
+      "eval_samples_per_second": 104.947,
+      "eval_steps_per_second": 13.132,
+      "step": 300
+    },
+    {
+      "epoch": 1.46,
+      "eval_loss": 3.7475600242614746,
+      "eval_runtime": 47.0451,
+      "eval_samples_per_second": 104.984,
+      "eval_steps_per_second": 13.136,
+      "step": 450
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.3031283710895363e-05,
+      "loss": 4.3158,
+      "step": 500
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 3.6228787899017334,
+      "eval_runtime": 47.1741,
+      "eval_samples_per_second": 104.697,
+      "eval_steps_per_second": 13.1,
+      "step": 600
+    }
+  ],
+  "max_steps": 927,
+  "num_train_epochs": 3,
+  "total_flos": 707796264479022.0,
+  "trial_name": null,
+  "trial_params": null
+}