Config and tokenizer

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "fgaim/tielectra-small",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "amharic",
+    "1": "blin",
+    "2": "geez",
+    "3": "tigre",
+    "4": "tigrinya"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "amharic": 0,
+    "blin": 1,
+    "geez": 2,
+    "tigre": 3,
+    "tigrinya": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

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": 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, "name_or_path": "fgaim/tielectra-small", "tokenizer_class": "ElectraTokenizer"}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 705,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.13,
+      "learning_rate": 5.815602836879432e-06,
+      "loss": 0.7527,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 705,
+      "total_flos": 165498802560000.0,
+      "train_loss": 0.6064913972895196,
+      "train_runtime": 192.036,
+      "train_samples_per_second": 117.166,
+      "train_steps_per_second": 3.671
+    }
+  ],
+  "max_steps": 705,
+  "num_train_epochs": 3,
+  "total_flos": 165498802560000.0,
+  "trial_name": null,
+  "trial_params": null
+}