Upload 10 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "sultan/BioM-ELECTRA-Large-SQuAD2",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "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": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28895
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8888bc269e1a2f761b96196b7b20de293260f6f85baaaaa90d2e7c2c0630fd
+size 1329761136

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc4be7bb3587820d046a604ea166f0a562993814be967c7dc419b7da8371449
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca69ce5aa68dceb8d9e101c592864d7ed08ecc7417b88341179a57fb29294d93
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.05977272242307663,
+  "best_model_checkpoint": "BioM-ELECTRA-Large-SQuAD2-HTT/checkpoint-408",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 408,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.19639992713928223,
+      "eval_runtime": 25.536,
+      "eval_samples_per_second": 42.528,
+      "eval_steps_per_second": 5.326,
+      "step": 136
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.08615566045045853,
+      "eval_runtime": 25.4227,
+      "eval_samples_per_second": 42.718,
+      "eval_steps_per_second": 5.35,
+      "step": 272
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.05977272242307663,
+      "eval_runtime": 25.4468,
+      "eval_samples_per_second": 42.677,
+      "eval_steps_per_second": 5.344,
+      "step": 408
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 408,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2269295535264768.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b377ac312893bb6327e5a7474f3b3c0e1a4b5c0704c40b01b146d2a993c605
+size 5048