upload expat precision 0.75 model

checkpoint-8307/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": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28895
+}

checkpoint-8307/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5bc183132b454f542debe36c6b942b02519a3dfe4e41a5d47471b69f826b0ea
+size 2659653861

checkpoint-8307/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db553e708c1589f1cad3c19964e163b6459f37c4f8df7f4609874841a7d7650c
+size 1329849649

checkpoint-8307/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6a42f63aa50b4b0bbd4d57538fecedac501e97a3b196c37a34faf348e0fd71
+size 14503

checkpoint-8307/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7578e015e7e8438469f854ec614f24889192bf014effa58ba89f4308e33f9f0d
+size 559

checkpoint-8307/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8b97964380dcff667c5fd420f2d0a3a8c25b0b7a791d7386a704fad19bed24
+size 623

checkpoint-8307/special_tokens_map.json

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

checkpoint-8307/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "sultan/BioM-ELECTRA-Large-SQuAD2",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-8307/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 8307,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.928349584687613e-05,
+      "loss": 0.2,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.856265799927772e-05,
+      "loss": 0.1575,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7840375586854463e-05,
+      "loss": 0.1372,
+      "step": 1500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7118093174431205e-05,
+      "loss": 0.1235,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6395810762007947e-05,
+      "loss": 0.088,
+      "step": 2500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.567352834958469e-05,
+      "loss": 0.0828,
+      "step": 3000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.4951245937161432e-05,
+      "loss": 0.0648,
+      "step": 3500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.4228963524738174e-05,
+      "loss": 0.0649,
+      "step": 4000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.3506681112314917e-05,
+      "loss": 0.0637,
+      "step": 4500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.2787287829541352e-05,
+      "loss": 0.048,
+      "step": 5000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2065005417118094e-05,
+      "loss": 0.0744,
+      "step": 5500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.1344167569519684e-05,
+      "loss": 0.0782,
+      "step": 6000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.0623329721921271e-05,
+      "loss": 0.0685,
+      "step": 6500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 9.901047309498015e-06,
+      "loss": 0.0527,
+      "step": 7000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 9.178764897074757e-06,
+      "loss": 0.0576,
+      "step": 7500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 8.457927049476346e-06,
+      "loss": 0.0456,
+      "step": 8000
+    }
+  ],
+  "max_steps": 13845,
+  "num_train_epochs": 5,
+  "total_flos": 4.62844347201792e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8307/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffe34a01858ba14009aab52082e1d3a0201b9d8a747bc294d21a18bc85392bf
+size 3503