初始化项目，由ModelHub XC社区提供模型

Model: NastasiaM/mbert-loraxs-qa-vanilla
Source: Original Platform

run-9/checkpoint-1902/config.json

@@ -0,0 +1,34 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

run-9/checkpoint-1902/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046e1d19b953cde25c6aaec193c545e702060e58639edd87b8eb50b06dc07321
+size 709080872

run-9/checkpoint-1902/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc6f31985bed3de9290bdc61f078939446056cf925e5bc7c74860c35bd8361a
+size 1418284811

run-9/checkpoint-1902/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9fa0ce0401512fa9896892571f419761e8535885785b10a28df3e18c4bcd070
+size 14645

run-9/checkpoint-1902/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac140e1b6bbcce63909a351d377fa0c3f6321ccf3d2fd007ec399e99ac0a2cb2
+size 1383

run-9/checkpoint-1902/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d40b307bcb67d397c6357bf0769ddf3f01f436a60962fa92d98049e640296a8
+size 1465

run-9/checkpoint-1902/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-9/checkpoint-1902/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_global_step": 1268,
+  "best_metric": 78.18340762080186,
+  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-9/checkpoint-1268",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1902,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7886435331230284,
+      "grad_norm": 28.185476303100586,
+      "learning_rate": 1.950773981150722e-05,
+      "loss": 2.463543212890625,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 61.84,
+      "eval_f1": 76.07411778933292,
+      "eval_loss": 1.221575140953064,
+      "eval_runtime": 5.8101,
+      "eval_samples_per_second": 217.724,
+      "eval_steps_per_second": 13.769,
+      "step": 634
+    },
+    {
+      "epoch": 1.5772870662460567,
+      "grad_norm": 30.28702735900879,
+      "learning_rate": 1.2555587348389893e-05,
+      "loss": 1.1182257080078124,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 64.4,
+      "eval_f1": 78.18340762080186,
+      "eval_loss": 1.1935663223266602,
+      "eval_runtime": 5.9873,
+      "eval_samples_per_second": 211.279,
+      "eval_steps_per_second": 13.362,
+      "step": 1268
+    },
+    {
+      "epoch": 2.365930599369085,
+      "grad_norm": 10.738986015319824,
+      "learning_rate": 5.603434885272566e-06,
+      "loss": 0.8330254516601563,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 64.08,
+      "eval_f1": 77.88883243489298,
+      "eval_loss": 1.2758605480194092,
+      "eval_runtime": 5.9149,
+      "eval_samples_per_second": 213.866,
+      "eval_steps_per_second": 13.525,
+      "step": 1902
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1902,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5122918888376832.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3790265728787493e-05,
+    "num_train_epochs": 3,
+    "weight_decay": 0.03290502978450524
+  }
+}

run-9/checkpoint-1902/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1084741d83f139111675ead8df2066cf8b07c705fbe8f01b50cfddb4d086161e
+size 5265