初始化项目，由ModelHub XC社区提供模型

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

run-3/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-3/checkpoint-1902/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6619e1ca4ae50db7ded3577a45c1501215c6dc5bd9bf53438d8f2a94b9b2dc9d
+size 709080872

run-3/checkpoint-1902/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58808cb6ed3056db6170ff833594006f38a934ee4553e9a98cb2702074e1175
+size 1418284811

run-3/checkpoint-1902/rng_state.pth

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

run-3/checkpoint-1902/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0a0c7f6c8509d672722a939f4d396dea735fa475e6d89775c3d859d2450df1
+size 1383

run-3/checkpoint-1902/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1d0a962ced2c06199bbd6c5c425db43a120b9239e51cd13c71321d98fa2b3c
+size 1465

run-3/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-3/checkpoint-1902/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_global_step": 1902,
+  "best_metric": 78.458442399707,
+  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-3/checkpoint-1902",
+  "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": 31.252710342407227,
+      "learning_rate": 2.5915663787327118e-05,
+      "loss": 2.36512060546875,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 61.76,
+      "eval_f1": 76.08343679857553,
+      "eval_loss": 1.205523133277893,
+      "eval_runtime": 5.7547,
+      "eval_samples_per_second": 219.822,
+      "eval_steps_per_second": 13.902,
+      "step": 634
+    },
+    {
+      "epoch": 1.5772870662460567,
+      "grad_norm": 29.112215042114258,
+      "learning_rate": 1.6679860584430782e-05,
+      "loss": 1.0828076171875,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 64.4,
+      "eval_f1": 77.92568009442539,
+      "eval_loss": 1.2169331312179565,
+      "eval_runtime": 5.8111,
+      "eval_samples_per_second": 217.687,
+      "eval_steps_per_second": 13.767,
+      "step": 1268
+    },
+    {
+      "epoch": 2.365930599369085,
+      "grad_norm": 7.044902324676514,
+      "learning_rate": 7.444057381534446e-06,
+      "loss": 0.7706432495117187,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 64.24,
+      "eval_f1": 78.458442399707,
+      "eval_loss": 1.3074095249176025,
+      "eval_runtime": 6.3974,
+      "eval_samples_per_second": 197.738,
+      "eval_steps_per_second": 12.505,
+      "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": 4702949676112896.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.160491856031126e-05,
+    "num_train_epochs": 3,
+    "weight_decay": 0.022722580353297495
+  }
+}

run-3/checkpoint-1902/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36729c4002495c3bd45ea9dbd839a6d681edb2dc4c2c499e2b6267d586c6ddfd
+size 5265