End of training

README.md

@@ -1,12 +1,29 @@
 ---
 library_name: transformers
+language:
+- zh
 license: apache-2.0
 base_model: hfl/chinese-bert-wwm-ext
 tags:
 - generated_from_trainer
+datasets:
+- chinese_paragraph_relevance
+metrics:
+- accuracy
 model-index:
 - name: chinese_paragraph_bert-ext
-  results: []
+  results:
+  - task:
+      name: Multiple Choice
+      type: multiple-choice
+    dataset:
+      name: Chinese Relevance Paragraphs
+      type: chinese_paragraph_relevance
+      args: relevant_paragraph
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9617813229560852
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # chinese_paragraph_bert-ext
 
-This model is a fine-tuned version of [hfl/chinese-bert-wwm-ext](https://huggingface.co/hfl/chinese-bert-wwm-ext) on an unknown dataset.
+This model is a fine-tuned version of [hfl/chinese-bert-wwm-ext](https://huggingface.co/hfl/chinese-bert-wwm-ext) on the Chinese Relevance Paragraphs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1717
+- Accuracy: 0.9618
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9617813229560852,
+    "eval_loss": 0.17168329656124115,
+    "eval_runtime": 75.5186,
+    "eval_samples": 3009,
+    "eval_samples_per_second": 39.844,
+    "eval_steps_per_second": 2.503,
+    "total_flos": 6.855770591553946e+16,
+    "train_loss": 0.08668158495607596,
+    "train_runtime": 5343.4587,
+    "train_samples": 21714,
+    "train_samples_per_second": 12.191,
+    "train_steps_per_second": 0.762
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9617813229560852,
+    "eval_loss": 0.17168329656124115,
+    "eval_runtime": 75.5186,
+    "eval_samples": 3009,
+    "eval_samples_per_second": 39.844,
+    "eval_steps_per_second": 2.503
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6.855770591553946e+16,
+    "train_loss": 0.08668158495607596,
+    "train_runtime": 5343.4587,
+    "train_samples": 21714,
+    "train_samples_per_second": 12.191,
+    "train_steps_per_second": 0.762
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 4074,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36818851251840945,
+      "grad_norm": 14.467572212219238,
+      "learning_rate": 2.6318114874815905e-05,
+      "loss": 0.198,
+      "step": 500
+    },
+    {
+      "epoch": 0.7363770250368189,
+      "grad_norm": 10.934176445007324,
+      "learning_rate": 2.263622974963181e-05,
+      "loss": 0.1377,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1045655375552283,
+      "grad_norm": 0.5147254467010498,
+      "learning_rate": 1.8954344624447718e-05,
+      "loss": 0.1138,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4727540500736378,
+      "grad_norm": 33.273719787597656,
+      "learning_rate": 1.5272459499263623e-05,
+      "loss": 0.0751,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8409425625920472,
+      "grad_norm": 7.599516868591309,
+      "learning_rate": 1.1590574374079529e-05,
+      "loss": 0.0707,
+      "step": 2500
+    },
+    {
+      "epoch": 2.2091310751104567,
+      "grad_norm": 13.896529197692871,
+      "learning_rate": 7.908689248895435e-06,
+      "loss": 0.0569,
+      "step": 3000
+    },
+    {
+      "epoch": 2.5773195876288657,
+      "grad_norm": 12.114886283874512,
+      "learning_rate": 4.2268041237113405e-06,
+      "loss": 0.024,
+      "step": 3500
+    },
+    {
+      "epoch": 2.9455081001472756,
+      "grad_norm": 0.2183772623538971,
+      "learning_rate": 5.44918998527246e-07,
+      "loss": 0.0249,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "step": 4074,
+      "total_flos": 6.855770591553946e+16,
+      "train_loss": 0.08668158495607596,
+      "train_runtime": 5343.4587,
+      "train_samples_per_second": 12.191,
+      "train_steps_per_second": 0.762
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4074,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.855770591553946e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}