End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert-base-cased-finetuned-qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9108830076675736
+    - name: F1
+      type: f1
+      value: 0.8804618294018115
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,7 +35,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-cased-finetuned-qqp
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3568
 - Accuracy: 0.9109

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9108830076675736,
+    "eval_combined_score": 0.8956724185346925,
+    "eval_f1": 0.8804618294018115,
+    "eval_loss": 0.3567805886268616,
+    "eval_runtime": 125.063,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 323.277,
+    "eval_steps_per_second": 40.412,
+    "total_flos": 2.8719571514554368e+17,
+    "train_loss": 0.20675522433668814,
+    "train_runtime": 11186.3828,
+    "train_samples": 363846,
+    "train_samples_per_second": 97.577,
+    "train_steps_per_second": 6.099
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9108830076675736,
+    "eval_combined_score": 0.8956724185346925,
+    "eval_f1": 0.8804618294018115,
+    "eval_loss": 0.3567805886268616,
+    "eval_runtime": 125.063,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 323.277,
+    "eval_steps_per_second": 40.412
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.8719571514554368e+17,
+    "train_loss": 0.20675522433668814,
+    "train_runtime": 11186.3828,
+    "train_samples": 363846,
+    "train_samples_per_second": 97.577,
+    "train_steps_per_second": 6.099
+}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 68223,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.0593485832214355,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2942,
+      "step": 22741
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9008656937917388,
+      "eval_combined_score": 0.8844814218975149,
+      "eval_f1": 0.868097150003291,
+      "eval_loss": 0.2476482093334198,
+      "eval_runtime": 125.5141,
+      "eval_samples_per_second": 322.115,
+      "eval_steps_per_second": 40.266,
+      "step": 22741
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.616366386413574,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1919,
+      "step": 45482
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9079643828839971,
+      "eval_combined_score": 0.892029542512559,
+      "eval_f1": 0.8760947021411208,
+      "eval_loss": 0.2705819010734558,
+      "eval_runtime": 126.0816,
+      "eval_samples_per_second": 320.665,
+      "eval_steps_per_second": 40.085,
+      "step": 45482
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2998017370700836,
+      "learning_rate": 0.0,
+      "loss": 0.1342,
+      "step": 68223
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9108830076675736,
+      "eval_combined_score": 0.8956724185346925,
+      "eval_f1": 0.8804618294018115,
+      "eval_loss": 0.3567805886268616,
+      "eval_runtime": 126.0333,
+      "eval_samples_per_second": 320.788,
+      "eval_steps_per_second": 40.101,
+      "step": 68223
+    },
+    {
+      "epoch": 3.0,
+      "step": 68223,
+      "total_flos": 2.8719571514554368e+17,
+      "train_loss": 0.20675522433668814,
+      "train_runtime": 11186.3828,
+      "train_samples_per_second": 97.577,
+      "train_steps_per_second": 6.099
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 68223,
+  "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": 2.8719571514554368e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}