End of training

README.md

@@ -1,13 +1,30 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
 - glue
+metrics:
+- spearmanr
 model-index:
 - name: out-glue-stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      config: stsb
+      split: validation
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.8807188703976201
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # out-glue-stsb
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE STSB dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5336
+- Pearson: 0.8853
+- Spearmanr: 0.8807
+- Combined Score: 0.8830
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 20.0,
+    "eval_combined_score": 0.8830287553865886,
+    "eval_loss": 0.533576250076294,
+    "eval_pearson": 0.8853386403755572,
+    "eval_runtime": 1.1414,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1314.172,
+    "eval_spearmanr": 0.8807188703976201,
+    "eval_steps_per_second": 5.257,
+    "train_loss": 0.4903079410394033,
+    "train_runtime": 237.6265,
+    "train_samples": 5749,
+    "train_samples_per_second": 483.869,
+    "train_steps_per_second": 2.525
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 20.0,
+    "eval_combined_score": 0.8830287553865886,
+    "eval_loss": 0.533576250076294,
+    "eval_pearson": 0.8853386403755572,
+    "eval_runtime": 1.1414,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1314.172,
+    "eval_spearmanr": 0.8807188703976201,
+    "eval_steps_per_second": 5.257
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.4903079410394033,
+    "train_runtime": 237.6265,
+    "train_samples": 5749,
+    "train_samples_per_second": 483.869,
+    "train_steps_per_second": 2.525
+}

trainer_state.json

@@ -0,0 +1,172 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 2.0,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.926666666666667e-05,
+      "loss": 5.4856,
+      "step": 25
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.8433333333333335e-05,
+      "loss": 1.108,
+      "step": 50
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.76e-05,
+      "loss": 0.6811,
+      "step": 75
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 1.676666666666667e-05,
+      "loss": 0.5356,
+      "step": 100
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 1.5933333333333336e-05,
+      "loss": 0.4742,
+      "step": 125
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.5100000000000001e-05,
+      "loss": 0.3909,
+      "step": 150
+    },
+    {
+      "epoch": 5.83,
+      "learning_rate": 1.4266666666666668e-05,
+      "loss": 0.3342,
+      "step": 175
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 1.3433333333333334e-05,
+      "loss": 0.2914,
+      "step": 200
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 1.2600000000000001e-05,
+      "loss": 0.2638,
+      "step": 225
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 1.1766666666666669e-05,
+      "loss": 0.2275,
+      "step": 250
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 1.0933333333333334e-05,
+      "loss": 0.2238,
+      "step": 275
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 0.1909,
+      "step": 300
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 9.266666666666667e-06,
+      "loss": 0.17,
+      "step": 325
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 8.433333333333334e-06,
+      "loss": 0.1637,
+      "step": 350
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.1513,
+      "step": 375
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 6.7666666666666665e-06,
+      "loss": 0.1415,
+      "step": 400
+    },
+    {
+      "epoch": 14.17,
+      "learning_rate": 5.933333333333335e-06,
+      "loss": 0.1404,
+      "step": 425
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 5.1e-06,
+      "loss": 0.1244,
+      "step": 450
+    },
+    {
+      "epoch": 15.83,
+      "learning_rate": 4.266666666666668e-06,
+      "loss": 0.1235,
+      "step": 475
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 3.4333333333333336e-06,
+      "loss": 0.115,
+      "step": 500
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.6e-06,
+      "loss": 0.1095,
+      "step": 525
+    },
+    {
+      "epoch": 18.33,
+      "learning_rate": 1.7666666666666668e-06,
+      "loss": 0.1088,
+      "step": 550
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 9.333333333333334e-07,
+      "loss": 0.106,
+      "step": 575
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 0.1063,
+      "step": 600
+    },
+    {
+      "epoch": 20.0,
+      "step": 600,
+      "total_flos": 7563059380055040.0,
+      "train_loss": 0.4903079410394033,
+      "train_runtime": 237.6265,
+      "train_samples_per_second": 483.869,
+      "train_steps_per_second": 2.525
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 600,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 7563059380055040.0,
+  "trial_name": null,
+  "trial_params": null
+}