End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -14,7 +16,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE COLA
       type: glue
       config: cola
       split: validation
@@ -22,10 +24,10 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.08269458252328303
+      value: 0.0
     - name: Accuracy
       type: accuracy
-      value: 0.5848513841629028
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,11 +35,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sa_BERT_24_cola
 
-This model is a fine-tuned version of [gokuls/bert_base_24](https://huggingface.co/gokuls/bert_base_24) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_base_24](https://huggingface.co/gokuls/bert_base_24) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8221
-- Matthews Correlation: 0.0827
-- Accuracy: 0.5849
+- Loss: 0.6120
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6119913458824158,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 2.1694,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 480.769,
+    "eval_steps_per_second": 5.07,
+    "train_loss": 0.5213487059981735,
+    "train_runtime": 387.7853,
+    "train_samples": 8551,
+    "train_samples_per_second": 1102.543,
+    "train_steps_per_second": 11.604
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6119913458824158,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 2.1694,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 480.769,
+    "eval_steps_per_second": 5.07
+}

logs/events.out.tfevents.1686863361.serv-3317.1921073.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f90bc6ad48ee81b1452fd7890936eaa415fe34f39c3363ba9a2f66558b7bc4
+size 427

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.5213487059981735,
+    "train_runtime": 387.7853,
+    "train_samples": 8551,
+    "train_samples_per_second": 1102.543,
+    "train_steps_per_second": 11.604
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.6119913458824158,
+  "best_model_checkpoint": "sa_BERT_24_cola/checkpoint-90",
+  "epoch": 6.0,
+  "global_step": 540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.6138,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6119913458824158,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.1692,
+      "eval_samples_per_second": 480.825,
+      "eval_steps_per_second": 5.071,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.5898,
+      "step": 180
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.693192720413208,
+      "eval_loss": 0.6241820454597473,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 2.1753,
+      "eval_samples_per_second": 479.479,
+      "eval_steps_per_second": 5.057,
+      "step": 180
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.5491,
+      "step": 270
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.640460193157196,
+      "eval_loss": 0.679804265499115,
+      "eval_matthews_correlation": 0.07331941707716809,
+      "eval_runtime": 2.1763,
+      "eval_samples_per_second": 479.247,
+      "eval_steps_per_second": 5.054,
+      "step": 270
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.5027,
+      "step": 360
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6327900290489197,
+      "eval_loss": 0.6873075366020203,
+      "eval_matthews_correlation": 0.0666923742122696,
+      "eval_runtime": 2.1818,
+      "eval_samples_per_second": 478.037,
+      "eval_steps_per_second": 5.042,
+      "step": 360
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.4549,
+      "step": 450
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6299136877059937,
+      "eval_loss": 0.7840977907180786,
+      "eval_matthews_correlation": 0.10251809083407509,
+      "eval_runtime": 2.1908,
+      "eval_samples_per_second": 476.072,
+      "eval_steps_per_second": 5.021,
+      "step": 450
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.4177,
+      "step": 540
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5848513841629028,
+      "eval_loss": 0.8220876455307007,
+      "eval_matthews_correlation": 0.08269458252328303,
+      "eval_runtime": 2.1807,
+      "eval_samples_per_second": 478.281,
+      "eval_steps_per_second": 5.044,
+      "step": 540
+    },
+    {
+      "epoch": 6.0,
+      "step": 540,
+      "total_flos": 6749587947651072.0,
+      "train_loss": 0.5213487059981735,
+      "train_runtime": 387.7853,
+      "train_samples_per_second": 1102.543,
+      "train_steps_per_second": 11.604
+    }
+  ],
+  "max_steps": 4500,
+  "num_train_epochs": 50,
+  "total_flos": 6749587947651072.0,
+  "trial_name": null,
+  "trial_params": null
+}