End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE RTE
       type: glue
       config: rte
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.49097472924187724
+      value: 0.5451263537906137
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_rte
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8230
-- Accuracy: 0.4910
+- Loss: 0.6896
+- Accuracy: 0.5451
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5451263537906137,
+    "eval_loss": 0.6895958781242371,
+    "eval_runtime": 0.3771,
+    "eval_samples": 277,
+    "eval_samples_per_second": 734.458,
+    "eval_steps_per_second": 5.303,
+    "train_loss": 0.6846395254135131,
+    "train_runtime": 78.7517,
+    "train_samples": 2490,
+    "train_samples_per_second": 1580.919,
+    "train_steps_per_second": 6.349
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5451263537906137,
+    "eval_loss": 0.6895958781242371,
+    "eval_runtime": 0.3771,
+    "eval_samples": 277,
+    "eval_samples_per_second": 734.458,
+    "eval_steps_per_second": 5.303
+}

logs/events.out.tfevents.1677696537.serv-9220.1178704.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d00c598c707d584c5dcf41d83b0b39b67f1c87464913e3d61fe0994d452c3b0
+size 357

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.6846395254135131,
+    "train_runtime": 78.7517,
+    "train_samples": 2490,
+    "train_samples_per_second": 1580.919,
+    "train_steps_per_second": 6.349
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6895958781242371,
+  "best_model_checkpoint": "hBERTv1_rte/checkpoint-10",
+  "epoch": 6.0,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7247,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5451263537906137,
+      "eval_loss": 0.6895958781242371,
+      "eval_runtime": 0.3609,
+      "eval_samples_per_second": 767.565,
+      "eval_steps_per_second": 5.542,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7046,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7013799548149109,
+      "eval_runtime": 0.3547,
+      "eval_samples_per_second": 780.85,
+      "eval_steps_per_second": 5.638,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6934,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6982845067977905,
+      "eval_runtime": 0.3536,
+      "eval_samples_per_second": 783.333,
+      "eval_steps_per_second": 5.656,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6846,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5126353790613718,
+      "eval_loss": 0.7091580033302307,
+      "eval_runtime": 0.3613,
+      "eval_samples_per_second": 766.716,
+      "eval_steps_per_second": 5.536,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6853,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5126353790613718,
+      "eval_loss": 0.713951826095581,
+      "eval_runtime": 0.3543,
+      "eval_samples_per_second": 781.867,
+      "eval_steps_per_second": 5.645,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6152,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.49097472924187724,
+      "eval_loss": 0.8229976892471313,
+      "eval_runtime": 0.3532,
+      "eval_samples_per_second": 784.179,
+      "eval_steps_per_second": 5.662,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "step": 60,
+      "total_flos": 1887086894383104.0,
+      "train_loss": 0.6846395254135131,
+      "train_runtime": 78.7517,
+      "train_samples_per_second": 1580.919,
+      "train_steps_per_second": 6.349
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 50,
+  "total_flos": 1887086894383104.0,
+  "trial_name": null,
+  "trial_params": null
+}