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: 0.5306859205776173
+      value: 0.5379061371841155
 ---
 
 <!-- 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. -->
 
 # hBERTv2_new_pretrain_48_rte
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0455
-- Accuracy: 0.5307
+- Loss: 0.6901
+- Accuracy: 0.5379
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5379061371841155,
+    "eval_loss": 0.6901229619979858,
+    "eval_runtime": 0.4844,
+    "eval_samples": 277,
+    "eval_samples_per_second": 571.882,
+    "eval_steps_per_second": 6.194,
+    "train_loss": 0.6037428766489029,
+    "train_runtime": 129.1965,
+    "train_samples": 2490,
+    "train_samples_per_second": 963.648,
+    "train_steps_per_second": 7.74
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5379061371841155,
+    "eval_loss": 0.6901229619979858,
+    "eval_runtime": 0.4844,
+    "eval_samples": 277,
+    "eval_samples_per_second": 571.882,
+    "eval_steps_per_second": 6.194
+}

logs/events.out.tfevents.1686054020.serv-9207.2387813.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7892618fd5931c2688a175268a5972b0dd0d983d289a76b36b849239055ca83e
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 0.6037428766489029,
+    "train_runtime": 129.1965,
+    "train_samples": 2490,
+    "train_samples_per_second": 963.648,
+    "train_steps_per_second": 7.74
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": 0.6901229619979858,
+  "best_model_checkpoint": "hBERTv2_new_pretrain_48_rte/checkpoint-60",
+  "epoch": 8.0,
+  "global_step": 160,
+  "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": 0.7454,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.789457380771637,
+      "eval_runtime": 0.4658,
+      "eval_samples_per_second": 594.645,
+      "eval_steps_per_second": 6.44,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.7171,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6994161605834961,
+      "eval_runtime": 0.467,
+      "eval_samples_per_second": 593.178,
+      "eval_steps_per_second": 6.424,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.701,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5379061371841155,
+      "eval_loss": 0.6901229619979858,
+      "eval_runtime": 0.466,
+      "eval_samples_per_second": 594.414,
+      "eval_steps_per_second": 6.438,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.6823,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.7257234454154968,
+      "eval_runtime": 0.4671,
+      "eval_samples_per_second": 593.01,
+      "eval_steps_per_second": 6.422,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.6383,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5379061371841155,
+      "eval_loss": 0.7477154731750488,
+      "eval_runtime": 0.4676,
+      "eval_samples_per_second": 592.433,
+      "eval_steps_per_second": 6.416,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.5227,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.9449917078018188,
+      "eval_runtime": 0.4675,
+      "eval_samples_per_second": 592.467,
+      "eval_steps_per_second": 6.417,
+      "step": 120
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.44e-05,
+      "loss": 0.4559,
+      "step": 140
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5234657039711191,
+      "eval_loss": 1.1971466541290283,
+      "eval_runtime": 0.4662,
+      "eval_samples_per_second": 594.192,
+      "eval_steps_per_second": 6.435,
+      "step": 140
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.3672,
+      "step": 160
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5306859205776173,
+      "eval_loss": 1.0455256700515747,
+      "eval_runtime": 0.4684,
+      "eval_samples_per_second": 591.428,
+      "eval_steps_per_second": 6.405,
+      "step": 160
+    },
+    {
+      "epoch": 8.0,
+      "step": 160,
+      "total_flos": 2915076176609280.0,
+      "train_loss": 0.6037428766489029,
+      "train_runtime": 129.1965,
+      "train_samples_per_second": 963.648,
+      "train_steps_per_second": 7.74
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 50,
+  "total_flos": 2915076176609280.0,
+  "trial_name": null,
+  "trial_params": null
+}