End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE COLA
       type: glue
       config: cola
       split: validation
@@ -32,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_new_pretrain_48_emb_com_cola
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6183
+- Loss: 0.6181
 - Matthews Correlation: 0.0
 - Accuracy: 0.6913
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6180804967880249,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 4.5305,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 230.218,
+    "eval_steps_per_second": 1.987,
+    "train_loss": 0.6143423155496046,
+    "train_runtime": 1424.3505,
+    "train_samples": 8551,
+    "train_samples_per_second": 300.172,
+    "train_steps_per_second": 2.352
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6180804967880249,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 4.5305,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 230.218,
+    "eval_steps_per_second": 1.987
+}

logs/events.out.tfevents.1686759040.glendale.42326.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bebf7e80ef5adfa7a7e949890121458d90ab5347d2202646143278aebfbf4b1
+size 427

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 0.6143423155496046,
+    "train_runtime": 1424.3505,
+    "train_samples": 8551,
+    "train_samples_per_second": 300.172,
+    "train_steps_per_second": 2.352
+}

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": 0.6180804967880249,
+  "best_model_checkpoint": "hBERTv2_new_pretrain_48_emb_com_cola/checkpoint-402",
+  "epoch": 11.0,
+  "global_step": 737,
+  "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": 0.6308,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6420325636863708,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.6088,
+      "eval_samples_per_second": 226.308,
+      "eval_steps_per_second": 1.953,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6219,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6212252974510193,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.6128,
+      "eval_samples_per_second": 226.11,
+      "eval_steps_per_second": 1.951,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6122,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6236904263496399,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5967,
+      "eval_samples_per_second": 226.9,
+      "eval_steps_per_second": 1.958,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.6165,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6197761297225952,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5903,
+      "eval_samples_per_second": 227.218,
+      "eval_steps_per_second": 1.961,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.6133,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6235945224761963,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5701,
+      "eval_samples_per_second": 228.224,
+      "eval_steps_per_second": 1.969,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.6105,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6180804967880249,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5756,
+      "eval_samples_per_second": 227.95,
+      "eval_steps_per_second": 1.967,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.44e-05,
+      "loss": 0.6132,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6288493871688843,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5675,
+      "eval_samples_per_second": 228.353,
+      "eval_steps_per_second": 1.97,
+      "step": 469
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.61,
+      "step": 536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6188379526138306,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5668,
+      "eval_samples_per_second": 228.386,
+      "eval_steps_per_second": 1.971,
+      "step": 536
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3.28e-05,
+      "loss": 0.6103,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6251513361930847,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5779,
+      "eval_samples_per_second": 227.836,
+      "eval_steps_per_second": 1.966,
+      "step": 603
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6099,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6301288604736328,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.5868,
+      "eval_samples_per_second": 227.389,
+      "eval_steps_per_second": 1.962,
+      "step": 670
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.1200000000000006e-05,
+      "loss": 0.6091,
+      "step": 737
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6183443069458008,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.6086,
+      "eval_samples_per_second": 226.317,
+      "eval_steps_per_second": 1.953,
+      "step": 737
+    },
+    {
+      "epoch": 11.0,
+      "step": 737,
+      "total_flos": 1.3778937716932608e+16,
+      "train_loss": 0.6143423155496046,
+      "train_runtime": 1424.3505,
+      "train_samples_per_second": 300.172,
+      "train_steps_per_second": 2.352
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 1.3778937716932608e+16,
+  "trial_name": null,
+  "trial_params": null
+}