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
@@ -21,10 +23,10 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.06864834703912359
+      value: 0.0
     - name: Accuracy
       type: accuracy
-      value: 0.6855225563049316
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_48_emb_com_cola
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6674
-- Matthews Correlation: 0.0686
-- Accuracy: 0.6855
+- Loss: 0.6307
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6307324171066284,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 4.6685,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 223.413,
+    "eval_steps_per_second": 1.928,
+    "train_loss": 0.5836383193286497,
+    "train_runtime": 969.9748,
+    "train_samples": 8551,
+    "train_samples_per_second": 440.785,
+    "train_steps_per_second": 3.454
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6307324171066284,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 4.6685,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 223.413,
+    "eval_steps_per_second": 1.928
+}

logs/events.out.tfevents.1686758731.garda.2601621.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf86989f31a98200c070c35d97c0a44699e4252117f2942791a41d18b9d735d7
+size 427

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.5836383193286497,
+    "train_runtime": 969.9748,
+    "train_samples": 8551,
+    "train_samples_per_second": 440.785,
+    "train_steps_per_second": 3.454
+}

trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": 0.6307324171066284,
+  "best_model_checkpoint": "hBERTv1_new_pretrain_48_emb_com_cola/checkpoint-134",
+  "epoch": 7.0,
+  "global_step": 469,
+  "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": 0.639,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6325676441192627,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.7202,
+      "eval_samples_per_second": 220.963,
+      "eval_steps_per_second": 1.907,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.608,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6307324171066284,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.715,
+      "eval_samples_per_second": 221.209,
+      "eval_steps_per_second": 1.909,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6029,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6311112642288208,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 4.707,
+      "eval_samples_per_second": 221.585,
+      "eval_steps_per_second": 1.912,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.5893,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6836050152778625,
+      "eval_loss": 0.6356986165046692,
+      "eval_matthews_correlation": 0.00300496871017747,
+      "eval_runtime": 4.7054,
+      "eval_samples_per_second": 221.658,
+      "eval_steps_per_second": 1.913,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.5692,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6605944633483887,
+      "eval_loss": 0.6723994612693787,
+      "eval_matthews_correlation": 0.026963793941824566,
+      "eval_runtime": 4.7007,
+      "eval_samples_per_second": 221.882,
+      "eval_steps_per_second": 1.915,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.5476,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6548417806625366,
+      "eval_loss": 0.6516734957695007,
+      "eval_matthews_correlation": 0.08300801435614485,
+      "eval_runtime": 4.7009,
+      "eval_samples_per_second": 221.87,
+      "eval_steps_per_second": 1.915,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.44e-05,
+      "loss": 0.5294,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6855225563049316,
+      "eval_loss": 0.6674203276634216,
+      "eval_matthews_correlation": 0.06864834703912359,
+      "eval_runtime": 4.7015,
+      "eval_samples_per_second": 221.845,
+      "eval_steps_per_second": 1.914,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "step": 469,
+      "total_flos": 8873620000473088.0,
+      "train_loss": 0.5836383193286497,
+      "train_runtime": 969.9748,
+      "train_samples_per_second": 440.785,
+      "train_steps_per_second": 3.454
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 8873620000473088.0,
+  "trial_name": null,
+  "trial_params": null
+}