End of training

README.md

@@ -1,11 +1,26 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 model-index:
 - name: hBERTv2_data_aug_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,9 +28,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_data_aug_cola
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on an unknown dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6203
+- Loss: 0.6181
 - Matthews Correlation: 0.0
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 8.0,
+    "eval_loss": 0.6180860996246338,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.2367,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 843.385,
+    "eval_steps_per_second": 4.043,
+    "train_loss": 0.6065069872462107,
+    "train_runtime": 5819.7121,
+    "train_samples": 213609,
+    "train_samples_per_second": 1835.22,
+    "train_steps_per_second": 7.174
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_loss": 0.6180860996246338,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.2367,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 843.385,
+    "eval_steps_per_second": 4.043
+}

logs/events.out.tfevents.1677666922.kyoto.1079667.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbab5a720b44f94c5991e05277762c512b7af89badd467cfcb8b171af64cc396
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 0.6065069872462107,
+    "train_runtime": 5819.7121,
+    "train_samples": 213609,
+    "train_samples_per_second": 1835.22,
+    "train_steps_per_second": 7.174
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": 0.6180860996246338,
+  "best_model_checkpoint": "hBERTv2_data_aug_cola/checkpoint-2505",
+  "epoch": 8.0,
+  "global_step": 6680,
+  "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": 0.6082,
+      "step": 835
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6237233281135559,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.226,
+      "eval_samples_per_second": 850.767,
+      "eval_steps_per_second": 4.078,
+      "step": 835
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8001197604790424e-05,
+      "loss": 0.6068,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6185952425003052,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2301,
+      "eval_samples_per_second": 847.869,
+      "eval_steps_per_second": 4.065,
+      "step": 1670
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.700119760479042e-05,
+      "loss": 0.6064,
+      "step": 2505
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6180860996246338,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2241,
+      "eval_samples_per_second": 852.069,
+      "eval_steps_per_second": 4.085,
+      "step": 2505
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.6001197604790416e-05,
+      "loss": 0.6062,
+      "step": 3340
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6217709183692932,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2229,
+      "eval_samples_per_second": 852.888,
+      "eval_steps_per_second": 4.089,
+      "step": 3340
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5001197604790425e-05,
+      "loss": 0.6061,
+      "step": 4175
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6211623549461365,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2257,
+      "eval_samples_per_second": 850.945,
+      "eval_steps_per_second": 4.079,
+      "step": 4175
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.400119760479042e-05,
+      "loss": 0.6062,
+      "step": 5010
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6185929179191589,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2236,
+      "eval_samples_per_second": 852.395,
+      "eval_steps_per_second": 4.086,
+      "step": 5010
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3001197604790424e-05,
+      "loss": 0.606,
+      "step": 5845
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.618870735168457,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2256,
+      "eval_samples_per_second": 851.023,
+      "eval_steps_per_second": 4.08,
+      "step": 5845
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.200119760479042e-05,
+      "loss": 0.6062,
+      "step": 6680
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.6202924847602844,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2276,
+      "eval_samples_per_second": 849.649,
+      "eval_steps_per_second": 4.073,
+      "step": 6680
+    },
+    {
+      "epoch": 8.0,
+      "step": 6680,
+      "total_flos": 2.1284586608656384e+17,
+      "train_loss": 0.6065069872462107,
+      "train_runtime": 5819.7121,
+      "train_samples_per_second": 1835.22,
+      "train_steps_per_second": 7.174
+    }
+  ],
+  "max_steps": 41750,
+  "num_train_epochs": 50,
+  "total_flos": 2.1284586608656384e+17,
+  "trial_name": null,
+  "trial_params": null
+}