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 COLA
       type: glue
       config: cola
       split: validation
@@ -28,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6212
+- Loss: 0.6180
 - Matthews Correlation: 0.0
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.6179953217506409,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.322,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 788.959,
+    "eval_steps_per_second": 3.782,
+    "train_loss": 0.6118226051330566,
+    "train_runtime": 236.3939,
+    "train_samples": 8551,
+    "train_samples_per_second": 1808.634,
+    "train_steps_per_second": 7.191
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.6179953217506409,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.322,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 788.959,
+    "eval_steps_per_second": 3.782
+}

logs/events.out.tfevents.1677680649.serv-9220.1178704.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b00afa87d09d13b7190cec3524200ea2a95537f0ffd56a9f3aca3c347b0a865
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.6118226051330566,
+    "train_runtime": 236.3939,
+    "train_samples": 8551,
+    "train_samples_per_second": 1808.634,
+    "train_steps_per_second": 7.191
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6179953217506409,
+  "best_model_checkpoint": "hBERTv1_cola/checkpoint-34",
+  "epoch": 6.0,
+  "global_step": 204,
+  "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": 0.6212,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6179953217506409,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3043,
+      "eval_samples_per_second": 799.657,
+      "eval_steps_per_second": 3.833,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6118,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6210665702819824,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3016,
+      "eval_samples_per_second": 801.321,
+      "eval_steps_per_second": 3.841,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6088,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6251837611198425,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3047,
+      "eval_samples_per_second": 799.413,
+      "eval_steps_per_second": 3.832,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6103,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6181675791740417,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3088,
+      "eval_samples_per_second": 796.936,
+      "eval_steps_per_second": 3.82,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6107,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6210399270057678,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3101,
+      "eval_samples_per_second": 796.146,
+      "eval_steps_per_second": 3.817,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6081,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6212285757064819,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3069,
+      "eval_samples_per_second": 798.045,
+      "eval_steps_per_second": 3.826,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "step": 204,
+      "total_flos": 6480513749483520.0,
+      "train_loss": 0.6118226051330566,
+      "train_runtime": 236.3939,
+      "train_samples_per_second": 1808.634,
+      "train_steps_per_second": 7.191
+    }
+  ],
+  "max_steps": 1700,
+  "num_train_epochs": 50,
+  "total_flos": 6480513749483520.0,
+  "trial_name": null,
+  "trial_params": null
+}