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. -->
 
 # add_BERT_no_pretrain_cola
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6277
+- Loss: 0.6181
 - Matthews Correlation: 0.0
 - Accuracy: 0.6913
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6180832982063293,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.6203,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 643.698,
+    "eval_steps_per_second": 5.554,
+    "train_loss": 0.6883503271162031,
+    "train_runtime": 605.2526,
+    "train_samples": 8551,
+    "train_samples_per_second": 706.399,
+    "train_steps_per_second": 5.535
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6180832982063293,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.6203,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 643.698,
+    "eval_steps_per_second": 5.554
+}

logs/events.out.tfevents.1685336900.serv-9215.1440072.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e962a0b3355f03131ba21ae7629a6fa890c9f0c284d0ca2c8a6d0e49fb078ca
+size 427

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 13.0,
+    "train_loss": 0.6883503271162031,
+    "train_runtime": 605.2526,
+    "train_samples": 8551,
+    "train_samples_per_second": 706.399,
+    "train_steps_per_second": 5.535
+}

trainer_state.json

@@ -0,0 +1,233 @@
+{
+  "best_metric": 0.6180832982063293,
+  "best_model_checkpoint": "add_BERT_no_pretrain_cola/checkpoint-536",
+  "epoch": 13.0,
+  "global_step": 871,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004902985074626866,
+      "loss": 0.9141,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6220115423202515,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6311,
+      "eval_samples_per_second": 639.436,
+      "eval_steps_per_second": 5.518,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00048029850746268655,
+      "loss": 0.6242,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6457749009132385,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6344,
+      "eval_samples_per_second": 638.155,
+      "eval_steps_per_second": 5.507,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0004702985074626866,
+      "loss": 0.62,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6181411147117615,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6358,
+      "eval_samples_per_second": 637.592,
+      "eval_steps_per_second": 5.502,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0004602985074626866,
+      "loss": 0.6121,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6184491515159607,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6381,
+      "eval_samples_per_second": 636.709,
+      "eval_steps_per_second": 5.494,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0004502985074626866,
+      "loss": 0.6096,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6188187599182129,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6398,
+      "eval_samples_per_second": 636.038,
+      "eval_steps_per_second": 5.488,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044029850746268656,
+      "loss": 0.6098,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6184147596359253,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.634,
+      "eval_samples_per_second": 638.322,
+      "eval_steps_per_second": 5.508,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0004302985074626866,
+      "loss": 0.6106,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.618549108505249,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6338,
+      "eval_samples_per_second": 638.4,
+      "eval_steps_per_second": 5.509,
+      "step": 469
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00042029850746268656,
+      "loss": 0.6117,
+      "step": 536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6180832982063293,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6419,
+      "eval_samples_per_second": 635.247,
+      "eval_steps_per_second": 5.482,
+      "step": 536
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.0004102985074626866,
+      "loss": 0.6088,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6262354254722595,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6351,
+      "eval_samples_per_second": 637.891,
+      "eval_steps_per_second": 5.504,
+      "step": 603
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0004002985074626866,
+      "loss": 0.6086,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6217857003211975,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6389,
+      "eval_samples_per_second": 636.396,
+      "eval_steps_per_second": 5.491,
+      "step": 670
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0003902985074626866,
+      "loss": 0.6087,
+      "step": 737
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6183873414993286,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6414,
+      "eval_samples_per_second": 635.439,
+      "eval_steps_per_second": 5.483,
+      "step": 737
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.00038044776119402986,
+      "loss": 0.7274,
+      "step": 804
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6210523247718811,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6384,
+      "eval_samples_per_second": 636.613,
+      "eval_steps_per_second": 5.493,
+      "step": 804
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 0.00037059701492537313,
+      "loss": 1.183,
+      "step": 871
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6277084946632385,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.6383,
+      "eval_samples_per_second": 636.652,
+      "eval_steps_per_second": 5.494,
+      "step": 871
+    },
+    {
+      "epoch": 13.0,
+      "step": 871,
+      "total_flos": 1.5876741075566592e+16,
+      "train_loss": 0.6883503271162031,
+      "train_runtime": 605.2526,
+      "train_samples_per_second": 706.399,
+      "train_steps_per_second": 5.535
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 1.5876741075566592e+16,
+  "trial_name": null,
+  "trial_params": null
+}