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 MRPC
       type: glue
       config: mrpc
       split: validation
@@ -32,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # add_BERT_no_pretrain_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6240
 - Accuracy: 0.6838

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 19.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6239899396896362,
+    "eval_runtime": 0.6442,
+    "eval_samples": 408,
+    "eval_samples_per_second": 633.308,
+    "eval_steps_per_second": 6.209,
+    "train_loss": 0.6928667667340453,
+    "train_runtime": 412.0299,
+    "train_samples": 3668,
+    "train_samples_per_second": 445.113,
+    "train_steps_per_second": 3.519
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 19.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6239899396896362,
+    "eval_runtime": 0.6442,
+    "eval_samples": 408,
+    "eval_samples_per_second": 633.308,
+    "eval_steps_per_second": 6.209
+}

logs/events.out.tfevents.1685337510.serv-9215.1440072.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5919689c282f3f84b6aab5c2e254324bb6bc05ec7ad970a2c4acf820ca184a
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.0,
+    "train_loss": 0.6928667667340453,
+    "train_runtime": 412.0299,
+    "train_samples": 3668,
+    "train_samples_per_second": 445.113,
+    "train_steps_per_second": 3.519
+}

trainer_state.json

@@ -0,0 +1,348 @@
+{
+  "best_metric": 0.6239899396896362,
+  "best_model_checkpoint": "add_BERT_no_pretrain_mrpc/checkpoint-406",
+  "epoch": 19.0,
+  "global_step": 551,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004910344827586207,
+      "loss": 1.154,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6856198906898499,
+      "eval_runtime": 0.6445,
+      "eval_samples_per_second": 633.061,
+      "eval_steps_per_second": 6.206,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0004810344827586207,
+      "loss": 0.6781,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6609018445014954,
+      "eval_runtime": 0.634,
+      "eval_samples_per_second": 643.583,
+      "eval_steps_per_second": 6.31,
+      "step": 58
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00047103448275862073,
+      "loss": 0.6458,
+      "step": 87
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.634788990020752,
+      "eval_runtime": 0.6427,
+      "eval_samples_per_second": 634.811,
+      "eval_steps_per_second": 6.224,
+      "step": 87
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0004610344827586207,
+      "loss": 0.6395,
+      "step": 116
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.31862745098039214,
+      "eval_combined_score": 0.16288515406162463,
+      "eval_f1": 0.0071428571428571435,
+      "eval_loss": 19.635393142700195,
+      "eval_runtime": 0.6439,
+      "eval_samples_per_second": 633.614,
+      "eval_steps_per_second": 6.212,
+      "step": 116
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0004510344827586207,
+      "loss": 1.1486,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6657487750053406,
+      "eval_runtime": 0.6436,
+      "eval_samples_per_second": 633.968,
+      "eval_steps_per_second": 6.215,
+      "step": 145
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044103448275862066,
+      "loss": 0.6446,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.627680778503418,
+      "eval_runtime": 0.6427,
+      "eval_samples_per_second": 634.78,
+      "eval_steps_per_second": 6.223,
+      "step": 174
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0004310344827586207,
+      "loss": 0.644,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6241939663887024,
+      "eval_runtime": 0.6436,
+      "eval_samples_per_second": 633.911,
+      "eval_steps_per_second": 6.215,
+      "step": 203
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0004210344827586207,
+      "loss": 0.6337,
+      "step": 232
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6242448687553406,
+      "eval_runtime": 0.6458,
+      "eval_samples_per_second": 631.822,
+      "eval_steps_per_second": 6.194,
+      "step": 232
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.0004110344827586207,
+      "loss": 0.6388,
+      "step": 261
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6252579092979431,
+      "eval_runtime": 0.6457,
+      "eval_samples_per_second": 631.91,
+      "eval_steps_per_second": 6.195,
+      "step": 261
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0004010344827586207,
+      "loss": 0.634,
+      "step": 290
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6241927742958069,
+      "eval_runtime": 0.6462,
+      "eval_samples_per_second": 631.361,
+      "eval_steps_per_second": 6.19,
+      "step": 290
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0003910344827586207,
+      "loss": 0.6346,
+      "step": 319
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6264073848724365,
+      "eval_runtime": 0.6465,
+      "eval_samples_per_second": 631.046,
+      "eval_steps_per_second": 6.187,
+      "step": 319
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.00038103448275862066,
+      "loss": 0.6338,
+      "step": 348
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6273019909858704,
+      "eval_runtime": 0.6464,
+      "eval_samples_per_second": 631.183,
+      "eval_steps_per_second": 6.188,
+      "step": 348
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 0.0003710344827586207,
+      "loss": 0.6343,
+      "step": 377
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6262201070785522,
+      "eval_runtime": 0.6462,
+      "eval_samples_per_second": 631.42,
+      "eval_steps_per_second": 6.19,
+      "step": 377
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 0.0003610344827586207,
+      "loss": 0.6339,
+      "step": 406
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6239899396896362,
+      "eval_runtime": 0.6481,
+      "eval_samples_per_second": 629.552,
+      "eval_steps_per_second": 6.172,
+      "step": 406
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.0003510344827586207,
+      "loss": 0.635,
+      "step": 435
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6244243383407593,
+      "eval_runtime": 0.6472,
+      "eval_samples_per_second": 630.443,
+      "eval_steps_per_second": 6.181,
+      "step": 435
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.0003410344827586207,
+      "loss": 0.6331,
+      "step": 464
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6240312457084656,
+      "eval_runtime": 0.6454,
+      "eval_samples_per_second": 632.149,
+      "eval_steps_per_second": 6.198,
+      "step": 464
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 0.0003310344827586207,
+      "loss": 0.6328,
+      "step": 493
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6266641020774841,
+      "eval_runtime": 0.646,
+      "eval_samples_per_second": 631.583,
+      "eval_steps_per_second": 6.192,
+      "step": 493
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00032103448275862067,
+      "loss": 0.6338,
+      "step": 522
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6256989240646362,
+      "eval_runtime": 0.6466,
+      "eval_samples_per_second": 630.959,
+      "eval_steps_per_second": 6.186,
+      "step": 522
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 0.0003110344827586207,
+      "loss": 0.6321,
+      "step": 551
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.623990535736084,
+      "eval_runtime": 0.6488,
+      "eval_samples_per_second": 628.807,
+      "eval_steps_per_second": 6.165,
+      "step": 551
+    },
+    {
+      "epoch": 19.0,
+      "step": 551,
+      "total_flos": 9953687707320320.0,
+      "train_loss": 0.6928667667340453,
+      "train_runtime": 412.0299,
+      "train_samples_per_second": 445.113,
+      "train_steps_per_second": 3.519
+    }
+  ],
+  "max_steps": 1450,
+  "num_train_epochs": 50,
+  "total_flos": 9953687707320320.0,
+  "trial_name": null,
+  "trial_params": null
+}