End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: mobilebert_sa_GLUE_Experiment_data_aug_mrpc_256
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 1.0
+    - name: F1
+      type: f1
+      value: 1.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_data_aug_mrpc_256
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0000
 - Accuracy: 1.0

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 24.0,
+    "eval_accuracy": 1.0,
+    "eval_combined_score": 1.0,
+    "eval_f1": 1.0,
+    "eval_loss": 2.921795860810761e-10,
+    "eval_runtime": 0.6557,
+    "eval_samples": 408,
+    "eval_samples_per_second": 622.237,
+    "eval_steps_per_second": 6.1,
+    "train_loss": 0.014149450120652881,
+    "train_runtime": 29037.589,
+    "train_samples": 250736,
+    "train_samples_per_second": 431.744,
+    "train_steps_per_second": 3.373
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 24.0,
+    "eval_accuracy": 1.0,
+    "eval_combined_score": 1.0,
+    "eval_f1": 1.0,
+    "eval_loss": 2.921795860810761e-10,
+    "eval_runtime": 0.6557,
+    "eval_samples": 408,
+    "eval_samples_per_second": 622.237,
+    "eval_steps_per_second": 6.1
+}

logs/events.out.tfevents.1675325941.serv-3332.749437.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d03c0969d66dc4fa8702c3f40a99277af486d8f15986efd05b4133dcced8ad
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 24.0,
+    "train_loss": 0.014149450120652881,
+    "train_runtime": 29037.589,
+    "train_samples": 250736,
+    "train_samples_per_second": 431.744,
+    "train_steps_per_second": 3.373
+}

trainer_state.json

@@ -0,0 +1,433 @@
+{
+  "best_metric": 2.921795860810761e-10,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_mrpc_256/checkpoint-37221",
+  "epoch": 24.0,
+  "global_step": 47016,
+  "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": 0.1854,
+      "step": 1959
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9975490196078431,
+      "eval_combined_score": 0.9978800554210951,
+      "eval_f1": 0.998211091234347,
+      "eval_loss": 0.019866587594151497,
+      "eval_runtime": 0.6404,
+      "eval_samples_per_second": 637.054,
+      "eval_steps_per_second": 6.246,
+      "step": 1959
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.04,
+      "step": 3918
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9975490196078431,
+      "eval_combined_score": 0.9978800554210951,
+      "eval_f1": 0.998211091234347,
+      "eval_loss": 0.00498608173802495,
+      "eval_runtime": 0.6362,
+      "eval_samples_per_second": 641.306,
+      "eval_steps_per_second": 6.287,
+      "step": 3918
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.0253,
+      "step": 5877
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.001509999856352806,
+      "eval_runtime": 0.6354,
+      "eval_samples_per_second": 642.069,
+      "eval_steps_per_second": 6.295,
+      "step": 5877
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.0175,
+      "step": 7836
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00034327851608395576,
+      "eval_runtime": 0.6381,
+      "eval_samples_per_second": 639.41,
+      "eval_steps_per_second": 6.269,
+      "step": 7836
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0134,
+      "step": 9795
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00011310506670270115,
+      "eval_runtime": 0.6339,
+      "eval_samples_per_second": 643.664,
+      "eval_steps_per_second": 6.31,
+      "step": 9795
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0107,
+      "step": 11754
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 7.095432374626398e-05,
+      "eval_runtime": 0.6345,
+      "eval_samples_per_second": 642.999,
+      "eval_steps_per_second": 6.304,
+      "step": 11754
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0081,
+      "step": 13713
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.001246878644451499,
+      "eval_runtime": 0.6382,
+      "eval_samples_per_second": 639.266,
+      "eval_steps_per_second": 6.267,
+      "step": 13713
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0062,
+      "step": 15672
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 1.0932646546280012e-05,
+      "eval_runtime": 0.6377,
+      "eval_samples_per_second": 639.798,
+      "eval_steps_per_second": 6.273,
+      "step": 15672
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.0061,
+      "step": 17631
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 5.195760240894742e-05,
+      "eval_runtime": 0.6362,
+      "eval_samples_per_second": 641.305,
+      "eval_steps_per_second": 6.287,
+      "step": 17631
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0044,
+      "step": 19590
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00019376023556105793,
+      "eval_runtime": 0.6566,
+      "eval_samples_per_second": 621.369,
+      "eval_steps_per_second": 6.092,
+      "step": 19590
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.0041,
+      "step": 21549
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 8.64493540575495e-06,
+      "eval_runtime": 0.6367,
+      "eval_samples_per_second": 640.813,
+      "eval_steps_per_second": 6.282,
+      "step": 21549
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 3.8e-05,
+      "loss": 0.0034,
+      "step": 23508
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 4.149795859120786e-05,
+      "eval_runtime": 0.6366,
+      "eval_samples_per_second": 640.909,
+      "eval_steps_per_second": 6.283,
+      "step": 23508
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 3.7e-05,
+      "loss": 0.0029,
+      "step": 25467
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 4.850913683185354e-06,
+      "eval_runtime": 0.6378,
+      "eval_samples_per_second": 639.729,
+      "eval_steps_per_second": 6.272,
+      "step": 25467
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.0016,
+      "step": 27426
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 1.1147426448587794e-06,
+      "eval_runtime": 0.6348,
+      "eval_samples_per_second": 642.754,
+      "eval_steps_per_second": 6.302,
+      "step": 27426
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 3.5e-05,
+      "loss": 0.0019,
+      "step": 29385
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9975490196078431,
+      "eval_combined_score": 0.997876843735699,
+      "eval_f1": 0.9982046678635548,
+      "eval_loss": 0.01404921431094408,
+      "eval_runtime": 0.6381,
+      "eval_samples_per_second": 639.38,
+      "eval_steps_per_second": 6.268,
+      "step": 29385
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.0018,
+      "step": 31344
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 7.099370122887194e-05,
+      "eval_runtime": 0.6372,
+      "eval_samples_per_second": 640.262,
+      "eval_steps_per_second": 6.277,
+      "step": 31344
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 3.3e-05,
+      "loss": 0.0012,
+      "step": 33303
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 2.2301992430584505e-06,
+      "eval_runtime": 0.635,
+      "eval_samples_per_second": 642.495,
+      "eval_steps_per_second": 6.299,
+      "step": 33303
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.0013,
+      "step": 35262
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 2.717222002956987e-07,
+      "eval_runtime": 0.6365,
+      "eval_samples_per_second": 640.956,
+      "eval_steps_per_second": 6.284,
+      "step": 35262
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 3.1e-05,
+      "loss": 0.0008,
+      "step": 37221
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 2.921795860810761e-10,
+      "eval_runtime": 0.6349,
+      "eval_samples_per_second": 642.639,
+      "eval_steps_per_second": 6.3,
+      "step": 37221
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 3e-05,
+      "loss": 0.0011,
+      "step": 39180
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 3.3395747323083924e-07,
+      "eval_runtime": 0.6371,
+      "eval_samples_per_second": 640.365,
+      "eval_steps_per_second": 6.278,
+      "step": 39180
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.9e-05,
+      "loss": 0.0005,
+      "step": 41139
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0006938398582860827,
+      "eval_runtime": 0.6326,
+      "eval_samples_per_second": 644.981,
+      "eval_steps_per_second": 6.323,
+      "step": 41139
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.0009,
+      "step": 43098
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 1.6654043122343865e-07,
+      "eval_runtime": 0.6367,
+      "eval_samples_per_second": 640.83,
+      "eval_steps_per_second": 6.283,
+      "step": 43098
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.0004,
+      "step": 45057
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 2.828248284458823e-07,
+      "eval_runtime": 0.6363,
+      "eval_samples_per_second": 641.164,
+      "eval_steps_per_second": 6.286,
+      "step": 45057
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.0004,
+      "step": 47016
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 1.0,
+      "eval_combined_score": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 1.7530776830199102e-09,
+      "eval_runtime": 0.6365,
+      "eval_samples_per_second": 640.972,
+      "eval_steps_per_second": 6.284,
+      "step": 47016
+    },
+    {
+      "epoch": 24.0,
+      "step": 47016,
+      "total_flos": 1.5851218903498752e+17,
+      "train_loss": 0.014149450120652881,
+      "train_runtime": 29037.589,
+      "train_samples_per_second": 431.744,
+      "train_steps_per_second": 3.373
+    }
+  ],
+  "max_steps": 97950,
+  "num_train_epochs": 50,
+  "total_flos": 1.5851218903498752e+17,
+  "trial_name": null,
+  "trial_params": null
+}