End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -14,7 +16,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE MRPC
       type: glue
       config: mrpc
       split: validation
@@ -33,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_logit_kd_mrpc_128
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the glue 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: 0.5714
+- Loss: 0.5534
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.5534398555755615,
+    "eval_runtime": 0.715,
+    "eval_samples": 408,
+    "eval_samples_per_second": 570.639,
+    "eval_steps_per_second": 5.594,
+    "train_loss": 0.5968392590370298,
+    "train_runtime": 234.3942,
+    "train_samples": 3668,
+    "train_samples_per_second": 782.443,
+    "train_steps_per_second": 6.186
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.5534398555755615,
+    "eval_runtime": 0.715,
+    "eval_samples": 408,
+    "eval_samples_per_second": 570.639,
+    "eval_steps_per_second": 5.594
+}

logs/events.out.tfevents.1674948097.serv-3334.518319.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4524d0cb4c0c27a9c474668a04829d678814a93b5c072659ac1121a28dc26bfe
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 0.5968392590370298,
+    "train_runtime": 234.3942,
+    "train_samples": 3668,
+    "train_samples_per_second": 782.443,
+    "train_steps_per_second": 6.186
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_metric": 0.5534398555755615,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_mrpc_128/checkpoint-174",
+  "epoch": 11.0,
+  "global_step": 319,
+  "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": 0.6399,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.55616295337677,
+      "eval_runtime": 0.6917,
+      "eval_samples_per_second": 589.862,
+      "eval_steps_per_second": 5.783,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6101,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5559439659118652,
+      "eval_runtime": 0.696,
+      "eval_samples_per_second": 586.243,
+      "eval_steps_per_second": 5.747,
+      "step": 58
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6111,
+      "step": 87
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5557237863540649,
+      "eval_runtime": 0.6873,
+      "eval_samples_per_second": 593.59,
+      "eval_steps_per_second": 5.82,
+      "step": 87
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6104,
+      "step": 116
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5572218298912048,
+      "eval_runtime": 0.6905,
+      "eval_samples_per_second": 590.849,
+      "eval_steps_per_second": 5.793,
+      "step": 116
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6086,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5549847483634949,
+      "eval_runtime": 0.6877,
+      "eval_samples_per_second": 593.317,
+      "eval_steps_per_second": 5.817,
+      "step": 145
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6058,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5534398555755615,
+      "eval_runtime": 0.6886,
+      "eval_samples_per_second": 592.53,
+      "eval_steps_per_second": 5.809,
+      "step": 174
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6036,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5745493769645691,
+      "eval_runtime": 0.6903,
+      "eval_samples_per_second": 591.038,
+      "eval_steps_per_second": 5.794,
+      "step": 203
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5969,
+      "step": 232
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5594767928123474,
+      "eval_runtime": 0.6934,
+      "eval_samples_per_second": 588.422,
+      "eval_steps_per_second": 5.769,
+      "step": 232
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5735,
+      "step": 261
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5699104070663452,
+      "eval_runtime": 0.6946,
+      "eval_samples_per_second": 587.423,
+      "eval_steps_per_second": 5.759,
+      "step": 261
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.5597,
+      "step": 290
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5608029961585999,
+      "eval_runtime": 0.6978,
+      "eval_samples_per_second": 584.717,
+      "eval_steps_per_second": 5.733,
+      "step": 290
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.5456,
+      "step": 319
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5714082717895508,
+      "eval_runtime": 0.7001,
+      "eval_samples_per_second": 582.765,
+      "eval_steps_per_second": 5.713,
+      "step": 319
+    },
+    {
+      "epoch": 11.0,
+      "step": 319,
+      "total_flos": 963213206224896.0,
+      "train_loss": 0.5968392590370298,
+      "train_runtime": 234.3942,
+      "train_samples_per_second": 782.443,
+      "train_steps_per_second": 6.186
+    }
+  ],
+  "max_steps": 1450,
+  "num_train_epochs": 50,
+  "total_flos": 963213206224896.0,
+  "trial_name": null,
+  "trial_params": null
+}