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
 
-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: 0.5660
+- Loss: 0.5529
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.5529410243034363,
+    "eval_runtime": 0.9959,
+    "eval_samples": 408,
+    "eval_samples_per_second": 409.698,
+    "eval_steps_per_second": 4.017,
+    "train_loss": 0.5956195451290671,
+    "train_runtime": 327.2529,
+    "train_samples": 3668,
+    "train_samples_per_second": 560.423,
+    "train_steps_per_second": 4.431
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.5529410243034363,
+    "eval_runtime": 0.9959,
+    "eval_samples": 408,
+    "eval_samples_per_second": 409.698,
+    "eval_steps_per_second": 4.017
+}

logs/events.out.tfevents.1674949553.serv-3332.3626077.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d223e53a2c3b12b965494c35922f09acfda7615410b299c098c8ec2c2400370
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "train_loss": 0.5956195451290671,
+    "train_runtime": 327.2529,
+    "train_samples": 3668,
+    "train_samples_per_second": 560.423,
+    "train_steps_per_second": 4.431
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.5529410243034363,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_mrpc/checkpoint-116",
+  "epoch": 9.0,
+  "global_step": 261,
+  "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": 0.6239,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.555836021900177,
+      "eval_runtime": 0.9841,
+      "eval_samples_per_second": 414.573,
+      "eval_steps_per_second": 4.064,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6109,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5552574396133423,
+      "eval_runtime": 0.9796,
+      "eval_samples_per_second": 416.498,
+      "eval_steps_per_second": 4.083,
+      "step": 58
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6095,
+      "step": 87
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5543215274810791,
+      "eval_runtime": 0.9675,
+      "eval_samples_per_second": 421.725,
+      "eval_steps_per_second": 4.135,
+      "step": 87
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6072,
+      "step": 116
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5529410243034363,
+      "eval_runtime": 0.9661,
+      "eval_samples_per_second": 422.334,
+      "eval_steps_per_second": 4.141,
+      "step": 116
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5996,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5556313395500183,
+      "eval_runtime": 0.9685,
+      "eval_samples_per_second": 421.291,
+      "eval_steps_per_second": 4.13,
+      "step": 145
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5884,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5737412571907043,
+      "eval_runtime": 0.9732,
+      "eval_samples_per_second": 419.24,
+      "eval_steps_per_second": 4.11,
+      "step": 174
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.59,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5704464912414551,
+      "eval_runtime": 0.9691,
+      "eval_samples_per_second": 421.002,
+      "eval_steps_per_second": 4.127,
+      "step": 203
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5715,
+      "step": 232
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6813725490196079,
+      "eval_combined_score": 0.7459340879208827,
+      "eval_f1": 0.8104956268221574,
+      "eval_loss": 0.5706341862678528,
+      "eval_runtime": 0.9664,
+      "eval_samples_per_second": 422.182,
+      "eval_steps_per_second": 4.139,
+      "step": 232
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5595,
+      "step": 261
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.5660258531570435,
+      "eval_runtime": 0.9731,
+      "eval_samples_per_second": 419.288,
+      "eval_steps_per_second": 4.111,
+      "step": 261
+    },
+    {
+      "epoch": 9.0,
+      "step": 261,
+      "total_flos": 976507027587072.0,
+      "train_loss": 0.5956195451290671,
+      "train_runtime": 327.2529,
+      "train_samples_per_second": 560.423,
+      "train_steps_per_second": 4.431
+    }
+  ],
+  "max_steps": 1450,
+  "num_train_epochs": 50,
+  "total_flos": 976507027587072.0,
+  "trial_name": null,
+  "trial_params": null
+}