End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE SST2
       type: glue
       config: sst2
       split: validation
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.4908256880733945
+      value: 0.7075688073394495
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_logit_kd_sst2_256
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Accuracy: 0.4908
+- Loss: 1.2641
+- Accuracy: 0.7076
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.7075688073394495,
+    "eval_loss": 1.2641148567199707,
+    "eval_runtime": 1.9376,
+    "eval_samples": 872,
+    "eval_samples_per_second": 450.044,
+    "eval_steps_per_second": 3.613,
+    "train_loss": 0.7754758815426487,
+    "train_runtime": 4341.2127,
+    "train_samples": 67349,
+    "train_samples_per_second": 775.693,
+    "train_steps_per_second": 6.07
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.7075688073394495,
+    "eval_loss": 1.2641148567199707,
+    "eval_runtime": 1.9376,
+    "eval_samples": 872,
+    "eval_samples_per_second": 450.044,
+    "eval_steps_per_second": 3.613
+}

logs/events.out.tfevents.1674981224.serv-3328.2501856.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056ad0142e525f8136441b00625643130e853205a7331b994ffced2d4bf8365a
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 0.7754758815426487,
+    "train_runtime": 4341.2127,
+    "train_samples": 67349,
+    "train_samples_per_second": 775.693,
+    "train_steps_per_second": 6.07
+}

trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_metric": 1.2641148567199707,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_sst2_256/checkpoint-3162",
+  "epoch": 11.0,
+  "global_step": 5797,
+  "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": 1.5438,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5814220183486238,
+      "eval_loss": 1.4011807441711426,
+      "eval_runtime": 1.9244,
+      "eval_samples_per_second": 453.117,
+      "eval_steps_per_second": 3.637,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 1.364,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5412844036697247,
+      "eval_loss": 1.5474371910095215,
+      "eval_runtime": 1.9252,
+      "eval_samples_per_second": 452.943,
+      "eval_steps_per_second": 3.636,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 1.2907,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5642201834862385,
+      "eval_loss": 1.5137693881988525,
+      "eval_runtime": 1.9325,
+      "eval_samples_per_second": 451.237,
+      "eval_steps_per_second": 3.622,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.257,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5665137614678899,
+      "eval_loss": 1.4408754110336304,
+      "eval_runtime": 1.9137,
+      "eval_samples_per_second": 455.672,
+      "eval_steps_per_second": 3.658,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 1.2417,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5928899082568807,
+      "eval_loss": 1.4473283290863037,
+      "eval_runtime": 1.9221,
+      "eval_samples_per_second": 453.677,
+      "eval_steps_per_second": 3.642,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.2056,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7075688073394495,
+      "eval_loss": 1.2641148567199707,
+      "eval_runtime": 2.067,
+      "eval_samples_per_second": 421.868,
+      "eval_steps_per_second": 3.387,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6274,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4908256880733945,
+      "eval_loss": NaN,
+      "eval_runtime": 1.9207,
+      "eval_samples_per_second": 453.996,
+      "eval_steps_per_second": 3.644,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4908256880733945,
+      "eval_loss": NaN,
+      "eval_runtime": 1.9183,
+      "eval_samples_per_second": 454.57,
+      "eval_steps_per_second": 3.649,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.0,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4908256880733945,
+      "eval_loss": NaN,
+      "eval_runtime": 1.917,
+      "eval_samples_per_second": 454.883,
+      "eval_steps_per_second": 3.652,
+      "step": 4743
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 5270
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.4908256880733945,
+      "eval_loss": NaN,
+      "eval_runtime": 1.9509,
+      "eval_samples_per_second": 446.978,
+      "eval_steps_per_second": 3.588,
+      "step": 5270
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.0,
+      "step": 5797
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.4908256880733945,
+      "eval_loss": NaN,
+      "eval_runtime": 1.9254,
+      "eval_samples_per_second": 452.883,
+      "eval_steps_per_second": 3.636,
+      "step": 5797
+    },
+    {
+      "epoch": 11.0,
+      "step": 5797,
+      "total_flos": 1.9095284072054784e+16,
+      "train_loss": 0.7754758815426487,
+      "train_runtime": 4341.2127,
+      "train_samples_per_second": 775.693,
+      "train_steps_per_second": 6.07
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 1.9095284072054784e+16,
+  "trial_name": null,
+  "trial_params": null
+}