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: 0.7947247706422018
+      value: 0.7981651376146789
 ---
 
 <!-- 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_sst2_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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5943
-- Accuracy: 0.7947
+- Loss: 0.4543
+- Accuracy: 0.7982
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.7981651376146789,
+    "eval_loss": 0.4542507827281952,
+    "eval_runtime": 1.5528,
+    "eval_samples": 872,
+    "eval_samples_per_second": 561.568,
+    "eval_steps_per_second": 4.508,
+    "train_loss": 0.3588200110110356,
+    "train_runtime": 4204.4171,
+    "train_samples": 67349,
+    "train_samples_per_second": 800.931,
+    "train_steps_per_second": 6.267
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.7981651376146789,
+    "eval_loss": 0.4542507827281952,
+    "eval_runtime": 1.5528,
+    "eval_samples": 872,
+    "eval_samples_per_second": 561.568,
+    "eval_steps_per_second": 4.508
+}

logs/events.out.tfevents.1674763356.gera.2822633.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c9559427833f5c5e6d2925ad3ada38c620f7df53286605212946645b4ff4d2
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "train_loss": 0.3588200110110356,
+    "train_runtime": 4204.4171,
+    "train_samples": 67349,
+    "train_samples_per_second": 800.931,
+    "train_steps_per_second": 6.267
+}

trainer_state.json

@@ -0,0 +1,205 @@
+{
+  "best_metric": 0.4542507827281952,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_sst2_128/checkpoint-3689",
+  "epoch": 12.0,
+  "global_step": 6324,
+  "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": 0.6677,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5756880733944955,
+      "eval_loss": 0.677055299282074,
+      "eval_runtime": 1.7061,
+      "eval_samples_per_second": 511.104,
+      "eval_steps_per_second": 4.103,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5966,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5424311926605505,
+      "eval_loss": 0.7135030627250671,
+      "eval_runtime": 1.5325,
+      "eval_samples_per_second": 569.001,
+      "eval_steps_per_second": 4.568,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5714,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.555045871559633,
+      "eval_loss": 0.7271105647087097,
+      "eval_runtime": 1.5765,
+      "eval_samples_per_second": 553.131,
+      "eval_steps_per_second": 4.44,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5573,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5619266055045872,
+      "eval_loss": 0.6891608238220215,
+      "eval_runtime": 1.5223,
+      "eval_samples_per_second": 572.828,
+      "eval_steps_per_second": 4.598,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.501,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7798165137614679,
+      "eval_loss": 0.45462021231651306,
+      "eval_runtime": 1.5903,
+      "eval_samples_per_second": 548.34,
+      "eval_steps_per_second": 4.402,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2856,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 0.46127501130104065,
+      "eval_runtime": 1.5321,
+      "eval_samples_per_second": 569.164,
+      "eval_steps_per_second": 4.569,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2288,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.4542507827281952,
+      "eval_runtime": 1.5229,
+      "eval_samples_per_second": 572.609,
+      "eval_steps_per_second": 4.597,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2027,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.4661611020565033,
+      "eval_runtime": 1.5648,
+      "eval_samples_per_second": 557.264,
+      "eval_steps_per_second": 4.473,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1883,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8038990825688074,
+      "eval_loss": 0.516830563545227,
+      "eval_runtime": 1.5219,
+      "eval_samples_per_second": 572.954,
+      "eval_steps_per_second": 4.599,
+      "step": 4743
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.1779,
+      "step": 5270
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7855504587155964,
+      "eval_loss": 0.5748016834259033,
+      "eval_runtime": 1.5164,
+      "eval_samples_per_second": 575.045,
+      "eval_steps_per_second": 4.616,
+      "step": 5270
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.1691,
+      "step": 5797
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8027522935779816,
+      "eval_loss": 0.5195825099945068,
+      "eval_runtime": 1.5266,
+      "eval_samples_per_second": 571.211,
+      "eval_steps_per_second": 4.585,
+      "step": 5797
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 3.8e-05,
+      "loss": 0.1596,
+      "step": 6324
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7947247706422018,
+      "eval_loss": 0.5943012237548828,
+      "eval_runtime": 1.5592,
+      "eval_samples_per_second": 559.25,
+      "eval_steps_per_second": 4.489,
+      "step": 6324
+    },
+    {
+      "epoch": 12.0,
+      "step": 6324,
+      "total_flos": 1.9293579893538816e+16,
+      "train_loss": 0.3588200110110356,
+      "train_runtime": 4204.4171,
+      "train_samples_per_second": 800.931,
+      "train_steps_per_second": 6.267
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 1.9293579893538816e+16,
+  "trial_name": null,
+  "trial_params": null
+}