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: 0.7981651376146789
+      value: 0.7821100917431193
 ---
 
 <!-- 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_sa_GLUE_Experiment_logit_kd_sst2
 
-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: 0.9633
-- Accuracy: 0.7982
+- Loss: 0.8241
+- Accuracy: 0.7821
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7821100917431193,
+    "eval_loss": 0.8241134285926819,
+    "eval_runtime": 2.0435,
+    "eval_samples": 872,
+    "eval_samples_per_second": 426.713,
+    "eval_steps_per_second": 3.425,
+    "train_loss": 0.45344161263453214,
+    "train_runtime": 2923.0123,
+    "train_samples": 67349,
+    "train_samples_per_second": 1152.048,
+    "train_steps_per_second": 9.015
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7821100917431193,
+    "eval_loss": 0.8241134285926819,
+    "eval_runtime": 2.0435,
+    "eval_samples": 872,
+    "eval_samples_per_second": 426.713,
+    "eval_steps_per_second": 3.425
+}

logs/events.out.tfevents.1675075516.serv-3330.1319687.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b69ef77ef04b01eddffd7e883add54fab8fa8332d0724a8db7b37269af4382
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.45344161263453214,
+    "train_runtime": 2923.0123,
+    "train_samples": 67349,
+    "train_samples_per_second": 1152.048,
+    "train_steps_per_second": 9.015
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.8241134285926819,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_sst2/checkpoint-1054",
+  "epoch": 7.0,
+  "global_step": 3689,
+  "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": 1.0702,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7740825688073395,
+      "eval_loss": 0.8403842449188232,
+      "eval_runtime": 2.1461,
+      "eval_samples_per_second": 406.316,
+      "eval_steps_per_second": 3.262,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5148,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7821100917431193,
+      "eval_loss": 0.8241134285926819,
+      "eval_runtime": 2.0443,
+      "eval_samples_per_second": 426.558,
+      "eval_steps_per_second": 3.424,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3924,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7855504587155964,
+      "eval_loss": 1.0814857482910156,
+      "eval_runtime": 2.0476,
+      "eval_samples_per_second": 425.864,
+      "eval_steps_per_second": 3.419,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3413,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7809633027522935,
+      "eval_loss": 0.9158650040626526,
+      "eval_runtime": 2.0515,
+      "eval_samples_per_second": 425.049,
+      "eval_steps_per_second": 3.412,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3068,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7947247706422018,
+      "eval_loss": 0.883631706237793,
+      "eval_runtime": 2.0338,
+      "eval_samples_per_second": 428.759,
+      "eval_steps_per_second": 3.442,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2837,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.9832125306129456,
+      "eval_runtime": 2.0645,
+      "eval_samples_per_second": 422.377,
+      "eval_steps_per_second": 3.391,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2648,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.963298499584198,
+      "eval_runtime": 2.0555,
+      "eval_samples_per_second": 424.233,
+      "eval_steps_per_second": 3.406,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "step": 3689,
+      "total_flos": 1.4781746813861888e+16,
+      "train_loss": 0.45344161263453214,
+      "train_runtime": 2923.0123,
+      "train_samples_per_second": 1152.048,
+      "train_steps_per_second": 9.015
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 1.4781746813861888e+16,
+  "trial_name": null,
+  "trial_params": null
+}