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: 0.7901376146788991
+      value: 0.8004587155963303
 ---
 
 <!-- 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_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: 0.6028
-- Accuracy: 0.7901
+- Loss: 0.4330
+- Accuracy: 0.8005
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8004587155963303,
+    "eval_loss": 0.43304944038391113,
+    "eval_runtime": 1.9571,
+    "eval_samples": 872,
+    "eval_samples_per_second": 445.553,
+    "eval_steps_per_second": 3.577,
+    "train_loss": 0.2643498825468948,
+    "train_runtime": 2680.456,
+    "train_samples": 67349,
+    "train_samples_per_second": 1256.297,
+    "train_steps_per_second": 9.83
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8004587155963303,
+    "eval_loss": 0.43304944038391113,
+    "eval_runtime": 1.9571,
+    "eval_samples": 872,
+    "eval_samples_per_second": 445.553,
+    "eval_steps_per_second": 3.577
+}

logs/events.out.tfevents.1674684430.garda.227848.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc31fd9a5e2b0f658837f134459c0b1780771082ec81e4674b3e21f345e2af9
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.2643498825468948,
+    "train_runtime": 2680.456,
+    "train_samples": 67349,
+    "train_samples_per_second": 1256.297,
+    "train_steps_per_second": 9.83
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.43304944038391113,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_sst2_128/checkpoint-527",
+  "epoch": 6.0,
+  "global_step": 3162,
+  "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": 0.5124,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 0.43304944038391113,
+      "eval_runtime": 1.9289,
+      "eval_samples_per_second": 452.066,
+      "eval_steps_per_second": 3.629,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2842,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8027522935779816,
+      "eval_loss": 0.4711274206638336,
+      "eval_runtime": 1.9312,
+      "eval_samples_per_second": 451.532,
+      "eval_steps_per_second": 3.625,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2267,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.45929697155952454,
+      "eval_runtime": 1.9325,
+      "eval_samples_per_second": 451.224,
+      "eval_steps_per_second": 3.622,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2025,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7855504587155964,
+      "eval_loss": 0.7141198515892029,
+      "eval_runtime": 1.9331,
+      "eval_samples_per_second": 451.08,
+      "eval_steps_per_second": 3.621,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1849,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.4770691990852356,
+      "eval_runtime": 1.9365,
+      "eval_samples_per_second": 450.303,
+      "eval_steps_per_second": 3.615,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1754,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 0.6027570366859436,
+      "eval_runtime": 1.93,
+      "eval_samples_per_second": 451.81,
+      "eval_steps_per_second": 3.627,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "step": 3162,
+      "total_flos": 9631416648204288.0,
+      "train_loss": 0.2643498825468948,
+      "train_runtime": 2680.456,
+      "train_samples_per_second": 1256.297,
+      "train_steps_per_second": 9.83
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 9631416648204288.0,
+  "trial_name": null,
+  "trial_params": null
+}