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: 0.7855504587155964
+      value: 0.801605504587156
 ---
 
 <!-- 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_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: 0.5061
-- Accuracy: 0.7856
+- Loss: 0.4333
+- Accuracy: 0.8016
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.801605504587156,
+    "eval_loss": 0.43329915404319763,
+    "eval_runtime": 1.9851,
+    "eval_samples": 872,
+    "eval_samples_per_second": 439.276,
+    "eval_steps_per_second": 3.526,
+    "train_loss": 0.25946182453654976,
+    "train_runtime": 2837.2785,
+    "train_samples": 67349,
+    "train_samples_per_second": 1186.859,
+    "train_steps_per_second": 9.287
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.801605504587156,
+    "eval_loss": 0.43329915404319763,
+    "eval_runtime": 1.9851,
+    "eval_samples": 872,
+    "eval_samples_per_second": 439.276,
+    "eval_steps_per_second": 3.526
+}

logs/events.out.tfevents.1674663531.garda.1292005.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a47514cdd89ca56b913b6bcb3dc23b2adff573796184ee2067817c11c51fd22
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.25946182453654976,
+    "train_runtime": 2837.2785,
+    "train_samples": 67349,
+    "train_samples_per_second": 1186.859,
+    "train_steps_per_second": 9.287
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.43329915404319763,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_sst2_256/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": 0.4969,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.801605504587156,
+      "eval_loss": 0.43329915404319763,
+      "eval_runtime": 1.9711,
+      "eval_samples_per_second": 442.394,
+      "eval_steps_per_second": 3.551,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2781,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.783256880733945,
+      "eval_loss": 0.49986955523490906,
+      "eval_runtime": 1.9746,
+      "eval_samples_per_second": 441.601,
+      "eval_steps_per_second": 3.545,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2274,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7924311926605505,
+      "eval_loss": 0.4782297611236572,
+      "eval_runtime": 1.9765,
+      "eval_samples_per_second": 441.178,
+      "eval_steps_per_second": 3.542,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7935779816513762,
+      "eval_loss": 0.5582388043403625,
+      "eval_runtime": 1.9778,
+      "eval_samples_per_second": 440.902,
+      "eval_steps_per_second": 3.539,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1835,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7912844036697247,
+      "eval_loss": 0.4966583251953125,
+      "eval_runtime": 1.9757,
+      "eval_samples_per_second": 441.36,
+      "eval_steps_per_second": 3.543,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1708,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7855504587155964,
+      "eval_loss": 0.5061066746711731,
+      "eval_runtime": 1.9793,
+      "eval_samples_per_second": 440.565,
+      "eval_steps_per_second": 3.537,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "step": 3162,
+      "total_flos": 1.0644300396232704e+16,
+      "train_loss": 0.25946182453654976,
+      "train_runtime": 2837.2785,
+      "train_samples_per_second": 1186.859,
+      "train_steps_per_second": 9.287
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 1.0644300396232704e+16,
+  "trial_name": null,
+  "trial_params": null
+}