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: 0.5871559633027523
+      value: 0.5561926605504587
 ---
 
 <!-- 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_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: 0.6983
-- Accuracy: 0.5872
+- Loss: 0.6814
+- Accuracy: 0.5562
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5561926605504587,
+    "eval_loss": 0.6813856959342957,
+    "eval_runtime": 1.6098,
+    "eval_samples": 872,
+    "eval_samples_per_second": 541.676,
+    "eval_steps_per_second": 4.348,
+    "train_loss": 0.5790761504876017,
+    "train_runtime": 2176.4824,
+    "train_samples": 67349,
+    "train_samples_per_second": 1547.198,
+    "train_steps_per_second": 12.107
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5561926605504587,
+    "eval_loss": 0.6813856959342957,
+    "eval_runtime": 1.6098,
+    "eval_samples": 872,
+    "eval_samples_per_second": 541.676,
+    "eval_steps_per_second": 4.348
+}

logs/events.out.tfevents.1674762349.gera.2823283.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49024cfdb265d67081f21ba7a56e1624da02c421eb7a539ac745c1036ae7d035
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.5790761504876017,
+    "train_runtime": 2176.4824,
+    "train_samples": 67349,
+    "train_samples_per_second": 1547.198,
+    "train_steps_per_second": 12.107
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6813856959342957,
+  "best_model_checkpoint": "mobilebert_add_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": 0.6662,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5561926605504587,
+      "eval_loss": 0.6813856959342957,
+      "eval_runtime": 1.5529,
+      "eval_samples_per_second": 561.531,
+      "eval_steps_per_second": 4.508,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5954,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5493119266055045,
+      "eval_loss": 0.7089729905128479,
+      "eval_runtime": 1.5587,
+      "eval_samples_per_second": 559.425,
+      "eval_steps_per_second": 4.491,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5689,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5596330275229358,
+      "eval_loss": 0.715036153793335,
+      "eval_runtime": 1.6372,
+      "eval_samples_per_second": 532.618,
+      "eval_steps_per_second": 4.276,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5546,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5538990825688074,
+      "eval_loss": 0.6892502307891846,
+      "eval_runtime": 1.5477,
+      "eval_samples_per_second": 563.399,
+      "eval_steps_per_second": 4.523,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5473,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5871559633027523,
+      "eval_loss": 0.7050522565841675,
+      "eval_runtime": 1.5988,
+      "eval_samples_per_second": 545.394,
+      "eval_steps_per_second": 4.378,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5421,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5871559633027523,
+      "eval_loss": 0.69826340675354,
+      "eval_runtime": 1.5749,
+      "eval_samples_per_second": 553.7,
+      "eval_steps_per_second": 4.445,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "step": 3162,
+      "total_flos": 1.0415609493848064e+16,
+      "train_loss": 0.5790761504876017,
+      "train_runtime": 2176.4824,
+      "train_samples_per_second": 1547.198,
+      "train_steps_per_second": 12.107
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 1.0415609493848064e+16,
+  "trial_name": null,
+  "trial_params": null
+}