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 WNLI
       type: glue
       config: wnli
       split: validation
@@ -29,9 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_wnli
 
-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 WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6901
+- Loss: 0.6895
 - Accuracy: 0.5634
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6894944310188293,
+    "eval_runtime": 0.1376,
+    "eval_samples": 71,
+    "eval_samples_per_second": 516.142,
+    "eval_steps_per_second": 7.27,
+    "train_loss": 0.6938152154286702,
+    "train_runtime": 47.698,
+    "train_samples": 635,
+    "train_samples_per_second": 665.646,
+    "train_steps_per_second": 5.241
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6894944310188293,
+    "eval_runtime": 0.1376,
+    "eval_samples": 71,
+    "eval_samples_per_second": 516.142,
+    "eval_steps_per_second": 7.27
+}

logs/events.out.tfevents.1674651566.garda.1933772.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7aa8ba7b9581e39d8c65a5c49d8db324aab0e8868ce147faab834b8f6e384f
+size 357

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.6938152154286702,
+    "train_runtime": 47.698,
+    "train_samples": 635,
+    "train_samples_per_second": 665.646,
+    "train_steps_per_second": 5.241
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6894944310188293,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_wnli/checkpoint-5",
+  "epoch": 6.0,
+  "global_step": 30,
+  "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": 0.6956,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6894944310188293,
+      "eval_runtime": 0.1314,
+      "eval_samples_per_second": 540.311,
+      "eval_steps_per_second": 7.61,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6944,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.6944735050201416,
+      "eval_runtime": 0.1308,
+      "eval_samples_per_second": 542.667,
+      "eval_steps_per_second": 7.643,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6937,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.6946936845779419,
+      "eval_runtime": 0.1297,
+      "eval_samples_per_second": 547.408,
+      "eval_steps_per_second": 7.71,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.693,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6914201378822327,
+      "eval_runtime": 0.1315,
+      "eval_samples_per_second": 540.072,
+      "eval_steps_per_second": 7.607,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.693,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6898038387298584,
+      "eval_runtime": 0.1293,
+      "eval_samples_per_second": 549.119,
+      "eval_steps_per_second": 7.734,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6932,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6900650858879089,
+      "eval_runtime": 0.1293,
+      "eval_samples_per_second": 549.18,
+      "eval_steps_per_second": 7.735,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "step": 30,
+      "total_flos": 119459738025984.0,
+      "train_loss": 0.6938152154286702,
+      "train_runtime": 47.698,
+      "train_samples_per_second": 665.646,
+      "train_steps_per_second": 5.241
+    }
+  ],
+  "max_steps": 250,
+  "num_train_epochs": 50,
+  "total_flos": 119459738025984.0,
+  "trial_name": null,
+  "trial_params": null
+}