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_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 WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6909
+- Loss: 0.6899
 - Accuracy: 0.5634
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.689942479133606,
+    "eval_runtime": 0.1815,
+    "eval_samples": 71,
+    "eval_samples_per_second": 391.259,
+    "eval_steps_per_second": 5.511,
+    "train_loss": 0.6933449824651082,
+    "train_runtime": 52.5011,
+    "train_samples": 635,
+    "train_samples_per_second": 604.75,
+    "train_steps_per_second": 4.762
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.689942479133606,
+    "eval_runtime": 0.1815,
+    "eval_samples": 71,
+    "eval_samples_per_second": 391.259,
+    "eval_steps_per_second": 5.511
+}

logs/events.out.tfevents.1674664044.garda.1292005.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35481b4aeaec216f04a1790a6f027ddc89ddce1ac366949a4cf6d09bff04732c
+size 357

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.6933449824651082,
+    "train_runtime": 52.5011,
+    "train_samples": 635,
+    "train_samples_per_second": 604.75,
+    "train_steps_per_second": 4.762
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.689942479133606,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_wnli_256/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": 0.6942,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.689942479133606,
+      "eval_runtime": 0.1778,
+      "eval_samples_per_second": 399.271,
+      "eval_steps_per_second": 5.624,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6935,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6920180916786194,
+      "eval_runtime": 0.1776,
+      "eval_samples_per_second": 399.764,
+      "eval_steps_per_second": 5.63,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6933,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6929550766944885,
+      "eval_runtime": 0.1765,
+      "eval_samples_per_second": 402.166,
+      "eval_steps_per_second": 5.664,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.693,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6921097636222839,
+      "eval_runtime": 0.1769,
+      "eval_samples_per_second": 401.466,
+      "eval_steps_per_second": 5.654,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.693,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.691243052482605,
+      "eval_runtime": 0.177,
+      "eval_samples_per_second": 401.133,
+      "eval_steps_per_second": 5.65,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.693,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.690945565700531,
+      "eval_runtime": 0.1787,
+      "eval_samples_per_second": 397.341,
+      "eval_steps_per_second": 5.596,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "step": 30,
+      "total_flos": 100359777288192.0,
+      "train_loss": 0.6933449824651082,
+      "train_runtime": 52.5011,
+      "train_samples_per_second": 604.75,
+      "train_steps_per_second": 4.762
+    }
+  ],
+  "max_steps": 250,
+  "num_train_epochs": 50,
+  "total_flos": 100359777288192.0,
+  "trial_name": null,
+  "trial_params": null
+}