End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -14,7 +16,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE MRPC
       type: glue
       config: mrpc
       split: validation
@@ -33,7 +35,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_logit_kd_pretrain_mrpc
 
-This model is a fine-tuned version of [gokuls/mobilebert_add_pre-training-complete](https://huggingface.co/gokuls/mobilebert_add_pre-training-complete) on the glue dataset.
+This model is a fine-tuned version of [gokuls/mobilebert_add_pre-training-complete](https://huggingface.co/gokuls/mobilebert_add_pre-training-complete) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 - Accuracy: 0.3162

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.3161764705882353,
+    "eval_combined_score": 0.15808823529411764,
+    "eval_f1": 0.0,
+    "eval_loss": NaN,
+    "eval_runtime": 0.7619,
+    "eval_samples": 408,
+    "eval_samples_per_second": 535.509,
+    "eval_steps_per_second": 5.25,
+    "train_loss": 0.0,
+    "train_runtime": 138.3637,
+    "train_samples": 3668,
+    "train_samples_per_second": 1325.492,
+    "train_steps_per_second": 10.48
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.3161764705882353,
+    "eval_combined_score": 0.15808823529411764,
+    "eval_f1": 0.0,
+    "eval_loss": NaN,
+    "eval_runtime": 0.7619,
+    "eval_samples": 408,
+    "eval_samples_per_second": 535.509,
+    "eval_steps_per_second": 5.25
+}

logs/events.out.tfevents.1675033135.serv-3331.1557471.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6995c3d104a8e685feb90a495cccd8627c15ca676f42e218e1a28f74f28efc
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.0,
+    "train_runtime": 138.3637,
+    "train_samples": 3668,
+    "train_samples_per_second": 1325.492,
+    "train_steps_per_second": 10.48
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": NaN,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_pretrain_mrpc/checkpoint-29",
+  "epoch": 6.0,
+  "global_step": 174,
+  "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": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3161764705882353,
+      "eval_combined_score": 0.15808823529411764,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7358,
+      "eval_samples_per_second": 554.512,
+      "eval_steps_per_second": 5.436,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3161764705882353,
+      "eval_combined_score": 0.15808823529411764,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7382,
+      "eval_samples_per_second": 552.7,
+      "eval_steps_per_second": 5.419,
+      "step": 58
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3161764705882353,
+      "eval_combined_score": 0.15808823529411764,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7402,
+      "eval_samples_per_second": 551.224,
+      "eval_steps_per_second": 5.404,
+      "step": 87
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.0,
+      "step": 116
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3161764705882353,
+      "eval_combined_score": 0.15808823529411764,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7385,
+      "eval_samples_per_second": 552.451,
+      "eval_steps_per_second": 5.416,
+      "step": 116
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3161764705882353,
+      "eval_combined_score": 0.15808823529411764,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7334,
+      "eval_samples_per_second": 556.297,
+      "eval_steps_per_second": 5.454,
+      "step": 145
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3161764705882353,
+      "eval_combined_score": 0.15808823529411764,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7457,
+      "eval_samples_per_second": 547.144,
+      "eval_steps_per_second": 5.364,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "step": 174,
+      "total_flos": 659883590418432.0,
+      "train_loss": 0.0,
+      "train_runtime": 138.3637,
+      "train_samples_per_second": 1325.492,
+      "train_steps_per_second": 10.48
+    }
+  ],
+  "max_steps": 1450,
+  "num_train_epochs": 50,
+  "total_flos": 659883590418432.0,
+  "trial_name": null,
+  "trial_params": null
+}