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 QNLI
       type: glue
       config: qnli
       split: validation
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6822258832143511
+      value: 0.6522057477576423
 ---
 
 <!-- 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. -->
 
 # distilbert_add_GLUE_Experiment_logit_kd_pretrain_qnli
 
-This model is a fine-tuned version of [gokuls/distilbert_add_pre-training-complete](https://huggingface.co/gokuls/distilbert_add_pre-training-complete) on the glue dataset.
+This model is a fine-tuned version of [gokuls/distilbert_add_pre-training-complete](https://huggingface.co/gokuls/distilbert_add_pre-training-complete) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3942
-- Accuracy: 0.6822
+- Loss: 0.3579
+- Accuracy: 0.6522
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.6522057477576423,
+    "eval_loss": 0.3579190969467163,
+    "eval_runtime": 7.9297,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 688.932,
+    "eval_steps_per_second": 2.774,
+    "train_loss": 0.3297072930064628,
+    "train_runtime": 2134.3753,
+    "train_samples": 104743,
+    "train_samples_per_second": 2453.716,
+    "train_steps_per_second": 9.605
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.6522057477576423,
+    "eval_loss": 0.3579190969467163,
+    "eval_runtime": 7.9297,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 688.932,
+    "eval_steps_per_second": 2.774
+}

logs/events.out.tfevents.1675036328.serv-3328.2260432.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44483565b0c7140bbb93bee1da41c72127e5258d17a3465c977394bf35d33e28
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "train_loss": 0.3297072930064628,
+    "train_runtime": 2134.3753,
+    "train_samples": 104743,
+    "train_samples_per_second": 2453.716,
+    "train_steps_per_second": 9.605
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.3579190969467163,
+  "best_model_checkpoint": "distilbert_add_GLUE_Experiment_logit_kd_pretrain_qnli/checkpoint-1640",
+  "epoch": 9.0,
+  "global_step": 3690,
+  "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": 0.4059,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5584843492586491,
+      "eval_loss": 0.40156200528144836,
+      "eval_runtime": 7.8241,
+      "eval_samples_per_second": 698.227,
+      "eval_steps_per_second": 2.812,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3907,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6093721398498994,
+      "eval_loss": 0.3734533190727234,
+      "eval_runtime": 7.8866,
+      "eval_samples_per_second": 692.697,
+      "eval_steps_per_second": 2.79,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3715,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6479956068094453,
+      "eval_loss": 0.3601550757884979,
+      "eval_runtime": 7.8261,
+      "eval_samples_per_second": 698.049,
+      "eval_steps_per_second": 2.811,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.352,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6522057477576423,
+      "eval_loss": 0.3579190969467163,
+      "eval_runtime": 7.7424,
+      "eval_samples_per_second": 705.594,
+      "eval_steps_per_second": 2.841,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3314,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6670327658795534,
+      "eval_loss": 0.3626244366168976,
+      "eval_runtime": 7.9513,
+      "eval_samples_per_second": 687.057,
+      "eval_steps_per_second": 2.767,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.309,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6776496430532675,
+      "eval_loss": 0.36497482657432556,
+      "eval_runtime": 7.8104,
+      "eval_samples_per_second": 699.448,
+      "eval_steps_per_second": 2.817,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2865,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6776496430532675,
+      "eval_loss": 0.37994131445884705,
+      "eval_runtime": 7.7799,
+      "eval_samples_per_second": 702.195,
+      "eval_steps_per_second": 2.828,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2679,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6902800658978583,
+      "eval_loss": 0.3816882073879242,
+      "eval_runtime": 7.7701,
+      "eval_samples_per_second": 703.08,
+      "eval_steps_per_second": 2.831,
+      "step": 3280
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.2525,
+      "step": 3690
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6822258832143511,
+      "eval_loss": 0.39422982931137085,
+      "eval_runtime": 7.9075,
+      "eval_samples_per_second": 690.862,
+      "eval_steps_per_second": 2.782,
+      "step": 3690
+    },
+    {
+      "epoch": 9.0,
+      "step": 3690,
+      "total_flos": 5.74670425250857e+16,
+      "train_loss": 0.3297072930064628,
+      "train_runtime": 2134.3753,
+      "train_samples_per_second": 2453.716,
+      "train_steps_per_second": 9.605
+    }
+  ],
+  "max_steps": 20500,
+  "num_train_epochs": 50,
+  "total_flos": 5.74670425250857e+16,
+  "trial_name": null,
+  "trial_params": null
+}