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: 0.5809994508511807
+      value: 0.5905180303862346
 ---
 
 <!-- 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_qnli_256
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7093
-- Accuracy: 0.5810
+- Loss: 0.6656
+- Accuracy: 0.5905
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5905180303862346,
+    "eval_loss": 0.6655521988868713,
+    "eval_runtime": 2.75,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1986.551,
+    "eval_steps_per_second": 8.0,
+    "train_loss": 0.643012532622972,
+    "train_runtime": 720.0292,
+    "train_samples": 104743,
+    "train_samples_per_second": 7273.525,
+    "train_steps_per_second": 28.471
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5905180303862346,
+    "eval_loss": 0.6655521988868713,
+    "eval_runtime": 2.75,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1986.551,
+    "eval_steps_per_second": 8.0
+}

logs/events.out.tfevents.1674737300.glendale.2597965.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb3a851b0ae5c81e49bf77bc01883ec246b1c9cbdba946aea7f874ed12af840
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.643012532622972,
+    "train_runtime": 720.0292,
+    "train_samples": 104743,
+    "train_samples_per_second": 7273.525,
+    "train_steps_per_second": 28.471
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.6655521988868713,
+  "best_model_checkpoint": "distilbert_add_GLUE_Experiment_qnli_256/checkpoint-820",
+  "epoch": 7.0,
+  "global_step": 2870,
+  "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": 0.6936,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5654402343034962,
+      "eval_loss": 0.6893095970153809,
+      "eval_runtime": 2.594,
+      "eval_samples_per_second": 2106.01,
+      "eval_steps_per_second": 8.481,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6702,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5905180303862346,
+      "eval_loss": 0.6655521988868713,
+      "eval_runtime": 2.7202,
+      "eval_samples_per_second": 2008.294,
+      "eval_steps_per_second": 8.088,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6477,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5965586673988651,
+      "eval_loss": 0.6664628982543945,
+      "eval_runtime": 2.5249,
+      "eval_samples_per_second": 2163.624,
+      "eval_steps_per_second": 8.713,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6369,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5952773201537617,
+      "eval_loss": 0.6665092706680298,
+      "eval_runtime": 2.9306,
+      "eval_samples_per_second": 1864.119,
+      "eval_steps_per_second": 7.507,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.627,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5934468240893283,
+      "eval_loss": 0.6724303960800171,
+      "eval_runtime": 2.6494,
+      "eval_samples_per_second": 2061.941,
+      "eval_steps_per_second": 8.304,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6173,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5919824272377814,
+      "eval_loss": 0.6841514110565186,
+      "eval_runtime": 2.614,
+      "eval_samples_per_second": 2089.876,
+      "eval_steps_per_second": 8.416,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6083,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5809994508511807,
+      "eval_loss": 0.7093197107315063,
+      "eval_runtime": 2.5368,
+      "eval_samples_per_second": 2153.465,
+      "eval_steps_per_second": 8.672,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "step": 2870,
+      "total_flos": 1.2080381096361984e+16,
+      "train_loss": 0.643012532622972,
+      "train_runtime": 720.0292,
+      "train_samples_per_second": 7273.525,
+      "train_steps_per_second": 28.471
+    }
+  ],
+  "max_steps": 20500,
+  "num_train_epochs": 50,
+  "total_flos": 1.2080381096361984e+16,
+  "trial_name": null,
+  "trial_params": null
+}