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: 0.5799011532125206
+      value: 0.594911220940875
 ---
 
 <!-- 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_192
 
-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: 0.6977
-- Accuracy: 0.5799
+- Loss: 0.6649
+- Accuracy: 0.5949
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.594911220940875,
+    "eval_loss": 0.6649324297904968,
+    "eval_runtime": 2.8831,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1894.828,
+    "eval_steps_per_second": 7.631,
+    "train_loss": 0.6365918704810828,
+    "train_runtime": 961.5765,
+    "train_samples": 104743,
+    "train_samples_per_second": 5446.421,
+    "train_steps_per_second": 21.319
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.594911220940875,
+    "eval_loss": 0.6649324297904968,
+    "eval_runtime": 2.8831,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1894.828,
+    "eval_steps_per_second": 7.631
+}

logs/events.out.tfevents.1674737431.garda.772758.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731277424396bce38497910d156604d0a50fd2f4968feb458433f6094fde1f72
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "train_loss": 0.6365918704810828,
+    "train_runtime": 961.5765,
+    "train_samples": 104743,
+    "train_samples_per_second": 5446.421,
+    "train_steps_per_second": 21.319
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.6649324297904968,
+  "best_model_checkpoint": "distilbert_add_GLUE_Experiment_qnli_192/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": 0.6936,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930174231529236,
+      "eval_runtime": 2.8795,
+      "eval_samples_per_second": 1897.189,
+      "eval_steps_per_second": 7.64,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6793,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5822807980962841,
+      "eval_loss": 0.6683834195137024,
+      "eval_runtime": 2.8752,
+      "eval_samples_per_second": 1900.013,
+      "eval_steps_per_second": 7.652,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6511,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5938129233022149,
+      "eval_loss": 0.6650460958480835,
+      "eval_runtime": 2.8719,
+      "eval_samples_per_second": 1902.237,
+      "eval_steps_per_second": 7.66,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6385,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.594911220940875,
+      "eval_loss": 0.6649324297904968,
+      "eval_runtime": 2.8688,
+      "eval_samples_per_second": 1904.28,
+      "eval_steps_per_second": 7.669,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6306,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5923485264506682,
+      "eval_loss": 0.6668136715888977,
+      "eval_runtime": 2.8758,
+      "eval_samples_per_second": 1899.653,
+      "eval_steps_per_second": 7.65,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6215,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5930807248764415,
+      "eval_loss": 0.6782591938972473,
+      "eval_runtime": 2.8591,
+      "eval_samples_per_second": 1910.745,
+      "eval_steps_per_second": 7.695,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6137,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5852095917993776,
+      "eval_loss": 0.6969286799430847,
+      "eval_runtime": 2.8555,
+      "eval_samples_per_second": 1913.152,
+      "eval_steps_per_second": 7.704,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6046,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5881383855024712,
+      "eval_loss": 0.6887645125389099,
+      "eval_runtime": 2.8669,
+      "eval_samples_per_second": 1905.541,
+      "eval_steps_per_second": 7.674,
+      "step": 3280
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5964,
+      "step": 3690
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5799011532125206,
+      "eval_loss": 0.6977052688598633,
+      "eval_runtime": 2.862,
+      "eval_samples_per_second": 1908.827,
+      "eval_steps_per_second": 7.687,
+      "step": 3690
+    },
+    {
+      "epoch": 9.0,
+      "step": 3690,
+      "total_flos": 1.1314216644378624e+16,
+      "train_loss": 0.6365918704810828,
+      "train_runtime": 961.5765,
+      "train_samples_per_second": 5446.421,
+      "train_steps_per_second": 21.319
+    }
+  ],
+  "max_steps": 20500,
+  "num_train_epochs": 50,
+  "total_flos": 1.1314216644378624e+16,
+  "trial_name": null,
+  "trial_params": null
+}