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: 0.5718469705290133
+      value: 0.6029654036243822
 ---
 
 <!-- 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_sa_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: 0.7653
-- Accuracy: 0.5718
+- Loss: 0.6564
+- Accuracy: 0.6030
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6029654036243822,
+    "eval_loss": 0.6563981175422668,
+    "eval_runtime": 3.2603,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1675.595,
+    "eval_steps_per_second": 6.748,
+    "train_loss": 0.606161908405583,
+    "train_runtime": 917.3964,
+    "train_samples": 104743,
+    "train_samples_per_second": 5708.71,
+    "train_steps_per_second": 22.346
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6029654036243822,
+    "eval_loss": 0.6563981175422668,
+    "eval_runtime": 3.2603,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1675.595,
+    "eval_steps_per_second": 6.748
+}

logs/events.out.tfevents.1674622472.glendale.3902328.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0995b4ebcb196f2deaebdbae6a81c7e5501cf179133cc969e00476dfd873164f
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.606161908405583,
+    "train_runtime": 917.3964,
+    "train_samples": 104743,
+    "train_samples_per_second": 5708.71,
+    "train_steps_per_second": 22.346
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.6563981175422668,
+  "best_model_checkpoint": "distilbert_sa_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": 0.679,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5938129233022149,
+      "eval_loss": 0.6613895297050476,
+      "eval_runtime": 3.2297,
+      "eval_samples_per_second": 1691.499,
+      "eval_steps_per_second": 6.812,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6496,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6029654036243822,
+      "eval_loss": 0.6563981175422668,
+      "eval_runtime": 3.2407,
+      "eval_samples_per_second": 1685.736,
+      "eval_steps_per_second": 6.789,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6268,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5978400146439685,
+      "eval_loss": 0.6634846329689026,
+      "eval_runtime": 3.2185,
+      "eval_samples_per_second": 1697.373,
+      "eval_steps_per_second": 6.835,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6055,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5932637744828848,
+      "eval_loss": 0.6714160442352295,
+      "eval_runtime": 3.1995,
+      "eval_samples_per_second": 1707.477,
+      "eval_steps_per_second": 6.876,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5836,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5912502288120081,
+      "eval_loss": 0.6963688135147095,
+      "eval_runtime": 3.1762,
+      "eval_samples_per_second": 1720.003,
+      "eval_steps_per_second": 6.927,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5602,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5831960461285008,
+      "eval_loss": 0.7318801283836365,
+      "eval_runtime": 3.2345,
+      "eval_samples_per_second": 1688.985,
+      "eval_steps_per_second": 6.802,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5385,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5718469705290133,
+      "eval_loss": 0.7652592658996582,
+      "eval_runtime": 3.2105,
+      "eval_samples_per_second": 1701.597,
+      "eval_steps_per_second": 6.852,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "step": 2870,
+      "total_flos": 1.2511057062920192e+16,
+      "train_loss": 0.606161908405583,
+      "train_runtime": 917.3964,
+      "train_samples_per_second": 5708.71,
+      "train_steps_per_second": 22.346
+    }
+  ],
+  "max_steps": 20500,
+  "num_train_epochs": 50,
+  "total_flos": 1.2511057062920192e+16,
+  "trial_name": null,
+  "trial_params": null
+}