End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8837920489296636
+      value: 0.8834862385321101
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the boolq dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6847
-- Accuracy: 0.8838
+- Loss: 0.4601
+- Accuracy: 0.8835
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8834862385321101,
+    "eval_loss": 0.46006181836128235,
+    "eval_runtime": 57.8938,
+    "eval_samples": 3270,
+    "eval_samples_per_second": 56.483,
+    "eval_steps_per_second": 7.065,
+    "train_loss": 0.06997121843241029,
+    "train_runtime": 3241.1036,
+    "train_samples": 9427,
+    "train_samples_per_second": 14.543,
+    "train_steps_per_second": 0.455
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8834862385321101,
+    "eval_loss": 0.46006181836128235,
+    "eval_runtime": 57.8938,
+    "eval_samples": 3270,
+    "eval_samples_per_second": 56.483,
+    "eval_steps_per_second": 7.065
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.06997121843241029,
+    "train_runtime": 3241.1036,
+    "train_samples": 9427,
+    "train_samples_per_second": 14.543,
+    "train_steps_per_second": 0.455
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.46006181836128235,
+  "best_model_checkpoint": "./deberta-v3-large_boolq/checkpoint-500",
+  "epoch": 5.0,
+  "eval_steps": 250,
+  "global_step": 1475,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.882262996941896,
+      "eval_loss": 0.5305724740028381,
+      "eval_runtime": 58.8571,
+      "eval_samples_per_second": 55.558,
+      "eval_steps_per_second": 6.949,
+      "step": 250
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.623728813559322e-06,
+      "loss": 0.1151,
+      "step": 500
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.8834862385321101,
+      "eval_loss": 0.46006181836128235,
+      "eval_runtime": 58.6016,
+      "eval_samples_per_second": 55.801,
+      "eval_steps_per_second": 6.979,
+      "step": 500
+    },
+    {
+      "epoch": 2.54,
+      "eval_accuracy": 0.8792048929663608,
+      "eval_loss": 0.5896904468536377,
+      "eval_runtime": 58.6309,
+      "eval_samples_per_second": 55.773,
+      "eval_steps_per_second": 6.976,
+      "step": 750
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 3.2338983050847462e-06,
+      "loss": 0.0656,
+      "step": 1000
+    },
+    {
+      "epoch": 3.39,
+      "eval_accuracy": 0.8804281345565749,
+      "eval_loss": 0.6476820111274719,
+      "eval_runtime": 58.833,
+      "eval_samples_per_second": 55.581,
+      "eval_steps_per_second": 6.952,
+      "step": 1000
+    },
+    {
+      "epoch": 4.24,
+      "eval_accuracy": 0.8837920489296636,
+      "eval_loss": 0.684716522693634,
+      "eval_runtime": 58.2099,
+      "eval_samples_per_second": 56.176,
+      "eval_steps_per_second": 7.026,
+      "step": 1250
+    },
+    {
+      "epoch": 5.0,
+      "step": 1475,
+      "total_flos": 4.392688135824384e+16,
+      "train_loss": 0.06997121843241029,
+      "train_runtime": 3241.1036,
+      "train_samples_per_second": 14.543,
+      "train_steps_per_second": 0.455
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1475,
+  "num_train_epochs": 5,
+  "save_steps": 250,
+  "total_flos": 4.392688135824384e+16,
+  "trial_name": null,
+  "trial_params": null
+}