End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- F1: 0.3068
-- Loss: 7.9021
+- Loss: 7.9823
+- F1: 0.3103
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 9.275862068965518,
     "eval_f1": 0.31034482758620696,
     "eval_loss": 7.982325553894043,
-    "eval_runtime": 0.1853,
+    "eval_runtime": 0.1837,
     "eval_samples": 10,
-    "eval_samples_per_second": 53.96,
-    "eval_steps_per_second": 26.98,
+    "eval_samples_per_second": 54.436,
+    "eval_steps_per_second": 27.218,
     "total_flos": 202609940734866.0,
-    "train_loss": 7.418544769287109,
-    "train_runtime": 132.4614,
+    "train_loss": 0.0,
+    "train_runtime": 0.245,
     "train_samples": 87,
-    "train_samples_per_second": 6.568,
-    "train_steps_per_second": 0.604
+    "train_samples_per_second": 355.061,
+    "train_steps_per_second": 32.649
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 9.275862068965518,
     "eval_f1": 0.31034482758620696,
     "eval_loss": 7.982325553894043,
-    "eval_runtime": 0.1853,
+    "eval_runtime": 0.1837,
     "eval_samples": 10,
-    "eval_samples_per_second": 53.96,
-    "eval_steps_per_second": 26.98
+    "eval_samples_per_second": 54.436,
+    "eval_steps_per_second": 27.218
 }

runs/Jul28_20-17-26_766925b9bca5/events.out.tfevents.1722197871.766925b9bca5.538.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287ffe2a52be2f928f0e74181b7475297dc39213cf47159968b62e14200dd44c
+size 399

runs/Jul28_20-17-26_766925b9bca5/events.out.tfevents.1722197871.766925b9bca5.538.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276cf75ee0ef5a52c8e036cf457f3819f25bd8e2bf8d4fa9318e6d85434f3cad
+size 399

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 9.275862068965518,
     "total_flos": 202609940734866.0,
-    "train_loss": 7.418544769287109,
-    "train_runtime": 132.4614,
+    "train_loss": 0.0,
+    "train_runtime": 0.245,
     "train_samples": 87,
-    "train_samples_per_second": 6.568,
-    "train_steps_per_second": 0.604
+    "train_samples_per_second": 355.061,
+    "train_steps_per_second": 32.649
 }

trainer_state.json

@@ -124,12 +124,21 @@
       "train_runtime": 132.4614,
       "train_samples_per_second": 6.568,
       "train_steps_per_second": 0.604
+    },
+    {
+      "epoch": 9.275862068965518,
+      "step": 80,
+      "total_flos": 202609940734866.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.245,
+      "train_samples_per_second": 355.061,
+      "train_steps_per_second": 32.649
     }
   ],
   "logging_steps": 500,
-  "max_steps": 80,
+  "max_steps": 8,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {