Date of push: 20240728222808

README.md

@@ -2,6 +2,9 @@
 license: mit
 base_model: microsoft/deberta-v3-base
 tags:
+- deberta
+- fine-tune
+- huggingface
 - generated_from_trainer
 metrics:
 - f1
@@ -17,8 +20,8 @@ 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": 0.1837,
+    "eval_runtime": 0.1806,
     "eval_samples": 10,
-    "eval_samples_per_second": 54.436,
-    "eval_steps_per_second": 27.218,
+    "eval_samples_per_second": 55.367,
+    "eval_steps_per_second": 27.683,
     "total_flos": 202609940734866.0,
     "train_loss": 0.0,
-    "train_runtime": 0.245,
+    "train_runtime": 0.244,
     "train_samples": 87,
-    "train_samples_per_second": 355.061,
-    "train_steps_per_second": 32.649
+    "train_samples_per_second": 356.519,
+    "train_steps_per_second": 32.783
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 9.275862068965518,
     "eval_f1": 0.31034482758620696,
     "eval_loss": 7.982325553894043,
-    "eval_runtime": 0.1837,
+    "eval_runtime": 0.1806,
     "eval_samples": 10,
-    "eval_samples_per_second": 54.436,
-    "eval_steps_per_second": 27.218
+    "eval_samples_per_second": 55.367,
+    "eval_steps_per_second": 27.683
 }

runs/Jul28_20-17-26_766925b9bca5/events.out.tfevents.1722198477.766925b9bca5.538.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41c2107145978f1c94e8c96495628f6dba6302749a4b25f5ef740d99e41c332
+size 399

runs/Jul28_20-17-26_766925b9bca5/events.out.tfevents.1722198477.766925b9bca5.538.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa7c530342a64db60a01513fcfca76b6656c20fb6b982fb021b95fceeb870aa
+size 399

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 9.275862068965518,
     "total_flos": 202609940734866.0,
     "train_loss": 0.0,
-    "train_runtime": 0.245,
+    "train_runtime": 0.244,
     "train_samples": 87,
-    "train_samples_per_second": 355.061,
-    "train_steps_per_second": 32.649
+    "train_samples_per_second": 356.519,
+    "train_steps_per_second": 32.783
 }

trainer_state.json

@@ -133,6 +133,15 @@
       "train_runtime": 0.245,
       "train_samples_per_second": 355.061,
       "train_steps_per_second": 32.649
+    },
+    {
+      "epoch": 9.275862068965518,
+      "step": 80,
+      "total_flos": 202609940734866.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.244,
+      "train_samples_per_second": 356.519,
+      "train_steps_per_second": 32.783
     }
   ],
   "logging_steps": 500,