End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_km_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: distilbert_km_100_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7009803921568627
+    - name: F1
+      type: f1
+      value: 0.8145896656534954
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_km_100_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/distilbert_km_100_v1](https://huggingface.co/Hartunka/distilbert_km_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_km_100_v1](https://huggingface.co/Hartunka/distilbert_km_100_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0242
-- Accuracy: 0.6299
-- F1: 0.7209
-- Combined Score: 0.6754
+- Loss: 0.6028
+- Accuracy: 0.7010
+- F1: 0.8146
+- Combined Score: 0.7578
 
 ## Model description
 

all_results.json

@@ -4,14 +4,14 @@
     "eval_combined_score": 0.7577850289051791,
     "eval_f1": 0.8145896656534954,
     "eval_loss": 0.6028358340263367,
-    "eval_runtime": 0.1975,
+    "eval_runtime": 0.2107,
     "eval_samples": 408,
-    "eval_samples_per_second": 2065.99,
-    "eval_steps_per_second": 10.127,
+    "eval_samples_per_second": 1936.667,
+    "eval_steps_per_second": 9.493,
     "total_flos": 1700616463945728.0,
     "train_loss": 0.41734157516842796,
-    "train_runtime": 34.5933,
+    "train_runtime": 34.77,
     "train_samples": 3668,
-    "train_samples_per_second": 5301.605,
-    "train_steps_per_second": 21.681
+    "train_samples_per_second": 5274.666,
+    "train_steps_per_second": 21.57
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7577850289051791,
     "eval_f1": 0.8145896656534954,
     "eval_loss": 0.6028358340263367,
-    "eval_runtime": 0.1975,
+    "eval_runtime": 0.2107,
     "eval_samples": 408,
-    "eval_samples_per_second": 2065.99,
-    "eval_steps_per_second": 10.127
+    "eval_samples_per_second": 1936.667,
+    "eval_steps_per_second": 9.493
 }

logs/events.out.tfevents.1744905119.s_005_m.2758941.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a92b746ad51fc1cb832475dad33beaa52d7abb41f27fcef67a10bfc0f1856d1
+size 459

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "total_flos": 1700616463945728.0,
     "train_loss": 0.41734157516842796,
-    "train_runtime": 34.5933,
+    "train_runtime": 34.77,
     "train_samples": 3668,
-    "train_samples_per_second": 5301.605,
-    "train_steps_per_second": 21.681
+    "train_samples_per_second": 5274.666,
+    "train_steps_per_second": 21.57
 }

trainer_state.json

@@ -22,9 +22,9 @@
       "eval_combined_score": 0.7542106100554595,
       "eval_f1": 0.8098918083462133,
       "eval_loss": 0.6127546429634094,
-      "eval_runtime": 0.1797,
-      "eval_samples_per_second": 2270.72,
-      "eval_steps_per_second": 11.131,
+      "eval_runtime": 0.1878,
+      "eval_samples_per_second": 2172.001,
+      "eval_steps_per_second": 10.647,
       "step": 15
     },
     {
@@ -40,9 +40,9 @@
       "eval_combined_score": 0.7577850289051791,
       "eval_f1": 0.8145896656534954,
       "eval_loss": 0.6028358340263367,
-      "eval_runtime": 0.2139,
-      "eval_samples_per_second": 1907.615,
-      "eval_steps_per_second": 9.351,
+      "eval_runtime": 0.189,
+      "eval_samples_per_second": 2158.195,
+      "eval_steps_per_second": 10.579,
       "step": 30
     },
     {
@@ -58,9 +58,9 @@
       "eval_combined_score": 0.7640608875128999,
       "eval_f1": 0.8173374613003096,
       "eval_loss": 0.6116268038749695,
-      "eval_runtime": 0.1837,
-      "eval_samples_per_second": 2221.291,
-      "eval_steps_per_second": 10.889,
+      "eval_runtime": 0.1889,
+      "eval_samples_per_second": 2159.655,
+      "eval_steps_per_second": 10.587,
       "step": 45
     },
     {
@@ -76,9 +76,9 @@
       "eval_combined_score": 0.7228506787330318,
       "eval_f1": 0.7692307692307693,
       "eval_loss": 0.6474385261535645,
-      "eval_runtime": 0.2182,
-      "eval_samples_per_second": 1869.959,
-      "eval_steps_per_second": 9.166,
+      "eval_runtime": 0.2034,
+      "eval_samples_per_second": 2005.884,
+      "eval_steps_per_second": 9.833,
       "step": 60
     },
     {
@@ -94,9 +94,9 @@
       "eval_combined_score": 0.718651446592623,
       "eval_f1": 0.7657342657342657,
       "eval_loss": 0.6890015602111816,
-      "eval_runtime": 0.1772,
-      "eval_samples_per_second": 2302.668,
-      "eval_steps_per_second": 11.288,
+      "eval_runtime": 0.1869,
+      "eval_samples_per_second": 2183.112,
+      "eval_steps_per_second": 10.702,
       "step": 75
     },
     {
@@ -112,9 +112,9 @@
       "eval_combined_score": 0.6419314852377733,
       "eval_f1": 0.685823754789272,
       "eval_loss": 0.9257688522338867,
-      "eval_runtime": 0.1986,
-      "eval_samples_per_second": 2054.795,
-      "eval_steps_per_second": 10.073,
+      "eval_runtime": 0.1842,
+      "eval_samples_per_second": 2214.734,
+      "eval_steps_per_second": 10.857,
       "step": 90
     },
     {
@@ -130,9 +130,9 @@
       "eval_combined_score": 0.6753946033126744,
       "eval_f1": 0.7208872458410351,
       "eval_loss": 1.0241893529891968,
-      "eval_runtime": 0.1858,
-      "eval_samples_per_second": 2195.638,
-      "eval_steps_per_second": 10.763,
+      "eval_runtime": 0.1836,
+      "eval_samples_per_second": 2221.784,
+      "eval_steps_per_second": 10.891,
       "step": 105
     },
     {
@@ -140,9 +140,9 @@
       "step": 105,
       "total_flos": 1700616463945728.0,
       "train_loss": 0.41734157516842796,
-      "train_runtime": 34.5933,
-      "train_samples_per_second": 5301.605,
-      "train_steps_per_second": 21.681
+      "train_runtime": 34.77,
+      "train_samples_per_second": 5274.666,
+      "train_steps_per_second": 21.57
     }
   ],
   "logging_steps": 1,