End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_km_20_v1_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.2806848266082787
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,12 +30,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_km_20_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4996
-- Pearson: 0.3085
-- Spearmanr: 0.3151
-- Combined Score: 0.3118
+- Loss: 2.1734
+- Pearson: 0.2765
+- Spearmanr: 0.2807
+- Combined Score: 0.2786
 
 ## Model description
 

all_results.json

@@ -3,15 +3,15 @@
     "eval_combined_score": 0.27859606936951653,
     "eval_loss": 2.1733975410461426,
     "eval_pearson": 0.27650731213075436,
-    "eval_runtime": 0.9705,
+    "eval_runtime": 0.9765,
     "eval_samples": 1500,
-    "eval_samples_per_second": 1545.65,
+    "eval_samples_per_second": 1536.087,
     "eval_spearmanr": 0.2806848266082787,
-    "eval_steps_per_second": 6.183,
+    "eval_steps_per_second": 6.144,
     "total_flos": 6050447504044032.0,
     "train_loss": 1.3817211441371753,
-    "train_runtime": 98.0352,
+    "train_runtime": 98.9888,
     "train_samples": 5749,
-    "train_samples_per_second": 2932.112,
-    "train_steps_per_second": 11.73
+    "train_samples_per_second": 2903.865,
+    "train_steps_per_second": 11.617
 }

eval_results.json

@@ -3,9 +3,9 @@
     "eval_combined_score": 0.27859606936951653,
     "eval_loss": 2.1733975410461426,
     "eval_pearson": 0.27650731213075436,
-    "eval_runtime": 0.9705,
+    "eval_runtime": 0.9765,
     "eval_samples": 1500,
-    "eval_samples_per_second": 1545.65,
+    "eval_samples_per_second": 1536.087,
     "eval_spearmanr": 0.2806848266082787,
-    "eval_steps_per_second": 6.183
+    "eval_steps_per_second": 6.144
 }

logs/events.out.tfevents.1745050757.s_005_m.2788007.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba840a98d6ea8e5a3e41f017768645745eeb57affde3c13c7ae76c38fcee8310
+size 473

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 8.0,
     "total_flos": 6050447504044032.0,
     "train_loss": 1.3817211441371753,
-    "train_runtime": 98.0352,
+    "train_runtime": 98.9888,
     "train_samples": 5749,
-    "train_samples_per_second": 2932.112,
-    "train_steps_per_second": 11.73
+    "train_samples_per_second": 2903.865,
+    "train_steps_per_second": 11.617
 }

trainer_state.json

@@ -21,10 +21,10 @@
       "eval_combined_score": 0.21883840300992635,
       "eval_loss": 2.362926721572876,
       "eval_pearson": 0.22315559305765864,
-      "eval_runtime": 0.9514,
-      "eval_samples_per_second": 1576.685,
+      "eval_runtime": 0.9537,
+      "eval_samples_per_second": 1572.84,
       "eval_spearmanr": 0.21452121296219404,
-      "eval_steps_per_second": 6.307,
+      "eval_steps_per_second": 6.291,
       "step": 23
     },
     {
@@ -39,10 +39,10 @@
       "eval_combined_score": 0.2250433116133167,
       "eval_loss": 2.223330020904541,
       "eval_pearson": 0.22643903431708493,
-      "eval_runtime": 0.9766,
-      "eval_samples_per_second": 1536.013,
+      "eval_runtime": 0.9462,
+      "eval_samples_per_second": 1585.334,
       "eval_spearmanr": 0.2236475889095485,
-      "eval_steps_per_second": 6.144,
+      "eval_steps_per_second": 6.341,
       "step": 46
     },
     {
@@ -57,10 +57,10 @@
       "eval_combined_score": 0.27859606936951653,
       "eval_loss": 2.1733975410461426,
       "eval_pearson": 0.27650731213075436,
-      "eval_runtime": 0.9499,
-      "eval_samples_per_second": 1579.115,
+      "eval_runtime": 0.9646,
+      "eval_samples_per_second": 1555.115,
       "eval_spearmanr": 0.2806848266082787,
-      "eval_steps_per_second": 6.316,
+      "eval_steps_per_second": 6.22,
       "step": 69
     },
     {
@@ -75,10 +75,10 @@
       "eval_combined_score": 0.2857232862338934,
       "eval_loss": 2.284653902053833,
       "eval_pearson": 0.28481215085198996,
-      "eval_runtime": 0.9437,
-      "eval_samples_per_second": 1589.456,
+      "eval_runtime": 0.9772,
+      "eval_samples_per_second": 1534.935,
       "eval_spearmanr": 0.28663442161579694,
-      "eval_steps_per_second": 6.358,
+      "eval_steps_per_second": 6.14,
       "step": 92
     },
     {
@@ -93,10 +93,10 @@
       "eval_combined_score": 0.2801317348206342,
       "eval_loss": 2.755934238433838,
       "eval_pearson": 0.27054585694075417,
-      "eval_runtime": 0.997,
-      "eval_samples_per_second": 1504.452,
+      "eval_runtime": 0.9542,
+      "eval_samples_per_second": 1572.032,
       "eval_spearmanr": 0.2897176127005142,
-      "eval_steps_per_second": 6.018,
+      "eval_steps_per_second": 6.288,
       "step": 115
     },
     {
@@ -111,10 +111,10 @@
       "eval_combined_score": 0.30899397408639784,
       "eval_loss": 2.474417209625244,
       "eval_pearson": 0.3009404135965045,
-      "eval_runtime": 0.9611,
-      "eval_samples_per_second": 1560.688,
+      "eval_runtime": 0.9638,
+      "eval_samples_per_second": 1556.332,
       "eval_spearmanr": 0.31704753457629126,
-      "eval_steps_per_second": 6.243,
+      "eval_steps_per_second": 6.225,
       "step": 138
     },
     {
@@ -129,10 +129,10 @@
       "eval_combined_score": 0.2980624641456129,
       "eval_loss": 2.5624561309814453,
       "eval_pearson": 0.29500261904772385,
-      "eval_runtime": 0.994,
-      "eval_samples_per_second": 1508.988,
+      "eval_runtime": 0.9704,
+      "eval_samples_per_second": 1545.698,
       "eval_spearmanr": 0.301122309243502,
-      "eval_steps_per_second": 6.036,
+      "eval_steps_per_second": 6.183,
       "step": 161
     },
     {
@@ -147,10 +147,10 @@
       "eval_combined_score": 0.31179634058913464,
       "eval_loss": 2.499624252319336,
       "eval_pearson": 0.3084881703414194,
-      "eval_runtime": 0.9583,
-      "eval_samples_per_second": 1565.335,
+      "eval_runtime": 0.9545,
+      "eval_samples_per_second": 1571.47,
       "eval_spearmanr": 0.3151045108368498,
-      "eval_steps_per_second": 6.261,
+      "eval_steps_per_second": 6.286,
       "step": 184
     },
     {
@@ -158,9 +158,9 @@
       "step": 184,
       "total_flos": 6050447504044032.0,
       "train_loss": 1.3817211441371753,
-      "train_runtime": 98.0352,
-      "train_samples_per_second": 2932.112,
-      "train_steps_per_second": 11.73
+      "train_runtime": 98.9888,
+      "train_samples_per_second": 2903.865,
+      "train_steps_per_second": 11.617
     }
   ],
   "logging_steps": 1,