End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert-base-uncased-finetuned-stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.8812306945520035
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +31,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-finetuned-stsb
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Combined Score: 0.8836
-- Loss: 0.5010
-- Pearson: 0.8856
-- Spearmanr: 0.8816
+- Loss: 0.4998
+- Pearson: 0.8854
+- Spearmanr: 0.8812
+- Combined Score: 0.8833
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 3.0,
-    "eval_combined_score": 0.8800819163371243,
-    "eval_loss": 0.5214201807975769,
-    "eval_pearson": 0.8814083337783813,
-    "eval_runtime": 22.2962,
+    "eval_combined_score": 0.8833182367184456,
+    "eval_loss": 0.499796986579895,
+    "eval_pearson": 0.8854057788848877,
+    "eval_runtime": 41.0515,
     "eval_samples": 1500,
-    "eval_samples_per_second": 67.276,
-    "eval_spearmanr": 0.8787554988958671,
-    "eval_steps_per_second": 8.432,
+    "eval_samples_per_second": 36.539,
+    "eval_spearmanr": 0.8812306945520035,
+    "eval_steps_per_second": 4.58,
     "total_flos": 4537835628033024.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0012,
+    "train_runtime": 0.0013,
     "train_samples": 5749,
-    "train_samples_per_second": 14364408.477,
-    "train_steps_per_second": 899493.312
+    "train_samples_per_second": 13531455.497,
+    "train_steps_per_second": 847334.141
 }

config.json

@@ -25,6 +25,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "regression",
   "torch_dtype": "float32",
   "transformers_version": "4.45.0.dev0",
   "type_vocab_size": 2,

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_combined_score": 0.8800819163371243,
-    "eval_loss": 0.5214201807975769,
-    "eval_pearson": 0.8814083337783813,
-    "eval_runtime": 22.2962,
+    "eval_combined_score": 0.8833182367184456,
+    "eval_loss": 0.499796986579895,
+    "eval_pearson": 0.8854057788848877,
+    "eval_runtime": 41.0515,
     "eval_samples": 1500,
-    "eval_samples_per_second": 67.276,
-    "eval_spearmanr": 0.8787554988958671,
-    "eval_steps_per_second": 8.432
+    "eval_samples_per_second": 36.539,
+    "eval_spearmanr": 0.8812306945520035,
+    "eval_steps_per_second": 4.58
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 4537835628033024.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0012,
+    "train_runtime": 0.0013,
     "train_samples": 5749,
-    "train_samples_per_second": 14364408.477,
-    "train_steps_per_second": 899493.312
+    "train_samples_per_second": 13531455.497,
+    "train_steps_per_second": 847334.141
 }

trainer_state.json

@@ -67,9 +67,9 @@
       "step": 1080,
       "total_flos": 4537835628033024.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0012,
-      "train_samples_per_second": 14364408.477,
-      "train_steps_per_second": 899493.312
+      "train_runtime": 0.0013,
+      "train_samples_per_second": 13531455.497,
+      "train_steps_per_second": 847334.141
     }
   ],
   "logging_steps": 500,