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: 0.8809995769549899
 ---
 
 <!-- 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: 0.5016
+- Pearson: 0.8850
+- Spearmanr: 0.8810
+- Combined Score: 0.8830
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 3.0,
-    "eval_combined_score": 0.8830160060889146,
-    "eval_loss": 0.5016871094703674,
-    "eval_pearson": 0.8850284814834595,
-    "eval_runtime": 218.7456,
+    "eval_combined_score": 0.8830166518235948,
+    "eval_loss": 0.501645565032959,
+    "eval_pearson": 0.8850337266921997,
+    "eval_runtime": 221.4478,
     "eval_samples": 1500,
-    "eval_samples_per_second": 6.857,
-    "eval_spearmanr": 0.8810035306943698,
-    "eval_steps_per_second": 0.859,
+    "eval_samples_per_second": 6.774,
+    "eval_spearmanr": 0.8809995769549899,
+    "eval_steps_per_second": 0.849,
     "total_flos": 4537835628033024.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0017,
+    "train_runtime": 0.0014,
     "train_samples": 5749,
-    "train_samples_per_second": 9951734.914,
-    "train_steps_per_second": 623173.52
+    "train_samples_per_second": 12008492.876,
+    "train_steps_per_second": 751966.853
 }

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": 0.8830160060889146,
-    "eval_loss": 0.5016871094703674,
-    "eval_pearson": 0.8850284814834595,
-    "eval_runtime": 218.7456,
+    "eval_combined_score": 0.8830166518235948,
+    "eval_loss": 0.501645565032959,
+    "eval_pearson": 0.8850337266921997,
+    "eval_runtime": 221.4478,
     "eval_samples": 1500,
-    "eval_samples_per_second": 6.857,
-    "eval_spearmanr": 0.8810035306943698,
-    "eval_steps_per_second": 0.859
+    "eval_samples_per_second": 6.774,
+    "eval_spearmanr": 0.8809995769549899,
+    "eval_steps_per_second": 0.849
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 4537835628033024.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0017,
+    "train_runtime": 0.0014,
     "train_samples": 5749,
-    "train_samples_per_second": 9951734.914,
-    "train_steps_per_second": 623173.52
+    "train_samples_per_second": 12008492.876,
+    "train_steps_per_second": 751966.853
 }

trainer_state.json

@@ -67,9 +67,9 @@
       "step": 1080,
       "total_flos": 4537835628033024.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0017,
-      "train_samples_per_second": 9951734.914,
-      "train_steps_per_second": 623173.52
+      "train_runtime": 0.0014,
+      "train_samples_per_second": 12008492.876,
+      "train_steps_per_second": 751966.853
     }
   ],
   "logging_steps": 500,