End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: roberta-base
 tags:
 - generated_from_trainer
+datasets:
+- lltala/e-ner-roberta-base
 model-index:
 - name: ner-2-roberta-base
   results: []
@@ -13,7 +15,25 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ner-2-roberta-base
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the lltala/e-ner-roberta-base dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0798
+- Loc Precision: 0.625
+- Loc Recall: 0.7216
+- Loc F1: 0.6699
+- Loc Number: 97
+- Org Precision: 0.8401
+- Org Recall: 0.6716
+- Org F1: 0.7465
+- Org Number: 673
+- Per Precision: 0.9425
+- Per Recall: 0.9762
+- Per F1: 0.9591
+- Per Number: 84
+- Overall Precision: 0.8195
+- Overall Recall: 0.7073
+- Overall F1: 0.7593
+- Overall Accuracy: 0.9854
 
 ## Model description
 

all_results.json

@@ -1,30 +1,30 @@
 {
     "epoch": 3.0,
-    "eval_LOC_f1": 0.6274509803921569,
-    "eval_LOC_number": 76,
-    "eval_LOC_precision": 0.6233766233766234,
-    "eval_LOC_recall": 0.631578947368421,
-    "eval_ORG_f1": 0.7366375121477162,
-    "eval_ORG_number": 562,
-    "eval_ORG_precision": 0.8115631691648822,
-    "eval_ORG_recall": 0.6743772241992882,
-    "eval_PER_f1": 0.9866666666666666,
-    "eval_PER_number": 74,
-    "eval_PER_precision": 0.9736842105263158,
-    "eval_PER_recall": 1.0,
-    "eval_loss": 0.0689539760351181,
-    "eval_overall_accuracy": 0.9864484019907658,
-    "eval_overall_f1": 0.7522522522522522,
-    "eval_overall_precision": 0.8080645161290323,
-    "eval_overall_recall": 0.7036516853932584,
-    "eval_runtime": 3.6349,
+    "eval_LOC_f1": 0.6698564593301435,
+    "eval_LOC_number": 97,
+    "eval_LOC_precision": 0.625,
+    "eval_LOC_recall": 0.7216494845360825,
+    "eval_ORG_f1": 0.7464905037159372,
+    "eval_ORG_number": 673,
+    "eval_ORG_precision": 0.8401486988847584,
+    "eval_ORG_recall": 0.6716196136701337,
+    "eval_PER_f1": 0.95906432748538,
+    "eval_PER_number": 84,
+    "eval_PER_precision": 0.9425287356321839,
+    "eval_PER_recall": 0.9761904761904762,
+    "eval_loss": 0.07983002066612244,
+    "eval_overall_accuracy": 0.9853830393283693,
+    "eval_overall_f1": 0.7592708988057825,
+    "eval_overall_precision": 0.819538670284939,
+    "eval_overall_recall": 0.7072599531615925,
+    "eval_runtime": 4.4768,
     "eval_samples": 90,
-    "eval_samples_per_second": 24.76,
-    "eval_steps_per_second": 1.651,
+    "eval_samples_per_second": 20.104,
+    "eval_steps_per_second": 1.34,
     "total_flos": 658497592811520.0,
-    "train_loss": 0.07163158152838173,
-    "train_runtime": 255.4729,
+    "train_loss": 0.05426802725162146,
+    "train_runtime": 235.8554,
     "train_samples": 840,
-    "train_samples_per_second": 9.864,
-    "train_steps_per_second": 0.622
+    "train_samples_per_second": 10.685,
+    "train_steps_per_second": 0.674
 }

eval_results.json

@@ -1,24 +1,24 @@
 {
     "epoch": 3.0,
-    "eval_LOC_f1": 0.6274509803921569,
-    "eval_LOC_number": 76,
-    "eval_LOC_precision": 0.6233766233766234,
-    "eval_LOC_recall": 0.631578947368421,
-    "eval_ORG_f1": 0.7366375121477162,
-    "eval_ORG_number": 562,
-    "eval_ORG_precision": 0.8115631691648822,
-    "eval_ORG_recall": 0.6743772241992882,
-    "eval_PER_f1": 0.9866666666666666,
-    "eval_PER_number": 74,
-    "eval_PER_precision": 0.9736842105263158,
-    "eval_PER_recall": 1.0,
-    "eval_loss": 0.0689539760351181,
-    "eval_overall_accuracy": 0.9864484019907658,
-    "eval_overall_f1": 0.7522522522522522,
-    "eval_overall_precision": 0.8080645161290323,
-    "eval_overall_recall": 0.7036516853932584,
-    "eval_runtime": 3.6349,
+    "eval_LOC_f1": 0.6698564593301435,
+    "eval_LOC_number": 97,
+    "eval_LOC_precision": 0.625,
+    "eval_LOC_recall": 0.7216494845360825,
+    "eval_ORG_f1": 0.7464905037159372,
+    "eval_ORG_number": 673,
+    "eval_ORG_precision": 0.8401486988847584,
+    "eval_ORG_recall": 0.6716196136701337,
+    "eval_PER_f1": 0.95906432748538,
+    "eval_PER_number": 84,
+    "eval_PER_precision": 0.9425287356321839,
+    "eval_PER_recall": 0.9761904761904762,
+    "eval_loss": 0.07983002066612244,
+    "eval_overall_accuracy": 0.9853830393283693,
+    "eval_overall_f1": 0.7592708988057825,
+    "eval_overall_precision": 0.819538670284939,
+    "eval_overall_recall": 0.7072599531615925,
+    "eval_runtime": 4.4768,
     "eval_samples": 90,
-    "eval_samples_per_second": 24.76,
-    "eval_steps_per_second": 1.651
+    "eval_samples_per_second": 20.104,
+    "eval_steps_per_second": 1.34
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 658497592811520.0,
-    "train_loss": 0.07163158152838173,
-    "train_runtime": 255.4729,
+    "train_loss": 0.05426802725162146,
+    "train_runtime": 235.8554,
     "train_samples": 840,
-    "train_samples_per_second": 9.864,
-    "train_steps_per_second": 0.622
+    "train_samples_per_second": 10.685,
+    "train_steps_per_second": 0.674
 }

trainer_state.json

@@ -12,10 +12,10 @@
       "epoch": 3.0,
       "step": 159,
       "total_flos": 658497592811520.0,
-      "train_loss": 0.07163158152838173,
-      "train_runtime": 255.4729,
-      "train_samples_per_second": 9.864,
-      "train_steps_per_second": 0.622
+      "train_loss": 0.05426802725162146,
+      "train_runtime": 235.8554,
+      "train_samples_per_second": 10.685,
+      "train_steps_per_second": 0.674
     }
   ],
   "logging_steps": 500,