Upload demo NER model for de

README.md

@@ -1,9 +1,13 @@
 ---
 library_name: transformers
+language:
+- multilingual
 license: other
 base_model: DedalusHealthCare/tinybert-mlm-de
 tags:
 - generated_from_trainer
+datasets:
+- ner_demo_de
 model-index:
 - name: tinybert-demo-de
   results: []
@@ -14,7 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinybert-demo-de
 
-This model is a fine-tuned version of [DedalusHealthCare/tinybert-mlm-de](https://huggingface.co/DedalusHealthCare/tinybert-mlm-de) on the None dataset.
+This model is a fine-tuned version of [DedalusHealthCare/tinybert-mlm-de](https://huggingface.co/DedalusHealthCare/tinybert-mlm-de) on the ner_demo_de dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4318
+- Disorder Finding Precision: 0.0
+- Disorder Finding Recall: 0.0
+- Disorder Finding F1: 0.0
+- Disorder Finding Number: 15
+- Overall Precision: 0.0
+- Overall Recall: 0.0
+- Overall F1: 0.0
+- Overall Accuracy: 0.8945
 
 ## Model description
 

all_results.json

@@ -1,22 +1,22 @@
 {
     "epoch": 1.0,
-    "eval_DISORDER_FINDING_f1": 0.2105263157894737,
-    "eval_DISORDER_FINDING_number": 11,
-    "eval_DISORDER_FINDING_precision": 0.25,
-    "eval_DISORDER_FINDING_recall": 0.18181818181818182,
-    "eval_loss": 0.4068782925605774,
-    "eval_overall_accuracy": 0.9285714285714286,
-    "eval_overall_f1": 0.2105263157894737,
-    "eval_overall_precision": 0.25,
-    "eval_overall_recall": 0.18181818181818182,
-    "eval_runtime": 0.3382,
+    "eval_DISORDER_FINDING_f1": 0.0,
+    "eval_DISORDER_FINDING_number": 15,
+    "eval_DISORDER_FINDING_precision": 0.0,
+    "eval_DISORDER_FINDING_recall": 0.0,
+    "eval_loss": 0.4317980706691742,
+    "eval_overall_accuracy": 0.8944954128440367,
+    "eval_overall_f1": 0.0,
+    "eval_overall_precision": 0.0,
+    "eval_overall_recall": 0.0,
+    "eval_runtime": 0.1838,
     "eval_samples": 8,
-    "eval_samples_per_second": 23.656,
-    "eval_steps_per_second": 2.957,
+    "eval_samples_per_second": 43.516,
+    "eval_steps_per_second": 5.439,
     "total_flos": 169988587296.0,
-    "train_loss": 0.5817014575004578,
-    "train_runtime": 2.8467,
+    "train_loss": 0.5974887609481812,
+    "train_runtime": 2.6732,
     "train_samples": 364,
-    "train_samples_per_second": 127.867,
-    "train_steps_per_second": 2.108
+    "train_samples_per_second": 136.168,
+    "train_steps_per_second": 2.245
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 1.0,
-    "eval_DISORDER_FINDING_f1": 0.2105263157894737,
-    "eval_DISORDER_FINDING_number": 11,
-    "eval_DISORDER_FINDING_precision": 0.25,
-    "eval_DISORDER_FINDING_recall": 0.18181818181818182,
-    "eval_loss": 0.4068782925605774,
-    "eval_overall_accuracy": 0.9285714285714286,
-    "eval_overall_f1": 0.2105263157894737,
-    "eval_overall_precision": 0.25,
-    "eval_overall_recall": 0.18181818181818182,
-    "eval_runtime": 0.3382,
+    "eval_DISORDER_FINDING_f1": 0.0,
+    "eval_DISORDER_FINDING_number": 15,
+    "eval_DISORDER_FINDING_precision": 0.0,
+    "eval_DISORDER_FINDING_recall": 0.0,
+    "eval_loss": 0.4317980706691742,
+    "eval_overall_accuracy": 0.8944954128440367,
+    "eval_overall_f1": 0.0,
+    "eval_overall_precision": 0.0,
+    "eval_overall_recall": 0.0,
+    "eval_runtime": 0.1838,
     "eval_samples": 8,
-    "eval_samples_per_second": 23.656,
-    "eval_steps_per_second": 2.957
+    "eval_samples_per_second": 43.516,
+    "eval_steps_per_second": 5.439
 }

runs/Oct20_12-48-25_ip-172-31-12-22/events.out.tfevents.1760964524.ip-172-31-12-22.6673.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f1d6a4274dc507795b5c50b129d1ec23e2affa81732567ad1ea897a9968cf5
+size 846

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 169988587296.0,
-    "train_loss": 0.5817014575004578,
-    "train_runtime": 2.8467,
+    "train_loss": 0.5974887609481812,
+    "train_runtime": 2.6732,
     "train_samples": 364,
-    "train_samples_per_second": 127.867,
-    "train_steps_per_second": 2.108
+    "train_samples_per_second": 136.168,
+    "train_steps_per_second": 2.245
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 6.177765846252441,
+      "grad_norm": 5.697927474975586,
       "learning_rate": 5e-05,
-      "loss": 0.6855,
+      "loss": 0.7112,
       "step": 1
     },
     {
       "epoch": 1.0,
       "step": 6,
       "total_flos": 169988587296.0,
-      "train_loss": 0.5817014575004578,
-      "train_runtime": 2.8467,
-      "train_samples_per_second": 127.867,
-      "train_steps_per_second": 2.108
+      "train_loss": 0.5974887609481812,
+      "train_runtime": 2.6732,
+      "train_samples_per_second": 136.168,
+      "train_steps_per_second": 2.245
     }
   ],
   "logging_steps": 100,