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: 0.3905
+- Disorder Finding Precision: 0.0
+- Disorder Finding Recall: 0.0
+- Disorder Finding F1: 0.0
+- Disorder Finding Number: 3
+- Overall Precision: 0.0
+- Overall Recall: 0.0
+- Overall F1: 0.0
+- Overall Accuracy: 0.9466
 
 ## Model description
 

all_results.json

@@ -1,22 +1,22 @@
 {
     "epoch": 1.0,
     "eval_DISORDER_FINDING_f1": 0.0,
-    "eval_DISORDER_FINDING_number": 15,
+    "eval_DISORDER_FINDING_number": 3,
     "eval_DISORDER_FINDING_precision": 0.0,
     "eval_DISORDER_FINDING_recall": 0.0,
-    "eval_loss": 0.4317980706691742,
-    "eval_overall_accuracy": 0.8944954128440367,
+    "eval_loss": 0.39048948884010315,
+    "eval_overall_accuracy": 0.9466019417475728,
     "eval_overall_f1": 0.0,
     "eval_overall_precision": 0.0,
     "eval_overall_recall": 0.0,
-    "eval_runtime": 0.2659,
+    "eval_runtime": 0.1748,
     "eval_samples": 8,
-    "eval_samples_per_second": 30.086,
-    "eval_steps_per_second": 3.761,
+    "eval_samples_per_second": 45.761,
+    "eval_steps_per_second": 5.72,
     "total_flos": 169988587296.0,
-    "train_loss": 0.5974887609481812,
-    "train_runtime": 5.1721,
+    "train_loss": 0.5619458059469858,
+    "train_runtime": 3.0391,
     "train_samples": 364,
-    "train_samples_per_second": 70.377,
-    "train_steps_per_second": 1.16
+    "train_samples_per_second": 119.77,
+    "train_steps_per_second": 1.974
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 1.0,
     "eval_DISORDER_FINDING_f1": 0.0,
-    "eval_DISORDER_FINDING_number": 15,
+    "eval_DISORDER_FINDING_number": 3,
     "eval_DISORDER_FINDING_precision": 0.0,
     "eval_DISORDER_FINDING_recall": 0.0,
-    "eval_loss": 0.4317980706691742,
-    "eval_overall_accuracy": 0.8944954128440367,
+    "eval_loss": 0.39048948884010315,
+    "eval_overall_accuracy": 0.9466019417475728,
     "eval_overall_f1": 0.0,
     "eval_overall_precision": 0.0,
     "eval_overall_recall": 0.0,
-    "eval_runtime": 0.2659,
+    "eval_runtime": 0.1748,
     "eval_samples": 8,
-    "eval_samples_per_second": 30.086,
-    "eval_steps_per_second": 3.761
+    "eval_samples_per_second": 45.761,
+    "eval_steps_per_second": 5.72
 }

runs/Oct24_07-52-45_ip-172-31-12-22/events.out.tfevents.1761292383.ip-172-31-12-22.19193.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538bbabdda2f8d19fe562f6093da648481bed7003fa88327499fe027cde8299e
+size 846

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 169988587296.0,
-    "train_loss": 0.5974887609481812,
-    "train_runtime": 5.1721,
+    "train_loss": 0.5619458059469858,
+    "train_runtime": 3.0391,
     "train_samples": 364,
-    "train_samples_per_second": 70.377,
-    "train_steps_per_second": 1.16
+    "train_samples_per_second": 119.77,
+    "train_steps_per_second": 1.974
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 5.697927474975586,
+      "grad_norm": 6.950458526611328,
       "learning_rate": 5e-05,
-      "loss": 0.7112,
+      "loss": 0.7032,
       "step": 1
     },
     {
       "epoch": 1.0,
       "step": 6,
       "total_flos": 169988587296.0,
-      "train_loss": 0.5974887609481812,
-      "train_runtime": 5.1721,
-      "train_samples_per_second": 70.377,
-      "train_steps_per_second": 1.16
+      "train_loss": 0.5619458059469858,
+      "train_runtime": 3.0391,
+      "train_samples_per_second": 119.77,
+      "train_steps_per_second": 1.974
     }
   ],
   "logging_steps": 100,