End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: microsoft/deberta-v3-base
 tags:
 - generated_from_trainer
+datasets:
+- nbroad/company_names
 metrics:
 - precision
 - recall
@@ -10,7 +12,26 @@ metrics:
 - accuracy
 model-index:
 - name: deberta-v3-base-company-names
-  results: []
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: nbroad/company_names
+      type: nbroad/company_names
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.7739696312364425
+    - name: Recall
+      type: recall
+      value: 0.7962863774326013
+    - name: F1
+      type: f1
+      value: 0.7849694196330357
+    - name: Accuracy
+      type: accuracy
+      value: 0.9769126125154315
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,7 +39,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # deberta-v3-base-company-names
 
-This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the nbroad/company_names dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0693
 - Precision: 0.7740

all_results.json

@@ -5,13 +5,13 @@
     "eval_loss": 0.06933891773223877,
     "eval_precision": 0.7739696312364425,
     "eval_recall": 0.7962863774326013,
-    "eval_runtime": 13.9655,
+    "eval_runtime": 14.3197,
     "eval_samples": 14160,
-    "eval_samples_per_second": 1013.925,
-    "eval_steps_per_second": 126.741,
+    "eval_samples_per_second": 988.85,
+    "eval_steps_per_second": 123.606,
     "train_loss": 0.06623676680927928,
-    "train_runtime": 486.7718,
+    "train_runtime": 577.8703,
     "train_samples": 102018,
-    "train_samples_per_second": 628.742,
-    "train_steps_per_second": 13.103
+    "train_samples_per_second": 529.624,
+    "train_steps_per_second": 11.037
 }

eval_results.json

@@ -5,8 +5,8 @@
     "eval_loss": 0.06933891773223877,
     "eval_precision": 0.7739696312364425,
     "eval_recall": 0.7962863774326013,
-    "eval_runtime": 13.9655,
+    "eval_runtime": 14.3197,
     "eval_samples": 14160,
-    "eval_samples_per_second": 1013.925,
-    "eval_steps_per_second": 126.741
+    "eval_samples_per_second": 988.85,
+    "eval_steps_per_second": 123.606
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 0.06623676680927928,
-    "train_runtime": 486.7718,
+    "train_runtime": 577.8703,
     "train_samples": 102018,
-    "train_samples_per_second": 628.742,
-    "train_steps_per_second": 13.103
+    "train_samples_per_second": 529.624,
+    "train_steps_per_second": 11.037
 }

trainer_state.json

@@ -1287,9 +1287,9 @@
       "eval_loss": 0.0664275586605072,
       "eval_precision": 0.7416196481911715,
       "eval_recall": 0.7978932333511873,
-      "eval_runtime": 14.1977,
-      "eval_samples_per_second": 997.344,
-      "eval_steps_per_second": 124.668,
+      "eval_runtime": 16.3951,
+      "eval_samples_per_second": 863.673,
+      "eval_steps_per_second": 107.959,
       "step": 2126
     },
     {
@@ -2577,9 +2577,9 @@
       "eval_loss": 0.06523581594228745,
       "eval_precision": 0.7725130890052356,
       "eval_recall": 0.7903053026245314,
-      "eval_runtime": 14.0928,
-      "eval_samples_per_second": 1004.765,
-      "eval_steps_per_second": 125.596,
+      "eval_runtime": 16.6261,
+      "eval_samples_per_second": 851.671,
+      "eval_steps_per_second": 106.459,
       "step": 4252
     },
     {
@@ -3861,9 +3861,9 @@
       "eval_loss": 0.06933891773223877,
       "eval_precision": 0.7739696312364425,
       "eval_recall": 0.7962863774326013,
-      "eval_runtime": 14.2581,
-      "eval_samples_per_second": 993.122,
-      "eval_steps_per_second": 124.14,
+      "eval_runtime": 16.4386,
+      "eval_samples_per_second": 861.385,
+      "eval_steps_per_second": 107.673,
       "step": 6378
     },
     {
@@ -3871,9 +3871,9 @@
       "step": 6378,
       "total_flos": 1.2518895383371872e+16,
       "train_loss": 0.06623676680927928,
-      "train_runtime": 486.7718,
-      "train_samples_per_second": 628.742,
-      "train_steps_per_second": 13.103
+      "train_runtime": 577.8703,
+      "train_samples_per_second": 529.624,
+      "train_steps_per_second": 11.037
     }
   ],
   "logging_steps": 10,