End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: microsoft/xtremedistil-l6-h256-uncased
 tags:
 - generated_from_trainer
+datasets:
+- nbroad/company_names
 metrics:
 - precision
 - recall
@@ -10,7 +12,26 @@ metrics:
 - accuracy
 model-index:
 - name: xtremedistil-l6-h256-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: 0.6998602375960866
+    - name: Recall
+      type: recall
+      value: 0.7154210197339048
+    - name: F1
+      type: f1
+      value: 0.7075550845586612
+    - name: Accuracy
+      type: accuracy
+      value: 0.9702296390871982
 ---
 
 <!-- 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. -->
 
 # xtremedistil-l6-h256-company-names
 
-This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on the nbroad/company_names dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0789
 - Precision: 0.6999

all_results.json

@@ -5,13 +5,13 @@
     "eval_loss": 0.07886078208684921,
     "eval_precision": 0.6998602375960866,
     "eval_recall": 0.7154210197339048,
-    "eval_runtime": 7.1372,
+    "eval_runtime": 7.0144,
     "eval_samples": 14160,
-    "eval_samples_per_second": 1983.973,
-    "eval_steps_per_second": 247.997,
+    "eval_samples_per_second": 2018.718,
+    "eval_steps_per_second": 252.34,
     "train_loss": 0.11718836608034722,
-    "train_runtime": 82.9226,
+    "train_runtime": 82.4816,
     "train_samples": 102018,
-    "train_samples_per_second": 3690.84,
-    "train_steps_per_second": 76.915
+    "train_samples_per_second": 3710.575,
+    "train_steps_per_second": 77.326
 }

eval_results.json

@@ -5,8 +5,8 @@
     "eval_loss": 0.07886078208684921,
     "eval_precision": 0.6998602375960866,
     "eval_recall": 0.7154210197339048,
-    "eval_runtime": 7.1372,
+    "eval_runtime": 7.0144,
     "eval_samples": 14160,
-    "eval_samples_per_second": 1983.973,
-    "eval_steps_per_second": 247.997
+    "eval_samples_per_second": 2018.718,
+    "eval_steps_per_second": 252.34
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 0.11718836608034722,
-    "train_runtime": 82.9226,
+    "train_runtime": 82.4816,
     "train_samples": 102018,
-    "train_samples_per_second": 3690.84,
-    "train_steps_per_second": 76.915
+    "train_samples_per_second": 3710.575,
+    "train_steps_per_second": 77.326
 }

trainer_state.json

@@ -1287,9 +1287,9 @@
       "eval_loss": 0.08540353178977966,
       "eval_precision": 0.6823800738007381,
       "eval_recall": 0.6605054022680596,
-      "eval_runtime": 7.0155,
-      "eval_samples_per_second": 2018.388,
-      "eval_steps_per_second": 252.299,
+      "eval_runtime": 6.9434,
+      "eval_samples_per_second": 2039.333,
+      "eval_steps_per_second": 254.917,
       "step": 2126
     },
     {
@@ -2577,9 +2577,9 @@
       "eval_loss": 0.08137683570384979,
       "eval_precision": 0.692483315770987,
       "eval_recall": 0.7041700151799268,
-      "eval_runtime": 7.1401,
-      "eval_samples_per_second": 1983.156,
-      "eval_steps_per_second": 247.895,
+      "eval_runtime": 7.0711,
+      "eval_samples_per_second": 2002.51,
+      "eval_steps_per_second": 250.314,
       "step": 4252
     },
     {
@@ -3861,9 +3861,9 @@
       "eval_loss": 0.07886078208684921,
       "eval_precision": 0.6998602375960866,
       "eval_recall": 0.7154210197339048,
-      "eval_runtime": 7.0493,
-      "eval_samples_per_second": 2008.711,
-      "eval_steps_per_second": 251.089,
+      "eval_runtime": 6.9707,
+      "eval_samples_per_second": 2031.371,
+      "eval_steps_per_second": 253.921,
       "step": 6378
     },
     {
@@ -3871,9 +3871,9 @@
       "step": 6378,
       "total_flos": 725952230430336.0,
       "train_loss": 0.11718836608034722,
-      "train_runtime": 82.9226,
-      "train_samples_per_second": 3690.84,
-      "train_steps_per_second": 76.915
+      "train_runtime": 82.4816,
+      "train_samples_per_second": 3710.575,
+      "train_steps_per_second": 77.326
     }
   ],
   "logging_steps": 10,