End of training

README.md

@@ -5,9 +5,36 @@ tags:
 - generated_from_trainer
 datasets:
 - wnut_17
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: ner_model
-  results: []
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: wnut_17
+      type: wnut_17
+      config: wnut_17
+      split: validation
+      args: wnut_17
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.6122448979591837
+    - name: Recall
+      type: recall
+      value: 0.430622009569378
+    - name: F1
+      type: f1
+      value: 0.5056179775280899
+    - name: Accuracy
+      type: accuracy
+      value: 0.9499141930973114
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +43,12 @@ should probably proofread and complete it, then remove this comment. -->
 # ner_model
 
 This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the wnut_17 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2729
+- Precision: 0.6122
+- Recall: 0.4306
+- F1: 0.5056
+- Accuracy: 0.9499
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9553054866806535,
-    "eval_f1": 0.590027700831025,
-    "eval_loss": 0.2586243450641632,
-    "eval_precision": 0.7006578947368421,
-    "eval_recall": 0.5095693779904307,
-    "eval_runtime": 1.8637,
+    "eval_accuracy": 0.9499141930973114,
+    "eval_f1": 0.5056179775280899,
+    "eval_loss": 0.2729117274284363,
+    "eval_precision": 0.6122448979591837,
+    "eval_recall": 0.430622009569378,
+    "eval_runtime": 1.9245,
     "eval_samples": 1009,
-    "eval_samples_per_second": 541.382,
-    "eval_steps_per_second": 68.142,
-    "train_loss": 0.10290272581811044,
-    "train_runtime": 78.6134,
+    "eval_samples_per_second": 524.305,
+    "eval_steps_per_second": 65.993,
+    "train_loss": 0.09562072828704235,
+    "train_runtime": 125.9576,
     "train_samples": 3394,
-    "train_samples_per_second": 129.52,
-    "train_steps_per_second": 16.219
+    "train_samples_per_second": 80.837,
+    "train_steps_per_second": 10.122
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9553054866806535,
-    "eval_f1": 0.590027700831025,
-    "eval_loss": 0.2586243450641632,
-    "eval_precision": 0.7006578947368421,
-    "eval_recall": 0.5095693779904307,
-    "eval_runtime": 1.8637,
+    "eval_accuracy": 0.9499141930973114,
+    "eval_f1": 0.5056179775280899,
+    "eval_loss": 0.2729117274284363,
+    "eval_precision": 0.6122448979591837,
+    "eval_recall": 0.430622009569378,
+    "eval_runtime": 1.9245,
     "eval_samples": 1009,
-    "eval_samples_per_second": 541.382,
-    "eval_steps_per_second": 68.142
+    "eval_samples_per_second": 524.305,
+    "eval_steps_per_second": 65.993
 }

runs/Dec05_06-40-48_ddba0bfe6b5f/events.out.tfevents.1701758685.ddba0bfe6b5f.848.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c50f93de690ca19f3468f7b801752ef8db1a70257073c549cae838bcdcd5ad
+size 560

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.10290272581811044,
-    "train_runtime": 78.6134,
+    "train_loss": 0.09562072828704235,
+    "train_runtime": 125.9576,
     "train_samples": 3394,
-    "train_samples_per_second": 129.52,
-    "train_steps_per_second": 16.219
+    "train_samples_per_second": 80.837,
+    "train_steps_per_second": 10.122
 }

trainer_state.json

@@ -11,23 +11,23 @@
     {
       "epoch": 1.18,
       "learning_rate": 3.0392156862745097e-05,
-      "loss": 0.1847,
+      "loss": 0.1665,
       "step": 500
     },
     {
       "epoch": 2.35,
       "learning_rate": 1.0784313725490197e-05,
-      "loss": 0.0585,
+      "loss": 0.0587,
       "step": 1000
     },
     {
       "epoch": 3.0,
       "step": 1275,
-      "total_flos": 127179336805920.0,
-      "train_loss": 0.10290272581811044,
-      "train_runtime": 78.6134,
-      "train_samples_per_second": 129.52,
-      "train_steps_per_second": 16.219
+      "total_flos": 140113503536760.0,
+      "train_loss": 0.09562072828704235,
+      "train_runtime": 125.9576,
+      "train_samples_per_second": 80.837,
+      "train_steps_per_second": 10.122
     }
   ],
   "logging_steps": 500,
@@ -35,7 +35,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 127179336805920.0,
+  "total_flos": 140113503536760.0,
   "trial_name": null,
   "trial_params": null
 }