End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: roberta-base
 tags:
 - generated_from_trainer
+datasets:
+- lltala/edgar_all_4-simple-no-valid-roberta-base
 model-index:
 - name: ner__edgar_all_4-simple-no-valid-roberta-base__roberta-base
   results: []
@@ -13,7 +15,25 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ner__edgar_all_4-simple-no-valid-roberta-base__roberta-base
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the lltala/edgar_all_4-simple-no-valid-roberta-base dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0045
+- Loc Precision: 0.8614
+- Loc Recall: 0.9355
+- Loc F1: 0.8969
+- Loc Number: 93
+- Org Precision: 0.9807
+- Org Recall: 0.9880
+- Org F1: 0.9844
+- Org Number: 669
+- Per Precision: 0.9432
+- Per Recall: 0.9881
+- Per F1: 0.9651
+- Per Number: 84
+- Overall Precision: 0.9629
+- Overall Recall: 0.9823
+- Overall F1: 0.9725
+- Overall Accuracy: 0.9987
 
 ## Model description
 

all_results.json

@@ -0,0 +1,30 @@
+{
+    "epoch": 3.0,
+    "eval_LOC_f1": 0.8969072164948454,
+    "eval_LOC_number": 93,
+    "eval_LOC_precision": 0.8613861386138614,
+    "eval_LOC_recall": 0.9354838709677419,
+    "eval_ORG_f1": 0.9843633655994043,
+    "eval_ORG_number": 669,
+    "eval_ORG_precision": 0.9807121661721068,
+    "eval_ORG_recall": 0.9880418535127056,
+    "eval_PER_f1": 0.9651162790697674,
+    "eval_PER_number": 84,
+    "eval_PER_precision": 0.9431818181818182,
+    "eval_PER_recall": 0.9880952380952381,
+    "eval_loss": 0.0044641378335654736,
+    "eval_overall_accuracy": 0.9986757283494079,
+    "eval_overall_f1": 0.9724985371562317,
+    "eval_overall_precision": 0.9629200463499421,
+    "eval_overall_recall": 0.9822695035460993,
+    "eval_runtime": 4.1653,
+    "eval_samples": 90,
+    "eval_samples_per_second": 21.607,
+    "eval_steps_per_second": 1.44,
+    "total_flos": 729031133306880.0,
+    "train_loss": 0.039226553534383826,
+    "train_runtime": 272.0205,
+    "train_samples": 930,
+    "train_samples_per_second": 10.257,
+    "train_steps_per_second": 0.651
+}

eval_results.json

@@ -0,0 +1,24 @@
+{
+    "epoch": 3.0,
+    "eval_LOC_f1": 0.8969072164948454,
+    "eval_LOC_number": 93,
+    "eval_LOC_precision": 0.8613861386138614,
+    "eval_LOC_recall": 0.9354838709677419,
+    "eval_ORG_f1": 0.9843633655994043,
+    "eval_ORG_number": 669,
+    "eval_ORG_precision": 0.9807121661721068,
+    "eval_ORG_recall": 0.9880418535127056,
+    "eval_PER_f1": 0.9651162790697674,
+    "eval_PER_number": 84,
+    "eval_PER_precision": 0.9431818181818182,
+    "eval_PER_recall": 0.9880952380952381,
+    "eval_loss": 0.0044641378335654736,
+    "eval_overall_accuracy": 0.9986757283494079,
+    "eval_overall_f1": 0.9724985371562317,
+    "eval_overall_precision": 0.9629200463499421,
+    "eval_overall_recall": 0.9822695035460993,
+    "eval_runtime": 4.1653,
+    "eval_samples": 90,
+    "eval_samples_per_second": 21.607,
+    "eval_steps_per_second": 1.44
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 729031133306880.0,
+    "train_loss": 0.039226553534383826,
+    "train_runtime": 272.0205,
+    "train_samples": 930,
+    "train_samples_per_second": 10.257,
+    "train_steps_per_second": 0.651
+}

trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 177,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 177,
+      "total_flos": 729031133306880.0,
+      "train_loss": 0.039226553534383826,
+      "train_runtime": 272.0205,
+      "train_samples_per_second": 10.257,
+      "train_steps_per_second": 0.651
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 177,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 729031133306880.0,
+  "trial_name": null,
+  "trial_params": null
+}