End of training

README.md

@@ -3,6 +3,11 @@ license: mit
 base_model: IRI2070/fa-address-bert-small-pytorch
 tags:
 - generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: fa-address-bert-small-pytorch-finetuned-ner
   results: []
@@ -14,6 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 # fa-address-bert-small-pytorch-finetuned-ner
 
 This model is a fine-tuned version of [IRI2070/fa-address-bert-small-pytorch](https://huggingface.co/IRI2070/fa-address-bert-small-pytorch) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2014
+- Precision: 0.9304
+- Recall: 0.9463
+- F1: 0.9383
+- Accuracy: 0.9689
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9688869881321501,
+    "eval_f1": 0.9383033419023136,
+    "eval_loss": 0.20143646001815796,
+    "eval_precision": 0.9304442825928624,
+    "eval_recall": 0.9462962962962963,
+    "eval_runtime": 0.8764,
+    "eval_samples": 859,
+    "eval_samples_per_second": 980.156,
+    "eval_steps_per_second": 123.233,
+    "train_loss": 0.031623102454038765,
+    "train_runtime": 93.4151,
+    "train_samples": 2595,
+    "train_samples_per_second": 277.792,
+    "train_steps_per_second": 34.791
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9688869881321501,
+    "eval_f1": 0.9383033419023136,
+    "eval_loss": 0.20143646001815796,
+    "eval_precision": 0.9304442825928624,
+    "eval_recall": 0.9462962962962963,
+    "eval_runtime": 0.8764,
+    "eval_samples": 859,
+    "eval_samples_per_second": 980.156,
+    "eval_steps_per_second": 123.233
+}

runs/Feb01_04-56-28_7cfc978934bd/events.out.tfevents.1706763499.7cfc978934bd.3577.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233119b1f3e11bbc68e968219bbcdbe4bf4b7b91719b6e205d4107c4b827ef46
+size 560

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.031623102454038765,
+    "train_runtime": 93.4151,
+    "train_samples": 2595,
+    "train_samples_per_second": 277.792,
+    "train_steps_per_second": 34.791
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 3250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.230769230769231e-05,
+      "loss": 0.1361,
+      "step": 500
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 0.0416,
+      "step": 1000
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 2.6923076923076923e-05,
+      "loss": 0.0154,
+      "step": 1500
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 0.0071,
+      "step": 2000
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.153846153846154e-05,
+      "loss": 0.0027,
+      "step": 2500
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.0021,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "step": 3250,
+      "total_flos": 34736444859384.0,
+      "train_loss": 0.031623102454038765,
+      "train_runtime": 93.4151,
+      "train_samples_per_second": 277.792,
+      "train_steps_per_second": 34.791
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 34736444859384.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}