End of training

README.md

@@ -3,12 +3,27 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Llama-3.1-8B-Instruct
 tags:
+- multi-label
+- question-answering
+- text-classification
 - generated_from_trainer
+datasets:
+- beavertails
 metrics:
 - accuracy
 model-index:
 - name: QA-Llama-3.1-4155
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: saiteki-kai/BeaverTails-it
+      type: beavertails
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6964434241607612
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,20 +31,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # QA-Llama-3.1-4155
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the saiteki-kai/BeaverTails-it dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0781
-- Accuracy: 0.6965
-- Macro F1: 0.6444
-- Macro Precision: 0.7361
-- Macro Recall: 0.5968
+- Accuracy: 0.6964
+- Macro F1: 0.6445
+- Macro Precision: 0.7365
+- Macro Recall: 0.5970
 - Micro F1: 0.7539
-- Micro Precision: 0.8035
+- Micro Precision: 0.8036
 - Micro Recall: 0.7100
-- Flagged/accuracy: 0.8561
+- Flagged/accuracy: 0.8560
 - Flagged/precision: 0.9050
-- Flagged/recall: 0.8284
-- Flagged/f1: 0.8650
+- Flagged/recall: 0.8283
+- Flagged/f1: 0.8649
 
 ## Model description
 

all_results.json

@@ -0,0 +1,38 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6964434241607612,
+    "eval_flagged/accuracy": 0.856040190305087,
+    "eval_flagged/f1": 0.8649247674346008,
+    "eval_flagged/precision": 0.9049547636933729,
+    "eval_flagged/recall": 0.8282861498908852,
+    "eval_loss": 0.07808855175971985,
+    "eval_macro_f1": 0.6445018666803658,
+    "eval_macro_precision": 0.7364622252548454,
+    "eval_macro_recall": 0.5969831652053833,
+    "eval_micro_f1": 0.7539061393653881,
+    "eval_micro_precision": 0.8036066497604959,
+    "eval_micro_recall": 0.7099951988904102,
+    "eval_runtime": 86.4772,
+    "eval_samples_per_second": 695.143,
+    "eval_steps_per_second": 5.435,
+    "test_accuracy": 0.6834501137860821,
+    "test_flagged/accuracy": 0.8485147921906815,
+    "test_flagged/f1": 0.8584934687141619,
+    "test_flagged/precision": 0.8994256241941155,
+    "test_flagged/recall": 0.8211247257745198,
+    "test_loss": 0.08345632255077362,
+    "test_macro_f1": 0.6200746051485584,
+    "test_macro_precision": 0.7147873439119878,
+    "test_macro_recall": 0.5715412667131191,
+    "test_micro_f1": 0.7434023275005474,
+    "test_micro_precision": 0.7991924971031287,
+    "test_micro_recall": 0.6948931078996253,
+    "test_runtime": 90.6304,
+    "test_samples_per_second": 736.971,
+    "test_steps_per_second": 5.76,
+    "total_flos": 1.0625604952409506e+19,
+    "train_loss": 0.07807489077325368,
+    "train_runtime": 15386.354,
+    "train_samples_per_second": 105.487,
+    "train_steps_per_second": 1.648
+}

eval_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6964434241607612,
+    "eval_flagged/accuracy": 0.856040190305087,
+    "eval_flagged/f1": 0.8649247674346008,
+    "eval_flagged/precision": 0.9049547636933729,
+    "eval_flagged/recall": 0.8282861498908852,
+    "eval_loss": 0.07808855175971985,
+    "eval_macro_f1": 0.6445018666803658,
+    "eval_macro_precision": 0.7364622252548454,
+    "eval_macro_recall": 0.5969831652053833,
+    "eval_micro_f1": 0.7539061393653881,
+    "eval_micro_precision": 0.8036066497604959,
+    "eval_micro_recall": 0.7099951988904102,
+    "eval_runtime": 86.4772,
+    "eval_samples_per_second": 695.143,
+    "eval_steps_per_second": 5.435
+}

test_results.json

@@ -0,0 +1,17 @@
+{
+    "test_accuracy": 0.6834501137860821,
+    "test_flagged/accuracy": 0.8485147921906815,
+    "test_flagged/f1": 0.8584934687141619,
+    "test_flagged/precision": 0.8994256241941155,
+    "test_flagged/recall": 0.8211247257745198,
+    "test_loss": 0.08345632255077362,
+    "test_macro_f1": 0.6200746051485584,
+    "test_macro_precision": 0.7147873439119878,
+    "test_macro_recall": 0.5715412667131191,
+    "test_micro_f1": 0.7434023275005474,
+    "test_micro_precision": 0.7991924971031287,
+    "test_micro_recall": 0.6948931078996253,
+    "test_runtime": 90.6304,
+    "test_samples_per_second": 736.971,
+    "test_steps_per_second": 5.76
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.0625604952409506e+19,
+    "train_loss": 0.07807489077325368,
+    "train_runtime": 15386.354,
+    "train_samples_per_second": 105.487,
+    "train_steps_per_second": 1.648
+}