End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+trainer_state.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,9 +1,23 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- roneneldan/TinyStories
+metrics:
+- accuracy
 model-index:
 - name: mistral-1L-tiny
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: roneneldan/TinyStories
+      type: roneneldan/TinyStories
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5792084706530948
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,7 +25,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-1L-tiny
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the roneneldan/TinyStories dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6868
+- Accuracy: 0.5792
 
 ## Model description
 

all_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5792084706530948,
+    "eval_loss": 1.6868340969085693,
+    "eval_runtime": 23.785,
+    "eval_samples": 19348,
+    "eval_samples_per_second": 813.455,
+    "eval_steps_per_second": 101.703,
+    "perplexity": 5.4023502853454595
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5792084706530948,
+    "eval_loss": 1.6868340969085693,
+    "eval_runtime": 23.785,
+    "eval_samples": 19348,
+    "eval_samples_per_second": 813.455,
+    "eval_steps_per_second": 101.703,
+    "perplexity": 5.4023502853454595
+}