End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0412
-- F1: 0.9867
+- Loss: 0.0257
+- F1: 0.9846
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 29.86912468336617,
+    "eval_f1": 0.9845907544526716,
+    "eval_loss": 0.025670213624835014,
+    "eval_runtime": 26.3199,
+    "eval_samples": 4998,
+    "eval_samples_per_second": 189.894,
+    "eval_steps_per_second": 5.965,
+    "total_flos": 6.416188329447916e+18,
+    "train_loss": 0.47501611844734387,
+    "train_runtime": 78338.6368,
+    "train_samples": 227390,
+    "train_samples_per_second": 87.08,
+    "train_steps_per_second": 0.085
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 29.86912468336617,
+    "eval_f1": 0.9845907544526716,
+    "eval_loss": 0.025670213624835014,
+    "eval_runtime": 26.3199,
+    "eval_samples": 4998,
+    "eval_samples_per_second": 189.894,
+    "eval_steps_per_second": 5.965
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 29.86912468336617,
+    "total_flos": 6.416188329447916e+18,
+    "train_loss": 0.47501611844734387,
+    "train_runtime": 78338.6368,
+    "train_samples": 227390,
+    "train_samples_per_second": 87.08,
+    "train_steps_per_second": 0.085
+}