End of training

README.md

@@ -4,6 +4,7 @@ license: gemma
 base_model: google/gemma-3-1b-it
 tags:
 - llama-factory
+- ia3
 - generated_from_trainer
 datasets:
 - super_glue
@@ -17,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_boolq_1745950271
 
-This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) on the super_glue dataset.
+This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) on the boolq dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2003
+- Loss: 0.1989
 - Num Input Tokens Seen: 34633072
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 18.85902876001886,
+    "eval_loss": 0.19886288046836853,
+    "eval_runtime": 22.1847,
+    "eval_samples_per_second": 42.507,
+    "eval_steps_per_second": 21.276,
+    "num_input_tokens_seen": 34633072,
+    "total_flos": 1.450306979895337e+17,
+    "train_loss": 0.19550500297993423,
+    "train_runtime": 18418.8323,
+    "train_samples_per_second": 8.687,
+    "train_steps_per_second": 2.172
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 18.85902876001886,
+    "eval_loss": 0.19886288046836853,
+    "eval_runtime": 22.1847,
+    "eval_samples_per_second": 42.507,
+    "eval_steps_per_second": 21.276,
+    "num_input_tokens_seen": 34633072
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 18.85902876001886,
+    "num_input_tokens_seen": 34633072,
+    "total_flos": 1.450306979895337e+17,
+    "train_loss": 0.19550500297993423,
+    "train_runtime": 18418.8323,
+    "train_samples_per_second": 8.687,
+    "train_steps_per_second": 2.172
+}