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
 model-index:
 - name: train_wsc_1745950296
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_wsc_1745950296
 
-This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) on the wsc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5860
+- Loss: 0.2355
 - Num Input Tokens Seen: 14005200
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 320.0,
+    "eval_loss": 0.2355487048625946,
+    "eval_runtime": 2.3179,
+    "eval_samples_per_second": 24.16,
+    "eval_steps_per_second": 12.08,
+    "num_input_tokens_seen": 14005200,
+    "total_flos": 5.86486792590336e+16,
+    "train_loss": 0.20673438400998712,
+    "train_runtime": 14412.7884,
+    "train_samples_per_second": 11.101,
+    "train_steps_per_second": 2.775
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 320.0,
+    "eval_loss": 0.2355487048625946,
+    "eval_runtime": 2.3179,
+    "eval_samples_per_second": 24.16,
+    "eval_steps_per_second": 12.08,
+    "num_input_tokens_seen": 14005200
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 320.0,
+    "num_input_tokens_seen": 14005200,
+    "total_flos": 5.86486792590336e+16,
+    "train_loss": 0.20673438400998712,
+    "train_runtime": 14412.7884,
+    "train_samples_per_second": 11.101,
+    "train_steps_per_second": 2.775
+}