End of training

README.md

@@ -4,6 +4,7 @@ license: gemma
 base_model: google/gemma-3-1b-it
 tags:
 - llama-factory
+- prompt-tuning
 - generated_from_trainer
 model-index:
 - name: train_qqp_1744902593
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_qqp_1744902593
 
-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 qqp dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0835
+- Loss: 0.0834
 - Num Input Tokens Seen: 51858816
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.9544377397210075,
+    "eval_loss": 0.08336079865694046,
+    "eval_runtime": 401.6364,
+    "eval_samples_per_second": 90.592,
+    "eval_steps_per_second": 22.65,
+    "num_input_tokens_seen": 51858816,
+    "total_flos": 2.1715238142060134e+17,
+    "train_loss": 0.10561876927614212,
+    "train_runtime": 96179.8765,
+    "train_samples_per_second": 6.654,
+    "train_steps_per_second": 0.416
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9544377397210075,
+    "eval_loss": 0.08336079865694046,
+    "eval_runtime": 401.6364,
+    "eval_samples_per_second": 90.592,
+    "eval_steps_per_second": 22.65,
+    "num_input_tokens_seen": 51858816
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9544377397210075,
+    "num_input_tokens_seen": 51858816,
+    "total_flos": 2.1715238142060134e+17,
+    "train_loss": 0.10561876927614212,
+    "train_runtime": 96179.8765,
+    "train_samples_per_second": 6.654,
+    "train_steps_per_second": 0.416
+}