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
 datasets:
 - super_glue
@@ -17,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_cb_1745950309
 
-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 cb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8050
+- Loss: 0.1622
 - Num Input Tokens Seen: 22718312
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 701.7610619469026,
+    "eval_loss": 0.16221453249454498,
+    "eval_runtime": 0.9163,
+    "eval_samples_per_second": 27.285,
+    "eval_steps_per_second": 14.188,
+    "num_input_tokens_seen": 22718312,
+    "total_flos": 9.51301231531438e+16,
+    "train_loss": 0.015288212282552349,
+    "train_runtime": 8564.9201,
+    "train_samples_per_second": 18.681,
+    "train_steps_per_second": 4.67
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 701.7610619469026,
+    "eval_loss": 0.16221453249454498,
+    "eval_runtime": 0.9163,
+    "eval_samples_per_second": 27.285,
+    "eval_steps_per_second": 14.188,
+    "num_input_tokens_seen": 22718312
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 701.7610619469026,
+    "num_input_tokens_seen": 22718312,
+    "total_flos": 9.51301231531438e+16,
+    "train_loss": 0.015288212282552349,
+    "train_runtime": 8564.9201,
+    "train_samples_per_second": 18.681,
+    "train_steps_per_second": 4.67
+}