End of training

README.md

@@ -4,6 +4,7 @@ license: gemma
 base_model: google/gemma-3-1b-it
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: train_sst2_1744902619
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_sst2_1744902619
 
-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 sst2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2111
+- Loss: 0.0449
 - Num Input Tokens Seen: 36181120
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.55694866041969,
+    "eval_loss": 0.04491552338004112,
+    "eval_runtime": 89.247,
+    "eval_samples_per_second": 75.465,
+    "eval_steps_per_second": 18.869,
+    "num_input_tokens_seen": 36181120,
+    "total_flos": 1.5248651929632768e+17,
+    "train_loss": 0.01863706299899816,
+    "train_runtime": 51468.3542,
+    "train_samples_per_second": 12.435,
+    "train_steps_per_second": 0.777
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.55694866041969,
+    "eval_loss": 0.04491552338004112,
+    "eval_runtime": 89.247,
+    "eval_samples_per_second": 75.465,
+    "eval_steps_per_second": 18.869,
+    "num_input_tokens_seen": 36181120
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.55694866041969,
+    "num_input_tokens_seen": 36181120,
+    "total_flos": 1.5248651929632768e+17,
+    "train_loss": 0.01863706299899816,
+    "train_runtime": 51468.3542,
+    "train_samples_per_second": 12.435,
+    "train_steps_per_second": 0.777
+}