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_2025-04-14-12-59-00
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_2025-04-14-12-59-00
 
-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 mnli_train dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.259452411994785,
+    "eval_mnli_eval_loss": 0.1455933004617691,
+    "eval_mnli_eval_runtime": 69.3338,
+    "eval_mnli_eval_samples_per_second": 141.807,
+    "eval_mnli_eval_steps_per_second": 17.726,
+    "num_input_tokens_seen": 108554416,
+    "total_flos": 4.545863769268347e+17,
+    "train_loss": 0.16975983584523202,
+    "train_runtime": 36201.0747,
+    "train_samples_per_second": 35.358,
+    "train_steps_per_second": 0.552
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.259452411994785,
+    "eval_mnli_eval_loss": 0.1455933004617691,
+    "eval_mnli_eval_runtime": 69.3338,
+    "eval_mnli_eval_samples_per_second": 141.807,
+    "eval_mnli_eval_steps_per_second": 17.726,
+    "num_input_tokens_seen": 108554416
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.259452411994785,
+    "num_input_tokens_seen": 108554416,
+    "total_flos": 4.545863769268347e+17,
+    "train_loss": 0.16975983584523202,
+    "train_runtime": 36201.0747,
+    "train_samples_per_second": 35.358,
+    "train_steps_per_second": 0.552
+}