End of training

README.md

@@ -4,6 +4,7 @@ license: gemma
 base_model: google/gemma-3-1b-it
 tags:
 - llama-factory
+- lntuning
 - generated_from_trainer
 model-index:
 - name: train_multirc_1745950262
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_multirc_1745950262
 
-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 multirc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3402
+- Loss: 3.3166
 - Num Input Tokens Seen: 76963024
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.525328330206379,
+    "eval_loss": 3.316624164581299,
+    "eval_runtime": 66.2212,
+    "eval_samples_per_second": 41.15,
+    "eval_steps_per_second": 20.583,
+    "num_input_tokens_seen": 76963024,
+    "total_flos": 3.2232900582312346e+17,
+    "train_loss": 3.2710773272037508,
+    "train_runtime": 26847.8872,
+    "train_samples_per_second": 5.96,
+    "train_steps_per_second": 1.49
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.525328330206379,
+    "eval_loss": 3.316624164581299,
+    "eval_runtime": 66.2212,
+    "eval_samples_per_second": 41.15,
+    "eval_steps_per_second": 20.583,
+    "num_input_tokens_seen": 76963024
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.525328330206379,
+    "num_input_tokens_seen": 76963024,
+    "total_flos": 3.2232900582312346e+17,
+    "train_loss": 3.2710773272037508,
+    "train_runtime": 26847.8872,
+    "train_samples_per_second": 5.96,
+    "train_steps_per_second": 1.49
+}