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_record_1745950246
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_record_1745950246
 
-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 record dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7300
+- Loss: 0.7299
 - Num Input Tokens Seen: 55002224
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.2803277639075603,
+    "eval_loss": 0.7298663258552551,
+    "eval_runtime": 347.8477,
+    "eval_samples_per_second": 39.92,
+    "eval_steps_per_second": 19.96,
+    "num_input_tokens_seen": 55002224,
+    "total_flos": 2.3032929154239283e+17,
+    "train_loss": 0.8202396101236343,
+    "train_runtime": 83869.5715,
+    "train_samples_per_second": 1.908,
+    "train_steps_per_second": 0.477
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.2803277639075603,
+    "eval_loss": 0.7298663258552551,
+    "eval_runtime": 347.8477,
+    "eval_samples_per_second": 39.92,
+    "eval_steps_per_second": 19.96,
+    "num_input_tokens_seen": 55002224
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.2803277639075603,
+    "num_input_tokens_seen": 55002224,
+    "total_flos": 2.3032929154239283e+17,
+    "train_loss": 0.8202396101236343,
+    "train_runtime": 83869.5715,
+    "train_samples_per_second": 1.908,
+    "train_steps_per_second": 0.477
+}