End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- ia3
 - generated_from_trainer
 model-index:
 - name: train_multirc_456_1767559857
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_multirc_456_1767559857
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the multirc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1315
+- Loss: 0.1269
 - Num Input Tokens Seen: 264580656
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.1268720179796219,
+    "eval_runtime": 91.1457,
+    "eval_samples_per_second": 29.897,
+    "eval_steps_per_second": 7.483,
+    "num_input_tokens_seen": 264580656,
+    "total_flos": 1.1914259469731758e+19,
+    "train_loss": 0.12831777033804753,
+    "train_runtime": 55289.6349,
+    "train_samples_per_second": 8.869,
+    "train_steps_per_second": 2.217
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.1268720179796219,
+    "eval_runtime": 91.1457,
+    "eval_samples_per_second": 29.897,
+    "eval_steps_per_second": 7.483,
+    "num_input_tokens_seen": 264580656
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 264580656,
+    "total_flos": 1.1914259469731758e+19,
+    "train_loss": 0.12831777033804753,
+    "train_runtime": 55289.6349,
+    "train_samples_per_second": 8.869,
+    "train_steps_per_second": 2.217
+}