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_codealpacapy_456_1765330670
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_codealpacapy_456_1765330670
 
-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 codealpacapy dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4603
 - Num Input Tokens Seen: 24973864

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.4603464603424072,
+    "eval_runtime": 9.8948,
+    "eval_samples_per_second": 85.702,
+    "eval_steps_per_second": 21.425,
+    "num_input_tokens_seen": 24973864,
+    "total_flos": 1.1245912689013555e+18,
+    "train_loss": 0.5332972578844934,
+    "train_runtime": 7012.9299,
+    "train_samples_per_second": 21.757,
+    "train_steps_per_second": 5.441
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.4603464603424072,
+    "eval_runtime": 9.8948,
+    "eval_samples_per_second": 85.702,
+    "eval_steps_per_second": 21.425,
+    "num_input_tokens_seen": 24973864
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 24973864,
+    "total_flos": 1.1245912689013555e+18,
+    "train_loss": 0.5332972578844934,
+    "train_runtime": 7012.9299,
+    "train_samples_per_second": 21.757,
+    "train_steps_per_second": 5.441
+}