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_copa_1745950325
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_copa_1745950325
 
-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 copa dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3407
+- Loss: 0.0824
 - Num Input Tokens Seen: 10717440
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 444.44444444444446,
+    "eval_loss": 0.0824187621474266,
+    "eval_runtime": 1.0472,
+    "eval_samples_per_second": 38.197,
+    "eval_steps_per_second": 19.098,
+    "num_input_tokens_seen": 10717440,
+    "total_flos": 4.826141220667392e+17,
+    "train_loss": 0.005107367473887284,
+    "train_runtime": 12281.6577,
+    "train_samples_per_second": 13.028,
+    "train_steps_per_second": 3.257
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 444.44444444444446,
+    "eval_loss": 0.0824187621474266,
+    "eval_runtime": 1.0472,
+    "eval_samples_per_second": 38.197,
+    "eval_steps_per_second": 19.098,
+    "num_input_tokens_seen": 10717440
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 444.44444444444446,
+    "num_input_tokens_seen": 10717440,
+    "total_flos": 4.826141220667392e+17,
+    "train_loss": 0.005107367473887284,
+    "train_runtime": 12281.6577,
+    "train_samples_per_second": 13.028,
+    "train_steps_per_second": 3.257
+}