MHGanainy/gpt2-xl-lora-multi-shared-512

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # gpt2-xl-lora-multi-shared-512
 
 This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1271
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.1270644664764404,
+    "eval_runtime": 1317.2806,
+    "eval_samples_per_second": 143.783,
+    "eval_steps_per_second": 8.987,
+    "perplexity": 8.39020090932304,
+    "total_flos": 1.2729340395184456e+19,
+    "train_loss": 2.32545618685814,
+    "train_runtime": 27204.7388,
+    "train_samples_per_second": 51.377,
+    "train_steps_per_second": 3.211
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.1270644664764404,
+    "eval_runtime": 1317.2806,
+    "eval_samples_per_second": 143.783,
+    "eval_steps_per_second": 8.987,
+    "perplexity": 8.39020090932304
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.2729340395184456e+19,
+    "train_loss": 2.32545618685814,
+    "train_runtime": 27204.7388,
+    "train_samples_per_second": 51.377,
+    "train_steps_per_second": 3.211
+}