MHGanainy/16-clusters-imbalanced-5

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-imbalanced-5
 
 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: 2.1312
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 1.0,
-    "eval_loss": 2.1312105655670166,
-    "eval_runtime": 2.6958,
-    "eval_samples_per_second": 13.725,
-    "eval_steps_per_second": 1.855,
-    "perplexity": 8.425059727805095,
+    "eval_loss": 2.1312263011932373,
+    "eval_runtime": 2.6837,
+    "eval_samples_per_second": 13.787,
+    "eval_steps_per_second": 1.863,
+    "perplexity": 8.425192302438928,
     "total_flos": 4161668422041600.0,
-    "train_loss": 2.3458979244315468,
-    "train_runtime": 72.3208,
-    "train_samples_per_second": 6.333,
-    "train_steps_per_second": 3.166
+    "train_loss": 2.3460041029484513,
+    "train_runtime": 71.1285,
+    "train_samples_per_second": 6.439,
+    "train_steps_per_second": 3.22
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 2.1312105655670166,
-    "eval_runtime": 2.6958,
-    "eval_samples_per_second": 13.725,
-    "eval_steps_per_second": 1.855,
-    "perplexity": 8.425059727805095
+    "eval_loss": 2.1312263011932373,
+    "eval_runtime": 2.6837,
+    "eval_samples_per_second": 13.787,
+    "eval_steps_per_second": 1.863,
+    "perplexity": 8.425192302438928
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 4161668422041600.0,
-    "train_loss": 2.3458979244315468,
-    "train_runtime": 72.3208,
-    "train_samples_per_second": 6.333,
-    "train_steps_per_second": 3.166
+    "train_loss": 2.3460041029484513,
+    "train_runtime": 71.1285,
+    "train_samples_per_second": 6.439,
+    "train_steps_per_second": 3.22
 }

trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 0.4366812227074236,
-      "grad_norm": 0.10677418857812881,
+      "grad_norm": 0.10466119647026062,
       "learning_rate": 6.666666666666667e-06,
       "loss": 2.3802,
       "step": 100
     },
     {
       "epoch": 0.8733624454148472,
-      "grad_norm": 0.2271566540002823,
+      "grad_norm": 0.2237740308046341,
       "learning_rate": 1.3333333333333333e-05,
-      "loss": 2.3234,
+      "loss": 2.3236,
       "step": 200
     },
     {
       "epoch": 1.0,
       "step": 229,
       "total_flos": 4161668422041600.0,
-      "train_loss": 2.3458979244315468,
-      "train_runtime": 72.3208,
-      "train_samples_per_second": 6.333,
-      "train_steps_per_second": 3.166
+      "train_loss": 2.3460041029484513,
+      "train_runtime": 71.1285,
+      "train_samples_per_second": 6.439,
+      "train_steps_per_second": 3.22
     }
   ],
   "logging_steps": 100,