End of training

README.md

@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mega-ar-350m-v0.12-napierone_epub-UltraTextbooks-2.1-fw_mix-vN
 
-This model is a fine-tuned version of [pszemraj/mega-ar-350m-v0.12-napierone_epub](https://huggingface.co/pszemraj/mega-ar-350m-v0.12-napierone_epub) on an unknown dataset.
+This model is a fine-tuned version of [pszemraj/mega-ar-350m-v0.12-napierone_epub](https://huggingface.co/pszemraj/mega-ar-350m-v0.12-napierone_epub) on the BEE-spoke-data/UltraTextbooks-2.1-fw_mix dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.9926
-- Accuracy: 0.5884
-- Num Input Tokens Seen: 3460300800
+- Accuracy: 0.5885
+- Num Input Tokens Seen: 3468165120
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 0.9999893708612791,
+    "eval_accuracy": 0.5884871794871794,
+    "eval_loss": 1.992581844329834,
+    "eval_runtime": 128.1327,
+    "eval_samples": 400,
+    "eval_samples_per_second": 3.122,
+    "eval_steps_per_second": 1.046,
+    "num_input_tokens_seen": 3468165120,
+    "perplexity": 7.334445735052817,
+    "total_flos": 4.540784328132526e+18,
+    "train_loss": 2.065564124978859,
+    "train_runtime": 98524.0638,
+    "train_samples": 846729,
+    "train_samples_per_second": 8.594,
+    "train_steps_per_second": 0.09
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 0.9999893708612791,
+    "eval_accuracy": 0.5884871794871794,
+    "eval_loss": 1.992581844329834,
+    "eval_runtime": 128.1327,
+    "eval_samples": 400,
+    "eval_samples_per_second": 3.122,
+    "eval_steps_per_second": 1.046,
+    "num_input_tokens_seen": 3468165120,
+    "perplexity": 7.334445735052817
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9999893708612791,
+    "num_input_tokens_seen": 3468165120,
+    "total_flos": 4.540784328132526e+18,
+    "train_loss": 2.065564124978859,
+    "train_runtime": 98524.0638,
+    "train_samples": 846729,
+    "train_samples_per_second": 8.594,
+    "train_steps_per_second": 0.09
+}