End of training

README.md

@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mega-ar-350m-L3t-v0.07-cosmo_webmath_py-UltraTextbooks-2.1-fw_mix-vN
 
-This model is a fine-tuned version of [pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py](https://huggingface.co/pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py) on an unknown dataset.
+This model is a fine-tuned version of [pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py](https://huggingface.co/pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py) on the BEE-spoke-data/UltraTextbooks-2.1-fw_mix dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0802
-- Accuracy: 0.5744
-- Num Input Tokens Seen: 3355443200
+- Loss: 2.0787
+- Accuracy: 0.5746
+- Num Input Tokens Seen: 3492282368
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 0.9998921074234783,
+    "eval_accuracy": 0.5745966625966626,
+    "eval_loss": 2.0787301063537598,
+    "eval_runtime": 88.3261,
+    "eval_samples": 300,
+    "eval_samples_per_second": 3.397,
+    "eval_steps_per_second": 0.849,
+    "num_input_tokens_seen": 3492282368,
+    "perplexity": 7.994310541472254,
+    "total_flos": 4.5723602603621745e+18,
+    "train_loss": 2.154333936901462,
+    "train_runtime": 99522.0612,
+    "train_samples": 852698,
+    "train_samples_per_second": 8.568,
+    "train_steps_per_second": 0.067
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 0.9998921074234783,
+    "eval_accuracy": 0.5745966625966626,
+    "eval_loss": 2.0787301063537598,
+    "eval_runtime": 88.3261,
+    "eval_samples": 300,
+    "eval_samples_per_second": 3.397,
+    "eval_steps_per_second": 0.849,
+    "num_input_tokens_seen": 3492282368,
+    "perplexity": 7.994310541472254
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9998921074234783,
+    "num_input_tokens_seen": 3492282368,
+    "total_flos": 4.5723602603621745e+18,
+    "train_loss": 2.154333936901462,
+    "train_runtime": 99522.0612,
+    "train_samples": 852698,
+    "train_samples_per_second": 8.568,
+    "train_steps_per_second": 0.067
+}