End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9966555183946488,
+    "eval_loss": 1.360945463180542,
+    "eval_runtime": 0.4869,
+    "eval_samples": 16,
+    "eval_samples_per_second": 20.539,
+    "eval_steps_per_second": 2.054,
     "total_flos": 20483974103040.0,
     "train_loss": 1.7931190865151834,
     "train_runtime": 1036.7998,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9966555183946488,
+    "eval_loss": 1.360945463180542,
+    "eval_runtime": 0.4869,
+    "eval_samples": 16,
+    "eval_samples_per_second": 20.539,
+    "eval_steps_per_second": 2.054
+}

runs/Nov21_20-02-18_main-fft-gemma-coding-0-0/events.out.tfevents.1732239425.main-fft-gemma-coding-0-0.545.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f192ced80925ef0dd030a527de15c6d808286a56d9eb9a64efb4bcd75cd15e9
+size 359