End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9925925925925926,
+    "eval_loss": 1.4180262088775635,
+    "eval_runtime": 0.7651,
+    "eval_samples": 16,
+    "eval_samples_per_second": 11.763,
+    "eval_steps_per_second": 1.307,
     "total_flos": 27952184033280.0,
     "train_loss": 0.8094243202636491,
     "train_runtime": 773.5157,

config.json

@@ -26,6 +26,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128258
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9925925925925926,
+    "eval_loss": 1.4180262088775635,
+    "eval_runtime": 0.7651,
+    "eval_samples": 16,
+    "eval_samples_per_second": 11.763,
+    "eval_steps_per_second": 1.307
+}

runs/Nov21_21-17-23_main-fft-llama-coding-0-0/events.out.tfevents.1732243646.main-fft-llama-coding-0-0.548.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2346b8af9d520cf10722540b13066135541cc4d957a5de7e89aa810af36522ba
+size 354