End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9863013698630136,
+    "eval_loss": 2.2775027751922607,
+    "eval_runtime": 0.7684,
+    "eval_samples": 25,
+    "eval_samples_per_second": 27.33,
+    "eval_steps_per_second": 1.301,
     "total_flos": 22508312985600.0,
     "train_loss": 1.2952520185046725,
     "train_runtime": 626.5642,

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": 0.9863013698630136,
+    "eval_loss": 2.2775027751922607,
+    "eval_runtime": 0.7684,
+    "eval_samples": 25,
+    "eval_samples_per_second": 27.33,
+    "eval_steps_per_second": 1.301
+}

runs/Nov21_22-37-21_main-fft-llama-summarization-0-0/events.out.tfevents.1732248330.main-fft-llama-summarization-0-0.546.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d2a65f435b0f1f323e33d16e682848ffb990a21f1a385b94a044498c2e39b7
+size 354