End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 2.326753616333008,
+    "eval_runtime": 0.4763,
+    "eval_samples": 15,
+    "eval_samples_per_second": 25.195,
+    "eval_steps_per_second": 2.1,
     "total_flos": 17867533713408.0,
     "train_loss": 2.6317037490698008,
     "train_runtime": 910.2032,

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": 1.0,
+    "eval_loss": 2.326753616333008,
+    "eval_runtime": 0.4763,
+    "eval_samples": 15,
+    "eval_samples_per_second": 25.195,
+    "eval_steps_per_second": 2.1
+}

runs/Nov21_11-55-46_main-fft-mistral7b-alpaca-0-0/events.out.tfevents.1732210102.main-fft-mistral7b-alpaca-0-0.545.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3afd322ec768eba2ee38e367a7374ebc0e7174c0342bf5c5d5407d8fe0ecdaf1
+size 359