End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 2.876784563064575,
+    "eval_runtime": 0.8738,
+    "eval_samples": 16,
+    "eval_samples_per_second": 4.578,
+    "eval_steps_per_second": 1.144,
     "total_flos": 8193589641216.0,
     "train_loss": 12.591909694671632,
     "train_runtime": 386.7747,

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": 2.876784563064575,
+    "eval_runtime": 0.8738,
+    "eval_samples": 16,
+    "eval_samples_per_second": 4.578,
+    "eval_steps_per_second": 1.144
+}

runs/Nov21_10-56-31_main-fft-mistral7b-alpaca-0-0/events.out.tfevents.1732205937.main-fft-mistral7b-alpaca-0-0.546.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b18d5d886c73f6fc7bdd443b27213f89dcb41b439f83ce3bc644daffce1fb76
+size 354