End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9850746268656716,
+    "eval_loss": 1.7861212491989136,
+    "eval_runtime": 0.7324,
+    "eval_samples": 16,
+    "eval_samples_per_second": 5.462,
+    "eval_steps_per_second": 1.365,
     "total_flos": 13714367447040.0,
     "train_loss": 1.5271921013340806,
     "train_runtime": 363.6097,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32770
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9850746268656716,
+    "eval_loss": 1.7861212491989136,
+    "eval_runtime": 0.7324,
+    "eval_samples": 16,
+    "eval_samples_per_second": 5.462,
+    "eval_steps_per_second": 1.365
+}

runs/Nov21_11-28-01_main-fft-mistral7b-alpaca-0-0/events.out.tfevents.1732207712.main-fft-mistral7b-alpaca-0-0.546.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc714096f6057dca8f5ffa87f09da1a452d6eba139015737a3d292cb2ae9c63
+size 354