End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.0718671083450317,
+    "eval_runtime": 1.4181,
+    "eval_samples": 518,
+    "eval_samples_per_second": 136.1,
+    "eval_steps_per_second": 1.41,
     "total_flos": 15808164003840.0,
     "train_loss": 1.2820051688896983,
     "train_runtime": 418.9516,

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": 1.0,
+    "eval_loss": 1.0718671083450317,
+    "eval_runtime": 1.4181,
+    "eval_samples": 518,
+    "eval_samples_per_second": 136.1,
+    "eval_steps_per_second": 1.41
+}

runs/Nov21_10-29-02_main-fft-mistral7b-alpaca-0-0/events.out.tfevents.1732204187.main-fft-mistral7b-alpaca-0-0.546.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc95d84f41d6857b3423b90790cddcda9d60017f656f210010b323e08ebccf0d
+size 354