End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.6668897867202759,
+    "eval_runtime": 102.7014,
+    "eval_samples": 13319,
+    "eval_samples_per_second": 129.687,
+    "eval_steps_per_second": 16.212,
+    "perplexity": 5.295671489170355,
+    "train_loss": 1.9931427570304485,
+    "train_runtime": 30194.781,
+    "train_samples": 253694,
+    "train_samples_per_second": 33.608,
+    "train_steps_per_second": 0.131
+}

config.json

@@ -21,7 +21,7 @@
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "prefix": "</s>",
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.25.0.dev0",
   "use_cache": true,
   "vocab_size": 50272,

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.6668897867202759,
+    "eval_runtime": 102.7014,
+    "eval_samples": 13319,
+    "eval_samples_per_second": 129.687,
+    "eval_steps_per_second": 16.212,
+    "perplexity": 5.295671489170355
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2648d976595b9b0cfbad08b91da10fda8b0c838456789fe0b413346c60ba274b
-size 1324917277
+oid sha256:743eb512852251be08a75f53fcbdc54da6810c302f91b9f948513d6064ebc538
+size 662524445

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 1.9931427570304485,
+    "train_runtime": 30194.781,
+    "train_samples": 253694,
+    "train_samples_per_second": 33.608,
+    "train_steps_per_second": 0.131
+}