Training in progress, step 300

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.1",
   "use_cache": false,
   "vocab_size": 32000
 }

runs/Jun21_22-25-45_n136-082-130/events.out.tfevents.1718979969.n136-082-130.2272566.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a76ab11dd53b4cc9f6568f769747c474bb6bfcc3f3a06a02b975d28a4576c216
-size 19418
+oid sha256:4d093c681f923fb6d2c228b0217a34ca8f0535afc550d35f1bb44a7b760933a3
+size 26298

tokenizer.json

@@ -134,6 +134,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757107ddd7f3c13927517a8af8b1157fab16f5f413513e07562fc610e6014451
-size 6264
+oid sha256:e918d0131d0ee4af99308608d8219f8f12f8ff244dd058ff7f1fcded5260eb5e
+size 6520