Training in progress, step 200

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": 32002
 }

runs/Jun13_11-21-59_n136-082-130/events.out.tfevents.1718249050.n136-082-130.1433425.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1912fca13edeb646fa41dcf89679ac656f48bd9a74b208354f4eeb344472082a
-size 12543
+oid sha256:35cfe77511afc0b128ae2f40524836ecc950ec023cce147e1c95d99d8ebb033a
+size 19399

tokenizer.json

@@ -152,6 +152,7 @@
     "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:fe097aaf422806e6212d3d33e9ca3a27fa65a81ab506341c5b178d1980a001f6
-size 6264
+oid sha256:374090dab1472e47e0fe5d92b88b9a0e72a756de13d7112560b3adc44f64a7d7
+size 6520