Training in progress, step 200

config.json

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

runs/Jun21_22-53-57_n136-112-146/events.out.tfevents.1718982063.n136-112-146.3173047.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf9a5e6f3ac917453388891e09472fcf211f566faa36b61506576d7184c6045
-size 13085
+oid sha256:f4ccd6091772eb958af0678c1787cbdd59ff49d2d640de3c025f4fdccf9af9e7
+size 20681

tokenizer.json

@@ -134,7 +134,6 @@
     "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:e918d0131d0ee4af99308608d8219f8f12f8ff244dd058ff7f1fcded5260eb5e
-size 6520
+oid sha256:4d3fb180207917890a173df42ab512a382917bb3e4948bc7f7734e774a31efc2
+size 6328