Training in progress, step 300

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/Jun22_01-24-16_n136-112-146/events.out.tfevents.1718991113.n136-112-146.3250601.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed6c0ab80b0d092cda3d6dd74f23646ee5020189e41e9d2c2b62763c6ba57d5
-size 19218
+oid sha256:e785d39bc045741a989dc639329466a17ffc23c419821238b7d5bfddf6241171
+size 26098

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:bf765daeff145762a3fa632b01cccb18d8d1f4664dc9658a48bcbecb448c6367
-size 6520
+oid sha256:c46a043ab303535917560fd89542c405187453fe88a04c8c789ec363f76563bc
+size 6328