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/Jun30_16-42-14_n136-100-194/events.out.tfevents.1719737283.n136-100-194.302982.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb99b6fc5e5984b9dacebd12730efd1c7a591274e1e039f3162da4273e63ca09
-size 19183
+oid sha256:861ba4647ebb9108c160943d3650c7c91cfbbaf2f0a1cc70e55ed258abaaf5a6
+size 26063

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:c3a645c7a17ab4c7ed2624bb6f63a7530266096f7cd34d78eb56492568bf376c
-size 6456
+oid sha256:d13f3fc8759aca2ff57e3efc81099fc07a2315dc63120d75fb63db001a764cfe
+size 6264